Authors: Syeda Nahida Akter, Sangwu Lee, Yingshan Chang, Yonatan Bisk, Eric Nyberg
Abstract: Verifying a question's validity before answering is crucial in real-world applications, where users may provide imperfect instructions. In this scenario, an ideal model should address the discrepancies in the query and convey them to the users rather than generating the best possible answer. Addressing this requirement, we introduce a new compositional visual question-answering dataset, VISREAS, that consists of answerable and unanswerable visual queries formulated by traversing and perturbing commonalities and differences among objects, attributes, and relations. VISREAS contains 2.07M semantically diverse queries generated automatically using Visual Genome scene graphs. The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, LOGIC2VISION that reasons by producing and executing pseudocode without any external modules to generate the answer. LOGIC2VISION outperforms generative models in VISREAS (+4.82% over LLaVA-1.5; +12.23% over InstructBLIP) and achieves a significant gain in performance against the classification models.
Authors: Yuanqing Huang, Yinggui Wang, Jianshu Li, Le Yang, Kai Song, Lei Wang
Abstract: The utilization of personal sensitive data in training face recognition (FR) models poses significant privacy concerns, as adversaries can employ model inversion attacks (MIA) to infer the original training data. Existing defense methods, such as data augmentation and differential privacy, have been employed to mitigate this issue. However, these methods often fail to strike an optimal balance between privacy and accuracy. To address this limitation, this paper introduces an adaptive hybrid masking algorithm against MIA. Specifically, face images are masked in the frequency domain using an adaptive MixUp strategy. Unlike the traditional MixUp algorithm, which is predominantly used for data augmentation, our modified approach incorporates frequency domain mixing. Previous studies have shown that increasing the number of images mixed in MixUp can enhance privacy preservation but at the expense of reduced face recognition accuracy. To overcome this trade-off, we develop an enhanced adaptive MixUp strategy based on reinforcement learning, which enables us to mix a larger number of images while maintaining satisfactory recognition accuracy. To optimize privacy protection, we propose maximizing the reward function (i.e., the loss function of the FR system) during the training of the strategy network. While the loss function of the FR network is minimized in the phase of training the FR network. The strategy network and the face recognition network can be viewed as antagonistic entities in the training process, ultimately reaching a more balanced trade-off. Experimental results demonstrate that our proposed hybrid masking scheme outperforms existing defense algorithms in terms of privacy preservation and recognition accuracy against MIA.
Authors: Jinxia Xie, Bineng Zhong, Zhiyi Mo, Shengping Zhang, Liangtao Shi, Shuxiang Song, Rongrong Ji
Abstract: The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal information aggregation. Consequently, the spatio-temporal information is far away from being fully explored. To alleviate this issue, we propose an adaptive tracker with spatio-temporal transformers (named AQATrack), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components. Firstly, we introduce a set of learnable and autoregressive queries to capture the instantaneous target appearance changes in a sliding window fashion. Then, we design a novel attention mechanism for the interaction of existing queries to generate a new query in current frame. Finally, based on the initial target template and learnt autoregressive queries, a spatio-temporal information fusion module (STM) is designed for spatiotemporal formation aggregation to locate a target object. Benefiting from the STM, we can effectively combine the static appearance and instantaneous changes to guide robust tracking. Extensive experiments show that our method significantly improves the tracker's performance on six popular tracking benchmarks: LaSOT, LaSOText, TrackingNet, GOT-10k, TNL2K, and UAV123.
Authors: Numan Saeed, Muhammad Ridzuan, Fadillah Adamsyah Maani, Hussain Alasmawi, Karthik Nandakumar, Mohammad Yaqub
Abstract: Predicting the likelihood of survival is of paramount importance for individuals diagnosed with cancer as it provides invaluable information regarding prognosis at an early stage. This knowledge enables the formulation of effective treatment plans that lead to improved patient outcomes. In the past few years, deep learning models have provided a feasible solution for assessing medical images, electronic health records, and genomic data to estimate cancer risk scores. However, these models often fall short of their potential because they struggle to learn regression-aware feature representations. In this study, we propose Survival Rank-N Contrast (SurvRNC) method, which introduces a loss function as a regularizer to obtain an ordered representation based on the survival times. This function can handle censored data and can be incorporated into any survival model to ensure that the learned representation is ordinal. The model was extensively evaluated on a HEad \& NeCK TumOR (HECKTOR) segmentation and the outcome-prediction task dataset. We demonstrate that using the SurvRNC method for training can achieve higher performance on different deep survival models. Additionally, it outperforms state-of-the-art methods by 3.6% on the concordance index. The code is publicly available on https://github.com/numanai/SurvRNC
Authors: Peter Kocsis (Technical University of Munich), Julien Philip (Adobe Research), Kalyan Sunkavalli (Adobe Research), Matthias Nie{\ss}ner (Technical University of Munich), Yannick Hold-Geoffroy (Adobe Research)
Abstract: We introduce LightIt, a method for explicit illumination control for image generation. Recent generative methods lack lighting control, which is crucial to numerous artistic aspects of image generation such as setting the overall mood or cinematic appearance. To overcome these limitations, we propose to condition the generation on shading and normal maps. We model the lighting with single bounce shading, which includes cast shadows. We first train a shading estimation module to generate a dataset of real-world images and shading pairs. Then, we train a control network using the estimated shading and normals as input. Our method demonstrates high-quality image generation and lighting control in numerous scenes. Additionally, we use our generated dataset to train an identity-preserving relighting model, conditioned on an image and a target shading. Our method is the first that enables the generation of images with controllable, consistent lighting and performs on par with specialized relighting state-of-the-art methods.
Authors: Miao Zhang, Rumi Chunara
Abstract: Performance disparities across sub-populations are known to exist in deep learning-based vision recognition models, but previous work has largely addressed such fairness concerns assuming knowledge of sensitive attribute labels. To overcome this reliance, previous strategies have involved separate learning structures to expose and adjust for disparities. In this work, we explore a new paradigm that does not require sensitive attribute labels, and evades the need for extra training by leveraging the vision-language model, CLIP, as a rich knowledge source to infer sensitive information. We present sample clustering based on similarity derived from image and attribute-specified language embeddings and assess their correspondence to true attribute distribution. We train a target model by re-sampling and augmenting under-performed clusters. Extensive experiments on multiple benchmark bias datasets show clear fairness gains of the model over existing baselines, which indicate that CLIP can extract discriminative sensitive information prompted by language, and used to promote model fairness.
Authors: Wenrui Fan, Mohammod Naimul Islam Suvon, Shuo Zhou, Xianyuan Liu, Samer Alabed, Venet Osmani, Andrew Swift, Chen Chen, Haiping Lu
Abstract: Vision-language pre-training (VLP) models have shown significant advancements in the medical domain. Yet, most VLP models align raw reports to images at a very coarse level, without modeling fine-grained relationships between anatomical and pathological concepts outlined in reports and the corresponding semantic counterparts in images. To address this problem, we propose a Medical Dual-Stream Language-Image Pre-training (MeDSLIP) framework. Specifically, MeDSLIP establishes vision-language fine-grained alignments via disentangling visual and textual representations into anatomy-relevant and pathology-relevant streams. Moreover, a novel vision-language Prototypical Contr-astive Learning (ProtoCL) method is adopted in MeDSLIP to enhance the alignment within the anatomical and pathological streams. MeDSLIP further employs cross-stream Intra-image Contrastive Learning (ICL) to ensure the consistent coexistence of paired anatomical and pathological concepts within the same image. Such a cross-stream regularization encourages the model to exploit the synchrony between two streams for a more comprehensive representation learning. MeDSLIP is evaluated under zero-shot and supervised fine-tuning settings on three public datasets: NIH CXR14, RSNA Pneumonia, and SIIM-ACR Pneumothorax. Under these settings, MeDSLIP outperforms six leading CNN-based models on classification, grounding, and segmentation tasks.
Authors: Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo
Abstract: Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Continual test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains using test data. A highly effective CTTA method involves applying layer-wise adaptive learning rates, and selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. In this work, we aim to overcome these limitations by identifying layers through the quantification of model prediction uncertainty without relying on pseudo-labels. We utilize the magnitude of gradients as a metric, calculated by backpropagating the KL divergence between the softmax output and a uniform distribution, to select layers for further adaptation. Subsequently, for the parameters exclusively belonging to these selected layers, with the remaining ones frozen, we evaluate their sensitivity in order to approximate the domain shift, followed by adjusting their learning rates accordingly. Overall, this approach leads to a more robust and stable optimization than prior approaches. We conduct extensive image classification experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C and demonstrate the efficacy of our method against standard benchmarks and prior methods.
Authors: Zhe Huang, Xiaowei Yu, Dajiang Zhu, Michael C. Hughes
Abstract: Semi-supervised learning (SSL) seeks to enhance task performance by training on both labeled and unlabeled data. Mainstream SSL image classification methods mostly optimize a loss that additively combines a supervised classification objective with a regularization term derived solely from unlabeled data. This formulation neglects the potential for interaction between labeled and unlabeled images. In this paper, we introduce InterLUDE, a new approach to enhance SSL made of two parts that each benefit from labeled-unlabeled interaction. The first part, embedding fusion, interpolates between labeled and unlabeled embeddings to improve representation learning. The second part is a new loss, grounded in the principle of consistency regularization, that aims to minimize discrepancies in the model's predictions between labeled versus unlabeled inputs. Experiments on standard closed-set SSL benchmarks and a medical SSL task with an uncurated unlabeled set show clear benefits to our approach. On the STL-10 dataset with only 40 labels, InterLUDE achieves 3.2% error rate, while the best previous method reports 14.9%.
Authors: Pardis Taghavi, Reza Langari, Gaurav Pandey
Abstract: This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera. The proposed approach is based on a shared encoder-decoder architecture, which integrates various techniques to improve the accuracy of the depth estimation and semantic segmentation task without compromising computational efficiency. Additionally, the paper incorporates an adversarial training component, employing a Wasserstein GAN framework with a critic network, to refine model's predictions. The framework is thoroughly evaluated on two datasets - the outdoor Cityscapes dataset and the indoor NYU Depth V2 dataset - and it outperforms existing state-of-the-art methods in both segmentation and depth estimation tasks. We also conducted ablation studies to analyze the contributions of different components, including pre-training strategies, the inclusion of critics, the use of logarithmic depth scaling, and advanced image augmentations, to provide a better understanding of the proposed framework. The accompanying source code is accessible at \url{https://github.com/PardisTaghavi/SwinMTL}.
Authors: Dingding Cai, Janne Heikkil\"a, Esa Rahtu
Abstract: This paper introduces GS-Pose, an end-to-end framework for locating and estimating the 6D pose of objects. GS-Pose begins with a set of posed RGB images of a previously unseen object and builds three distinct representations stored in a database. At inference, GS-Pose operates sequentially by locating the object in the input image, estimating its initial 6D pose using a retrieval approach, and refining the pose with a render-and-compare method. The key insight is the application of the appropriate object representation at each stage of the process. In particular, for the refinement step, we utilize 3D Gaussian splatting, a novel differentiable rendering technique that offers high rendering speed and relatively low optimization time. Off-the-shelf toolchains and commodity hardware, such as mobile phones, can be used to capture new objects to be added to the database. Extensive evaluations on the LINEMOD and OnePose-LowTexture datasets demonstrate excellent performance, establishing the new state-of-the-art. Project page: https://dingdingcai.github.io/gs-pose.
Authors: Diganta Misra, Jay Gala, Antonio Orvieto
Abstract: The strength of modern large-scale neural networks lies in their ability to efficiently adapt to new tasks with few examples. Although extensive research has investigated the transferability of Vision Transformers (ViTs) to various downstream tasks under diverse constraints, this study shifts focus to explore the transfer learning potential of [V]-Mamba. We compare its performance with ViTs across different few-shot data budgets and efficient transfer methods. Our analysis yields three key insights into [V]-Mamba's few-shot transfer performance: (a) [V]-Mamba demonstrates superior or equivalent few-shot learning capabilities compared to ViTs when utilizing linear probing (LP) for transfer, (b) Conversely, [V]-Mamba exhibits weaker or similar few-shot learning performance compared to ViTs when employing visual prompting (VP) as the transfer method, and (c) We observe a weak positive correlation between the performance gap in transfer via LP and VP and the scale of the [V]-Mamba model. This preliminary analysis lays the foundation for more comprehensive studies aimed at furthering our understanding of the capabilities of [V]-Mamba variants and their distinctions from ViTs.
Authors: Minh-Hao Van, Alycia N. Carey, Xintao Wu
Abstract: Correctly classifying brain tumors is imperative to the prompt and accurate treatment of a patient. While several classification algorithms based on classical image processing or deep learning methods have been proposed to rapidly classify tumors in MR images, most assume the unrealistic setting of noise-free training data. In this work, we study a difficult but realistic setting of training a deep learning model on noisy MR images to classify brain tumors. We propose two training methods that are robust to noisy MRI training data, Influence-based Sample Reweighing (ISR) and Influence-based Sample Perturbation (ISP), which are based on influence functions from robust statistics. Using the influence functions, in ISR, we adaptively reweigh training examples according to how helpful/harmful they are to the training process, while in ISP, we craft and inject helpful perturbation proportional to the influence score. Both ISR and ISP harden the classification model against noisy training data without significantly affecting the generalization ability of the model on test data. We conduct empirical evaluations over a common brain tumor dataset and compare ISR and ISP to three baselines. Our empirical results show that ISR and ISP can efficiently train deep learning models robust against noisy training data.
Authors: Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Daniel Aliaga
Abstract: Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both view-invariant and conducive to enhanced detail preservation. The subsequent stage leverages this representation to learn seamless harmonization of the object composited to the background. In addition, IMPRINT incorporates a shape-guidance mechanism offering user-directed control over the compositing process. Extensive experiments demonstrate that IMPRINT significantly outperforms existing methods and various baselines on identity preservation and composition quality.
Authors: Toqi Tahamid Sarker, Taminul Islam, Khaled R Ahmed
Abstract: Analyzing and detecting cannabis seed variants is crucial for the agriculture industry. It enables precision breeding, allowing cultivators to selectively enhance desirable traits. Accurate identification of seed variants also ensures regulatory compliance, facilitating the cultivation of specific cannabis strains with defined characteristics, ultimately improving agricultural productivity and meeting diverse market demands. This paper presents a study on cannabis seed variant detection by employing a state-of-the-art object detection model Faster R-CNN. This study implemented the model on a locally sourced cannabis seed dataset in Thailand, comprising 17 distinct classes. We evaluate six Faster R-CNN models by comparing performance on various metrics and achieving a mAP score of 94.08\% and an F1 score of 95.66\%. This paper presents the first known application of deep neural network object detection models to the novel task of visually identifying cannabis seed types.
Authors: Anton Pelykh, Ozge Mercanoglu Sincan, Richard Bowden
Abstract: Recent years have seen significant progress in human image generation, particularly with the advancements in diffusion models. However, existing diffusion methods encounter challenges when producing consistent hand anatomy and the generated images often lack precise control over the hand pose. To address this limitation, we introduce a novel approach to pose-conditioned human image generation, dividing the process into two stages: hand generation and subsequent body out-painting around the hands. We propose training the hand generator in a multi-task setting to produce both hand images and their corresponding segmentation masks, and employ the trained model in the first stage of generation. An adapted ControlNet model is then used in the second stage to outpaint the body around the generated hands, producing the final result. A novel blending technique is introduced to preserve the hand details during the second stage that combines the results of both stages in a coherent way. This involves sequential expansion of the out-painted region while fusing the latent representations, to ensure a seamless and cohesive synthesis of the final image. Experimental evaluations demonstrate the superiority of our proposed method over state-of-the-art techniques, in both pose accuracy and image quality, as validated on the HaGRID dataset. Our approach not only enhances the quality of the generated hands but also offers improved control over hand pose, advancing the capabilities of pose-conditioned human image generation. The source code of the proposed approach is available at https://github.com/apelykh/hand-to-diffusion.
Authors: Liupei Lu, Yufeng Yin, Yuming Gu, Yizhen Wu, Pratusha Prasad, Yajie Zhao, Mohammad Soleymani
Abstract: Facial action unit (AU) detection is a fundamental block for objective facial expression analysis. Supervised learning approaches require a large amount of manual labeling which is costly. The limited labeled data are also not diverse in terms of gender which can affect model fairness. In this paper, we propose to use synthetically generated data and multi-source domain adaptation (MSDA) to address the problems of the scarcity of labeled data and the diversity of subjects. Specifically, we propose to generate a diverse dataset through synthetic facial expression re-targeting by transferring the expressions from real faces to synthetic avatars. Then, we use MSDA to transfer the AU detection knowledge from a real dataset and the synthetic dataset to a target dataset. Instead of aligning the overall distributions of different domains, we propose Paired Moment Matching (PM2) to align the features of the paired real and synthetic data with the same facial expression. To further improve gender fairness, PM2 matches the features of the real data with a female and a male synthetic image. Our results indicate that synthetic data and the proposed model improve both AU detection performance and fairness across genders, demonstrating its potential to solve AU detection in-the-wild.
Authors: Gergely Szilvasy, Pierre-Emmanuel Mazar\'e, Matthijs Douze
Abstract: In recent years, the dominant accuracy metric for vector search is the recall of a result list of fixed size (top-k retrieval), considering as ground truth the exact vector retrieval results. Although convenient to compute, this metric is distantly related to the end-to-end accuracy of a full system that integrates vector search. In this paper we focus on the common case where a hard decision needs to be taken depending on the vector retrieval results, for example, deciding whether a query image matches a database image or not. We solve this as a range search task, where all vectors within a certain radius from the query are returned. We show that the value of a range search result can be modeled rigorously based on the query-to-vector distance. This yields a metric for range search, RSM, that is both principled and easy to compute without running an end-to-end evaluation. We apply this metric to the case of image retrieval. We show that indexing methods that are adapted for top-k retrieval do not necessarily maximize the RSM. In particular, for inverted file based indexes, we show that visiting a limited set of clusters and encoding vectors compactly yields near optimal results.
Authors: Junpeng Jing, Ye Mao, Krystian Mikolajczyk
Abstract: Dynamic stereo matching is the task of estimating consistent disparities from stereo videos with dynamic objects. Recent learning-based methods prioritize optimal performance on a single stereo pair, resulting in temporal inconsistencies. Existing video methods apply per-frame matching and window-based cost aggregation across the time dimension, leading to low-frequency oscillations at the scale of the window size. Towards this challenge, we develop a bidirectional alignment mechanism for adjacent frames as a fundamental operation. We further propose a novel framework, BiDAStereo, that achieves consistent dynamic stereo matching. Unlike the existing methods, we model this task as local matching and global aggregation. Locally, we consider correlation in a triple-frame manner to pool information from adjacent frames and improve the temporal consistency. Globally, to exploit the entire sequence's consistency and extract dynamic scene cues for aggregation, we develop a motion-propagation recurrent unit. Extensive experiments demonstrate the performance of our method, showcasing improvements in prediction quality and achieving state-of-the-art results on various commonly used benchmarks.
Authors: Shibiao Xu, ShuChen Zheng, Wenhao Xu, Rongtao Xu, Changwei Wang, Jiguang Zhang, Xiaoqiang Teng, Ao Li, Li Guo
Abstract: Infrared small object detection is an important computer vision task involving the recognition and localization of tiny objects in infrared images, which usually contain only a few pixels. However, it encounters difficulties due to the diminutive size of the objects and the generally complex backgrounds in infrared images. In this paper, we propose a deep learning method, HCF-Net, that significantly improves infrared small object detection performance through multiple practical modules. Specifically, it includes the parallelized patch-aware attention (PPA) module, dimension-aware selective integration (DASI) module, and multi-dilated channel refiner (MDCR) module. The PPA module uses a multi-branch feature extraction strategy to capture feature information at different scales and levels. The DASI module enables adaptive channel selection and fusion. The MDCR module captures spatial features of different receptive field ranges through multiple depth-separable convolutional layers. Extensive experimental results on the SIRST infrared single-frame image dataset show that the proposed HCF-Net performs well, surpassing other traditional and deep learning models. Code is available at https://github.com/zhengshuchen/HCFNet.
Authors: Mariia Khan, Yue Qiu, Yuren Cong, Jumana Abu-Khalaf, David Suter, Bodo Rosenhahn
Abstract: Multi-class multi-instance segmentation is the task of identifying masks for multiple object classes and multiple instances of the same class within an image. The foundational Segment Anything Model (SAM) is designed for promptable multi-class multi-instance segmentation but tends to output part or sub-part masks in the "everything" mode for various real-world applications. Whole object segmentation masks play a crucial role for indoor scene understanding, especially in robotics applications. We propose a new domain invariant Real-to-Simulation (Real-Sim) fine-tuning strategy for SAM. We use object images and ground truth data collected from Ai2Thor simulator during fine-tuning (real-to-sim). To allow our Segment Any Object Model (SAOM) to work in the "everything" mode, we propose the novel nearest neighbour assignment method, updating point embeddings for each ground-truth mask. SAOM is evaluated on our own dataset collected from Ai2Thor simulator. SAOM significantly improves on SAM, with a 28% increase in mIoU and a 25% increase in mAcc for 54 frequently-seen indoor object classes. Moreover, our Real-to-Simulation fine-tuning strategy demonstrates promising generalization performance in real environments without being trained on the real-world data (sim-to-real). The dataset and the code will be released after publication.
Authors: Mahdi Alehdaghi, Pourya Shamsolmoali, Rafael M. O. Cruz, Eric Granger
Abstract: A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces the Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by finding and aligning body part features extracted from both I and V modalities. Indeed, BMDG aims to reduce the modality gaps in two steps. First, it aligns modalities in feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. In particular, our method minimizes the cross-modal gap by identifying and aligning shared prototypes that capture key discriminative features across modalities, then uses multiple bridging steps based on this information to enhance the feature representation. Experiments conducted on challenging V-I ReID datasets indicate that our BMDG approach outperforms state-of-the-art part-based models or methods that generate an intermediate domain from V-I person ReID.
Authors: Rui Wang, Hailong Guo, Jiaming Liu, Huaxia Li, Haibo Zhao, Xu Tang, Yao Hu, Hao Tang, Peipei Li
Abstract: In this paper, we introduce StableGarment, a unified framework to tackle garment-centric(GC) generation tasks, including GC text-to-image, controllable GC text-to-image, stylized GC text-to-image, and robust virtual try-on. The main challenge lies in retaining the intricate textures of the garment while maintaining the flexibility of pre-trained Stable Diffusion. Our solution involves the development of a garment encoder, a trainable copy of the denoising UNet equipped with additive self-attention (ASA) layers. These ASA layers are specifically devised to transfer detailed garment textures, also facilitating the integration of stylized base models for the creation of stylized images. Furthermore, the incorporation of a dedicated try-on ControlNet enables StableGarment to execute virtual try-on tasks with precision. We also build a novel data engine that produces high-quality synthesized data to preserve the model's ability to follow prompts. Extensive experiments demonstrate that our approach delivers state-of-the-art (SOTA) results among existing virtual try-on methods and exhibits high flexibility with broad potential applications in various garment-centric image generation.
Authors: Shichao Kan, Yuhai Deng, Yixiong Liang, Lihui Cen, Zhe Qu, Yigang Cen, Zhihai He
Abstract: The task of searching for visual objects in a large image dataset is difficult because it requires efficient matching and accurate localization of objects that can vary in size. Although the segment anything model (SAM) offers a potential solution for extracting object spatial context, learning embeddings for local objects remains a challenging problem. This paper presents a novel unsupervised deep metric learning approach, termed unsupervised collaborative metric learning with mixed-scale groups (MS-UGCML), devised to learn embeddings for objects of varying scales. Following this, a benchmark of challenges is assembled by utilizing COCO 2017 and VOC 2007 datasets to facilitate the training and evaluation of general object retrieval models. Finally, we conduct comprehensive ablation studies and discuss the complexities faced within the domain of general object retrieval. Our object retrieval evaluations span a range of datasets, including BelgaLogos, Visual Genome, LVIS, in addition to a challenging evaluation set that we have individually assembled for open-vocabulary evaluation. These comprehensive evaluations effectively highlight the robustness of our unsupervised MS-UGCML approach, with an object level and image level mAPs improvement of up to 6.69% and 10.03%, respectively. The code is publicly available at https://github.com/dengyuhai/MS-UGCML.
Authors: Ziqi Zhou, Minghui Li, Wei Liu, Shengshan Hu, Yechao Zhang, Wei Wan, Lulu Xue, Leo Yu Zhang, Dezhong Yang, Hai Jin
Abstract: With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Our extensive experiments, conducted across ten self-supervised training methods and six datasets, demonstrate that Gen-AF attains high testing accuracy and robust testing accuracy against state-of-the-art DAEs.
Authors: Tianyi Zhang, Kaining Huang, Weiming Zhi, Matthew Johnson-Roberson
Abstract: Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this same capability. In this paper, we tackle the challenge of constructing a photorealistic scene representation under poorly illuminated conditions and with a moving light source. We approach the task of modeling illumination as a learning problem, and utilize the developed illumination model to aid in scene reconstruction. We introduce an innovative framework that uses a data-driven approach, Neural Light Simulators (NeLiS), to model and calibrate the camera-light system. Furthermore, we present DarkGS, a method that applies NeLiS to create a relightable 3D Gaussian scene model capable of real-time, photorealistic rendering from novel viewpoints. We show the applicability and robustness of our proposed simulator and system in a variety of real-world environments.
Authors: Hoyoung Kim, Sehyun Hwang, Suha Kwak, Jungseul Ok
Abstract: Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundation models or crowdsourced datasets are available, they are error-prone. We hence propose an effective framework of active label correction (ALC) based on a design of correction query to rectify pseudo labels of pixels, which in turn is more annotator-friendly than the standard one inquiring to classify a pixel directly according to our theoretical analysis and user study. Specifically, leveraging foundation models providing useful zero-shot predictions on pseudo labels and superpixels, our method comprises two key techniques: (i) an annotator-friendly design of correction query with the pseudo labels, and (ii) an acquisition function looking ahead label expansions based on the superpixels. Experimental results on PASCAL, Cityscapes, and Kvasir-SEG datasets demonstrate the effectiveness of our ALC framework, outperforming prior methods for active semantic segmentation and label correction. Notably, utilizing our method, we obtained a revised dataset of PASCAL by rectifying errors in 2.6 million pixels in PASCAL dataset.
Authors: Hao Wei, Bowen Liu, Minqing Zhang, Peilun Shi, Wu Yuan
Abstract: Generalist foundation model has ushered in newfound capabilities in medical domain. However, the contradiction between the growing demand for high-quality annotated data with patient privacy continues to intensify. The utilization of medical artificial intelligence generated content (Med-AIGC) as an inexhaustible resource repository arises as a potential solution to address the aforementioned challenge. Here we harness 1 million open-source synthetic fundus images paired with natural language descriptions, to curate an ethical language-image foundation model for retina image analysis named VisionCLIP. VisionCLIP achieves competitive performance on three external datasets compared with the existing method pre-trained on real-world data in a zero-shot fashion. The employment of artificially synthetic images alongside corresponding textual data for training enables the medical foundation model to successfully assimilate knowledge of disease symptomatology, thereby circumventing potential breaches of patient confidentiality.
Authors: Wei Zhang, Feng Qiu, Chen Liu, Lincheng Li, Heming Du, Tiancheng Guo, Xin Yu
Abstract: Affective Behavior Analysis aims to facilitate technology emotionally smart, creating a world where devices can understand and react to our emotions as humans do. To comprehensively evaluate the authenticity and applicability of emotional behavior analysis techniques in natural environments, the 6th competition on Affective Behavior Analysis in-the-wild (ABAW) utilizes the Aff-Wild2, Hume-Vidmimic2, and C-EXPR-DB datasets to set up five competitive tracks, i.e., Valence-Arousal (VA) Estimation, Expression (EXPR) Recognition, Action Unit (AU) Detection, Compound Expression (CE) Recognition, and Emotional Mimicry Intensity (EMI) Estimation. In this paper, we present our method designs for the five tasks. Specifically, our design mainly includes three aspects: 1) Utilizing a transformer-based feature fusion module to fully integrate emotional information provided by audio signals, visual images, and transcripts, offering high-quality expression features for the downstream tasks. 2) To achieve high-quality facial feature representations, we employ Masked-Auto Encoder as the visual features extraction model and fine-tune it with our facial dataset. 3) Considering the complexity of the video collection scenes, we conduct a more detailed dataset division based on scene characteristics and train the classifier for each scene. Extensive experiments demonstrate the superiority of our designs.
Authors: Hsiang-Wei Huang, Cheng-Yen Yang, Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang
Abstract: In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman Filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman Filter with various learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman Filter-based systems. In this paper, we proposed MambaTrack, an online motion-based tracker that outperforms all existing motion-based trackers on the challenging DanceTrack and SportsMOT datasets. Moreover, we further exploit the potential of the state-space-model in trajectory feature extraction to boost the tracking performance and proposed MambaTrack+, which achieves the state-of-the-art performance on DanceTrack dataset with 56.1 HOTA and 54.9 IDF1.
Authors: Deyi Ji, Siqi Gao, Lanyun Zhu, Yiru Zhao, Peng Xu, Hongtao Lu, Feng Zhao
Abstract: In this paper, we address the challenge of multi-object tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left/right, and moving up/down, lead to significantly greater complexity compared to fixed-camera MOT. Specifically, changes in the scene background not only render traditional frame-to-frame object IOU association methods ineffective but also introduce significant view shifts in the objects, which complicates tracking. To overcome these issues, we propose a novel universal HomView-MOT framework, which for the first time, harnesses the view Homography inherent in changing scenes to solve MOT challenges in moving environments, incorporating Homographic Matching and View-Centric concepts. We introduce a Fast Homography Estimation (FHE) algorithm for rapid computation of Homography matrices between video frames, enabling object View-Centric ID Learning (VCIL) and leveraging multi-view Homography to learn cross-view ID features. Concurrently, our Homographic Matching Filter (HMF) maps object bounding boxes from different frames onto a common view plane for a more realistic physical IOU association. Extensive experiments have proven that these innovations allow HomView-MOT to achieve state-of-the-art performance on prominent UAV MOT datasets VisDrone and UAVDT.
Authors: Qilong Zhao, Yifei Zhang, Mengdan Zhu, Siyi Gu, Yuyang Gao, Xiaofeng Yang, Liang Zhao
Abstract: Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications.
Authors: Uiwon Hwang, Jonghyun Lee, Juhyeon Shin, Sungroh Yoon
Abstract: In the face of the deep learning model's vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although the potential benefits of applying data augmentation to SFDA are attractive, several challenges arise such as the dependence on prior knowledge of class-preserving transformations and the increase in memory and computational requirements. In this paper, we propose Source-free Domain Adaptation Through the Lens of Data Augmentation (SF(DA)$^2$), a novel approach that leverages the benefits of data augmentation without suffering from these challenges. We construct an augmentation graph in the feature space of the pretrained model using the neighbor relationships between target features and propose spectral neighborhood clustering to identify partitions in the prediction space. Furthermore, we propose implicit feature augmentation and feature disentanglement as regularization loss functions that effectively utilize class semantic information within the feature space. These regularizers simulate the inclusion of an unlimited number of augmented target features into the augmentation graph while minimizing computational and memory demands. Our method shows superior adaptation performance in SFDA scenarios, including 2D image and 3D point cloud datasets and a highly imbalanced dataset.
Authors: Tianhe Wu, Kede Ma, Jie Liang, Yujiu Yang, Lei Zhang
Abstract: While Multimodal Large Language Models (MLLMs) have experienced significant advancement on visual understanding and reasoning, their potentials to serve as powerful, flexible, interpretable, and text-driven models for Image Quality Assessment (IQA) remains largely unexplored. In this paper, we conduct a comprehensive and systematic study of prompting MLLMs for IQA. Specifically, we first investigate nine prompting systems for MLLMs as the combinations of three standardized testing procedures in psychophysics (i.e., the single-stimulus, double-stimulus, and multiple-stimulus methods) and three popular prompting strategies in natural language processing (i.e., the standard, in-context, and chain-of-thought prompting). We then present a difficult sample selection procedure, taking into account sample diversity and uncertainty, to further challenge MLLMs equipped with the respective optimal prompting systems. We assess three open-source and one close-source MLLMs on several visual attributes of image quality (e.g., structural and textural distortions, color differences, and geometric transformations) in both full-reference and no-reference scenarios. Experimental results show that only the close-source GPT-4V provides a reasonable account for human perception of image quality, but is weak at discriminating fine-grained quality variations (e.g., color differences) and at comparing visual quality of multiple images, tasks humans can perform effortlessly.
Authors: Hongbo Chu, Qiehe Sun, Jiawen Li, Yuxuan Chen, Lizhong Zhang, Tian Guan, Anjia Han, Yonghong He
Abstract: Histopathological whole slide image (WSI) analysis with deep learning has become a research focus in computational pathology. The current paradigm is mainly based on multiple instance learning (MIL), in which approaches with Transformer as the backbone are well discussed. These methods convert WSI tasks into sequence tasks by representing patches as tokens in the WSI sequence. However, the feature complexity brought by high heterogeneity and the ultra-long sequences brought by gigapixel size makes Transformer-based MIL suffer from the challenges of high memory consumption, slow inference speed, and lack of performance. To this end, we propose a retentive MIL method called RetMIL, which processes WSI sequences through hierarchical feature propagation structure. At the local level, the WSI sequence is divided into multiple subsequences. Tokens of each subsequence are updated through a parallel linear retention mechanism and aggregated utilizing an attention layer. At the global level, subsequences are fused into a global sequence, then updated through a serial retention mechanism, and finally the slide-level representation is obtained through a global attention pooling. We conduct experiments on two public CAMELYON and BRACS datasets and an public-internal LUNG dataset, confirming that RetMIL not only achieves state-of-the-art performance but also significantly reduces computational overhead. Our code will be accessed shortly.
Authors: Junyang Wu, Yun Gu, Guang-Zhong Yang
Abstract: Visual odometry plays a crucial role in endoscopic imaging, yet the scarcity of realistic images with ground truth poses poses a significant challenge. Therefore, domain adaptation offers a promising approach to bridge the pre-operative planning domain with the intra-operative real domain for learning odometry information. However, existing methodologies suffer from inefficiencies in the training time. In this work, an efficient neural style transfer framework for endoscopic visual odometry is proposed, which compresses the time from pre-operative planning to testing phase to less than five minutes. For efficient traing, this work focuses on training modules with only a limited number of real images and we exploit pre-operative prior information to dramatically reduce training duration. Moreover, during the testing phase, we propose a novel Test Time Adaptation (TTA) method to mitigate the gap in lighting conditions between training and testing datasets. Experimental evaluations conducted on two public endoscope datasets showcase that our method achieves state-of-the-art accuracy in visual odometry tasks while boasting the fastest training speeds. These results demonstrate significant promise for intra-operative surgery applications.
Authors: Somenath Kuiry, Alaka Das, Mita Nasipuri, Nibaran Das
Abstract: Deep Learning, particularly Convolutional Neural Networks (CNN), has been successful in computer vision tasks and medical image analysis. However, modern CNNs can be overconfident, making them difficult to deploy in real-world scenarios. Researchers propose regularizing techniques, such as Label Smoothing (LS), which introduces soft labels for training data, making the classifier more regularized. LS captures disagreements or lack of confidence in the training phase, making the classifier more regularized. Although LS is quite simple and effective, traditional LS techniques utilize a weighted average between target distribution and a uniform distribution across the classes, which limits the objective of LS as well as the performance. This paper introduces a novel LS technique based on the confusion penalty, which treats model confusion for each class with more importance than others. We have performed extensive experiments with well-known CNN architectures with this technique on publicly available Colorectal Histology datasets and got satisfactory results. Also, we have compared our findings with the State-of-the-art and shown our method's efficacy with Reliability diagrams and t-distributed Stochastic Neighbor Embedding (t-SNE) plots of feature space.
Authors: Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang, Haijing Guo, Jiafeng Wang, Shuyong Gao, Wenqiang Zhang
Abstract: Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models, resulting in a substantial performance gap from white-box attacks. We observe that prior work overlooks the interaction mechanisms between modalities, which plays a crucial role in understanding the intricacies of VLP models. In response, we propose a novel attack, called Collaborative Multimodal Interaction Attack (CMI-Attack), leveraging modality interaction through embedding guidance and interaction enhancement. Specifically, attacking text at the embedding level while preserving semantics, as well as utilizing interaction image gradients to enhance constraints on perturbations of texts and images. Significantly, in the image-text retrieval task on Flickr30K dataset, CMI-Attack raises the transfer success rates from ALBEF to TCL, $\text{CLIP}_{\text{ViT}}$ and $\text{CLIP}_{\text{CNN}}$ by 8.11%-16.75% over state-of-the-art methods. Moreover, CMI-Attack also demonstrates superior performance in cross-task generalization scenarios. Our work addresses the underexplored realm of transfer attacks on VLP models, shedding light on the importance of modality interaction for enhanced adversarial robustness.
Authors: Soumyajyoti Dey, Sukanta Chakraborty, Utso Guha Roy, Nibaran Das
Abstract: Cytology image segmentation is quite challenging due to its complex cellular structure and multiple overlapping regions. On the other hand, for supervised machine learning techniques, we need a large amount of annotated data, which is costly. In recent years, late fusion techniques have given some promising performances in the field of image classification. In this paper, we have explored a fuzzy-based late fusion techniques for cytology image segmentation. This fusion rule integrates three traditional semantic segmentation models UNet, SegNet, and PSPNet. The technique is applied on two cytology image datasets, i.e., cervical cytology(HErlev) and breast cytology(JUCYT-v1) image datasets. We have achieved maximum MeanIoU score 84.27% and 83.79% on the HErlev dataset and JUCYT-v1 dataset after the proposed late fusion technique, respectively which are better than that of the traditional fusion rules such as average probability, geometric mean, Borda Count, etc. The codes of the proposed model are available on GitHub.
Authors: Yuanxin Zhao, Mi Zhang, Bingnan Yang, Zhan Zhang, Jiaju Kang, Jianya Gong
Abstract: Image-text retrieval (ITR) plays a significant role in making informed decisions for various remote sensing (RS) applications. Nonetheless, creating ITR datasets containing vision and language modalities not only requires significant geo-spatial sampling area but also varing categories and detailed descriptions. To this end, we introduce an image caption dataset LuojiaHOG, which is geospatial-aware, label-extension-friendly and comprehensive-captioned. LuojiaHOG involves the hierarchical spatial sampling, extensible classification system to Open Geospatial Consortium (OGC) standards, and detailed caption generation. In addition, we propose a CLIP-based Image Semantic Enhancement Network (CISEN) to promote sophisticated ITR. CISEN consists of two components, namely dual-path knowledge transfer and progressive cross-modal feature fusion. Comprehensive statistics on LuojiaHOG reveal the richness in sampling diversity, labels quantity and descriptions granularity. The evaluation on LuojiaHOG is conducted across various state-of-the-art ITR models, including ALBEF, ALIGN, CLIP, FILIP, Wukong, GeoRSCLIP and CISEN. We use second- and third-level labels to evaluate these vision-language models through adapter-tuning and CISEN demonstrates superior performance. For instance, it achieves the highest scores with WMAP@5 of 88.47\% and 87.28\% on third-level ITR tasks, respectively. In particular, CISEN exhibits an improvement of approximately 1.3\% and 0.9\% in terms of WMAP@5 compared to its baseline. These findings highlight CISEN advancements accurately retrieving pertinent information across image and text. LuojiaHOG and CISEN can serve as a foundational resource for future RS image-text alignment research, facilitating a wide range of vision-language applications.
Authors: Guanzhou Ke, Bo Wang, Xiaoli Wang, Shengfeng He
Abstract: Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting a commonly overlooked aspect: the redundancy between view-consistent and view-specific representations. To this end, we propose an innovative framework for multi-view representation learning, which incorporates a technique we term 'distilled disentangling'. Our method introduces the concept of masked cross-view prediction, enabling the extraction of compact, high-quality view-consistent representations from various sources without incurring extra computational overhead. Additionally, we develop a distilled disentangling module that efficiently filters out consistency-related information from multi-view representations, resulting in purer view-specific representations. This approach significantly reduces redundancy between view-consistent and view-specific representations, enhancing the overall efficiency of the learning process. Our empirical evaluations reveal that higher mask ratios substantially improve the quality of view-consistent representations. Moreover, we find that reducing the dimensionality of view-consistent representations relative to that of view-specific representations further refines the quality of the combined representations. Our code is accessible at: https://github.com/Guanzhou-Ke/MRDD.
Authors: Seunghyeon Seo, Yeonjin Chang, Jayeon Yoo, Seungwoo Lee, Hojun Lee, Nojun Kwak
Abstract: Recent advancements in the Neural Radiance Field (NeRF) have bolstered its capabilities for novel view synthesis, yet its reliance on dense multi-view training images poses a practical challenge. Addressing this, we propose HourglassNeRF, an effective regularization-based approach with a novel hourglass casting strategy. Our proposed hourglass is conceptualized as a bundle of additional rays within the area between the original input ray and its corresponding reflection ray, by featurizing the conical frustum via Integrated Positional Encoding (IPE). This design expands the coverage of unseen views and enables an adaptive high-frequency regularization based on target pixel photo-consistency. Furthermore, we propose luminance consistency regularization based on the Lambertian assumption, which is known to be effective for training a set of augmented rays under the few-shot setting. Leveraging the inherent property of a Lambertian surface, which retains consistent luminance irrespective of the viewing angle, we assume our proposed hourglass as a collection of flipped diffuse reflection rays and enhance the luminance consistency between the original input ray and its corresponding hourglass, resulting in more physically grounded training framework and performance improvement. Our HourglassNeRF outperforms its baseline and achieves competitive results on multiple benchmarks with sharply rendered fine details. The code will be available.
Authors: Yeongtak Oh, Jonghyun Lee, Jooyoung Choi, Dahuin Jung, Uiwon Hwang, Sungroh Yoon
Abstract: Test-time adaptation (TTA) addresses the unforeseen distribution shifts occurring during test time. In TTA, both performance and, memory and time consumption serve as crucial considerations. A recent diffusion-based TTA approach for restoring corrupted images involves image-level updates. However, using pixel space diffusion significantly increases resource requirements compared to conventional model updating TTA approaches, revealing limitations as a TTA method. To address this, we propose a novel TTA method by leveraging a latent diffusion model (LDM) based image editing model and fine-tuning it with our newly introduced corruption modeling scheme. This scheme enhances the robustness of the diffusion model against distribution shifts by creating (clean, corrupted) image pairs and fine-tuning the model to edit corrupted images into clean ones. Moreover, we introduce a distilled variant to accelerate the model for corruption editing using only 4 network function evaluations (NFEs). We extensively validated our method across various architectures and datasets including image and video domains. Our model achieves the best performance with a 100 times faster runtime than that of a diffusion-based baseline. Furthermore, it outpaces the speed of the model updating TTA method based on data augmentation threefold, rendering an image-level updating approach more practical.
Authors: Anjali Karangiya, Anirudh Sharma, Divax Shah, Kartavya Badgujar, Dr. Chintan Thacker, Dainik Dave
Abstract: The proliferation of digital images and the advancements in deep learning have paved the way for innovative solutions in various domains, especially in the field of image classification. Our project presents an in-depth study and implementation of an image classification system specifically tailored to identify and classify images of Indian cities. Drawing from an extensive dataset, our model classifies images into five major Indian cities: Ahmedabad, Delhi, Kerala, Kolkata, and Mumbai to recognize the distinct features and characteristics of each city/state. To achieve high precision and recall rates, we adopted two approaches. The first, a vanilla Convolutional Neural Network (CNN) and then we explored the power of transfer learning by leveraging the VGG16 model. The vanilla CNN achieved commendable accuracy and the VGG16 model achieved a test accuracy of 63.6%. Evaluations highlighted the strengths and potential areas of improvement, positioning our model as not only competitive but also scalable for broader applications. With an emphasis on open-source ethos, our work aims to contribute to the community, encouraging further development and diverse applications. Our findings demonstrate the potential applications in tourism, urban planning, and even real-time location identification systems, among others.
Authors: Moseli Mots'oehli, Anton Nikolaev, Wawan B. IGede, John Lynham, Peter J. Mous, Peter Sadowski
Abstract: Fish stock assessment often involves manual fish counting by taxonomy specialists, which is both time-consuming and costly. We propose an automated computer vision system that performs both taxonomic classification and fish size estimation from images taken with a low-cost digital camera. The system first performs object detection and segmentation using a Mask R-CNN to identify individual fish from images containing multiple fish, possibly consisting of different species. Then each fish species is classified and the predicted length using separate machine learning models. These models are trained on a dataset of 50,000 hand-annotated images containing 163 different fish species, ranging in length from 10cm to 250cm. Evaluated on held-out test data, our system achieves a $92\%$ intersection over union on the fish segmentation task, a $89\%$ top-1 classification accuracy on single fish species classification, and a $2.3$~cm mean error on the fish length estimation task.
Authors: Zhiheng Li, Muheng Li, Jixuan Fan, Lei Chen, Yansong Tang, Jie Zhou, Jiwen Lu
Abstract: Scale arbitrary super-resolution based on implicit image function gains increasing popularity since it can better represent the visual world in a continuous manner. However, existing scale arbitrary works are trained and evaluated on simulated datasets, where low-resolution images are generated from their ground truths by the simplest bicubic downsampling. These models exhibit limited generalization to real-world scenarios due to the greater complexity of real-world degradations. To address this issue, we build a RealArbiSR dataset, a new real-world super-resolution benchmark with both integer and non-integer scaling factors for the training and evaluation of real-world scale arbitrary super-resolution. Moreover, we propose a Dual-level Deformable Implicit Representation (DDIR) to solve real-world scale arbitrary super-resolution. Specifically, we design the appearance embedding and deformation field to handle both image-level and pixel-level deformations caused by real-world degradations. The appearance embedding models the characteristics of low-resolution inputs to deal with photometric variations at different scales, and the pixel-based deformation field learns RGB differences which result from the deviations between the real-world and simulated degradations at arbitrary coordinates. Extensive experiments show our trained model achieves state-of-the-art performance on the RealArbiSR and RealSR benchmarks for real-world scale arbitrary super-resolution. Our dataset as well as source code will be publicly available.
Authors: Chengbin Du, Yanxi Li, Chang Xu
Abstract: Visual State Space Model (VMamba) has recently emerged as a promising architecture, exhibiting remarkable performance in various computer vision tasks. However, its robustness has not yet been thoroughly studied. In this paper, we delve into the robustness of this architecture through comprehensive investigations from multiple perspectives. Firstly, we investigate its robustness to adversarial attacks, employing both whole-image and patch-specific adversarial attacks. Results demonstrate superior adversarial robustness compared to Transformer architectures while revealing scalability weaknesses. Secondly, the general robustness of VMamba is assessed against diverse scenarios, including natural adversarial examples, out-of-distribution data, and common corruptions. VMamba exhibits exceptional generalizability with out-of-distribution data but shows scalability weaknesses against natural adversarial examples and common corruptions. Additionally, we explore VMamba's gradients and back-propagation during white-box attacks, uncovering unique vulnerabilities and defensive capabilities of its novel components. Lastly, the sensitivity of VMamba to image structure variations is examined, highlighting vulnerabilities associated with the distribution of disturbance areas and spatial information, with increased susceptibility closer to the image center. Through these comprehensive studies, we contribute to a deeper understanding of VMamba's robustness, providing valuable insights for refining and advancing the capabilities of deep neural networks in computer vision applications.
Authors: Federico Nocentini, Thomas Besnier, Claudio Ferrari, Sylvain Arguillere, Stefano Berretti, Mohamed Daoudi
Abstract: Speech-driven 3D talking heads generation has emerged as a significant area of interest among researchers, presenting numerous challenges. Existing methods are constrained by animating faces with fixed topologies, wherein point-wise correspondence is established, and the number and order of points remains consistent across all identities the model can animate. In this work, we present ScanTalk, a novel framework capable of animating 3D faces in arbitrary topologies including scanned data. Our approach relies on the DiffusionNet architecture to overcome the fixed topology constraint, offering promising avenues for more flexible and realistic 3D animations. By leveraging the power of DiffusionNet, ScanTalk not only adapts to diverse facial structures but also maintains fidelity when dealing with scanned data, thereby enhancing the authenticity and versatility of generated 3D talking heads. Through comprehensive comparisons with state-of-the-art methods, we validate the efficacy of our approach, demonstrating its capacity to generate realistic talking heads comparable to existing techniques. While our primary objective is to develop a generic method free from topological constraints, all state-of-the-art methodologies are bound by such limitations. Code for reproducing our results, and the pre-trained model will be made available.
Authors: Hongxiang Zhao, Xili Dai, Jianan Wang, Shengbang Tong, Jingyuan Zhang, Weida Wang, Lei Zhang, Yi Ma
Abstract: Large image diffusion models have demonstrated zero-shot capability in novel view synthesis (NVS). However, existing diffusion-based NVS methods struggle to generate novel views that are accurately consistent with the corresponding ground truth poses and appearances, even on the training set. This consequently limits the performance of downstream tasks, such as image-to-multiview generation and 3D reconstruction. We realize that such inconsistency is largely due to the fact that it is difficult to enforce accurate pose and appearance alignment directly in the diffusion training, as mostly done by existing methods such as Zero123. To remedy this problem, we propose Ctrl123, a closed-loop transcription-based NVS diffusion method that enforces alignment between the generated view and ground truth in a pose-sensitive feature space. Our extensive experiments demonstrate the effectiveness of Ctrl123 on the tasks of NVS and 3D reconstruction, achieving significant improvements in both multiview-consistency and pose-consistency over existing methods.
Authors: Baiyuan Chen
Abstract: This paper presents an innovative enhancement to the Sphere as Prior Generative Adversarial Network (SP-GAN) model, a state-of-the-art GAN designed for point cloud generation. A novel method is introduced for point cloud generation that elevates the structural integrity and overall quality of the generated point clouds by incorporating topological priors into the training process of the generator. Specifically, this work utilizes the K-means algorithm to segment a point cloud from the repository into clusters and extract centroids, which are then used as priors in the generation process of the SP-GAN. Furthermore, the discriminator component of the SP-GAN utilizes the identical point cloud that contributed the centroids, ensuring a coherent and consistent learning environment. This strategic use of centroids as intuitive guides not only boosts the efficiency of global feature learning but also substantially improves the structural coherence and fidelity of the generated point clouds. By applying the K-means algorithm to generate centroids as the prior, the work intuitively and experimentally demonstrates that such a prior enhances the quality of generated point clouds.
Authors: Xuehao Wang, Feiyang Ye, Yu Zhang
Abstract: The Segment Anything Model (SAM), with its remarkable zero-shot capability, has been proven to be a powerful foundation model for image segmentation tasks, which is an important task in computer vision. However, the transfer of its rich semantic information to multiple different downstream tasks remains unexplored. In this paper, we propose the Task-Aware Low-Rank Adaptation (TA-LoRA) method, which enables SAM to work as a foundation model for multi-task learning. Specifically, TA-LoRA injects an update parameter tensor into each layer of the encoder in SAM and leverages a low-rank tensor decomposition method to incorporate both task-shared and task-specific information. Furthermore, we introduce modified SAM (mSAM) for multi-task learning where we remove the prompt encoder of SAM and use task-specific no mask embeddings and mask decoder for each task. Extensive experiments conducted on benchmark datasets substantiate the efficacy of TA-LoRA in enhancing the performance of mSAM across multiple downstream tasks.
Authors: Zhe Kong, Yong Zhang, Tianyu Yang, Tao Wang, Kaihao Zhang, Bizhu Wu, Guanying Chen, Wei Liu, Wenhan Luo
Abstract: Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage sampling solution. The first stage takes charge of layout generation and visual comprehension information collection for handling occlusions. The second one utilizes the acquired visual comprehension information and the designed noise blending to integrate multiple concepts while considering occlusions. We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout. Moreover, our method can be combined with various single-concept models, such as LoRA and InstantID without additional tuning. Especially, LoRA models on civitai.com can be exploited directly. Extensive experiments demonstrate that OMG exhibits superior performance in multi-concept personalization.
Authors: Li-Yuan Tsao, Yi-Chen Lo, Chia-Che Chang, Hao-Wei Chen, Roy Tseng, Chien Feng, Chun-Yi Lee
Abstract: Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. To overcome these issues, this work introduces a conditional learned prior to the inference phase of a flow-based SR model. This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image. Our framework is designed to seamlessly integrate with any contemporary flow-based SR model without modifying its architecture or pre-trained weights. We evaluate the effectiveness of our proposed framework through extensive experiments and ablation analyses. The proposed framework successfully addresses all the inherent issues in flow-based SR models and enhances their performance in various SR scenarios. Our code is available at: https://github.com/liyuantsao/FlowSR-LP
Authors: Yash Bhalgat, Iro Laina, Jo\~ao F. Henriques, Andrew Zisserman, Andrea Vedaldi
Abstract: Understanding complex scenes at multiple levels of abstraction remains a formidable challenge in computer vision. To address this, we introduce Nested Neural Feature Fields (N2F2), a novel approach that employs hierarchical supervision to learn a single feature field, wherein different dimensions within the same high-dimensional feature encode scene properties at varying granularities. Our method allows for a flexible definition of hierarchies, tailored to either the physical dimensions or semantics or both, thereby enabling a comprehensive and nuanced understanding of scenes. We leverage a 2D class-agnostic segmentation model to provide semantically meaningful pixel groupings at arbitrary scales in the image space, and query the CLIP vision-encoder to obtain language-aligned embeddings for each of these segments. Our proposed hierarchical supervision method then assigns different nested dimensions of the feature field to distill the CLIP embeddings using deferred volumetric rendering at varying physical scales, creating a coarse-to-fine representation. Extensive experiments show that our approach outperforms the state-of-the-art feature field distillation methods on tasks such as open-vocabulary 3D segmentation and localization, demonstrating the effectiveness of the learned nested feature field.
Authors: Janmesh Ukey, Tushar Kataria, Shireen Y. Elhabian
Abstract: Statistical Shape Modeling (SSM) is an effective method for quantitatively analyzing anatomical variations within populations. However, its utility is limited by the need for manual segmentations of anatomies, a task that relies on the scarce expertise of medical professionals. Recent advances in deep learning have provided a promising approach that automatically generates statistical representations from unsegmented images. Once trained, these deep learning-based models eliminate the need for manual segmentation for new subjects. Nonetheless, most current methods still require manual pre-alignment of image volumes and specifying a bounding box around the target anatomy prior for inference, resulting in a partially manual inference process. Recent approaches facilitate anatomy localization but only estimate statistical representations at the population level. However, they cannot delineate anatomy directly in images and are limited to modeling a single anatomy. Here, we introduce MASSM, a novel end-to-end deep learning framework that simultaneously localizes multiple anatomies in an image, estimates population-level statistical representations, and delineates each anatomy. Our findings emphasize the crucial role of local correspondences, showcasing their indispensability in providing superior shape information for medical imaging tasks.
Authors: Minkyu Choi, Harsh Goel, Mohammad Omama, Yunhao Yang, Sahil Shah, Sandeep Chinchali
Abstract: The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems. While state-of-the-art foundation models, like VideoLLaMA and ViCLIP, are proficient in short-term semantic understanding, they surprisingly fail at long-term reasoning across frames. A key reason for this failure is that they intertwine per-frame perception and temporal reasoning into a single deep network. Hence, decoupling but co-designing semantic understanding and temporal reasoning is essential for efficient scene identification. We propose a system that leverages vision-language models for semantic understanding of individual frames but effectively reasons about the long-term evolution of events using state machines and temporal logic (TL) formulae that inherently capture memory. Our TL-based reasoning improves the F1 score of complex event identification by 9-15% compared to benchmarks that use GPT4 for reasoning on state-of-the-art self-driving datasets such as Waymo and NuScenes.
Authors: Ziqi Lu, Jianbo Ye, Xiaohan Fei, Xiaolong Li, Jiawei Mo, Ashwin Swaminathan, Stefano Soatto
Abstract: Neural Radiance Field (NeRF), as an implicit 3D scene representation, lacks inherent ability to accommodate changes made to the initial static scene. If objects are reconfigured, it is difficult to update the NeRF to reflect the new state of the scene without time-consuming data re-capturing and NeRF re-training. To address this limitation, we develop the first update method for NeRFs to physical changes. Our method takes only sparse new images (e.g. 4) of the altered scene as extra inputs and update the pre-trained NeRF in around 1 to 2 minutes. Particularly, we develop a pipeline to identify scene changes and update the NeRF accordingly. Our core idea is the use of a second helper NeRF to learn the local geometry and appearance changes, which sidesteps the optimization difficulties in direct NeRF fine-tuning. The interpolation power of the helper NeRF is the key to accurately reconstruct the un-occluded objects regions under sparse view supervision. Our method imposes no constraints on NeRF pre-training, and requires no extra user input or explicit semantic priors. It is an order of magnitude faster than re-training NeRF from scratch while maintaining on-par and even superior performance.
Authors: Abu Zahid Bin Aziz, Mokshagna Sai Teja Karanam, Tushar Kataria, Shireen Y. Elhabian
Abstract: Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper models. Despite their success, transformer-based models require substantial resources for training, including data, memory, and computational power, which may restrict their applicability for end users with limited resources. In particular, existing transformer-based 3D image registration architectures face three critical gaps that challenge their efficiency and effectiveness. Firstly, while mitigating the quadratic complexity of full attention by focusing on local regions, window-based attention mechanisms often fail to adequately integrate local and global information. Secondly, feature similarities across attention heads that were recently found in multi-head attention architectures indicate a significant computational redundancy, suggesting that the capacity of the network could be better utilized to enhance performance. Lastly, the granularity of tokenization, a key factor in registration accuracy, presents a trade-off; smaller tokens improve detail capture at the cost of higher computational complexity, increased memory demands, and a risk of overfitting. Here, we propose EfficientMorph, a transformer-based architecture for unsupervised 3D image registration. It optimizes the balance between local and global attention through a plane-based attention mechanism, reduces computational redundancy via cascaded group attention, and captures fine details without compromising computational efficiency, thanks to a Hi-Res tokenization strategy complemented by merging operations. Notably, EfficientMorph sets a new benchmark for performance on the OASIS dataset with 16-27x fewer parameters.
Authors: Jiachen Li, Weixi Feng, Wenhu Chen, William Yang Wang
Abstract: Latent Consistency Distillation (LCD) has emerged as a promising paradigm for efficient text-to-image synthesis. By distilling a latent consistency model (LCM) from a pre-trained teacher latent diffusion model (LDM), LCD facilitates the generation of high-fidelity images within merely 2 to 4 inference steps. However, the LCM's efficient inference is obtained at the cost of the sample quality. In this paper, we propose compensating the quality loss by aligning LCM's output with human preference during training. Specifically, we introduce Reward Guided LCD (RG-LCD), which integrates feedback from a reward model (RM) into the LCD process by augmenting the original LCD loss with the objective of maximizing the reward associated with LCM's single-step generation. As validated through human evaluation, when trained with the feedback of a good RM, the 2-step generations from our RG-LCM are favored by humans over the 50-step DDIM samples from the teacher LDM, representing a 25 times inference acceleration without quality loss. As directly optimizing towards differentiable RMs can suffer from over-optimization, we overcome this difficulty by proposing the use of a latent proxy RM (LRM). This novel component serves as an intermediary, connecting our LCM with the RM. Empirically, we demonstrate that incorporating the LRM into our RG-LCD successfully avoids high-frequency noise in the generated images, contributing to both improved FID on MS-COCO and a higher HPSv2.1 score on HPSv2's test set, surpassing those achieved by the baseline LCM.
Authors: Guangyu Cui, Sung Ha Kang
Abstract: We propose Texture Edge detection using Patch consensus (TEP) which is a training-free method to detect the boundary of texture. We propose a new simple way to identify the texture edge location, using the consensus of segmented local patch information. While on the boundary, even using local patch information, the distinction between textures are typically not clear, but using neighbor consensus give a clear idea of the boundary. We utilize local patch, and its response against neighboring regions, to emphasize the similarities and the differences across different textures. The step of segmentation of response further emphasizes the edge location, and the neighborhood voting gives consensus and stabilize the edge detection. We analyze texture as a stationary process to give insight into the patch width parameter verses the quality of edge detection. We derive the necessary condition for textures to be distinguished, and analyze the patch width with respect to the scale of textures. Various experiments are presented to validate the proposed model.
Authors: Zhen Zeng, Rachneet Kaur, Suchetha Siddagangappa, Tucker Balch, Manuela Veloso
Abstract: Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often employing lineplots as the visual representation of time series data. In this paper, we propose a novel approach that uses time-frequency spectrograms as the visual representation of time series data. We introduce the use of a vision transformer for multimodal learning, showcasing the advantages of our approach across diverse datasets from different domains. To evaluate its effectiveness, we compare our method against statistical baselines (EMA and ARIMA), a state-of-the-art deep learning-based approach (DeepAR), other visual representations of time series data (lineplot images), and an ablation study on using only the time series as input. Our experiments demonstrate the benefits of utilizing spectrograms as a visual representation for time series data, along with the advantages of employing a vision transformer for simultaneous learning in both the time and frequency domains.
Authors: Chenxin Li, Hengyu Liu, Yifan Liu, Brandon Y. Feng, Wuyang Li, Xinyu Liu, Zhen Chen, Jing Shao, Yixuan Yuan
Abstract: Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for machine learning. Despite progress in generating 2D medical images, the complex domain of clinical video generation has largely remained untapped.This paper introduces \model, an innovative approach to generate medical videos that simulate clinical endoscopy scenes. We present a novel generative model design that integrates a meticulously crafted spatial-temporal video transformer with advanced 2D vision foundation model priors, explicitly modeling spatial-temporal dynamics during video generation. We also pioneer the first public benchmark for endoscopy simulation with video generation models, adapting existing state-of-the-art methods for this endeavor.Endora demonstrates exceptional visual quality in generating endoscopy videos, surpassing state-of-the-art methods in extensive testing. Moreover, we explore how this endoscopy simulator can empower downstream video analysis tasks and even generate 3D medical scenes with multi-view consistency. In a nutshell, Endora marks a notable breakthrough in the deployment of generative AI for clinical endoscopy research, setting a substantial stage for further advances in medical content generation. For more details, please visit our project page: https://endora-medvidgen.github.io/.
Authors: Jie Ren, Yaxin Li, Shenglai Zen, Han Xu, Lingjuan Lyu, Yue Xing, Jiliang Tang
Abstract: Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images from their training data, raising tremendous concerns about potential copyright infringement and privacy risks. In our study, we provide a novel perspective to understand this memorization phenomenon by examining its relationship with cross-attention mechanisms. We reveal that during memorization, the cross-attention tends to focus disproportionately on the embeddings of specific tokens. The diffusion model is overfitted to these token embeddings, memorizing corresponding training images. To elucidate this phenomenon, we further identify and discuss various intrinsic findings of cross-attention that contribute to memorization. Building on these insights, we introduce an innovative approach to detect and mitigate memorization in diffusion models. The advantage of our proposed method is that it will not compromise the speed of either the training or the inference processes in these models while preserving the quality of generated images. Our code is available at https://github.com/renjie3/MemAttn .
Authors: Ye Wang, Zili Yi, Rui Ma
Abstract: Personalized text-to-image (T2I) models not only produce lifelike and varied visuals but also allow users to tailor the images to fit their personal taste. These personalization techniques can grasp the essence of a concept through a collection of images, or adjust a pre-trained text-to-image model with a specific image input for subject-driven or attribute-aware guidance. Yet, accurately capturing the distinct visual attributes of an individual image poses a challenge for these methods. To address this issue, we introduce OSTAF, a novel parameter-efficient one-shot fine-tuning method which only utilizes one reference image for T2I personalization. A novel hypernetwork-powered attribute-focused fine-tuning mechanism is employed to achieve the precise learning of various attribute features (e.g., appearance, shape or drawing style) from the reference image. Comparing to existing image customization methods, our method shows significant superiority in attribute identification and application, as well as achieves a good balance between efficiency and output quality.
Authors: Zhihao Liang, Qi Zhang, Wenbo Hu, Ying Feng, Lei Zhu, Kui Jia
Abstract: The 3D Gaussian Splatting (3DGS) gained its popularity recently by combining the advantages of both primitive-based and volumetric 3D representations, resulting in improved quality and efficiency for 3D scene rendering. However, 3DGS is not alias-free, and its rendering at varying resolutions could produce severe blurring or jaggies. This is because 3DGS treats each pixel as an isolated, single point rather than as an area, causing insensitivity to changes in the footprints of pixels. Consequently, this discrete sampling scheme inevitably results in aliasing, owing to the restricted sampling bandwidth. In this paper, we derive an analytical solution to address this issue. More specifically, we use a conditioned logistic function as the analytic approximation of the cumulative distribution function (CDF) in a one-dimensional Gaussian signal and calculate the Gaussian integral by subtracting the CDFs. We then introduce this approximation in the two-dimensional pixel shading, and present Analytic-Splatting, which analytically approximates the Gaussian integral within the 2D-pixel window area to better capture the intensity response of each pixel. Moreover, we use the approximated response of the pixel window integral area to participate in the transmittance calculation of volume rendering, making Analytic-Splatting sensitive to the changes in pixel footprint at different resolutions. Experiments on various datasets validate that our approach has better anti-aliasing capability that gives more details and better fidelity.
Authors: Xiaoji Zheng, Lixiu Wu, Zhijie Yan, Yuanrong Tang, Hao Zhao, Chen Zhong, Bokui Chen, Jiangtao Gong
Abstract: Motion prediction is among the most fundamental tasks in autonomous driving. Traditional methods of motion forecasting primarily encode vector information of maps and historical trajectory data of traffic participants, lacking a comprehensive understanding of overall traffic semantics, which in turn affects the performance of prediction tasks. In this paper, we utilized Large Language Models (LLMs) to enhance the global traffic context understanding for motion prediction tasks. We first conducted systematic prompt engineering, visualizing complex traffic environments and historical trajectory information of traffic participants into image prompts -- Transportation Context Map (TC-Map), accompanied by corresponding text prompts. Through this approach, we obtained rich traffic context information from the LLM. By integrating this information into the motion prediction model, we demonstrate that such context can enhance the accuracy of motion predictions. Furthermore, considering the cost associated with LLMs, we propose a cost-effective deployment strategy: enhancing the accuracy of motion prediction tasks at scale with 0.7\% LLM-augmented datasets. Our research offers valuable insights into enhancing the understanding of traffic scenes of LLMs and the motion prediction performance of autonomous driving.
Authors: Al Amin, Deo Chimba, Kamrul Hasan, Emmanuel Samson
Abstract: Crashes and delays at Railroad Highway Grade Crossings (RHGC), where highways and railroads intersect, pose significant safety concerns for the U.S. Federal Railroad Administration (FRA). Despite the critical importance of addressing accidents and traffic delays at highway-railroad intersections, there is a notable dearth of research on practical solutions for managing these issues. In response to this gap in the literature, our study introduces an intelligent system that leverages machine learning and computer vision techniques to enhance safety at Railroad Highway Grade crossings (RHGC). This research proposed a Non-Maximum Suppression (NMS)- based ensemble model that integrates a variety of YOLO variants, specifically YOLOv5S, YOLOv5M, and YOLOv5L, for grade-crossing object detection, utilizes segmentation techniques from the UNet architecture for detecting approaching rail at a grade crossing. Both methods are implemented on a Raspberry Pi. Moreover, the strategy employs high-definition cameras installed at the RHGC. This framework enables the system to monitor objects within the Region of Interest (ROI) at crossings, detect the approach of trains, and clear the crossing area before a train arrives. Regarding accuracy, precision, recall, and Intersection over Union (IoU), the proposed state-of-the-art NMS-based object detection ensemble model achieved 96% precision. In addition, the UNet segmentation model obtained a 98% IoU value. This automated railroad grade crossing system powered by artificial intelligence represents a promising solution for enhancing safety at highway-railroad intersections.
Authors: Yuan Zhou, Richang Hong, Yanrong Guo, Lin Liu, Shijie Hao, Hanwang Zhang
Abstract: In this paper, we propose to tackle Few-Shot Class-Incremental Learning (FSCIL) from a new perspective, i.e., relation disentanglement, which means enhancing FSCIL via disentangling spurious relation between categories. The challenge of disentangling spurious correlations lies in the poor controllability of FSCIL. On one hand, an FSCIL model is required to be trained in an incremental manner and thus it is very hard to directly control relationships between categories of different sessions. On the other hand, training samples per novel category are only in the few-shot setting, which increases the difficulty of alleviating spurious relation issues as well. To overcome this challenge, in this paper, we propose a new simple-yet-effective method, called ConTrollable Relation-disentangLed Few-Shot Class-Incremental Learning (CTRL-FSCIL). Specifically, during the base session, we propose to anchor base category embeddings in feature space and construct disentanglement proxies to bridge gaps between the learning for category representations in different sessions, thereby making category relation controllable. During incremental learning, the parameters of the backbone network are frozen in order to relieve the negative impact of data scarcity. Moreover, a disentanglement loss is designed to effectively guide a relation disentanglement controller to disentangle spurious correlations between the embeddings encoded by the backbone. In this way, the spurious correlation issue in FSCIL can be suppressed. Extensive experiments on CIFAR-100, mini-ImageNet, and CUB-200 datasets demonstrate the effectiveness of our CTRL-FSCIL method.
Authors: Haoxi Zhang, Xinxu Zhang, Yuanxin Lin, Maiqi Wang, Yi Lai, Yu Wang, Linfeng Yu, Yufeng Xu, Ran Cheng, Edward Szczerbicki
Abstract: Automatic karyotype analysis is often defined as a visual perception task focused solely on chromosomal object-level modeling. This definition has led most existing methods to overlook componential and holistic information, significantly constraining model performance. Moreover, the lack of interpretability in current technologies hinders clinical adoption. In this paper, we introduce Tokensome, a novel vision-language model based on chromosome tokenization for explainable and cognitive karyotyping. Tokensome elevates the method from the conventional visual perception layer to the cognitive decision-making layer. This elevation enables the integration of domain knowledge and cognitive reasoning via knowledge graphs and LLMs, markedly enhancing model's explainability and facilitating abnormality detection.
Authors: Jinxiang Liu, Yikun Liu, Fei Zhang, Chen Ju, Ya Zhang, Yanfeng Wang
Abstract: Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames. Although great progress has been witnessed, we experimentally reveal that current methods reach marginal performance gain within the use of the unlabeled frames, leading to the underutilization issue. To fully explore the potential of the unlabeled frames for AVS, we explicitly divide them into two categories based on their temporal characteristics, i.e., neighboring frame (NF) and distant frame (DF). NFs, temporally adjacent to the labeled frame, often contain rich motion information that assists in the accurate localization of sounding objects. Contrary to NFs, DFs have long temporal distances from the labeled frame, which share semantic-similar objects with appearance variations. Considering their unique characteristics, we propose a versatile framework that effectively leverages them to tackle AVS. Specifically, for NFs, we exploit the motion cues as the dynamic guidance to improve the objectness localization. Besides, we exploit the semantic cues in DFs by treating them as valid augmentations to the labeled frames, which are then used to enrich data diversity in a self-training manner. Extensive experimental results demonstrate the versatility and superiority of our method, unleashing the power of the abundant unlabeled frames.
Authors: Kangyang Xie, Binbin Yang, Hao Chen, Meng Wang, Cheng Zou, Hui Xue, Ming Yang, Chunhua Shen
Abstract: Beyond the superiority of the text-to-image diffusion model in generating high-quality images, recent studies have attempted to uncover its potential for adapting the learned semantic knowledge to visual perception tasks. In this work, instead of translating a generative diffusion model into a visual perception model, we explore to retain the generative ability with the perceptive adaptation. To accomplish this, we present Zippo, a unified framework for zipping the color and transparency distributions into a single diffusion model by expanding the diffusion latent into a joint representation of RGB images and alpha mattes. By alternatively selecting one modality as the condition and then applying the diffusion process to the counterpart modality, Zippo is capable of generating RGB images from alpha mattes and predicting transparency from input images. In addition to single-modality prediction, we propose a modality-aware noise reassignment strategy to further empower Zippo with jointly generating RGB images and its corresponding alpha mattes under the text guidance. Our experiments showcase Zippo's ability of efficient text-conditioned transparent image generation and present plausible results of Matte-to-RGB and RGB-to-Matte translation.
Authors: Xiaohao Xu, Yunkang Cao, Yongqi Chen, Weiming Shen, Xiaonan Huang
Abstract: Anomaly detection is vital in various industrial scenarios, including the identification of unusual patterns in production lines and the detection of manufacturing defects for quality control. Existing techniques tend to be specialized in individual scenarios and lack generalization capacities. In this study, we aim to develop a generic anomaly detection model applicable across multiple scenarios. To achieve this, we customize generic visual-language foundation models that possess extensive knowledge and robust reasoning abilities into anomaly detectors and reasoners. Specifically, we introduce a multi-modal prompting strategy that incorporates domain knowledge from experts as conditions to guide the models. Our approach considers multi-modal prompt types, including task descriptions, class context, normality rules, and reference images. In addition, we unify the input representation of multi-modality into a 2D image format, enabling multi-modal anomaly detection and reasoning. Our preliminary studies demonstrate that combining visual and language prompts as conditions for customizing the models enhances anomaly detection performance. The customized models showcase the ability to detect anomalies across different data modalities such as images and point clouds. Qualitative case studies further highlight the anomaly detection and reasoning capabilities, particularly for multi-object scenes and temporal data. Our code is available at https://github.com/Xiaohao-Xu/Customizable-VLM.
Authors: Zixian Ma, Weikai Huang, Jieyu Zhang, Tanmay Gupta, Ranjay Krishna
Abstract: Real-world multi-modal problems are rarely solved by a single machine learning model, and often require multi-step computational plans that involve stitching several models. Tool-augmented LLMs hold tremendous promise for automating the generation of such computational plans. However, the lack of standardized benchmarks for evaluating LLMs as planners for multi-step multi-modal tasks has prevented a systematic study of planner design decisions. Should LLMs generate a full plan in a single shot or step-by-step? Should they invoke tools directly with Python code or through structured data formats like JSON? Does feedback improve planning? To answer these questions and more, we introduce m&m's: a benchmark containing 4K+ multi-step multi-modal tasks involving 33 tools that include multi-modal models, (free) public APIs, and image processing modules. For each of these task queries, we provide automatically generated plans using this realistic toolset. We further provide a high-quality subset of 1,565 task plans that are human-verified and correctly executable. With m&m's, we evaluate 6 popular LLMs with 2 planning strategies (multi-step vs. step-by-step planning), 2 plan formats (JSON vs. code), and 3 types of feedback (parsing/verification/execution). Finally, we summarize takeaways from our extensive experiments. Our dataset and code are available on HuggingFace (https://huggingface.co/datasets/zixianma/mnms) and Github (https://github.com/RAIVNLab/mnms).
URLs: https://huggingface.co/datasets/zixianma/mnms), https://github.com/RAIVNLab/mnms).
Authors: Zuyuan He, Zongyong Deng, Qiaoyun He, Qijun Zhao
Abstract: Face morphing attacks circumvent face recognition systems (FRSs) by creating a morphed image that contains multiple identities. However, existing face morphing attack methods either sacrifice image quality or compromise the identity preservation capability. Consequently, these attacks fail to bypass FRSs verification well while still managing to deceive human observers. These methods typically rely on global information from contributing images, ignoring the detailed information from effective facial regions. To address the above issues, we propose a novel morphing attack method to improve the quality of morphed images and better preserve the contributing identities. Our proposed method leverages the hierarchical generative network to capture both local detailed and global consistency information. Additionally, a mask-guided image blending module is dedicated to removing artifacts from areas outside the face to improve the image's visual quality. The proposed attack method is compared to state-of-the-art methods on three public datasets in terms of FRSs' vulnerability, attack detectability, and image quality. The results show our method's potential threat of deceiving FRSs while being capable of passing multiple morphing attack detection (MAD) scenarios.
Authors: Ruibin Li, Ruihuang Li, Song Guo, Lei Zhang
Abstract: Text-driven diffusion models have significantly advanced the image editing performance by using text prompts as inputs. One crucial step in text-driven image editing is to invert the original image into a latent noise code conditioned on the source prompt. While previous methods have achieved promising results by refactoring the image synthesizing process, the inverted latent noise code is tightly coupled with the source prompt, limiting the image editability by target text prompts. To address this issue, we propose a novel method called Source Prompt Disentangled Inversion (SPDInv), which aims at reducing the impact of source prompt, thereby enhancing the text-driven image editing performance by employing diffusion models. To make the inverted noise code be independent of the given source prompt as much as possible, we indicate that the iterative inversion process should satisfy a fixed-point constraint. Consequently, we transform the inversion problem into a searching problem to find the fixed-point solution, and utilize the pre-trained diffusion models to facilitate the searching process. The experimental results show that our proposed SPDInv method can effectively mitigate the conflicts between the target editing prompt and the source prompt, leading to a significant decrease in editing artifacts. In addition to text-driven image editing, with SPDInv we can easily adapt customized image generation models to localized editing tasks and produce promising performance. The source code are available at https://github.com/leeruibin/SPDInv.
Authors: Souradeep Chakraborty, Dimitris Samaras
Abstract: Our paper introduces a novel two-stage self-supervised approach for detecting co-occurring salient objects (CoSOD) in image groups without requiring segmentation annotations. Unlike existing unsupervised methods that rely solely on patch-level information (e.g. clustering patch descriptors) or on computation heavy off-the-shelf components for CoSOD, our lightweight model leverages feature correspondences at both patch and region levels, significantly improving prediction performance. In the first stage, we train a self-supervised network that detects co-salient regions by computing local patch-level feature correspondences across images. We obtain the segmentation predictions using confidence-based adaptive thresholding. In the next stage, we refine these intermediate segmentations by eliminating the detected regions (within each image) whose averaged feature representations are dissimilar to the foreground feature representation averaged across all the cross-attention maps (from the previous stage). Extensive experiments on three CoSOD benchmark datasets show that our self-supervised model outperforms the corresponding state-of-the-art models by a huge margin (e.g. on the CoCA dataset, our model has a 13.7% F-measure gain over the SOTA unsupervised CoSOD model). Notably, our self-supervised model also outperforms several recent fully supervised CoSOD models on the three test datasets (e.g., on the CoCA dataset, our model has a 4.6% F-measure gain over a recent supervised CoSOD model).
Authors: Yongtao Ge, Wenjia Wang, Yongfan Chen, Hao Chen, Chunhua Shen
Abstract: In this work, we show that synthetic data created by generative models is complementary to computer graphics (CG) rendered data for achieving remarkable generalization performance on diverse real-world scenes for 3D human pose and shape estimation (HPS). Specifically, we propose an effective approach based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. We first collect a large-scale human-centric dataset with comprehensive annotations, e.g., text captions and surface normal images. Then, we train a customized ControlNet model upon this dataset to generate diverse human images and initial ground-truth labels. At the core of this step is that we can easily obtain numerous surface normal images from a 3D human parametric model, e.g., SMPL-X, by rendering the 3D mesh onto the image plane. As there exists inevitable noise in the initial labels, we then apply an off-the-shelf foundation segmentation model, i.e., SAM, to filter negative data samples. Our data generation pipeline is flexible and customizable to facilitate different real-world tasks, e.g., ego-centric scenes and perspective-distortion scenes. The generated dataset comprises 0.79M images with corresponding 3D annotations, covering versatile viewpoints, scenes, and human identities. We train various HPS regressors on top of the generated data and evaluate them on a wide range of benchmarks (3DPW, RICH, EgoBody, AGORA, SSP-3D) to verify the effectiveness of the generated data. By exclusively employing generative models, we generate large-scale in-the-wild human images and high-quality annotations, eliminating the need for real-world data collection.
Authors: Yiyang Chen, Lunhao Duan, Shanshan Zhao, Changxing Ding, Dacheng Tao
Abstract: Rotation invariance is an important requirement for point shape analysis. To achieve this, current state-of-the-art methods attempt to construct the local rotation-invariant representation through learning or defining the local reference frame (LRF). Although efficient, these LRF-based methods suffer from perturbation of local geometric relations, resulting in suboptimal local rotation invariance. To alleviate this issue, we propose a Local-consistent Transformation (LocoTrans) learning strategy. Specifically, we first construct the local-consistent reference frame (LCRF) by considering the symmetry of the two axes in LRF. In comparison with previous LRFs, our LCRF is able to preserve local geometric relationships better through performing local-consistent transformation. However, as the consistency only exists in local regions, the relative pose information is still lost in the intermediate layers of the network. We mitigate such a relative pose issue by developing a relative pose recovery (RPR) module. RPR aims to restore the relative pose between adjacent transformed patches. Equipped with LCRF and RPR, our LocoTrans is capable of learning local-consistent transformation and preserving local geometry, which benefits rotation invariance learning. Competitive performance under arbitrary rotations on both shape classification and part segmentation tasks and ablations can demonstrate the effectiveness of our method. Code will be available publicly at https://github.com/wdttt/LocoTrans.
Authors: Jiazhen Liu, Yuhan Fu, Ruobing Xie, Runquan Xie, Xingwu Sun, Fengzong Lian, Zhanhui Kang, Xirong Li
Abstract: The rapid growth of Large Language Models (LLMs) has driven the development of Large Vision-Language Models (LVLMs). The challenge of hallucination, prevalent in LLMs, also emerges in LVLMs. However, most existing efforts mainly focus on object hallucination in LVLM, ignoring diverse types of LVLM hallucinations. In this study, we delve into the Intrinsic Vision-Language Hallucination (IVL-Hallu) issue, thoroughly analyzing different types of IVL-Hallu on their causes and reflections. Specifically, we propose several novel IVL-Hallu tasks and categorize them into four types: (a) object hallucination, which arises from the misidentification of objects, (b) attribute hallucination, which is caused by the misidentification of attributes, (c) multi-modal conflicting hallucination, which derives from the contradictions between textual and visual information, and (d) counter-common-sense hallucination, which owes to the contradictions between the LVLM knowledge and actual images. Based on these taxonomies, we propose a more challenging benchmark named PhD to evaluate and explore IVL-Hallu. An automated pipeline is proposed for generating different types of IVL-Hallu data. Extensive experiments on five SOTA LVLMs reveal their inability to effectively tackle our proposed IVL-Hallu tasks, with detailed analyses and insights on the origins and possible solutions of these new challenging IVL-Hallu tasks, facilitating future researches on IVL-Hallu and LVLM. The benchmark can be accessed at \href{https://github.com/jiazhen-code/IntrinsicHallu}{this https URL}.
Authors: Sunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin
Abstract: This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit from one of two forms of aggregation: feature aggregation, which pertains to the alignment of similar features, or cost aggregation, a procedure aimed at instilling coherence in the flow estimates across neighboring pixels. In this work, we first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes. We then introduce a simple yet effective architecture that harnesses self- and cross-attention mechanisms to show that our approach unifies feature aggregation and cost aggregation and effectively harnesses the strengths of both techniques. Within the proposed attention layers, the features and cost volume both complement each other, and the attention layers are interleaved through a coarse-to-fine design to further promote accurate correspondence estimation. Finally at inference, our network produces multi-scale predictions, computes their confidence scores, and selects the most confident flow for final prediction. Our framework is evaluated on standard benchmarks for semantic matching, and also applied to geometric matching, where we show that our approach achieves significant improvements compared to existing methods.
Authors: Wei-Shi Zheng, Junkai Yan, Yi-Xing Peng
Abstract: Person Re-identification (ReID) has been extensively developed for a decade in order to learn the association of images of the same person across non-overlapping camera views. To overcome significant variations between images across camera views, mountains of variants of ReID models were developed for solving a number of challenges, such as resolution change, clothing change, occlusion, modality change, and so on. Despite the impressive performance of many ReID variants, these variants typically function distinctly and cannot be applied to other challenges. To our best knowledge, there is no versatile ReID model that can handle various ReID challenges at the same time. This work contributes to the first attempt at learning a versatile ReID model to solve such a problem. Our main idea is to form a two-stage prompt-based twin modeling framework called VersReID. Our VersReID firstly leverages the scene label to train a ReID Bank that contains abundant knowledge for handling various scenes, where several groups of scene-specific prompts are used to encode different scene-specific knowledge. In the second stage, we distill a V-Branch model with versatile prompts from the ReID Bank for adaptively solving the ReID of different scenes, eliminating the demand for scene labels during the inference stage. To facilitate training VersReID, we further introduce the multi-scene properties into self-supervised learning of ReID via a multi-scene prioris data augmentation (MPDA) strategy. Through extensive experiments, we demonstrate the success of learning an effective and versatile ReID model for handling ReID tasks under multi-scene conditions without manual assignment of scene labels in the inference stage, including general, low-resolution, clothing change, occlusion, and cross-modality scenes. Codes and models are available at https://github.com/iSEE-Laboratory/VersReID.
Authors: Hanze Ding, Zhangkai Wu, Jiyan Zhang, Ming Ping, Yanfang Liu
Abstract: Few-shot segmentation models excel in metal defect detection due to their rapid generalization ability to new classes and pixel-level segmentation, rendering them ideal for addressing data scarcity issues and achieving refined object delineation in industrial applications. Existing works neglect the \textit{Intra-Class Differences}, inherent in metal surface defect data, which hinders the model from learning sufficient knowledge from the support set to guide the query set segmentation. Specifically, it can be categorized into two types: the \textit{Semantic Difference} induced by internal factors in metal samples and the \textit{Distortion Difference} caused by external factors of surroundings. To address these differences, we introduce a \textbf{L}ocal d\textbf{E}scriptor based \textbf{R}easoning and \textbf{E}xcitation \textbf{Net}work (\textbf{LERENet}) to learn the two-view guidance, i.e., local and global information from the graph and feature space, and fuse them to segment precisely. Since the relation structure of local features embedded in graph space will help to eliminate \textit{Semantic Difference}, we employ Multi-Prototype Reasoning (MPR) module, extracting local descriptors based prototypes and analyzing local-view feature relevance in support-query pairs. Besides, due to the global information that will assist in countering the \textit{Distortion Difference} in observations, we utilize Multi-Prototype Excitation (MPE) module to capture the global-view relations in support-query pairs. Finally, we employ an Information Fusion Module (IFM) to fuse learned prototypes in local and global views to generate pixel-level masks. Our comprehensive experiments on defect datasets demonstrate that it outperforms existing benchmarks, establishing a new state-of-the-art.
Authors: Jiangshan Wang, Yifan Pu, Yizeng Han, Jiayi Guo, Yiru Wang, Xiu Li, Gao Huang
Abstract: Oriented object detection, an emerging task in recent years, aims to identify and locate objects across varied orientations. This requires the detector to accurately capture the orientation information, which varies significantly within and across images. Despite the existing substantial efforts, simultaneously ensuring model effectiveness and parameter efficiency remains challenging in this scenario. In this paper, we propose a lightweight yet effective \textbf{G}roup-wise \textbf{R}otating and \textbf{A}ttention (GRA) module to replace the convolution operations in backbone networks for oriented object detection. GRA can adaptively capture fine-grained features of objects with diverse orientations, comprising two key components: Group-wise Rotating and Group-wise Attention. Group-wise Rotating first divides the convolution kernel into groups, where each group extracts different object features by rotating at a specific angle according to the object orientation. Subsequently, Group-wise Attention is employed to adaptively enhance the object-related regions in the feature. The collaborative effort of these components enables GRA to effectively capture the various orientation information while maintaining parameter efficiency. Extensive experimental results demonstrate the superiority of our method. For example, GRA achieves a new state-of-the-art (SOTA) on the DOTA-v2.0 benchmark, while saving the parameters by nearly 50\% compared to the previous SOTA method. Code will be released.
Authors: Yonggan Fu, Huaizhi Qu, Zhifan Ye, Chaojian Li, Kevin Zhao, Yingyan Lin
Abstract: Recent breakthroughs in Neural Radiance Fields (NeRFs) have sparked significant demand for their integration into real-world 3D applications. However, the varied functionalities required by different 3D applications often necessitate diverse NeRF models with various pipelines, leading to tedious NeRF training for each target task and cumbersome trial-and-error experiments. Drawing inspiration from the generalization capability and adaptability of emerging foundation models, our work aims to develop one general-purpose NeRF for handling diverse 3D tasks. We achieve this by proposing a framework called Omni-Recon, which is capable of (1) generalizable 3D reconstruction and zero-shot multitask scene understanding, and (2) adaptability to diverse downstream 3D applications such as real-time rendering and scene editing. Our key insight is that an image-based rendering pipeline, with accurate geometry and appearance estimation, can lift 2D image features into their 3D counterparts, thus extending widely explored 2D tasks to the 3D world in a generalizable manner. Specifically, our Omni-Recon features a general-purpose NeRF model using image-based rendering with two decoupled branches: one complex transformer-based branch that progressively fuses geometry and appearance features for accurate geometry estimation, and one lightweight branch for predicting blending weights of source views. This design achieves state-of-the-art (SOTA) generalizable 3D surface reconstruction quality with blending weights reusable across diverse tasks for zero-shot multitask scene understanding. In addition, it can enable real-time rendering after baking the complex geometry branch into meshes, swift adaptation to achieve SOTA generalizable 3D understanding performance, and seamless integration with 2D diffusion models for text-guided 3D editing.
Authors: Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang, Jie Yang, Yan-Pei Cao, Ling-Qi Yan, Lin Gao
Abstract: The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and viewpoint-conditioned neural networks, 3D Gaussian Splatting utilizes a set of Gaussian ellipsoids to model the scene so that efficient rendering can be accomplished by rasterizing Gaussian ellipsoids into images. Apart from the fast rendering speed, the explicit representation of 3D Gaussian Splatting facilitates editing tasks like dynamic reconstruction, geometry editing, and physical simulation. Considering the rapid change and growing number of works in this field, we present a literature review of recent 3D Gaussian Splatting methods, which can be roughly classified into 3D reconstruction, 3D editing, and other downstream applications by functionality. Traditional point-based rendering methods and the rendering formulation of 3D Gaussian Splatting are also illustrated for a better understanding of this technique. This survey aims to help beginners get into this field quickly and provide experienced researchers with a comprehensive overview, which can stimulate the future development of the 3D Gaussian Splatting representation.
Authors: Jing Zhang, Liang Zheng, Dan Guo, Meng Wang
Abstract: This paper develops small vision language models to understand visual art, which, given an art work, aims to identify its emotion category and explain this prediction with natural language. While small models are computationally efficient, their capacity is much limited compared with large models. To break this trade-off, this paper builds a small emotional vision language model (SEVLM) by emotion modeling and input-output feature alignment. On the one hand, based on valence-arousal-dominance (VAD) knowledge annotated by psychology experts, we introduce and fuse emotional features derived through VAD dictionary and a VAD head to align VAD vectors of predicted emotion explanation and the ground truth. This allows the vision language model to better understand and generate emotional texts, compared with using traditional text embeddings alone. On the other hand, we design a contrastive head to pull close embeddings of the image, its emotion class, and explanation, which aligns model outputs and inputs. On two public affective explanation datasets, we show that the proposed techniques consistently improve the visual art understanding performance of baseline SEVLMs. Importantly, the proposed model can be trained and evaluated on a single RTX 2080 Ti while exhibiting very strong performance: it not only outperforms the state-of-the-art small models but is also competitive compared with LLaVA 7B after fine-tuning and GPT4(V).
Authors: Dian Zheng, Xiao-Ming Wu, Shuzhou Yang, Jian Zhang, Jian-Fang Hu, Wei-Shi Zheng
Abstract: Universal image restoration is a practical and potential computer vision task for real-world applications. The main challenge of this task is handling the different degradation distributions at once. Existing methods mainly utilize task-specific conditions (e.g., prompt) to guide the model to learn different distributions separately, named multi-partite mapping. However, it is not suitable for universal model learning as it ignores the shared information between different tasks. In this work, we propose an advanced selective hourglass mapping strategy based on diffusion model, termed DiffUIR. Two novel considerations make our DiffUIR non-trivial. Firstly, we equip the model with strong condition guidance to obtain accurate generation direction of diffusion model (selective). More importantly, DiffUIR integrates a flexible shared distribution term (SDT) into the diffusion algorithm elegantly and naturally, which gradually maps different distributions into a shared one. In the reverse process, combined with SDT and strong condition guidance, DiffUIR iteratively guides the shared distribution to the task-specific distribution with high image quality (hourglass). Without bells and whistles, by only modifying the mapping strategy, we achieve state-of-the-art performance on five image restoration tasks, 22 benchmarks in the universal setting and zero-shot generalization setting. Surprisingly, by only using a lightweight model (only 0.89M), we could achieve outstanding performance. The source code and pre-trained models are available at https://github.com/iSEE-Laboratory/DiffUIR
Authors: Xiaoyu Wu, Yang Hua, Chumeng Liang, Jiaru Zhang, Hao Wang, Tao Song, Haibing Guan
Abstract: Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capture a specific style or object. Despite their success, concerns exist about potential copyright violations stemming from the use of unauthorized data in this process. In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication. Our approach involves removing partial information of an image and recovering missing details by exploiting conceptual differences between the pretrained and fine-tuned models. We formulate the differences as KL divergence between latent variables of the two models when given the same input image, which can be maximized through Monte Carlo sampling and Projected Gradient Descent (PGD). The similarity between original and recovered images serves as a strong indicator of potential infringements. Extensive experiments on the WikiArt and Dreambooth datasets demonstrate the high accuracy of CGI-DM in digital copyright authentication, surpassing alternative validation techniques. Code implementation is available at https://github.com/Nicholas0228/Revelio.
Authors: Zheling Meng, Bo Peng, Jing Dong, Tieniu Tan
Abstract: In the era of AIGC, the fast development of visual content generation technologies, such as diffusion models, bring potential security risks to our society. Existing generated image detection methods suffer from performance drop when faced with out-of-domain generators and image scenes. To relieve this problem, we propose Artifact Purification Network (APN) to facilitate the artifact extraction from generated images through the explicit and implicit purification processes. For the explicit one, a suspicious frequency-band proposal method and a spatial feature decomposition method are proposed to extract artifact-related features. For the implicit one, a training strategy based on mutual information estimation is proposed to further purify the artifact-related features. Experiments show that for cross-generator detection, the average accuracy of APN is 5.6% ~ 16.4% higher than the previous 10 methods on GenImage dataset and 1.7% ~ 50.1% on DiffusionForensics dataset. For cross-scene detection, APN maintains its high performance. Via visualization analysis, we find that the proposed method extracts flexible forgery patterns and condenses the forgery information diluted in irrelevant features. We also find that the artifact features APN focuses on across generators and scenes are global and diverse. The code will be available on GitHub.
Authors: Lorenzo Agnolucci, Leonardo Galteri, Marco Bertini
Abstract: No-Reference Image Quality Assessment (NR-IQA) focuses on designing methods to measure image quality in alignment with human perception when a high-quality reference image is unavailable. The reliance on annotated Mean Opinion Scores (MOS) in the majority of state-of-the-art NR-IQA approaches limits their scalability and broader applicability to real-world scenarios. To overcome this limitation, we propose QualiCLIP (Quality-aware CLIP), a CLIP-based self-supervised opinion-unaware method that does not require labeled MOS. In particular, we introduce a quality-aware image-text alignment strategy to make CLIP generate representations that correlate with the inherent quality of the images. Starting from pristine images, we synthetically degrade them with increasing levels of intensity. Then, we train CLIP to rank these degraded images based on their similarity to quality-related antonym text prompts, while guaranteeing consistent representations for images with comparable quality. Our method achieves state-of-the-art performance on several datasets with authentic distortions. Moreover, despite not requiring MOS, QualiCLIP outperforms supervised methods when their training dataset differs from the testing one, thus proving to be more suitable for real-world scenarios. Furthermore, our approach demonstrates greater robustness and improved explainability than competing methods. The code and the model are publicly available at https://github.com/miccunifi/QualiCLIP.
Authors: Yuanchen Wu, Xichen Ye, Kequan Yang, Jide Li, Xiaoqiang Li
Abstract: Recently, One-stage Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained increasing interest due to simplification over its cumbersome multi-stage counterpart. Limited by the inherent ambiguity of Class Activation Map (CAM), we observe that one-stage pipelines often encounter confirmation bias caused by incorrect CAM pseudo-labels, impairing their final segmentation performance. Although recent works discard many unreliable pseudo-labels to implicitly alleviate this issue, they fail to exploit sufficient supervision for their models. To this end, we propose a dual student framework with trustworthy progressive learning (DuPL). Specifically, we propose a dual student network with a discrepancy loss to yield diverse CAMs for each sub-net. The two sub-nets generate supervision for each other, mitigating the confirmation bias caused by learning their own incorrect pseudo-labels. In this process, we progressively introduce more trustworthy pseudo-labels to be involved in the supervision through dynamic threshold adjustment with an adaptive noise filtering strategy. Moreover, we believe that every pixel, even discarded from supervision due to its unreliability, is important for WSSS. Thus, we develop consistency regularization on these discarded regions, providing supervision of every pixel. Experiment results demonstrate the superiority of the proposed DuPL over the recent state-of-the-art alternatives on PASCAL VOC 2012 and MS COCO datasets. Code is available at https://github.com/Wu0409/DuPL.
Authors: Guangze Zheng, Shijie Lin, Haobo Zuo, Changhong Fu, Jia Pan
Abstract: The complex dynamicity of open-world objects presents non-negligible challenges for multi-object tracking (MOT), often manifested as severe deformations, fast motion, and occlusions. Most methods that solely depend on coarse-grained object cues, such as boxes and the overall appearance of the object, are susceptible to degradation due to distorted internal relationships of dynamic objects. To address this problem, this work proposes NetTrack, an efficient, generic, and affordable tracking framework to introduce fine-grained learning that is robust to dynamicity. Specifically, NetTrack constructs a dynamicity-aware association with a fine-grained Net, leveraging point-level visual cues. Correspondingly, a fine-grained sampler and matching method have been incorporated. Furthermore, NetTrack learns object-text correspondence for fine-grained localization. To evaluate MOT in extremely dynamic open-world scenarios, a bird flock tracking (BFT) dataset is constructed, which exhibits high dynamicity with diverse species and open-world scenarios. Comprehensive evaluation on BFT validates the effectiveness of fine-grained learning on object dynamicity, and thorough transfer experiments on challenging open-world benchmarks, i.e., TAO, TAO-OW, AnimalTrack, and GMOT-40, validate the strong generalization ability of NetTrack even without finetuning. Project page: https://george-zhuang.github.io/nettrack/.
Authors: Kun Xia, Le Wang, Sanping Zhou, Gang Hua, Wei Tang
Abstract: The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone target class (i.e, the predicted class with the highest confidence) while ignoring informative semantics within non-target classes. This paper approaches SS-TAL from a novel perspective by advocating for learning from non-target classes, transcending the conventional focus solely on the target class. The proposed approach involves partitioning the label space of the predicted class distribution into distinct subspaces: target class, positive classes, negative classes, and ambiguous classes, aiming to mine both positive and negative semantics that are absent in the target class, while excluding ambiguous classes. To this end, we first devise innovative strategies to adaptively select high-quality positive and negative classes from the label space, by modeling both the confidence and rank of a class in relation to those of the target class. Then, we introduce novel positive and negative losses designed to guide the learning process, pushing predictions closer to positive classes and away from negative classes. Finally, the positive and negative processes are integrated into a hybrid positive-negative learning framework, facilitating the utilization of non-target classes in both labeled and unlabeled videos. Experimental results on THUMOS14 and ActivityNet v1.3 demonstrate the superiority of the proposed method over prior state-of-the-art approaches.
Authors: Renlong Wu, Zhilu Zhang, Shuohao Zhang, Longfei Gou, Haobin Chen, Lei Zhang, Hao Chen, Wangmeng Zuo
Abstract: Due to the difficulty of collecting real paired data, most existing desmoking methods train the models by synthesizing smoke, generalizing poorly to real surgical scenarios. Although a few works have explored single-image real-world desmoking in unpaired learning manners, they still encounter challenges in handling dense smoke. In this work, we address these issues together by introducing the self-supervised surgery video desmoking (SelfSVD). On the one hand, we observe that the frame captured before the activation of high-energy devices is generally clear (named pre-smoke frame, PS frame), thus it can serve as supervision for other smoky frames, making real-world self-supervised video desmoking practically feasible. On the other hand, in order to enhance the desmoking performance, we further feed the valuable information from PS frame into models, where a masking strategy and a regularization term are presented to avoid trivial solutions. In addition, we construct a real surgery video dataset for desmoking, which covers a variety of smoky scenes. Extensive experiments on the dataset show that our SelfSVD can remove smoke more effectively and efficiently while recovering more photo-realistic details than the state-of-the-art methods. The dataset, codes, and pre-trained models are available at \url{https://github.com/ZcsrenlongZ/SelfSVD}.
Authors: Tongfan Guan, Chen Wang, Yun-Hui Liu
Abstract: Stereo matching is a core task for many computer vision and robotics applications. Despite their dominance in traditional stereo methods, the hand-crafted Markov Random Field (MRF) models lack sufficient modeling accuracy compared to end-to-end deep models. While deep learning representations have greatly improved the unary terms of the MRF models, the overall accuracy is still severely limited by the hand-crafted pairwise terms and message passing. To address these issues, we propose a neural MRF model, where both potential functions and message passing are designed using data-driven neural networks. Our fully data-driven model is built on the foundation of variational inference theory, to prevent convergence issues and retain stereo MRF's graph inductive bias. To make the inference tractable and scale well to high-resolution images, we also propose a Disparity Proposal Network (DPN) to adaptively prune the search space of disparity. The proposed approach ranks $1^{st}$ on both KITTI 2012 and 2015 leaderboards among all published methods while running faster than 100 ms. This approach significantly outperforms prior global methods, e.g., lowering D1 metric by more than 50% on KITTI 2015. In addition, our method exhibits strong cross-domain generalization and can recover sharp edges. The codes at https://github.com/aeolusguan/NMRF .
Authors: Yasufumi Kawano, Yoshimitsu Aoki
Abstract: Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due to the limited predefined categories in supervised learning, models typically struggle with infrequent classes and are unable to predict novel classes. To address these limitations, we propose MaskDiffusion, an innovative approach that leverages pretrained frozen Stable Diffusion to achieve open-vocabulary semantic segmentation without the need for additional training or annotation, leading to improved performance compared to similar methods. We also demonstrate the superior performance of MaskDiffusion in handling open vocabularies, including fine-grained and proper noun-based categories, thus expanding the scope of segmentation applications. Overall, our MaskDiffusion shows significant qualitative and quantitative improvements in contrast to other comparable unsupervised segmentation methods, i.e. on the Potsdam dataset (+10.5 mIoU compared to GEM) and COCO-Stuff (+14.8 mIoU compared to DiffSeg). All code and data will be released at https://github.com/Valkyrja3607/MaskDiffusion.
Authors: Yasufumi Kawano, Yoshimitsu Aoki
Abstract: Semantic segmentation is a crucial task in computer vision, where each pixel in an image is classified into a category. However, traditional methods face significant challenges, including the need for pixel-level annotations and extensive training. Furthermore, because supervised learning uses a limited set of predefined categories, models typically struggle with rare classes and cannot recognize new ones. Unsupervised and open-vocabulary segmentation, proposed to tackle these issues, faces challenges, including the inability to assign specific class labels to clusters and the necessity of user-provided text queries for guidance. In this context, we propose a novel approach, TAG which achieves Training, Annotation, and Guidance-free open-vocabulary semantic segmentation. TAG utilizes pre-trained models such as CLIP and DINO to segment images into meaningful categories without additional training or dense annotations. It retrieves class labels from an external database, providing flexibility to adapt to new scenarios. Our TAG achieves state-of-the-art results on PascalVOC, PascalContext and ADE20K for open-vocabulary segmentation without given class names, i.e. improvement of +15.3 mIoU on PascalVOC. All code and data will be released at https://github.com/Valkyrja3607/TAG.
Authors: Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu, Thomas Naselaris, Kenneth A. Norman, Tanishq Mathew Abraham
Abstract: Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited. This is because such models are trained independently per subject where each subject requires dozens of hours of expensive fMRI training data to attain high-quality results. The present work showcases high-quality reconstructions using only 1 hour of fMRI training data. We pretrain our model across 7 subjects and then fine-tune on minimal data from a new subject. Our novel functional alignment procedure linearly maps all brain data to a shared-subject latent space, followed by a shared non-linear mapping to CLIP image space. We then map from CLIP space to pixel space by fine-tuning Stable Diffusion XL to accept CLIP latents as inputs instead of text. This approach improves out-of-subject generalization with limited training data and also attains state-of-the-art image retrieval and reconstruction metrics compared to single-subject approaches. MindEye2 demonstrates how accurate reconstructions of perception are possible from a single visit to the MRI facility. All code is available on GitHub.
Authors: Qianyang Wu, Ye Shi, Xiaoshui Huang, Jingyi Yu, Lan Xu, Jingya Wang
Abstract: This paper addresses new methodologies to deal with the challenging task of generating dynamic Human-Object Interactions from textual descriptions (Text2HOI). While most existing works assume interactions with limited body parts or static objects, our task involves addressing the variation in human motion, the diversity of object shapes, and the semantic vagueness of object motion simultaneously. To tackle this, we propose a novel Text-guided Human-Object Interaction diffusion model with Relation Intervention (THOR). THOR is a cohesive diffusion model equipped with a relation intervention mechanism. In each diffusion step, we initiate text-guided human and object motion and then leverage human-object relations to intervene in object motion. This intervention enhances the spatial-temporal relations between humans and objects, with human-centric interaction representation providing additional guidance for synthesizing consistent motion from text. To achieve more reasonable and realistic results, interaction losses is introduced at different levels of motion granularity. Moreover, we construct Text-BEHAVE, a Text2HOI dataset that seamlessly integrates textual descriptions with the currently largest publicly available 3D HOI dataset. Both quantitative and qualitative experiments demonstrate the effectiveness of our proposed model.
Authors: Qingrong Sun, Weixiang Zhong, Jie Zhou, Chong Lai, Xiaodong Teng, Maode Lai
Abstract: The annotation of digital pathological slide data for renal cell carcinoma is of paramount importance for correct diagnosis of artificial intelligence models due to the heterogeneous nature of the tumor. This process not only facilitates a deeper understanding of renal cell cancer heterogeneity but also aims to minimize noise in the data for more accurate studies. To enhance the applicability of the data, two pathologists were enlisted to meticulously curate, screen, and label a kidney cancer pathology image dataset from The Cancer Genome Atlas Program (TCGA) database. Subsequently, a Resnet model was developed to validate the annotated dataset against an additional dataset from the First Affiliated Hospital of Zhejiang University. Based on these results, we have meticulously compiled the TCGA digital pathological dataset with independent labeling of tumor regions and adjacent areas (RCdpia), which includes 109 cases of kidney chromophobe cell carcinoma, 486 cases of kidney clear cell carcinoma, and 292 cases of kidney papillary cell carcinoma. This dataset is now publicly accessible at http://39.171.241.18:8888/RCdpia/. Furthermore, model analysis has revealed significant discrepancies in predictive outcomes when applying the same model to datasets from different centers. Leveraging the RCdpia, we can now develop more precise digital pathology artificial intelligence models for tasks such as normalization, classification, and segmentation. These advancements underscore the potential for more nuanced and accurate AI applications in the field of digital pathology.
Authors: Yuwei Zhang, Yan Wu, Yanming Liu, Xinyue Peng
Abstract: Object detection methods under known single degradations have been extensively investigated. However, existing approaches require prior knowledge of the degradation type and train a separate model for each, limiting their practical applications in unpredictable environments. To address this challenge, we propose a chain-of-thought (CoT) prompted adaptive enhancer, CPA-Enhancer, for object detection under unknown degradations. Specifically, CPA-Enhancer progressively adapts its enhancement strategy under the step-by-step guidance of CoT prompts, that encode degradation-related information. To the best of our knowledge, it's the first work that exploits CoT prompting for object detection tasks. Overall, CPA-Enhancer is a plug-and-play enhancement model that can be integrated into any generic detectors to achieve substantial gains on degraded images, without knowing the degradation type priorly. Experimental results demonstrate that CPA-Enhancer not only sets the new state of the art for object detection but also boosts the performance of other downstream vision tasks under unknown degradations.
Authors: Lin Zhu, Kangmin Jia, Yifan Zhao, Yunshan Qi, Lizhi Wang, Hua Huang
Abstract: Spike cameras, leveraging spike-based integration sampling and high temporal resolution, offer distinct advantages over standard cameras. However, existing approaches reliant on spike cameras often assume optimal illumination, a condition frequently unmet in real-world scenarios. To address this, we introduce SpikeNeRF, the first work that derives a NeRF-based volumetric scene representation from spike camera data. Our approach leverages NeRF's multi-view consistency to establish robust self-supervision, effectively eliminating erroneous measurements and uncovering coherent structures within exceedingly noisy input amidst diverse real-world illumination scenarios. The framework comprises two core elements: a spike generation model incorporating an integrate-and-fire neuron layer and parameters accounting for non-idealities, such as threshold variation, and a spike rendering loss capable of generalizing across varying illumination conditions. We describe how to effectively optimize neural radiance fields to render photorealistic novel views from the novel continuous spike stream, demonstrating advantages over other vision sensors in certain scenes. Empirical evaluations conducted on both real and novel realistically simulated sequences affirm the efficacy of our methodology. The dataset and source code are released at https://github.com/BIT-Vision/SpikeNeRF.
Authors: Shumeng Li, Lei Qi, Qian Yu, Jing Huo, Yinghuan Shi, Yang Gao
Abstract: Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Concatenate, Fine-tuning, and Re-training (CFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our concatenation strategy mitigates the mismatch between natural and 3D medical images. The concatenated images are then used for fine-tuning SAM, providing robust initialization pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our CFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. Extensive experiments validate that our CFR achieves significant improvements in both moderate annotation and scarce annotation across four datasets. In particular, CFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset.
Authors: Wenyu Zhang, Qingmu Liu, Felix Ong Wei Cong, Mohamed Ragab, Chuan-Sheng Foo
Abstract: Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work, we introduce Universal Semi-Supervised Domain Adaptation (UniSSDA), a practical yet challenging setting where the target domain is partially labeled, and the source and target label space may not strictly match. UniSSDA is at the intersection of Universal Domain Adaptation (UniDA) and Semi-Supervised Domain Adaptation (SSDA): the UniDA setting does not allow for fine-grained categorization of target private classes not represented in the source domain, while SSDA focuses on the restricted closed-set setting where source and target label spaces match exactly. Existing UniDA and SSDA methods are susceptible to common-class bias in UniSSDA settings, where models overfit to data distributions of classes common to both domains at the expense of private classes. We propose a new prior-guided pseudo-label refinement strategy to reduce the reinforcement of common-class bias due to pseudo-labeling, a common label propagation strategy in domain adaptation. We demonstrate the effectiveness of the proposed strategy on benchmark datasets Office-Home, DomainNet, and VisDA. The proposed strategy attains the best performance across UniSSDA adaptation settings and establishes a new baseline for UniSSDA.
Authors: Xiaohan Zhang, Bharat Lal Bhatnagar, Sebastian Starke, Ilya Petrov, Vladimir Guzov, Helisa Dhamo, Eduardo P\'erez-Pellitero, Gerard Pons-Moll
Abstract: Interactions between human and objects are influenced not only by the object's pose and shape, but also by physical attributes such as object mass and surface friction. They introduce important motion nuances that are essential for diversity and realism. Despite advancements in recent kinematics-based methods, this aspect has been overlooked. Generating nuanced human motion presents two challenges. First, it is non-trivial to learn from multi-modal human and object information derived from both the physical and non-physical attributes. Second, there exists no dataset capturing nuanced human interactions with objects of varying physical properties, hampering model development. This work addresses the gap by introducing the FORCE model, a kinematic approach for synthesizing diverse, nuanced human-object interactions by modeling physical attributes. Our key insight is that human motion is dictated by the interrelation between the force exerted by the human and the perceived resistance. Guided by a novel intuitive physics encoding, the model captures the interplay between human force and resistance. Experiments also demonstrate incorporating human force facilitates learning multi-class motion. Accompanying our model, we contribute the FORCE dataset. It features diverse, different-styled motion through interactions with varying resistances.
Authors: Tianchen Deng, Yaohui Chen, Leyan Zhang, Jianfei Yang, Shenghai Yuan, Danwei Wang, Weidong Chen
Abstract: Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian ellipsoids, leading to high memory and storage costs, and slow training speed. To address the limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then we observe that the covariance matrix (geometry) of most 3D Gaussian ellipsoids are extremely similar, which motivates a novel geometry codebook to compress 3D Gaussian geometric attributes, i.e., the parameters. Robust and accurate pose estimation is achieved by a global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training and rendering speed while maintaining the state-of-the-art (SOTA) quality of the scene representation.
Authors: Vladimir Korviakov, Denis Koposov
Abstract: Most of the computer vision architectures nowadays are built upon the well-known foundation operations: fully-connected layers, convolutions and multi-head self-attention blocks. In this paper we propose a novel foundation operation - NeoCell - which learns matrix patterns and performs patchwise matrix multiplications with the input data. The main advantages of the proposed operator are (1) simple implementation without need in operations like im2col, (2) low computational complexity (especially for large matrices) and (3) simple and flexible implementation of up-/down-sampling. We validate NeoNeXt family of models based on this operation on ImageNet-1K classification task and show that they achieve competitive quality.
Authors: Xi Chen, Haosen Yang, Huicong Zhang, Hongxun Yao, Xiatian Zhu
Abstract: Source-free unsupervised domain adaptation (SFUDA) aims to enable the utilization of a pre-trained source model in an unlabeled target domain without access to source data. Self-training is a way to solve SFUDA, where confident target samples are iteratively selected as pseudo-labeled samples to guide target model learning. However, prior heuristic noisy pseudo-label filtering methods all involve introducing extra models, which are sensitive to model assumptions and may introduce additional errors or mislabeling. In this work, we propose a method called Uncertainty-aware Pseudo-label-filtering Adaptation (UPA) to efficiently address this issue in a coarse-to-fine manner. Specially, we first introduce a sample selection module named Adaptive Pseudo-label Selection (APS), which is responsible for filtering noisy pseudo labels. The APS utilizes a simple sample uncertainty estimation method by aggregating knowledge from neighboring samples and confident samples are selected as clean pseudo-labeled. Additionally, we incorporate Class-Aware Contrastive Learning (CACL) to mitigate the memorization of pseudo-label noise by learning robust pair-wise representation supervised by pseudo labels. Through extensive experiments conducted on three widely used benchmarks, we demonstrate that our proposed method achieves competitive performance on par with state-of-the-art SFUDA methods. Code is available at https://github.com/chenxi52/UPA.
Authors: Kwan Yun, Kwanggyoon Seo, Chang Wook Seo, Soyeon Yoon, Seongcheol Kim, Soohyun Ji, Amirsaman Ashtari, Junyong Noh
Abstract: Facial sketches are both a concise way of showing the identity of a person and a means to express artistic intention. While a few techniques have recently emerged that allow sketches to be extracted in different styles, they typically rely on a large amount of data that is difficult to obtain. Here, we propose StyleSketch, a method for extracting high-resolution stylized sketches from a face image. Using the rich semantics of the deep features from a pretrained StyleGAN, we are able to train a sketch generator with 16 pairs of face and the corresponding sketch images. The sketch generator utilizes part-based losses with two-stage learning for fast convergence during training for high-quality sketch extraction. Through a set of comparisons, we show that StyleSketch outperforms existing state-of-the-art sketch extraction methods and few-shot image adaptation methods for the task of extracting high-resolution abstract face sketches. We further demonstrate the versatility of StyleSketch by extending its use to other domains and explore the possibility of semantic editing. The project page can be found in https://kwanyun.github.io/stylesketch_project.
Authors: Jie Tang, Fei-Peng Tian, Boshi An, Jian Li, Ping Tan
Abstract: Depth completion aims to derive a dense depth map from sparse depth measurements with a synchronized color image. Current state-of-the-art (SOTA) methods are predominantly propagation-based, which work as an iterative refinement on the initial estimated dense depth. However, the initial depth estimations mostly result from direct applications of convolutional layers on the sparse depth map. In this paper, we present a Bilateral Propagation Network (BP-Net), that propagates depth at the earliest stage to avoid directly convolving on sparse data. Specifically, our approach propagates the target depth from nearby depth measurements via a non-linear model, whose coefficients are generated through a multi-layer perceptron conditioned on both \emph{radiometric difference} and \emph{spatial distance}. By integrating bilateral propagation with multi-modal fusion and depth refinement in a multi-scale framework, our BP-Net demonstrates outstanding performance on both indoor and outdoor scenes. It achieves SOTA on the NYUv2 dataset and ranks 1st on the KITTI depth completion benchmark at the time of submission. Experimental results not only show the effectiveness of bilateral propagation but also emphasize the significance of early-stage propagation in contrast to the refinement stage. Our code and trained models will be available on the project page.
Authors: Lutao Jiang, Lin Wang
Abstract: Text-to-3D synthesis has recently seen intriguing advances by combining the text-to-image models with 3D representation methods, e.g., Gaussian Splatting (GS), via Score Distillation Sampling (SDS). However, a hurdle of existing methods is the low efficiency, per-prompt optimization for a single 3D object. Therefore, it is imperative for a paradigm shift from per-prompt optimization to one-stage generation for any unseen text prompts, which yet remains challenging. A hurdle is how to directly generate a set of millions of 3D Gaussians to represent a 3D object. This paper presents BrightDreamer, an end-to-end single-stage approach that can achieve generalizable and fast (77 ms) text-to-3D generation. Our key idea is to formulate the generation process as estimating the 3D deformation from an anchor shape with predefined positions. For this, we first propose a Text-guided Shape Deformation (TSD) network to predict the deformed shape and its new positions, used as the centers (one attribute) of 3D Gaussians. To estimate the other four attributes (i.e., scaling, rotation, opacity, and SH coefficient), we then design a novel Text-guided Triplane Generator (TTG) to generate a triplane representation for a 3D object. The center of each Gaussian enables us to transform the triplane feature into the four attributes. The generated 3D Gaussians can be finally rendered at 705 frames per second. Extensive experiments demonstrate the superiority of our method over existing methods. Also, BrightDreamer possesses a strong semantic understanding capability even for complex text prompts. The project code is available at https://vlislab22.github.io/BrightDreamer.
Authors: Yuxuan Zhang, Yiren Song, Jinpeng Yu, Han Pan, Zhongliang Jing
Abstract: Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an effective and fast approach that could balance the text-image consistency and identity consistency of the generated image and reference image. Our method can generate personalized images without any fine-tuning while maintaining the inherent text-to-image generation ability of diffusion models. Given a prompt and a reference image, we merge the custom concept into generated images by manipulating cross-attention and self-attention layers of the original diffusion model to generate personalized images that match the text description. Comprehensive experiments highlight the superiority of our method.
Authors: Jesher Joshua M, Ragav V, Syed Ibrahim S P
Abstract: The maintenance, archiving and usage of the design drawings is cumbersome in physical form in different industries for longer period. It is hard to extract information by simple scanning of drawing sheets. Converting them to their digital formats such as Computer-Aided Design (CAD), with needed knowledge extraction can solve this problem. The conversion of these machine drawings to its digital form is a crucial challenge which requires advanced techniques. This research proposes an innovative methodology utilizing Deep Learning methods. The approach employs object detection model, such as Yolov7, Faster R-CNN, to detect physical drawing objects present in the images followed by, edge detection algorithms such as canny filter to extract and refine the identified lines from the drawing region and curve detection techniques to detect circle. Also ornaments (complex shapes) within the drawings are extracted. To ensure comprehensive conversion, an Optical Character Recognition (OCR) tool is integrated to identify and extract the text elements from the drawings. The extracted data which includes the lines, shapes and text is consolidated and stored in a structured comma separated values(.csv) file format. The accuracy and the efficiency of conversion is evaluated. Through this, conversion can be automated to help organizations enhance their productivity, facilitate seamless collaborations and preserve valuable design information in a digital format easily accessible. Overall, this study contributes to the advancement of CAD conversions, providing accurate results from the translating process. Future research can focus on handling diverse drawing types, enhanced accuracy in shape and line detection and extraction.
Authors: Marvin Anas Hahn, Kathl\'en Kohn, Orlando Marigliano, Tomas Pajdla
Abstract: Rolling shutter (RS) cameras dominate consumer and smartphone markets. Several methods for computing the absolute pose of RS cameras have appeared in the last 20 years, but the relative pose problem has not been fully solved yet. We provide a unified theory for the important class of order-one rolling shutter (RS$_1$) cameras. These cameras generalize the perspective projection to RS cameras, projecting a generic space point to exactly one image point via a rational map. We introduce a new back-projection RS camera model, characterize RS$_1$ cameras, construct explicit parameterizations of such cameras, and determine the image of a space line. We classify all minimal problems for solving the relative camera pose problem with linear RS$_1$ cameras and discover new practical cases. Finally, we show how the theory can be used to explain RS models previously used for absolute pose computation.
Authors: Guohao Sun, Can Qin, Jiamian Wang, Zeyuan Chen, Ran Xu, Zhiqiang Tao
Abstract: Recent advancements in the vision-language model have shown notable generalization in vision-language tasks after visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which are costly to obtain. However, the image contains rich contextual information that has been largely under-explored. This paper first attempts to harness this overlooked context within visual instruction data, training the model to self-supervised `learning' how to ask high-quality questions. In this way, we introduce a novel framework named SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant. SQ-LLaVA exhibits proficiency in generating flexible and meaningful image-related questions while analyzing the visual clue and prior language knowledge, signifying an advanced level of generalized visual understanding. Moreover, fine-tuning SQ-LLaVA on higher-quality instruction data shows a consistent performance improvement compared with traditional visual-instruction tuning methods. This improvement highlights the efficacy of self-questioning techniques in achieving a deeper and more nuanced comprehension of visual content across various contexts.
Authors: Qucheng Peng, Ce Zheng, Chen Chen
Abstract: 3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalization is employed. Current methodologies in domain generalization for 3D human pose estimation typically utilize adversarial training to generate synthetic poses for training. Nonetheless, these approaches exhibit several limitations. First, the lack of prior information about the target domain complicates the application of suitable augmentation through a single pose augmentor, affecting generalization on target domains. Moreover, adversarial training's discriminator tends to enforce similarity between source and synthesized poses, impeding the exploration of out-of-source distributions. Furthermore, the pose estimator's optimization is not exposed to domain shifts, limiting its overall generalization ability. To address these limitations, we propose a novel framework featuring two pose augmentors: the weak and the strong augmentors. Our framework employs differential strategies for generation and discrimination processes, facilitating the preservation of knowledge related to source poses and the exploration of out-of-source distributions without prior information about target poses. Besides, we leverage meta-optimization to simulate domain shifts in the optimization process of the pose estimator, thereby improving its generalization ability. Our proposed approach significantly outperforms existing methods, as demonstrated through comprehensive experiments on various benchmark datasets.
Authors: Yanyan Li, Chenyu Lyu, Yan Di, Guangyao Zhai, Gim Hee Lee, Federico Tombari
Abstract: During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved, especially in non-textured regions such as walls, ceilings, and furniture surfaces. This degradation significantly affects the rendering quality of novel views that deviate significantly from the viewpoints in the training data. To mitigate this issue, we propose a novel approach called GeoGaussian. Based on the smoothly connected areas observed from point clouds, this method introduces a novel pipeline to initialize thin Gaussians aligned with the surfaces, where the characteristic can be transferred to new generations through a carefully designed densification strategy. Finally, the pipeline ensures that the scene's geometry and texture are maintained through constrained optimization processes with explicit geometry constraints. Benefiting from the proposed architecture, the generative ability of 3D Gaussians is enhanced, especially in structured regions. Our proposed pipeline achieves state-of-the-art performance in novel view synthesis and geometric reconstruction, as evaluated qualitatively and quantitatively on public datasets.
Authors: Bavesh Balaji, Jerrin Bright, Sirisha Rambhatla, Yuhao Chen, Alexander Wong, John Zelek, David A Clausi
Abstract: Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatic detection of jersey numbers using deep features is challenging primarily due to: a) motion blur, b) low resolution video feed, and c) occlusions. With their recent success in various vision tasks, masked autoencoders (MAEs) have emerged as a superior alternative to conventional feature extractors. However, most MAEs simply zero-out image patches either randomly or focus on where to mask rather than how to mask. Motivated by human vision, we devise a novel domain-guided masking policy for MAEs termed d-MAE to facilitate robust feature extraction in the presence of motion blur for player identification. We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification. We conduct experiments on three large-scale sports datasets, including a curated baseball dataset, the SoccerNet dataset, and an in-house ice hockey dataset. We preprocess the datasets using an upgraded keyframe identification (KfID) module by focusing on frames containing jersey numbers. Additionally, we propose a keyframe-fusion technique to augment keyframes, preserving spatial and temporal context. Our spatio-temporal network showcases significant improvements, surpassing the current state-of-the-art by 8.58%, 4.29%, and 1.20% in the test set accuracies, respectively. Rigorous ablations highlight the effectiveness of our domain-guided masking approach and the refined KfID module, resulting in performance enhancements of 1.48% and 1.84% respectively, compared to original architectures.
Authors: Xue Bai, Tasmiah Haque, Sumit Mohan, Yuliang Cai, Byungheon Jeong, Adam Halasz, Srinjoy Das
Abstract: We propose a deep learning based novel prediction framework for enhanced bandwidth reduction in motion transfer enabled video applications such as video conferencing, virtual reality gaming and privacy preservation for patient health monitoring. To model complex motion, we use the First Order Motion Model (FOMM) that represents dynamic objects using learned keypoints along with their local affine transformations. Keypoints are extracted by a self-supervised keypoint detector and organized in a time series corresponding to the video frames. Prediction of keypoints, to enable transmission using lower frames per second on the source device, is performed using a Variational Recurrent Neural Network (VRNN). The predicted keypoints are then synthesized to video frames using an optical flow estimator and a generator network. This efficacy of leveraging keypoint based representations in conjunction with VRNN based prediction for both video animation and reconstruction is demonstrated on three diverse datasets. For real-time applications, our results show the effectiveness of our proposed architecture by enabling up to 2x additional bandwidth reduction over existing keypoint based video motion transfer frameworks without significantly compromising video quality.
Authors: Sai Tarun Sathyan, Thomas B. Kinsman
Abstract: It is desirable to create 3D object models and 3D maps from 2D input images for applications such as navigation, virtual tourism, and urban planning. The traditional methods of creating 3D maps, (such as photogrammetry), require a large number of images and odometry. Additionally, traditional methods have difficulty with reflective surfaces and specular reflections; windows and chrome in the scene can be problematic. Google Road View is a familiar application, which uses traditional methods to fuse a collection of 2D input images into the illusion of a 3D map. However, Google Road View does not create an actual 3D object model, only a collection of views. The objective of this work is to create an actual 3D object model using updated techniques. Neural Radiance Fields (NeRF[1]) has emerged as a potential solution, offering the capability to produce more precise and intricate 3D maps. Gaussian Splatting[4] is another contemporary technique. This investigation compares Neural Radiance Fields to Gaussian Splatting, and describes some of their inner workings. Our primary contribution is a method for improving the results of the 3D reconstructed models. Our results indicate that Gaussian Splatting was superior to the NeRF technique.
Authors: Peng Jiang, Gaurav Pandey, Srikanth Saripalli
Abstract: This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting. Our proposed method uses LiDAR and camera data to create accurate and visually plausible representations of the environment. By leveraging LiDAR data to initiate the training of the 3D Gaussian Splatting map, our system constructs maps that are both detailed and geometrically accurate. To mitigate excessive GPU memory usage and facilitate rapid spatial queries, we employ a combination of a 2D voxel map and a KD-tree. This preparation makes our method well-suited for visual localization tasks, enabling efficient identification of correspondences between the query image and the rendered image from the Gaussian Splatting map via normalized cross-correlation (NCC). Additionally, we refine the camera pose of the query image using feature-based matching and the Perspective-n-Point (PnP) technique. The effectiveness, adaptability, and precision of our system are demonstrated through extensive evaluation on the KITTI360 dataset.
Authors: Theresa Huber, Simon Schaefer, Stefan Leutenegger
Abstract: The assumption of a static environment is common in many geometric computer vision tasks like SLAM but limits their applicability in highly dynamic scenes. Since these tasks rely on identifying point correspondences between input images within the static part of the environment, we propose a graph neural network-based sparse feature matching network designed to perform robust matching under challenging conditions while excluding keypoints on moving objects. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks but augment the graph with epipolar and temporal information and vastly reduce the number of graph edges. Furthermore, we introduce a self-supervised training scheme to extract pseudo labels for image pairs in dynamic environments from exclusively unprocessed visual-inertial data. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks while still achieving similar results regarding conventional matching metrics. When integrated into a SLAM system, our network significantly improves performance, especially in highly dynamic scenes.
Authors: Baolu Li, Jinlong Li, Xinyu Liu, Runsheng Xu, Zhengzhong Tu, Jiacheng Guo, Xiaopeng Li, Hongkai Yu
Abstract: Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in unseen adverse weather conditions with the real-world domain gap. In this paper, we propose a domain generalization approach, named V2X-DGW, for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions. Not only in the clean weather does our research aim to ensure favorable multi-agent performance, but also in the unseen adverse weather conditions by learning only on the clean weather data. To advance research in this area, we have simulated the impact of three prevalent adverse weather conditions on two widely-used multi-agent datasets, resulting in the creation of two novel benchmark datasets: OPV2V-w and V2XSet-w. To this end, we first introduce the Adaptive Weather Augmentation (AWA) to mimic the unseen adverse weather conditions, and then propose two alignments for generalizable representation learning: Trust-region Weather-invariant Alignment (TWA) and Agent-aware Contrastive Alignment (ACA). Extensive experimental results demonstrate that our V2X-DGW achieved improvements in the unseen adverse weather conditions.
Authors: Shu Zhao, Xiaohan Zou, Tan Yu, Huijuan Xu
Abstract: Pre-trained large multi-modal models (LMMs) exploit fine-tuning to adapt diverse user applications. Nevertheless, fine-tuning may face challenges due to deactivated sensors (e.g., cameras turned off for privacy or technical issues), yielding modality-incomplete data and leading to inconsistency in training data and the data for inference. Additionally, continuous training leads to catastrophic forgetting, diluting the knowledge in pre-trained LMMs. To overcome these challenges, we introduce a novel task, Continual Missing Modality Learning (CMML), to investigate how models can generalize when data of certain modalities is missing during continual fine-tuning. Our preliminary benchmarks reveal that existing methods suffer from a significant performance drop in CMML, even with the aid of advanced continual learning techniques. Therefore, we devise a framework termed Reconstruct before Query (RebQ). It decomposes prompts into modality-specific ones and breaks them into components stored in pools accessible via a key-query mechanism, which facilitates ParameterEfficient Fine-Tuning and enhances knowledge transferability for subsequent tasks. Meanwhile, our RebQ leverages extensive multi-modal knowledge from pre-trained LMMs to reconstruct the data of missing modality. Comprehensive experiments demonstrate that RebQ effectively reconstructs the missing modality information and retains pre-trained knowledge. Specifically, compared with the baseline, RebQ improves average precision from 20.00 to 50.92 and decreases average forgetting from 75.95 to 8.56. Code and datasets are available on https://github.com/Tree-Shu-Zhao/RebQ.pytorch
Authors: Hongxiao Wang, Yang Yang, Zhuo Zhao, Pengfei Gu, Nishchal Sapkota, Danny Z. Chen
Abstract: For predicting cancer survival outcomes, standard approaches in clinical research are often based on two main modalities: pathology images for observing cell morphology features, and genomic (e.g., bulk RNA-seq) for quantifying gene expressions. However, existing pathology-genomic multi-modal algorithms face significant challenges: (1) Valuable biological insights regarding genes and gene-gene interactions are frequently overlooked; (2) one modality often dominates the optimization process, causing inadequate training for the other modality. In this paper, we introduce a new multi-modal ``Path-GPTOmic" framework for cancer survival outcome prediction. First, to extract valuable biological insights, we regulate the embedding space of a foundation model, scGPT, initially trained on single-cell RNA-seq data, making it adaptable for bulk RNA-seq data. Second, to address the imbalance-between-modalities problem, we propose a gradient modulation mechanism tailored to the Cox partial likelihood loss for survival prediction. The contributions of the modalities are dynamically monitored and adjusted during the training process, encouraging that both modalities are sufficiently trained. Evaluated on two TCGA(The Cancer Genome Atlas) datasets, our model achieves substantially improved survival prediction accuracy.
Authors: Minh Tran, Winston Bounsavy, Khoa Vo, Anh Nguyen, Tri Nguyen, Ngan Le
Abstract: Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bidirectional approach, encompassing both the transition from amodal features to visible features (amodal-to-visible) and from visible features to amodal features (visible-to-amodal). Our observation shows that the utilization of amodal features through the amodal-to-visible can confuse the visible features due to the extra information of occluded/hidden segments not presented in visible display. Consequently, this compromised quality of visible features during the subsequent visible-to-amodal transition. To tackle this issue, we introduce ShapeFormer, a decoupled Transformer-based model with a visible-to-amodal transition. It facilitates the explicit relationship between output segmentations and avoids the need for amodal-to-visible transitions. ShapeFormer comprises three key modules: (i) Visible-Occluding Mask Head for predicting visible segmentation with occlusion awareness, (ii) Shape-Prior Amodal Mask Head for predicting amodal and occluded masks, and (iii) Category-Specific Shape Prior Retriever aims to provide shape prior knowledge. Comprehensive experiments and extensive ablation studies across various AIS benchmarks demonstrate the effectiveness of our ShapeFormer. The code is available at: https://github.com/UARK-AICV/ShapeFormer
Authors: Beichen Zhang, Xiaoxing Wang, Xiaohan Qin, Junchi Yan
Abstract: Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the final performance of candidate architectures. Thus, it is critical that the top architectures ranked by a supernet should be consistent with those ranked by true performance, which is known as the order-preserving ability. In this work, we analyze the order-preserving ability on the whole search space (global) and a sub-space of top architectures (local), and empirically show that the local order-preserving for current two-stage NAS methods still need to be improved. To rectify this, we propose a novel concept of Supernet Shifting, a refined search strategy combining architecture searching with supernet fine-tuning. Specifically, apart from evaluating, the training loss is also accumulated in searching and the supernet is updated every iteration. Since superior architectures are sampled more frequently in evolutionary searching, the supernet is encouraged to focus on top architectures, thus improving local order-preserving. Besides, a pre-trained supernet is often un-reusable for one-shot methods. We show that Supernet Shifting can fulfill transferring supernet to a new dataset. Specifically, the last classifier layer will be unset and trained through evolutionary searching. Comprehensive experiments show that our method has better order-preserving ability and can find a dominating architecture. Moreover, the pre-trained supernet can be easily transferred into a new dataset with no loss of performance.
Authors: Yujia Liu, Chenxi Yang, Dingquan Li, Jianhao Ding, Tingting Jiang
Abstract: The task of No-Reference Image Quality Assessment (NR-IQA) is to estimate the quality score of an input image without additional information. NR-IQA models play a crucial role in the media industry, aiding in performance evaluation and optimization guidance. However, these models are found to be vulnerable to adversarial attacks, which introduce imperceptible perturbations to input images, resulting in significant changes in predicted scores. In this paper, we propose a defense method to improve the stability in predicted scores when attacked by small perturbations, thus enhancing the adversarial robustness of NR-IQA models. To be specific, we present theoretical evidence showing that the magnitude of score changes is related to the $\ell_1$ norm of the model's gradient with respect to the input image. Building upon this theoretical foundation, we propose a norm regularization training strategy aimed at reducing the $\ell_1$ norm of the gradient, thereby boosting the robustness of NR-IQA models. Experiments conducted on four NR-IQA baseline models demonstrate the effectiveness of our strategy in reducing score changes in the presence of adversarial attacks. To the best of our knowledge, this work marks the first attempt to defend against adversarial attacks on NR-IQA models. Our study offers valuable insights into the adversarial robustness of NR-IQA models and provides a foundation for future research in this area.
Authors: Rao Fu, Jingyu Liu, Xilun Chen, Yixin Nie, Wenhan Xiong
Abstract: This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs). Scene-LLM adopts a hybrid 3D visual feature representation, that incorporates dense spatial information and supports scene state updates. The model employs a projection layer to efficiently project these features in the pre-trained textual embedding space, enabling effective interpretation of 3D visual information. Unique to our approach is the integration of both scene-level and ego-centric 3D information. This combination is pivotal for interactive planning, where scene-level data supports global planning and ego-centric data is important for localization. Notably, we use ego-centric 3D frame features for feature alignment, an efficient technique that enhances the model's ability to align features of small objects within the scene. Our experiments with Scene-LLM demonstrate its strong capabilities in dense captioning, question answering, and interactive planning. We believe Scene-LLM advances the field of 3D visual understanding and reasoning, offering new possibilities for sophisticated agent interactions in indoor settings.
Authors: Jeongsol Kim, Geon Yeong Park, Jong Chul Ye
Abstract: Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature engineering, score distillation offers a simple yet powerful model-agnostic approach, but it is often prone to mode-collapsing. To address these limitations and leverage the strengths of both approaches, here we introduce a novel framework called {\em DreamSampler}, which seamlessly integrates these two distinct approaches through the lens of regularized latent optimization. Similar to score-distillation, DreamSampler is a model-agnostic approach applicable to any LDM architecture, but it allows both distillation and reverse sampling with additional guidance for image editing and reconstruction. Through experiments involving image editing, SVG reconstruction and etc, we demonstrate the competitive performance of DreamSampler compared to existing approaches, while providing new applications.
Authors: Yuan Shi, Bin Xia, Xiaoyu Jin, Xing Wang, Tianyu Zhao, Xin Xia, Xuefeng Xiao, Wenming Yang
Abstract: Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks (CNNs), generative adversarial networks (GANs), transformers, and diffusion models (DMs), have been employed to address this problem with significant impact. However, CNNs have limitations in capturing long-range dependencies. DMs require large prior models and computationally intensive denoising steps. Transformers have powerful modeling capabilities but face challenges due to quadratic complexity with input image size. To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks. We utilize a Unet architecture to stack our proposed Omni Selective Scan (OSS) blocks, consisting of an OSS module and an Efficient Feed-Forward Network (EFFN). Our proposed omni selective scan mechanism overcomes the unidirectional modeling limitation of SSMs by efficiently modeling image information flows in all six directions. Furthermore, we conducted a comprehensive evaluation of our VmambaIR across multiple image restoration tasks, including image deraining, single image super-resolution, and real-world image super-resolution. Extensive experimental results demonstrate that our proposed VmambaIR achieves state-of-the-art (SOTA) performance with much fewer computational resources and parameters. Our research highlights the potential of state space models as promising alternatives to the transformer and CNN architectures in serving as foundational frameworks for next-generation low-level visual tasks.
Authors: Xiaoqiong Liu, Yunhe Feng, Shu Hu, Xiaohui Yuan, Heng Fan
Abstract: The robustness of unmanned aerial vehicle (UAV) tracking is crucial in many tasks like surveillance and robotics. Despite its importance, little attention is paid to the performance of UAV trackers under common corruptions due to lack of a dedicated platform. Addressing this, we propose UAV-C, a large-scale benchmark for assessing robustness of UAV trackers under common corruptions. Specifically, UAV-C is built upon two popular UAV datasets by introducing 18 common corruptions from 4 representative categories including adversarial, sensor, blur, and composite corruptions in different levels. Finally, UAV-C contains more than 10K sequences. To understand the robustness of existing UAV trackers against corruptions, we extensively evaluate 12 representative algorithms on UAV-C. Our study reveals several key findings: 1) Current trackers are vulnerable to corruptions, indicating more attention needed in enhancing the robustness of UAV trackers; 2) When accompanying together, composite corruptions result in more severe degradation to trackers; and 3) While each tracker has its unique performance profile, some trackers may be more sensitive to specific corruptions. By releasing UAV-C, we hope it, along with comprehensive analysis, serves as a valuable resource for advancing the robustness of UAV tracking against corruption. Our UAV-C will be available at https://github.com/Xiaoqiong-Liu/UAV-C.
Authors: Tingyang Zhang, Qingzhe Gao, Weiyu Li, Libin Liu, Baoquan Chen
Abstract: Animatable 3D reconstruction has significant applications across various fields, primarily relying on artists' handcraft creation. Recently, some studies have successfully constructed animatable 3D models from monocular videos. However, these approaches require sufficient view coverage of the object within the input video and typically necessitate significant time and computational costs for training and rendering. This limitation restricts the practical applications. In this work, we propose a method to build animatable 3D Gaussian Splatting from monocular video with diffusion priors. The 3D Gaussian representations significantly accelerate the training and rendering process, and the diffusion priors allow the method to learn 3D models with limited viewpoints. We also present the rigid regularization to enhance the utilization of the priors. We perform an extensive evaluation across various real-world videos, demonstrating its superior performance compared to the current state-of-the-art methods.
Authors: Weiwei Zhou, Jiada Lu, Chenkun Ling, Weifeng Wang, Shaowei Liu
Abstract: Human emotion recognition holds a pivotal role in facilitating seamless human-computer interaction. This paper delineates our methodology in tackling the Valence-Arousal (VA) Estimation Challenge, Expression (Expr) Classification Challenge, and Action Unit (AU) Detection Challenge within the ambit of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW). Our study advocates a novel approach aimed at refining continuous emotion recognition. We achieve this by initially harnessing pre-training with Masked Autoencoders (MAE) on facial datasets, followed by fine-tuning on the aff-wild2 dataset annotated with expression (Expr) labels. The pre-trained model serves as an adept visual feature extractor, thereby enhancing the model's robustness. Furthermore, we bolster the performance of continuous emotion recognition by integrating Temporal Convolutional Network (TCN) modules and Transformer Encoder modules into our framework.
Authors: Zhiyang Guo, Wengang Zhou, Li Li, Min Wang, Houqiang Li
Abstract: 3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant representation, while overlooking the rich motion information carried by 2D observations, thus suffering from performance degradation and model redundancy. To address the above problem, we propose a novel motion-aware enhancement framework for dynamic scene reconstruction, which mines useful motion cues from optical flow to improve different paradigms of dynamic 3DGS. Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow. Then a novel flow augmentation method is introduced with additional insights into uncertainty and loss collaboration. Moreover, for the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed. We conduct extensive experiments on both multi-view and monocular scenes to verify the merits of our work. Compared with the baselines, our method shows significant superiority in both rendering quality and efficiency.
Authors: Linyu Tang, Lei Zhang
Abstract: Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to subtle adversarial perturbations, prompting the development of many advanced adversarial defense methods aimed at mitigating adversarial attacks. Current defense strategies usually train DNNs for a specific adversarial attack method and can achieve good robustness in defense against this type of adversarial attack. Nevertheless, when subjected to evaluations involving unfamiliar attack modalities, empirical evidence reveals a pronounced deterioration in the robustness of DNNs. Meanwhile, there is a trade-off between the classification accuracy of clean examples and adversarial examples. Most defense methods often sacrifice the accuracy of clean examples in order to improve the adversarial robustness of DNNs. To alleviate these problems and enhance the overall robust generalization of DNNs, we propose the Test-Time Pixel-Level Adversarial Purification (TPAP) method. This approach is based on the robust overfitting characteristic of DNNs to the fast gradient sign method (FGSM) on training and test datasets. It utilizes FGSM for adversarial purification, to process images for purifying unknown adversarial perturbations from pixels at testing time in a "counter changes with changelessness" manner, thereby enhancing the defense capability of DNNs against various unknown adversarial attacks. Extensive experimental results show that our method can effectively improve both overall robust generalization of DNNs, notably over previous methods.
Authors: Jiahe Wang, Jiale Huang, Bingzhao Cai, Yifan Cao, Xin Yun, Shangfei Wang
Abstract: Conventional approaches to facial expression recognition primarily focus on the classification of six basic facial expressions. Nevertheless, real-world situations present a wider range of complex compound expressions that consist of combinations of these basics ones due to limited availability of comprehensive training datasets. The 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW) offered unlabeled datasets containing compound expressions. In this study, we propose a zero-shot approach for recognizing compound expressions by leveraging a pretrained visual language model integrated with some traditional CNN networks.
Authors: Haolan Chen, Jinhua Hao, Kai Zhao, Kun Yuan, Ming Sun, Chao Zhou, Wei Hu
Abstract: The objective of image super-resolution is to generate clean and high-resolution images from degraded versions. Recent advancements in diffusion modeling have led to the emergence of various image super-resolution techniques that leverage pretrained text-to-image (T2I) models. Nevertheless, due to the prevalent severe degradation in low-resolution images and the inherent characteristics of diffusion models, achieving high-fidelity image restoration remains challenging. Existing methods often exhibit issues including semantic loss, artifacts, and the introduction of spurious content not present in the original image. To tackle this challenge, we propose Cascaded diffusion for Super-Resolution, CasSR , a novel method designed to produce highly detailed and realistic images. In particular, we develop a cascaded controllable diffusion model that aims to optimize the extraction of information from low-resolution images. This model generates a preliminary reference image to facilitate initial information extraction and degradation mitigation. Furthermore, we propose a multi-attention mechanism to enhance the T2I model's capability in maximizing the restoration of the original image content. Through a comprehensive blend of qualitative and quantitative analyses, we substantiate the efficacy and superiority of our approach.
Authors: Teppei Suzuki
Abstract: In this work, we present Fed3DGS, a scalable 3D reconstruction framework based on 3D Gaussian splatting (3DGS) with federated learning. Existing city-scale reconstruction methods typically adopt a centralized approach, which gathers all data in a central server and reconstructs scenes. The approach hampers scalability because it places a heavy load on the server and demands extensive data storage when reconstructing scenes on a scale beyond city-scale. In pursuit of a more scalable 3D reconstruction, we propose a federated learning framework with 3DGS, which is a decentralized framework and can potentially use distributed computational resources across millions of clients. We tailor a distillation-based model update scheme for 3DGS and introduce appearance modeling for handling non-IID data in the scenario of 3D reconstruction with federated learning. We simulate our method on several large-scale benchmarks, and our method demonstrates rendered image quality comparable to centralized approaches. In addition, we also simulate our method with data collected in different seasons, demonstrating that our framework can reflect changes in the scenes and our appearance modeling captures changes due to seasonal variations.
Authors: Chaolei Tan, Jianhuang Lai, Wei-Shi Zheng, Jian-Fang Hu
Abstract: Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to eliminate the need of temporal annotations. Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Augmentation Branch is utilized for directly regressing the temporal boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multiple sentences in a normal video. We demonstrate by extensive experiments that our paradigm has superior practicability and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision.
Authors: Siyu Xu, Yunke Wang, Daochang Liu, Chang Xu
Abstract: Recent advancements in generative AI have suggested that by taking visual prompt, GPT-4V can demonstrate significant proficiency in image recognition task. Despite its impressive capabilities, the financial cost associated with GPT-4V's inference presents a substantial barrier for its wide use. To address this challenge, our work introduces Collage Prompting, a budget-friendly prompting approach that concatenates multiple images into a single visual input. With collage prompt, GPT-4V is able to perform image recognition on several images simultaneously. Based on the observation that the accuracy of GPT-4V's image recognition varies significantly with the order of images within the collage prompt, our method further learns to optimize the arrangement of images for maximum recognition accuracy. A graph predictor is trained to indicate the accuracy of each collage prompt, then we propose an optimization method to navigate the search space of possible image arrangements. Experiment results across various datasets demonstrate the cost-efficiency score of collage prompt is much larger than standard prompt. Additionally, collage prompt with learned arrangement achieves clearly better accuracy than collage prompt with random arrangement in GPT-4V's visual recognition.
Authors: Jiaxu Zhang, Xin Chen, Gang Yu, Zhigang Tu
Abstract: Stylized motion breathes life into characters. However, the fixed skeleton structure and style representation hinder existing data-driven motion synthesis methods from generating stylized motion for various characters. In this work, we propose a generative motion stylization pipeline, named MotionS, for synthesizing diverse and stylized motion on cross-structure characters using cross-modality style prompts. Our key insight is to embed motion style into a cross-modality latent space and perceive the cross-structure skeleton topologies, allowing for motion stylization within a canonical motion space. Specifically, the large-scale Contrastive-Language-Image-Pre-training (CLIP) model is leveraged to construct the cross-modality latent space, enabling flexible style representation within this space. Additionally, two topology-encoded tokens are learned to capture the canonical and specific skeleton topologies, facilitating cross-structure topology shifting. Subsequently, the topology-shifted stylization diffusion is designed to generate motion content for the specific skeleton and stylize it in the shifted canonical motion space using multi-modality style descriptions. Through an extensive set of examples, we demonstrate the flexibility and generalizability of our pipeline across various characters and style descriptions. Qualitative and quantitative experiments underscore the superiority of our pipeline over state-of-the-art methods, consistently delivering high-quality stylized motion across a broad spectrum of skeletal structures.
Authors: Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li
Abstract: We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos. In particular, the proposed multimodal agent VideoAgent: 1) constructs a structured memory to store both the generic temporal event descriptions and object-centric tracking states of the video; 2) given an input task query, it employs tools including video segment localization and object memory querying along with other visual foundation models to interactively solve the task, utilizing the zero-shot tool-use ability of LLMs. VideoAgent demonstrates impressive performances on several long-horizon video understanding benchmarks, an average increase of 6.6% on NExT-QA and 26.0% on EgoSchema over baselines, closing the gap between open-sourced models and private counterparts including Gemini 1.5 Pro.
Authors: Yang Zhou, Hao Shao, Letian Wang, Steven L. Waslander, Hongsheng Li, Yu Liu
Abstract: Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. Context information, such as road maps and surrounding agents' states, provides crucial geometric and semantic information for motion behavior prediction. To this end, recent works explore two-stage prediction frameworks where coarse trajectories are first proposed, and then used to select critical context information for trajectory refinement. However, they either incur a large amount of computation or bring limited improvement, if not both. In this paper, we introduce a novel scenario-adaptive refinement strategy, named SmartRefine, to refine prediction with minimal additional computation. Specifically, SmartRefine can comprehensively adapt refinement configurations based on each scenario's properties, and smartly chooses the number of refinement iterations by introducing a quality score to measure the prediction quality and remaining refinement potential of each scenario. SmartRefine is designed as a generic and flexible approach that can be seamlessly integrated into most state-of-the-art motion prediction models. Experiments on Argoverse (1 & 2) show that our method consistently improves the prediction accuracy of multiple state-of-the-art prediction models. Specifically, by adding SmartRefine to QCNet, we outperform all published ensemble-free works on the Argoverse 2 leaderboard (single agent track) at submission. Comprehensive studies are also conducted to ablate design choices and explore the mechanism behind multi-iteration refinement. Codes are available at https://github.com/opendilab/SmartRefine/
Authors: Mrityunjoy Gain, Avi Deb Raha, Rameswar Debnath
Abstract: In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transform color values into color classes and vice versa. To optimize the classes, we experiment with different bin sizes for color class transformation. Observing class appearance, standard deviation, and model parameters on various extremely large-scale real-time images in practice we propose 532 color classes for our classification task. During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper saturation of individual objects. We adjust the weights of the major classes, which are more frequently observed, by lowering them, while escalating the weights of the minor classes, which are less commonly observed. In our class re-weight formula, we propose a hyper-parameter for finding the optimal trade-off between the major and minor appeared classes. As we apply regularization to enhance the stability of the minor class, occasional minor noise may appear at the object's edges. We propose a novel object-selective color harmonization method empowered by the Segment Anything Model (SAM) to refine and enhance these edges. We propose two new color image evaluation metrics, the Color Class Activation Ratio (CCAR), and the True Activation Ratio (TAR), to quantify the richness of color components. We compare our proposed model with state-of-the-art models using six different dataset: Place, ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in qualitative and quantitative approaches. The experimental results show that our proposed model outstrips other models in visualization, CNR and in our proposed CCAR and TAR measurement criteria while maintaining satisfactory performance in regression (MSE, PSNR), similarity (SSIM, LPIPS, UIUI), and generative criteria (FID).
Authors: Qizhou Wang, Yong Lin, Yongqiang Chen, Ludwig Schmidt, Bo Han, Tong Zhang
Abstract: Large vision language models, such as CLIPs, have revolutionized modern machine learning. CLIPs have demonstrated great generalizability under distribution shifts, supported by an increasing body of literature. However, the evaluation datasets for CLIPs are variations primarily designed for ImageNet benchmarks, which may not fully reflect the extent to which CLIPs, e.g., pre-trained on LAION, robust to spurious correlations. To bridge the gap, we collect a real-world dataset called CounterAnimal that contains realistic spurious features found in animal photos. CounterAnimal consists of a) the common group: comprising animals on common backgrounds, and b) the counter group: including animals on unusual backgrounds. The performance drops from the common to counter groups quantify the reliance of models on spurious features (i.e., backgrounds) to predict the animals. We find that CLIPs trained on either LAION or the OpenAI data exhibit notable performance drops on the counter group. Surprisingly, we observe that single-modal models trained on ImageNet are more robust than CLIPs. We provide both theoretical and empirical explanations for why CLIPs still learn spurious features. Our findings suggest that distribution shifts remain an open problem for CLIPs, and one needs to be cautious about test setups when evaluating foundation models pre-trained on a significantly different scale and distribution.
Authors: Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang, Xin Tong
Abstract: We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training specialized models, thus constraining their effectiveness on open-domain images featuring significantly more varied layouts and styles. In contrast, our method directly leverages powerful image diffusion models trained on a broad spectrum of text-image pairs and thus retain their exceptional generalization abilities. This objective is realized through the development of an iterative novel view synthesis and geometry alignment algorithm. The algorithm harnesses diffusion models for dual purposes: they provide appearance prior by predicting novel views of the selected object using estimated depth maps, and they act as a geometry critic by correcting misalignments in 3D shapes across the sampled views. Our method can generate high-quality 3D-aware image edits with large viewpoint transformations and high appearance and shape consistency with the input image, pushing the boundaries of what is possible with single-image 3D-aware editing.
Authors: Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu, Jianwei Niu
Abstract: Underwater video enhancement (UVE) aims to improve the visibility and frame quality of underwater videos, which has significant implications for marine research and exploration. However, existing methods primarily focus on developing image enhancement algorithms to enhance each frame independently. There is a lack of supervised datasets and models specifically tailored for UVE tasks. To fill this gap, we construct the Synthetic Underwater Video Enhancement (SUVE) dataset, comprising 840 diverse underwater-style videos paired with ground-truth reference videos. Based on this dataset, we train a novel underwater video enhancement model, UVENet, which utilizes inter-frame relationships to achieve better enhancement performance. Through extensive experiments on both synthetic and real underwater videos, we demonstrate the effectiveness of our approach. This study represents the first comprehensive exploration of UVE to our knowledge. The code is available at https://anonymous.4open.science/r/UVENet.
Authors: Juming Xiong, Ethan H. Nguyen, Yilin Liu, Ruining Deng, Regina N Tyree, Hernan Correa, Girish Hiremath, Yaohong Wang, Haichun Yang, Agnes B. Fogo, Yuankai Huo
Abstract: Recently, circle representation has been introduced for medical imaging, designed specifically to enhance the detection of instance objects that are spherically shaped (e.g., cells, glomeruli, and nuclei). Given its outstanding effectiveness in instance detection, it is compelling to consider the application of circle representation for segmenting instance medical objects. In this study, we introduce CircleSnake, a simple end-to-end segmentation approach that utilizes circle contour deformation for segmenting ball-shaped medical objects at the instance level. The innovation of CircleSnake lies in these three areas: (1) It substitutes the complex bounding box-to-octagon contour transformation with a more consistent and rotation-invariant bounding circle-to-circle contour adaptation. This adaptation specifically targets ball-shaped medical objects. (2) The circle representation employed in CircleSnake significantly reduces the degrees of freedom to two, compared to eight in the octagon representation. This reduction enhances both the robustness of the segmentation performance and the rotational consistency of the method. (3) CircleSnake is the first end-to-end deep instance segmentation pipeline to incorporate circle representation, encompassing consistent circle detection, circle contour proposal, and circular convolution in a unified framework. This integration is achieved through the novel application of circular graph convolution within the context of circle detection and instance segmentation. In practical applications, such as the detection of glomeruli, nuclei, and eosinophils in pathological images, CircleSnake has demonstrated superior performance and greater rotation invariance when compared to benchmarks. The code has been made publicly available: https://github.com/hrlblab/CircleSnake.
Authors: Sungphill Moon, Hyeontae Son, Dongcheol Hur, Sangwook Kim
Abstract: Despite the progress of learning-based methods for 6D object pose estimation, the trade-off between accuracy and scalability for novel objects still exists. Specifically, previous methods for novel objects do not make good use of the target object's 3D shape information since they focus on generalization by processing the shape indirectly, making them less effective. We present GenFlow, an approach that enables both accuracy and generalization to novel objects with the guidance of the target object's shape. Our method predicts optical flow between the rendered image and the observed image and refines the 6D pose iteratively. It boosts the performance by a constraint of the 3D shape and the generalizable geometric knowledge learned from an end-to-end differentiable system. We further improve our model by designing a cascade network architecture to exploit the multi-scale correlations and coarse-to-fine refinement. GenFlow ranked first on the unseen object pose estimation benchmarks in both the RGB and RGB-D cases. It also achieves performance competitive with existing state-of-the-art methods for the seen object pose estimation without any fine-tuning.
Authors: Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani, Bassem Ouni, Muhammad Shafique
Abstract: Monocular depth estimation (MDE) has advanced significantly, primarily through the integration of convolutional neural networks (CNNs) and more recently, Transformers. However, concerns about their susceptibility to adversarial attacks have emerged, especially in safety-critical domains like autonomous driving and robotic navigation. Existing approaches for assessing CNN-based depth prediction methods have fallen short in inducing comprehensive disruptions to the vision system, often limited to specific local areas. In this paper, we introduce SSAP (Shape-Sensitive Adversarial Patch), a novel approach designed to comprehensively disrupt monocular depth estimation (MDE) in autonomous navigation applications. Our patch is crafted to selectively undermine MDE in two distinct ways: by distorting estimated distances or by creating the illusion of an object disappearing from the system's perspective. Notably, our patch is shape-sensitive, meaning it considers the specific shape and scale of the target object, thereby extending its influence beyond immediate proximity. Furthermore, our patch is trained to effectively address different scales and distances from the camera. Experimental results demonstrate that our approach induces a mean depth estimation error surpassing 0.5, impacting up to 99% of the targeted region for CNN-based MDE models. Additionally, we investigate the vulnerability of Transformer-based MDE models to patch-based attacks, revealing that SSAP yields a significant error of 0.59 and exerts substantial influence over 99% of the target region on these models.
Authors: Hantao Zhou, Runze Hu, Xiu Li
Abstract: Storing intermediate frame segmentations as memory for long-range context modeling, spatial-temporal memory-based methods have recently showcased impressive results in semi-supervised video object segmentation (SVOS). However, these methods face two key limitations: 1) relying on non-local pixel-level matching to read memory, resulting in noisy retrieved features for segmentation; 2) segmenting each object independently without interaction. These shortcomings make the memory-based methods struggle in similar object and multi-object segmentation. To address these issues, we propose a query modulation method, termed QMVOS. This method summarizes object features into dynamic queries and then treats them as dynamic filters for mask prediction, thereby providing high-level descriptions and object-level perception for the model. Efficient and effective multi-object interactions are realized through inter-query attention. Extensive experiments demonstrate that our method can bring significant improvements to the memory-based SVOS method and achieve competitive performance on standard SVOS benchmarks. The code is available at https://github.com/zht8506/QMVOS.
Authors: Hongbo Zhao, Bolin Ni, Haochen Wang, Junsong Fan, Fei Zhu, Yuxi Wang, Yuntao Chen, Gaofeng Meng, Zhaoxiang Zhang
Abstract: For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners. These requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify two key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. To address them, we propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we use LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. GS-LoRA is effective, parameter-efficient, data-efficient, and easy to implement. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that GS-LoRA manages to forget specific classes with minimal impact on other classes. Codes will be released on \url{https://github.com/bjzhb666/GS-LoRA}.
Authors: Jianzhi liu, Junchen Zhu, Lianli Gao, Jingkuan Song
Abstract: Recent large-scale video datasets have facilitated the generation of diverse open-domain videos of Video Diffusion Models (VDMs). Nonetheless, the efficacy of VDMs in assimilating complex knowledge from these datasets remains constrained by their inherent scale, leading to suboptimal comprehension and synthesis of numerous actions. In this paper, we introduce EchoReel, a novel approach to augment the capability of VDMs in generating intricate actions by emulating motions from pre-existing videos, which are readily accessible from databases or online repositories. EchoReel seamlessly integrates with existing VDMs, enhancing their ability to produce realistic motions without compromising their fundamental capabilities. Specifically, the Action Prism (AP), is introduced to distill motion information from reference videos, which requires training on only a small dataset. Leveraging the knowledge from pre-trained VDMs, EchoReel incorporates new action features into VDMs through the additional layers, eliminating the need for any further fine-tuning of untrained actions. Extensive experiments demonstrate that EchoReel is not merely replicating the whole content from references, and it significantly improves the generation of realistic actions, even in situations where existing VDMs might directly fail.
Authors: Chih-Chung Hsu, Chia-Ming Lee, Chun-Hung Sun, Kuang-Ming Wu
Abstract: Automatic optical inspection (AOI) plays a pivotal role in the manufacturing process, predominantly leveraging high-resolution imaging instruments for scanning purposes. It detects anomalies by analyzing image textures or patterns, making it an essential tool in industrial manufacturing and quality control. Despite its importance, the deployment of models for AOI often faces challenges. These include limited sample sizes, which hinder effective feature learning, variations among source domains, and sensitivities to changes in lighting and camera positions during imaging. These factors collectively compromise the accuracy of model predictions. Traditional AOI often fails to capitalize on the rich mechanism-parameter information from machines or inside images, including statistical parameters, which typically benefit AOI classification. To address this, we introduce an external modality-guided data mining framework, primarily rooted in optical character recognition (OCR), to extract statistical features from images as a second modality to enhance performance, termed OANet (Ocr-Aoi-Net). A key aspect of our approach is the alignment of external modality features, extracted using a single modality-aware model, with image features encoded by a convolutional neural network. This synergy enables a more refined fusion of semantic representations from different modalities. We further introduce feature refinement and a gating function in our OANet to optimize the combination of these features, enhancing inference and decision-making capabilities. Experimental outcomes show that our methodology considerably boosts the recall rate of the defect detection model and maintains high robustness even in challenging scenarios.
Authors: Jisu Han, Jaemin Na, Wonjun Hwang
Abstract: Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the reliance on the rehearsal buffer. Although this approach has demonstrated outstanding results, existing methods depend on preceding task-selection process to choose appropriate prompts. However, imperfectness in task-selection may lead to negative impacts on the performance particularly in the scenarios where the number of tasks is large or task distributions are imbalanced. To address this issue, we introduce I-Prompt, a task-agnostic approach focuses on the visual semantic information of image tokens to eliminate task prediction. Our method consists of semantic prompt matching, which determines prompts based on similarities between tokens, and image token-level prompting, which applies prompts directly to image tokens in the intermediate layers. Consequently, our method achieves competitive performance on four benchmarks while significantly reducing training time compared to state-of-the-art methods. Moreover, we demonstrate the superiority of our method across various scenarios through extensive experiments.
Authors: Ming Xu, Zilong Xie
Abstract: Most Vision-and-Language Navigation (VLN) algorithms tend to make decision errors, primarily due to a lack of visual common sense and insufficient reasoning capabilities. To address this issue, this paper proposes a Hierarchical Spatial Proximity Reasoning (HSPR) model. Firstly, we design a Scene Understanding Auxiliary Task (SUAT) to assist the agent in constructing a knowledge base of hierarchical spatial proximity for reasoning navigation. Specifically, this task utilizes panoramic views and object features to identify regions in the navigation environment and uncover the adjacency relationships between regions, objects, and region-object pairs. Secondly, we dynamically construct a semantic topological map through agent-environment interactions and propose a Multi-step Reasoning Navigation Algorithm (MRNA) based on the map. This algorithm continuously plans various feasible paths from one region to another, utilizing the constructed proximity knowledge base, enabling more efficient exploration. Additionally, we introduce a Proximity Adaptive Attention Module (PAAM) and Residual Fusion Method (RFM) to enable the model to obtain more accurate navigation decision confidence. Finally, we conduct experiments on publicly available datasets including REVERIE, SOON, R2R, and R4R to validate the effectiveness of the proposed approach.
Authors: Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Dong Wang, Huchuan Lu, You He
Abstract: Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial due to (i) parameter shifts throughout lifelong learning and (ii) significant computational burdens associated with full-model tuning. In this work, we present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters in response to new tasks. To preserve the zero-shot recognition capability of vision-language models, we further introduce a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP, respectively. Through extensive experiments across various settings, our proposed method consistently outperforms previous state-of-the-art approaches while concurrently reducing parameter training burdens by 60%. Our code locates at https://github.com/JiazuoYu/MoE-Adapters4CL
Authors: Weiran Chen, Xin Li, Jiaqi Su, Guiqian Zhu, Ying Li, Yi Ji, Chunping Liu
Abstract: As a cross-modal task, visual storytelling aims to generate a story for an ordered image sequence automatically. Different from the image captioning task, visual storytelling requires not only modeling the relationships between objects in the image but also mining the connections between adjacent images. Recent approaches primarily utilize either end-to-end frameworks or multi-stage frameworks to generate relevant stories, but they usually overlook latent topic information. In this paper, in order to generate a more coherent and relevant story, we propose a novel method, Topic Aware Reinforcement Network for VIsual StoryTelling (TARN-VIST). In particular, we pre-extracted the topic information of stories from both visual and linguistic perspectives. Then we apply two topic-consistent reinforcement learning rewards to identify the discrepancy between the generated story and the human-labeled story so as to refine the whole generation process. Extensive experimental results on the VIST dataset and human evaluation demonstrate that our proposed model outperforms most of the competitive models across multiple evaluation metrics.
Authors: Liren He, Zhengkai Jiang, Jinlong Peng, Liang Liu, Qiangang Du, Xiaobin Hu, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
Abstract: In the field of multi-class anomaly detection, reconstruction-based methods derived from single-class anomaly detection face the well-known challenge of ``learning shortcuts'', wherein the model fails to learn the patterns of normal samples as it should, opting instead for shortcuts such as identity mapping or artificial noise elimination. Consequently, the model becomes unable to reconstruct genuine anomalies as normal instances, resulting in a failure of anomaly detection. To counter this issue, we present a novel unified feature reconstruction-based anomaly detection framework termed RLR (Reconstruct features from a Learnable Reference representation). Unlike previous methods, RLR utilizes learnable reference representations to compel the model to learn normal feature patterns explicitly, thereby prevents the model from succumbing to the ``learning shortcuts'' issue. Additionally, RLR incorporates locality constraints into the learnable reference to facilitate more effective normal pattern capture and utilizes a masked learnable key attention mechanism to enhance robustness. Evaluation of RLR on the 15-category MVTec-AD dataset and the 12-category VisA dataset shows superior performance compared to state-of-the-art methods under the unified setting. The code of RLR will be publicly available.
Authors: Zhenghao Zhang, Zuozhuo Dai, Long Qin, Weizhi Wang
Abstract: Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video editing methods commonly require per-video fine-tuning of diffusion models or specific inversion optimization to ensure high-fidelity edits. In this paper, we introduce EffiVED, an efficient diffusion-based model that directly supports instruction-guided video editing. To achieve this, we present two efficient workflows to gather video editing pairs, utilizing augmentation and fundamental vision-language techniques. These workflows transform vast image editing datasets and open-world videos into a high-quality dataset for training EffiVED. Experimental results reveal that EffiVED not only generates high-quality editing videos but also executes rapidly. Finally, we demonstrate that our data collection method significantly improves editing performance and can potentially tackle the scarcity of video editing data. The datasets will be made publicly available upon publication.
Authors: Yuhe Liu, Mengxue Kang, Zengchang Qin, Xiangxiang Chu
Abstract: Large text-to-image models have achieved astonishing performance in synthesizing diverse and high-quality images guided by texts. With detail-oriented conditioning control, even finer-grained spatial control can be achieved. However, some generated images still appear unreasonable, even with plentiful object features and a harmonious style. In this paper, we delve into the underlying causes and find that deep-level logical information, serving as common-sense knowledge, plays a significant role in understanding and processing images. Nonetheless, almost all models have neglected the importance of logical relations in images, resulting in poor performance in this aspect. Following this observation, we propose LogicalDefender, which combines images with the logical knowledge already summarized by humans in text. This encourages models to learn logical knowledge faster and better, and concurrently, extracts the widely applicable logical knowledge from both images and human knowledge. Experiments show that our model has achieved better logical performance, and the extracted logical knowledge can be effectively applied to other scenarios.
Authors: Chih-Chung Hsu, Chia-Ming Lee, Ming-Shyen Wu
Abstract: Instance segmentation is a fundamental task in computer vision with broad applications across various industries. In recent years, with the proliferation of deep learning and artificial intelligence applications, how to train effective models with limited data has become a pressing issue for both academia and industry. In the Visual Inductive Priors challenge (VIPriors2023), participants must train a model capable of precisely locating individuals on a basketball court, all while working with limited data and without the use of transfer learning or pre-trained models. We propose Memory effIciency inStance Segmentation framework based on visual inductive prior flow propagation that effectively incorporates inherent prior information from the dataset into both the data preprocessing and data augmentation stages, as well as the inference phase. Our team (ACVLAB) experiments demonstrate that our model achieves promising performance (0.509 AP@0.50:0.95) even under limited data and memory constraints.
Authors: Mincheol Chang, Siyeong Lee, Jinkyu Kim, Namil Kim
Abstract: Typical LiDAR-based 3D object detection models are trained in a supervised manner with real-world data collection, which is often imbalanced over classes (or long-tailed). To deal with it, augmenting minority-class examples by sampling ground truth (GT) LiDAR points from a database and pasting them into a scene of interest is often used, but challenges still remain: inflexibility in locating GT samples and limited sample diversity. In this work, we propose to leverage pseudo-LiDAR point clouds generated (at a low cost) from videos capturing a surround view of miniatures or real-world objects of minor classes. Our method, called Pseudo Ground Truth Augmentation (PGT-Aug), consists of three main steps: (i) volumetric 3D instance reconstruction using a 2D-to-3D view synthesis model, (ii) object-level domain alignment with LiDAR intensity estimation and (iii) a hybrid context-aware placement method from ground and map information. We demonstrate the superiority and generality of our method through performance improvements in extensive experiments conducted on three popular benchmarks, i.e., nuScenes, KITTI, and Lyft, especially for the datasets with large domain gaps captured by different LiDAR configurations. Our code and data will be publicly available upon publication.
Authors: Chih-Chung Hsu, Chia-Ming Lee
Abstract: Instance segmentation, a cornerstone task in computer vision, has wide-ranging applications in diverse industries. The advent of deep learning and artificial intelligence has underscored the criticality of training effective models, particularly in data-scarce scenarios - a concern that resonates in both academic and industrial circles. A significant impediment in this domain is the resource-intensive nature of procuring high-quality, annotated data for instance segmentation, a hurdle that amplifies the challenge of developing robust models under resource constraints. In this context, the strategic integration of a visual prior into the training dataset emerges as a potential solution to enhance congruity with the testing data distribution, consequently reducing the dependency on computational resources and the need for highly complex models. However, effectively embedding a visual prior into the learning process remains a complex endeavor. Addressing this challenge, we introduce the MISS (Memory-efficient Instance Segmentation System) framework. MISS leverages visual inductive prior flow propagation, integrating intrinsic prior knowledge from the Synergy-basketball dataset at various stages: data preprocessing, augmentation, training, and inference. Our empirical evaluations underscore the efficacy of MISS, demonstrating commendable performance in scenarios characterized by limited data availability and memory constraints.
Authors: Quentin Herau, Moussab Bennehar, Arthur Moreau, Nathan Piasco, Luis Roldao, Dzmitry Tsishkou, Cyrille Migniot, Pascal Vasseur, C\'edric Demonceaux
Abstract: Reliable multimodal sensor fusion algorithms re- quire accurate spatiotemporal calibration. Recently, targetless calibration techniques based on implicit neural representations have proven to provide precise and robust results. Nevertheless, such methods are inherently slow to train given the high compu- tational overhead caused by the large number of sampled points required for volume rendering. With the recent introduction of 3D Gaussian Splatting as a faster alternative to implicit representation methods, we propose to leverage this new ren- dering approach to achieve faster multi-sensor calibration. We introduce 3DGS-Calib, a new calibration method that relies on the speed and rendering accuracy of 3D Gaussian Splatting to achieve multimodal spatiotemporal calibration that is accurate, robust, and with a substantial speed-up compared to methods relying on implicit neural representations. We demonstrate the superiority of our proposal with experimental results on sequences from KITTI-360, a widely used driving dataset.
Authors: Seungbeom Woo, Geonwoo Baek, Taehoon Kim, Jaemin Na, Joong-won Hwang, Wonjun Hwang
Abstract: Multi-target domain adaptation (MTDA) for semantic segmentation poses a significant challenge, as it involves multiple target domains with varying distributions. The goal of MTDA is to minimize the domain discrepancies among a single source and multi-target domains, aiming to train a single model that excels across all target domains. Previous MTDA approaches typically employ multiple teacher architectures, where each teacher specializes in one target domain to simplify the task. However, these architectures hinder the student model from fully assimilating comprehensive knowledge from all target-specific teachers and escalate training costs with increasing target domains. In this paper, we propose an ouroboric domain bridging (OurDB) framework, offering an efficient solution to the MTDA problem using a single teacher architecture. This framework dynamically cycles through multiple target domains, aligning each domain individually to restrain the biased alignment problem, and utilizes Fisher information to minimize the forgetting of knowledge from previous target domains. We also propose a context-guided class-wise mixup (CGMix) that leverages contextual information tailored to diverse target contexts in MTDA. Experimental evaluations conducted on four urban driving datasets (i.e., GTA5, Cityscapes, IDD, and Mapillary) demonstrate the superiority of our method over existing state-of-the-art approaches.
Authors: Yuxin Yao, Siyu Ren, Junhui Hou, Zhi Deng, Juyong Zhang, Wenping Wang
Abstract: This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf.
Authors: Yujiao Jiang, Qingmin Liao, Xiaoyu Li, Li Ma, Qi Zhang, Chaopeng Zhang, Zongqing Lu, Ying Shan
Abstract: Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While existing NeRF-based methods can achieve high-quality novel view rendering of human models, both training and inference processes are time-consuming. Recent approaches have utilized 3D Gaussians to represent the human body, enabling faster training and rendering. However, they undermine the importance of the mesh guidance and directly predict Gaussians in 3D space with coarse mesh guidance. This hinders the learning procedure of the Gaussians and tends to produce blurry textures. Therefore, we propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures. We utilize the embedding of UV map to learn Gaussian textures in 2D space, leveraging the capabilities of powerful 2D networks to extract features. Additionally, through an independent Mesh network, we optimize pose-dependent geometric deformations, thereby guiding Gaussian rendering and significantly enhancing rendering quality. We collect and process a new dataset of human motion, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that our method achieves state-of-the-art synthesis of novel view and novel pose. The code and data will be made available on the homepage https://alex-jyj.github.io/UV-Gaussians/ once the paper is accepted.
Authors: Andrey V. Savchenko
Abstract: This article presents our results for the sixth Affective Behavior Analysis in-the-wild (ABAW) competition. To improve the trustworthiness of facial analysis, we study the possibility of using pre-trained deep models that extract reliable emotional features without the need to fine-tune the neural networks for a downstream task. In particular, we introduce several lightweight models based on MobileViT, MobileFaceNet, EfficientNet, and DDAMFN architectures trained in multi-task scenarios to recognize facial expressions, valence, and arousal on static photos. These neural networks extract frame-level features fed into a simple classifier, e.g., linear feed-forward neural network, to predict emotion intensity, compound expressions, action units, facial expressions, and valence/arousal. Experimental results for five tasks from the sixth ABAW challenge demonstrate that our approach lets us significantly improve quality metrics on validation sets compared to existing non-ensemble techniques.
Authors: S\'andor T\'oth, Stephen Wilson, Alexia Tsoukara, Enric Moreu, Anton Masalovich, Lars Roemheld
Abstract: Product matching, the task of identifying different representations of the same product for better discoverability, curation, and pricing, is a key capability for online marketplace and e-commerce companies. We present a robust multi-modal product matching system in an industry setting, where large datasets, data distribution shifts and unseen domains pose challenges. We compare different approaches and conclude that a relatively straightforward projection of pretrained image and text encoders, trained through contrastive learning, yields state-of-the-art results, while balancing cost and performance. Our solution outperforms single modality matching systems and large pretrained models, such as CLIP. Furthermore we show how a human-in-the-loop process can be combined with model-based predictions to achieve near perfect precision in a production system.
Authors: Datao Tang, Xiangyong Cao, Xingsong Hou, Zhongyuan Jiang, Deyu Meng
Abstract: The emergence of diffusion models has revolutionized the field of image generation, providing new methods for creating high-quality, high-resolution images across various applications. However, the potential of these models for generating domain-specific images, particularly remote sensing (RS) images, remains largely untapped. RS images that are notable for their high resolution, extensive coverage, and rich information content, bring new challenges that general diffusion models may not adequately address. This paper proposes CRS-Diff, a pioneering diffusion modeling framework specifically tailored for generating remote sensing imagery, leveraging the inherent advantages of diffusion models while integrating advanced control mechanisms to ensure that the imagery is not only visually clear but also enriched with geographic and temporal information. The model integrates global and local control inputs, enabling precise combinations of generation conditions to refine the generation process. A comprehensive evaluation of CRS-Diff has demonstrated its superior capability to generate RS imagery both in a single condition and multiple conditions compared with previous methods in terms of image quality and diversity.
Authors: Vijay John, Yasutomo Kawanishi
Abstract: For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are called as weak labels. However, training a multi-view video-based action recognition model with weak labels for frame-level perception is challenging. In this paper, we propose a novel learning framework, where the weak labels are first used to train a multi-view video-based base model, which is subsequently used for downstream frame-level perception tasks. The base model is trained to obtain individual latent embeddings for each view in the multi-view input. For training the model using the weak labels, we propose a novel latent loss function. We also propose a model that uses the view-specific latent embeddings for downstream frame-level action recognition and detection tasks. The proposed framework is evaluated using the MM Office dataset by comparing several baseline algorithms. The results show that the proposed base model is effectively trained using weak labels and the latent embeddings help the downstream models improve accuracy.
Authors: Xiaohan Lei, Min Wang, Wengang Zhou, Houqiang Li
Abstract: In embodied vision, Instance ImageGoal Navigation (IIN) requires an agent to locate a specific object depicted in a goal image within an unexplored environment. The primary difficulty of IIN stems from the necessity of recognizing the target object across varying viewpoints and rejecting potential distractors. Existing map-based navigation methods largely adopt the representation form of Bird's Eye View (BEV) maps, which, however, lack the representation of detailed textures in a scene. To address the above issues, we propose a new Gaussian Splatting Navigation (abbreviated as GaussNav) framework for IIN task, which constructs a novel map representation based on 3D Gaussian Splatting (3DGS). The proposed framework enables the agent to not only memorize the geometry and semantic information of the scene, but also retain the textural features of objects. Our GaussNav framework demonstrates a significant leap in performance, evidenced by an increase in Success weighted by Path Length (SPL) from 0.252 to 0.578 on the challenging Habitat-Matterport 3D (HM3D) dataset. Our code will be made publicly available.
Authors: Yang Yang, Wen Wang, Liang Peng, Chaotian Song, Yao Chen, Hengjia Li, Xiaolong Yang, Qinglin Lu, Deng Cai, Boxi Wu, Wei Liu
Abstract: Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a Low-Rank Adaptations (LoRA) fusion matrix of multiple LoRA to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, which occurs when the model cannot preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through Concept Injection Constraints, enhancing concept visibility via an expanded cross-attention mechanism. To combat concept confusion, Concept Isolation Constraints are introduced, refining the self-attention computation. Furthermore, Latent Re-initialization is proposed to effectively stimulate concept-specific latent within designated regions. Our extensive testing showcases a notable enhancement in LoRA-Composer's performance compared to standard baselines, especially when eliminating the image-based conditions like canny edge or pose estimations. Code is released at https://github.com/Young98CN/LoRA\_Composer.
Authors: Kun Ding, Xiaohui Li, Qiang Yu, Ying Wang, Haojian Zhang, Shiming Xiang
Abstract: Context Optimization (CoOp) has emerged as a simple yet effective technique for adapting CLIP-like vision-language models to downstream image recognition tasks. Nevertheless, learning compact context with satisfactory base-to-new, domain and cross-task generalization ability while adapting to new tasks is still a challenge. To tackle such a challenge, we propose a lightweight yet generalizable approach termed Compositional Kronecker Context Optimization (CK-CoOp). Technically, the prompt's context words in CK-CoOp are learnable vectors, which are crafted by linearly combining base vectors sourced from a dictionary. These base vectors consist of a non-learnable component obtained by quantizing the weights in the token embedding layer, and a learnable component constructed by applying Kronecker product on several learnable tiny matrices. Intuitively, the compositional structure mitigates the risk of overfitting on training data by remembering more pre-trained knowledge. Meantime, the Kronecker product breaks the non-learnable restrictions of the dictionary, thereby enhancing representation ability with minimal additional parameters. Extensive experiments confirm that CK-CoOp achieves state-of-the-art performance under base-to-new, domain and cross-task generalization evaluation, but also has the metrics of fewer learnable parameters and efficient training and inference speed.
Authors: Tom Wehrbein, Bodo Rosenhahn, Iain Matthews, Carsten Stoll
Abstract: Recently, regression-based methods have dominated the field of 3D human pose and shape estimation. Despite their promising results, a common issue is the misalignment between predictions and image observations, often caused by minor joint rotation errors that accumulate along the kinematic chain. To address this issue, we propose to construct dense correspondences between initial human model estimates and the corresponding images that can be used to refine the initial predictions. To this end, we utilize renderings of the 3D models to predict per-pixel 2D displacements between the synthetic renderings and the RGB images. This allows us to effectively integrate and exploit appearance information of the persons. Our per-pixel displacements can be efficiently transformed to per-visible-vertex displacements and then used for 3D model refinement by minimizing a reprojection loss. To demonstrate the effectiveness of our approach, we refine the initial 3D human mesh predictions of multiple models using different refinement procedures on 3DPW and RICH. We show that our approach not only consistently leads to better image-model alignment, but also to improved 3D accuracy.
Authors: Foivos Paraperas Papantoniou, Alexandros Lattas, Stylianos Moschoglou, Jiankang Deng, Bernhard Kainz, Stefanos Zafeiriou
Abstract: This paper presents Arc2Face, an identity-conditioned face foundation model, which, given the ArcFace embedding of a person, can generate diverse photo-realistic images with an unparalleled degree of face similarity than existing models. Despite previous attempts to decode face recognition features into detailed images, we find that common high-resolution datasets (e.g. FFHQ) lack sufficient identities to reconstruct any subject. To that end, we meticulously upsample a significant portion of the WebFace42M database, the largest public dataset for face recognition (FR). Arc2Face builds upon a pretrained Stable Diffusion model, yet adapts it to the task of ID-to-face generation, conditioned solely on ID vectors. Deviating from recent works that combine ID with text embeddings for zero-shot personalization of text-to-image models, we emphasize on the compactness of FR features, which can fully capture the essence of the human face, as opposed to hand-crafted prompts. Crucially, text-augmented models struggle to decouple identity and text, usually necessitating some description of the given face to achieve satisfactory similarity. Arc2Face, however, only needs the discriminative features of ArcFace to guide the generation, offering a robust prior for a plethora of tasks where ID consistency is of paramount importance. As an example, we train a FR model on synthetic images from our model and achieve superior performance to existing synthetic datasets.
Authors: Theodor Westny, Bj\"orn Olofsson, Erik Frisk
Abstract: The ability to predict the future trajectories of traffic participants is crucial for the safe and efficient operation of autonomous vehicles. In this paper, a diffusion-based generative model for multi-agent trajectory prediction is proposed. The model is capable of capturing the complex interactions between traffic participants and the environment, accurately learning the multimodal nature of the data. The effectiveness of the approach is assessed on large-scale datasets of real-world traffic scenarios, showing that our model outperforms several well-established methods in terms of prediction accuracy. By the incorporation of differential motion constraints on the model output, we illustrate that our model is capable of generating a diverse set of realistic future trajectories. Through the use of an interaction-aware guidance signal, we further demonstrate that the model can be adapted to predict the behavior of less cooperative agents, emphasizing its practical applicability under uncertain traffic conditions.
Authors: Ibrahim Almakky, Santosh Sanjeev, Anees Ur Rehman Hashmi, Mohammad Areeb Qazi, Mohammad Yaqub
Abstract: Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible performance gains for deep learning models. Some advancements have been made in boosting the transfer learning performance gain by merging models starting from the same initialization. However, in the medical imaging analysis domain, there is an opportunity in merging models starting from different initialisations, thus combining the features learnt from different tasks. In this work, we propose MedMerge, a method whereby the weights of different models can be merged, and their features can be effectively utilized to boost performance on a new task. With MedMerge, we learn kernel-level weights that can later be used to merge the models into a single model, even when starting from different initializations. Testing on various medical imaging analysis tasks, we show that our merged model can achieve significant performance gains, with up to 3% improvement on the F1 score. The code implementation of this work will be available at www.github.com/BioMedIA-MBZUAI/MedMerge.
Authors: K\'evin Polisano (LJK), Basile Dubois-Bonnaire (LJK), Sylvain Meignen (LJK)
Abstract: We present a new approach leveraging the Sliding Frank--Wolfe algorithm to address the challenge of line recovery in degraded images. Building upon advances in conditional gradient methods for sparse inverse problems with differentiable measurement models, we propose two distinct models tailored for line detection tasks within the realm of blurred line deconvolution and ridge detection of linear chirps in spectrogram images.
Authors: Xander Sun, Louis Lau, Hoyard Zhi, Ronghe Qiu, Junwei Liang
Abstract: We study zero-shot instance navigation, in which the agent navigates to a specific object without using object annotations for training. Previous object navigation approaches apply the image-goal navigation (ImageNav) task (go to the location of an image) for pretraining, and transfer the agent to achieve object goals using a vision-language model. However, these approaches lead to issues of semantic neglect, where the model fails to learn meaningful semantic alignments. In this paper, we propose a Prioritized Semantic Learning (PSL) method to improve the semantic understanding ability of navigation agents. Specifically, a semantic-enhanced PSL agent is proposed and a prioritized semantic training strategy is introduced to select goal images that exhibit clear semantic supervision and relax the reward function from strict exact view matching. At inference time, a semantic expansion inference scheme is designed to preserve the same granularity level of the goal-semantic as training. Furthermore, for the popular HM3D environment, we present an Instance Navigation (InstanceNav) task that requires going to a specific object instance with detailed descriptions, as opposed to the Object Navigation (ObjectNav) task where the goal is defined merely by the object category. Our PSL agent outperforms the previous state-of-the-art by 66% on zero-shot ObjectNav in terms of success rate and is also superior on the new InstanceNav task. Code will be released at https://anonymous.4open. science/r/PSL/.
URLs: https://anonymous.4open.
Authors: Yuxin Cao, Jinghao Li, Xi Xiao, Derui Wang, Minhui Xue, Hao Ge, Wei Liu, Guangwu Hu
Abstract: Previous work has shown that well-crafted adversarial perturbations can threaten the security of video recognition systems. Attackers can invade such models with a low query budget when the perturbations are semantic-invariant, such as StyleFool. Despite the query efficiency, the naturalness of the minutia areas still requires amelioration, since StyleFool leverages style transfer to all pixels in each frame. To close the gap, we propose LocalStyleFool, an improved black-box video adversarial attack that superimposes regional style-transfer-based perturbations on videos. Benefiting from the popularity and scalably usability of Segment Anything Model (SAM), we first extract different regions according to semantic information and then track them through the video stream to maintain the temporal consistency. Then, we add style-transfer-based perturbations to several regions selected based on the associative criterion of transfer-based gradient information and regional area. Perturbation fine adjustment is followed to make stylized videos adversarial. We demonstrate that LocalStyleFool can improve both intra-frame and inter-frame naturalness through a human-assessed survey, while maintaining competitive fooling rate and query efficiency. Successful experiments on the high-resolution dataset also showcase that scrupulous segmentation of SAM helps to improve the scalability of adversarial attacks under high-resolution data.
Authors: Wolfgang Fuhl
Abstract: We propose an improvement to the landmark validity loss. Landmark detection is widely used in head pose estimation, eyelid shape extraction, as well as pupil and iris segmentation. There are numerous additional applications where landmark detection is used to estimate the shape of complex objects. One part of this process is the accurate and fine-grained detection of the shape. The other part is the validity or inaccuracy per landmark, which can be used to detect unreliable areas, where the shape possibly does not fit, and to improve the accuracy of the entire shape extraction by excluding inaccurate landmarks. We propose a normalization in the loss formulation, which improves the accuracy of the entire approach due to the numerical balance of the normalized inaccuracy. In addition, we propose a margin for the inaccuracy to reduce the impact of gradients, which are produced by negligible errors close to the ground truth.
Authors: Julia Wolleb, Florentin Bieder, Paul Friedrich, Peter Zhang, Alicia Durrer, Philippe C. Cattin
Abstract: The high performance of denoising diffusion models for image generation has paved the way for their application in unsupervised medical anomaly detection. As diffusion-based methods require a lot of GPU memory and have long sampling times, we present a novel and fast unsupervised anomaly detection approach based on latent Bernoulli diffusion models. We first apply an autoencoder to compress the input images into a binary latent representation. Next, a diffusion model that follows a Bernoulli noise schedule is employed to this latent space and trained to restore binary latent representations from perturbed ones. The binary nature of this diffusion model allows us to identify entries in the latent space that have a high probability of flipping their binary code during the denoising process, which indicates out-of-distribution data. We propose a masking algorithm based on these probabilities, which improves the anomaly detection scores. We achieve state-of-the-art performance compared to other diffusion-based unsupervised anomaly detection algorithms while significantly reducing sampling time and memory consumption. The code is available at https://github.com/JuliaWolleb/Anomaly_berdiff.
Authors: Chamuditha Jayanga Galappaththige, Sanoojan Baliah, Malitha Gunawardhana, Muhammad Haris Khan
Abstract: We approach the challenge of addressing semi-supervised domain generalization (SSDG). Specifically, our aim is to obtain a model that learns domain-generalizable features by leveraging a limited subset of labelled data alongside a substantially larger pool of unlabeled data. Existing domain generalization (DG) methods which are unable to exploit unlabeled data perform poorly compared to semi-supervised learning (SSL) methods under SSDG setting. Nevertheless, SSL methods have considerable room for performance improvement when compared to fully-supervised DG training. To tackle this underexplored, yet highly practical problem of SSDG, we make the following core contributions. First, we propose a feature-based conformity technique that matches the posterior distributions from the feature space with the pseudo-label from the model's output space. Second, we develop a semantics alignment loss to learn semantically-compatible representations by regularizing the semantic structure in the feature space. Our method is plug-and-play and can be readily integrated with different SSL-based SSDG baselines without introducing any additional parameters. Extensive experimental results across five challenging DG benchmarks with four strong SSL baselines suggest that our method provides consistent and notable gains in two different SSDG settings.
Authors: Fran\c{c}ois Porcher, Camille Couprie, Marc Szafraniec, Jakob Verbeek
Abstract: Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant. In particular, for instance segmentation annotations are time-consuming to produce, and the distribution of instances is often highly skewed across classes. While semi-supervised teacher-student distillation methods show promise in leveraging vast amounts of unlabeled data, they suffer from miscalibration, resulting in overconfidence in frequently represented classes and underconfidence in rarer ones. Additionally, these methods encounter difficulties in efficiently learning from a limited set of examples. We introduce a dual-strategy to enhance the teacher model's training process, substantially improving the performance on few-shot learning. Secondly, we propose a calibration correction mechanism that that enables the student model to correct the teacher's calibration errors. Using our approach, we observed marked improvements over a state-of-the-art supervised baseline performance on the LVIS dataset, with an increase of 2.8% in average precision (AP) and 10.3% gain in AP for rare classes.
Authors: Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, Jeremie Mary, Andrew Comport, Val\'erie Gouet-Brunet
Abstract: We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory cost per scene. First, we learn a 3D-aware latent space in which we train Tri-Plane scene representations, hence reducing the resolution at which scenes are learned. Moreover, we present a way to share common information across scenes, hence allowing for a reduction of model complexity to learn a particular scene. Our method reduces effective per-scene memory costs by 44% and per-scene time costs by 86% when training 1000 scenes. Our project page can be found at https://3da-ae.github.io .
URLs: https://3da-ae.github.io
Authors: Yiming Ji, Yang Liu, Guanghu Xie, Boyu Ma, Zongwu Xie
Abstract: We propose NEDS-SLAM, an Explicit Dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we propose a Spatially Consistent Feature Fusion model to reduce the effect of erroneous estimates from pre-trained segmentation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping. Additionally, we employ a lightweight encoder-decoder to compress the high-dimensional semantic features into a compact 3D Gaussian representation, mitigating the burden of excessive memory consumption. Furthermore, we leverage the advantage of 3D Gaussian splatting, which enables efficient and differentiable novel view rendering, and propose a Virtual Camera View Pruning method to eliminate outlier GS points, thereby effectively enhancing the quality of scene representations. Our NEDS-SLAM method demonstrates competitive performance over existing dense semantic SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in 3D dense semantic mapping.
Authors: Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla
Abstract: Test-Time Training (TTT) proposes to adapt a pre-trained network to changing data distributions on-the-fly. In this work, we propose the first TTT method for 3D semantic segmentation, TTT-KD, which models Knowledge Distillation (KD) from foundation models (e.g. DINOv2) as a self-supervised objective for adaptation to distribution shifts at test-time. Given access to paired image-pointcloud (2D-3D) data, we first optimize a 3D segmentation backbone for the main task of semantic segmentation using the pointclouds and the task of 2D $\to$ 3D KD by using an off-the-shelf 2D pre-trained foundation model. At test-time, our TTT-KD updates the 3D segmentation backbone for each test sample, by using the self-supervised task of knowledge distillation, before performing the final prediction. Extensive evaluations on multiple indoor and outdoor 3D segmentation benchmarks show the utility of TTT-KD, as it improves performance for both in-distribution (ID) and out-of-distribution (ODO) test datasets. We achieve a gain of up to 13% mIoU (7% on average) when the train and test distributions are similar and up to 45% (20% on average) when adapting to OOD test samples.
Authors: Ali Asghar Sharifi, Ali Zoljodi, Masoud Daneshtalab
Abstract: Autonomous driving systems are a rapidly evolving technology that enables driverless car production. Trajectory prediction is a critical component of autonomous driving systems, enabling cars to anticipate the movements of surrounding objects for safe navigation. Trajectory prediction using Lidar point-cloud data performs better than 2D images due to providing 3D information. However, processing point-cloud data is more complicated and time-consuming than 2D images. Hence, state-of-the-art 3D trajectory predictions using point-cloud data suffer from slow and erroneous predictions. This paper introduces TrajectoryNAS, a pioneering method that focuses on utilizing point cloud data for trajectory prediction. By leveraging Neural Architecture Search (NAS), TrajectoryNAS automates the design of trajectory prediction models, encompassing object detection, tracking, and forecasting in a cohesive manner. This approach not only addresses the complex interdependencies among these tasks but also emphasizes the importance of accuracy and efficiency in trajectory modeling. Through empirical studies, TrajectoryNAS demonstrates its effectiveness in enhancing the performance of autonomous driving systems, marking a significant advancement in the field.Experimental results reveal that TrajcetoryNAS yield a minimum of 4.8 higger accuracy and 1.1* lower latency over competing methods on the NuScenes dataset.
Authors: Junge Zhang, Qihang Zhang, Li Zhang, Ramana Rao Kompella, Gaowen Liu, Bolei Zhou
Abstract: Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation. Urban scenes, unlike natural landscapes, consist of various complex man-made objects and structures such as roads, traffic signs, vehicles, and buildings. To create a realistic and detailed urban scene, it is crucial to accurately represent the geometry and semantics of the underlying objects, going beyond their visual appearance. In this work, we propose UrbanDiffusion, a 3D diffusion model that is conditioned on a Bird's-Eye View (BEV) map and generates an urban scene with geometry and semantics in the form of semantic occupancy map. Our model introduces a novel paradigm that learns the data distribution of scene-level structures within a latent space and further enables the expansion of the synthesized scene into an arbitrary scale. After training on real-world driving datasets, our model can generate a wide range of diverse urban scenes given the BEV maps from the held-out set and also generalize to the synthesized maps from a driving simulator. We further demonstrate its application to scene image synthesis with a pretrained image generator as a prior.
Authors: Ruyi Xu, Yuan Yao, Zonghao Guo, Junbo Cui, Zanlin Ni, Chunjiang Ge, Tat-Seng Chua, Zhiyuan Liu, Maosong Sun, Gao Huang
Abstract: Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in adaptivity, efficiency, and even correctness. In this work, we first take GPT-4V and LLaVA-1.5 as representative examples and expose systematic flaws rooted in their visual encoding strategy. To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution. LLaVA-UHD includes three key components: (1) An image modularization strategy that divides native-resolution images into smaller variable-sized slices for efficient and extensible encoding, (2) a compression module that further condenses image tokens from visual encoders, and (3) a spatial schema to organize slice tokens for LLMs. Comprehensive experiments show that LLaVA-UHD outperforms established LMMs trained with 2-3 orders of magnitude more data on 9 benchmarks. Notably, our model built on LLaVA-1.5 336x336 supports 6 times larger (i.e., 672x1088) resolution images using only 94% inference computation, and achieves 6.4 accuracy improvement on TextVQA. Moreover, the model can be efficiently trained in academic settings, within 23 hours on 8 A100 GPUs (vs. 26 hours of LLaVA-1.5). We make the data and code publicly available at https://github.com/thunlp/LLaVA-UHD.
Authors: Kaijie Ren, Lei Zhang
Abstract: Visible-Infrared Person Re-identification (VI-ReID) is a challenging cross-modal pedestrian retrieval task, due to significant intra-class variations and cross-modal discrepancies among different cameras. Existing works mainly focus on embedding images of different modalities into a unified space to mine modality-shared features. They only seek distinctive information within these shared features, while ignoring the identity-aware useful information that is implicit in the modality-specific features. To address this issue, we propose a novel Implicit Discriminative Knowledge Learning (IDKL) network to uncover and leverage the implicit discriminative information contained within the modality-specific. First, we extract modality-specific and modality-shared features using a novel dual-stream network. Then, the modality-specific features undergo purification to reduce their modality style discrepancies while preserving identity-aware discriminative knowledge. Subsequently, this kind of implicit knowledge is distilled into the modality-shared feature to enhance its distinctiveness. Finally, an alignment loss is proposed to minimize modality discrepancy on enhanced modality-shared features. Extensive experiments on multiple public datasets demonstrate the superiority of IDKL network over the state-of-the-art methods. Code is available at https://github.com/1KK077/IDKL.
Authors: Yuxuan Li, Xiang Li, Yimain Dai, Qibin Hou, Li Liu, Yongxiang Liu, Ming-Ming Cheng, Jian Yang
Abstract: Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios. Such prior knowledge can be useful because remote sensing objects may be mistakenly recognized without referencing a sufficiently long-range context, which can vary for different objects. This paper considers these priors and proposes a lightweight Large Selective Kernel Network (LSKNet) backbone. LSKNet can dynamically adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. To our knowledge, large and selective kernel mechanisms have not been previously explored in remote sensing images. Without bells and whistles, our lightweight LSKNet sets new state-of-the-art scores on standard remote sensing classification, object detection and semantic segmentation benchmarks. Our comprehensive analysis further validated the significance of the identified priors and the effectiveness of LSKNet. The code is available at https://github.com/zcablii/LSKNet.
Authors: Chuang Yu, Yunpeng Liu, Jinmiao Zhao, Dou Quan, Zelin Shi
Abstract: Recently, feature relation learning has drawn widespread attention in cross-spectral image patch matching. However, existing related research focuses on extracting diverse relations between image patch features and ignores sufficient intrinsic feature representations of individual image patches. Therefore, an innovative relational representation learning idea is proposed for the first time, which simultaneously focuses on sufficiently mining the intrinsic features of individual image patches and the relations between image patch features. Based on this, we construct a lightweight Relational Representation Learning Network (RRL-Net). Specifically, we innovatively construct an autoencoder to fully characterize the individual intrinsic features, and introduce a Feature Interaction Learning (FIL) module to extract deep-level feature relations. To further fully mine individual intrinsic features, a lightweight Multi-dimensional Global-to-Local Attention (MGLA) module is constructed to enhance the global feature extraction of individual image patches and capture local dependencies within global features. By combining the MGLA module, we further explore the feature extraction network and construct an Attention-based Lightweight Feature Extraction (ALFE) network. In addition, we propose a Multi-Loss Post-Pruning (MLPP) optimization strategy, which greatly promotes network optimization while avoiding increases in parameters and inference time. Extensive experiments demonstrate that our RRL-Net achieves state-of-the-art (SOTA) performance on multiple public datasets. Our code will be made public later.
Authors: M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Sivan Doveh, Jakub Micorek, Mateusz Kozinski, Hilde Kuhene, Horst Possegger
Abstract: Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language Models (VLMs). To obtain these category-specific prompts, the present methods rely on hand-crafting the prompts to the LLMs for generating VLM prompts for the downstream tasks. However, this requires manually composing these task-specific prompts and still, they might not cover the diverse set of visual concepts and task-specific styles associated with the categories of interest. To effectively take humans out of the loop and completely automate the prompt generation process for zero-shot recognition, we propose Meta-Prompting for Visual Recognition (MPVR). Taking as input only minimal information about the target task, in the form of its short natural language description, and a list of associated class labels, MPVR automatically produces a diverse set of category-specific prompts resulting in a strong zero-shot classifier. MPVR generalizes effectively across various popular zero-shot image recognition benchmarks belonging to widely different domains when tested with multiple LLMs and VLMs. For example, MPVR obtains a zero-shot recognition improvement over CLIP by up to 19.8% and 18.2% (5.0% and 4.5% on average over 20 datasets) leveraging GPT and Mixtral LLMs, respectively
Authors: Mitja Nikolaus, Milad Mozafari, Nicholas Asher, Leila Reddy, Rufin VanRullen
Abstract: Previous studies have shown that it is possible to map brain activation data of subjects viewing images onto the feature representation space of not only vision models (modality-specific decoding) but also language models (cross-modal decoding). In this work, we introduce and use a new large-scale fMRI dataset (~8,500 trials per subject) of people watching both images and text descriptions of such images. This novel dataset enables the development of modality-agnostic decoders: a single decoder that can predict which stimulus a subject is seeing, irrespective of the modality (image or text) in which the stimulus is presented. We train and evaluate such decoders to map brain signals onto stimulus representations from a large range of publicly available vision, language and multimodal (vision+language) models. Our findings reveal that (1) modality-agnostic decoders perform as well as (and sometimes even better than) modality-specific decoders (2) modality-agnostic decoders mapping brain data onto representations from unimodal models perform as well as decoders relying on multimodal representations (3) while language and low-level visual (occipital) brain regions are best at decoding text and image stimuli, respectively, high-level visual (temporal) regions perform well on both stimulus types.
Authors: Wenhua Wu, Guangming Wang, Ting Deng, Sebastian Aegidius, Stuart Shanks, Valerio Modugno, Dimitrios Kanoulas, Hesheng Wang
Abstract: Recent research on Simultaneous Localization and Mapping (SLAM) based on implicit representation has shown promising results in indoor environments. However, there are still some challenges: the limited scene representation capability of implicit encodings, the uncertainty in the rendering process from implicit representations, and the disruption of consistency by dynamic objects. To address these challenges, we propose a real-time dynamic visual SLAM system based on local-global fusion neural implicit representation, named DVN-SLAM. To improve the scene representation capability, we introduce a local-global fusion neural implicit representation that enables the construction of an implicit map while considering both global structure and local details. To tackle uncertainties arising from the rendering process, we design an information concentration loss for optimization, aiming to concentrate scene information on object surfaces. The proposed DVN-SLAM achieves competitive performance in localization and mapping across multiple datasets. More importantly, DVN-SLAM demonstrates robustness in dynamic scenes, a trait that sets it apart from other NeRF-based methods.
Authors: Yi Wu, Ziqiang Li, Heliang Zheng, Chaoyue Wang, Bin Li
Abstract: Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However, existing methods primarily integrate reference images within the text embedding space, leading to a complex entanglement of image and text information, which poses challenges for preserving both identity fidelity and semantic consistency. To tackle this challenge, we propose Infinite-ID, an ID-semantics decoupling paradigm for identity-preserved personalization. Specifically, we introduce identity-enhanced training, incorporating an additional image cross-attention module to capture sufficient ID information while deactivating the original text cross-attention module of the diffusion model. This ensures that the image stream faithfully represents the identity provided by the reference image while mitigating interference from textual input. Additionally, we introduce a feature interaction mechanism that combines a mixed attention module with an AdaIN-mean operation to seamlessly merge the two streams. This mechanism not only enhances the fidelity of identity and semantic consistency but also enables convenient control over the styles of the generated images. Extensive experimental results on both raw photo generation and style image generation demonstrate the superior performance of our proposed method.
Authors: Wenhua Wu, Qi Wang, Guangming Wang, Junping Wang, Tiankun Zhao, Yang Liu, Dongchao Gao, Zhe Liu, Hesheng Wang
Abstract: Road surface reconstruction plays a vital role in autonomous driving systems, enabling road lane perception and high-precision mapping. Recently, neural implicit encoding has achieved remarkable results in scene representation, particularly in the realistic rendering of scene textures. However, it faces challenges in directly representing geometric information for large-scale scenes. To address this, we propose EMIE-MAP, a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding. The road geometry is represented using explicit mesh, where each vertex stores implicit encoding representing the color and semantic information. To overcome the difficulty in optimizing road elevation, we introduce a trajectory-based elevation initialization and an elevation residual learning method based on Multi-Layer Perceptron (MLP). Additionally, by employing implicit encoding and multi-camera color MLPs decoding, we achieve separate modeling of scene physical properties and camera characteristics, allowing surround-view reconstruction compatible with different camera models. Our method achieves remarkable road surface reconstruction performance in a variety of real-world challenging scenarios.
Authors: Antonio Pepe, Richard Schussnig, Jianning Li, Christina Gsaxner, Dieter Schmalstieg, Jan Egger
Abstract: Shape reconstruction from imaging volumes is a recurring need in medical image analysis. Common workflows start with a segmentation step, followed by careful post-processing and,finally, ad hoc meshing algorithms. As this sequence can be timeconsuming, neural networks are trained to reconstruct shapes through template deformation. These networks deliver state-ofthe-art results without manual intervention, but, so far, they have primarily been evaluated on anatomical shapes with little topological variety between individuals. In contrast, other works favor learning implicit shape models, which have multiple benefits for meshing and visualization. Our work follows this direction by introducing deep medial voxels, a semi-implicit representation that faithfully approximates the topological skeleton from imaging volumes and eventually leads to shape reconstruction via convolution surfaces. Our reconstruction technique shows potential for both visualization and computer simulations.
Authors: Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao
Abstract: Domain generalization (DG) aims to enhance the model robustness against domain shifts without accessing target domains. A prevalent category of methods for DG is data augmentation, which focuses on generating virtual samples to simulate domain shifts. However, existing augmentation techniques in DG are mainly tailored for convolutional neural networks (CNNs), with limited exploration in token-based architectures, i.e., vision transformer (ViT) and multi-layer perceptrons (MLP) models. In this paper, we study the impact of prior CNN-based augmentation methods on token-based models, revealing their performance is suboptimal due to the lack of incentivizing the model to learn holistic shape information. To tackle the issue, we propose the SEmantic-aware Token Augmentation (SETA) method. SETA transforms token features by perturbing local edge cues while preserving global shape features, thereby enhancing the model learning of shape information. To further enhance the generalization ability of the model, we introduce two stylized variants of our method combined with two state-of-the-art style augmentation methods in DG. We provide a theoretical insight into our method, demonstrating its effectiveness in reducing the generalization risk bound. Comprehensive experiments on five benchmarks prove that our method achieves SOTA performances across various ViT and MLP architectures. Our code is available at https://github.com/lingeringlight/SETA.
Authors: Haochen Jiang, Yueming Xu, Yihan Zeng, Hang Xu, Wei Zhang, Jianfeng Feng, Li Zhang
Abstract: 3D reconstruction has been widely used in autonomous navigation fields of mobile robotics. However, the former research can only provide the basic geometry structure without the capability of open-world scene understanding, limiting advanced tasks like human interaction and visual navigation. Moreover, traditional 3D scene understanding approaches rely on expensive labeled 3D datasets to train a model for a single task with supervision. Thus, geometric reconstruction with zero-shot scene understanding i.e. Open vocabulary 3D Understanding and Reconstruction, is crucial for the future development of mobile robots. In this paper, we propose OpenOcc, a novel framework unifying the 3D scene reconstruction and open vocabulary understanding with neural radiance fields. We model the geometric structure of the scene with occupancy representation and distill the pre-trained open vocabulary model into a 3D language field via volume rendering for zero-shot inference. Furthermore, a novel semantic-aware confidence propagation (SCP) method has been proposed to relieve the issue of language field representation degeneracy caused by inconsistent measurements in distilled features. Experimental results show that our approach achieves competitive performance in 3D scene understanding tasks, especially for small and long-tail objects.
Authors: Qian Dai, Dong Wei, Hong Liu, Jinghan Sun, Liansheng Wang, Yefeng Zheng
Abstract: Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants' data. In addition, each participant would expect to obtain a personalized model tailored for its local data characteristics from the FL in such a scenario. In this work, we propose a new FL framework with federated modality-specific encoders and multimodal anchors (FedMEMA) to simultaneously address the two concurrent issues. Above all, FedMEMA employs an exclusive encoder for each modality to account for the inter-modal heterogeneity in the first place. In the meantime, while the encoders are shared by the participants, the decoders are personalized to meet individual needs. Specifically, a server with full-modal data employs a fusion decoder to aggregate and fuse representations from all modality-specific encoders, thus bridging the modalities to optimize the encoders via backpropagation reversely. Meanwhile, multiple anchors are extracted from the fused multimodal representations and distributed to the clients in addition to the encoder parameters. On the other end, the clients with incomplete modalities calibrate their missing-modal representations toward the global full-modal anchors via scaled dot-product cross-attention, making up the information loss due to absent modalities while adapting the representations of present ones. FedMEMA is validated on the BraTS 2020 benchmark for multimodal brain tumor segmentation. Results show that it outperforms various up-to-date methods for multimodal and personalized FL and that its novel designs are effective. Our code is available.
Authors: Wangbo Zhao, Jiasheng Tang, Yizeng Han, Yibing Song, Kai Wang, Gao Huang, Fan Wang, Yang You
Abstract: Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves comparable or even superior performance compared to existing PEFT methods while evoking only 71%-85% of their FLOPs on the VTAB-1K benchmark.
Authors: Yuqi Zhang, Guanying Chen, Jiaxing Chen, Shuguang Cui
Abstract: We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images by lifting noisy 2D labels to 3D. This is a challenging problem due to two primary reasons. Firstly, objects in urban aerial images exhibit substantial variations in size, including buildings, cars, and roads, which pose a significant challenge for accurate 2D segmentation. Secondly, the 2D labels generated by existing segmentation methods suffer from the multi-view inconsistency problem, especially in the case of aerial images, where each image captures only a small portion of the entire scene. To overcome these limitations, we first introduce a scale-adaptive semantic label fusion strategy that enhances the segmentation of objects of varying sizes by combining labels predicted from different altitudes, harnessing the novel-view synthesis capabilities of NeRF. We then introduce a novel cross-view instance label grouping strategy based on the 3D scene representation to mitigate the multi-view inconsistency problem in the 2D instance labels. Furthermore, we exploit multi-view reconstructed depth priors to improve the geometric quality of the reconstructed radiance field, resulting in enhanced segmentation results. Experiments on multiple real-world urban-scale datasets demonstrate that our approach outperforms existing methods, highlighting its effectiveness.
Authors: Sha Zhang, Jiajun Deng, Lei Bai, Houqiang Li, Wanli Ouyang, Yanyong Zhang
Abstract: We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised man- ner. By exploiting the geometric relationship between RGB cameras and LiDAR sensors, the correspondence between the two modalities based on both image- plane view and bird-eye view can be established, which facilitates representation learning. Specifically, the image-plane correspondences can be simply ob- tained by projecting the point clouds, while the bird- eye-view correspondences can be achieved by lifting pixels to the 3D space with the predicted depths un- der the supervision of projected point clouds. The image teacher networks provide rich semantics from the image-plane view and meanwhile acquire geometric information from the bird-eye view. Indeed, image features from the two views naturally comple- ment each other and together can ameliorate the learned feature representation of the point cloud stu- dent networks. Moreover, with a self-supervised pre- trained 2D network, HVDistill requires neither 2D nor 3D annotations. We pre-train our model on nuScenes dataset and transfer it to several downstream tasks on nuScenes, SemanticKITTI, and KITTI datasets for evaluation. Extensive experimental results show that our method achieves consistent improvements over the baseline trained from scratch and significantly out- performs the existing schemes. Codes are available at git@github.com:zhangsha1024/HVDistill.git.
Authors: Hui Lu, Albert Ali Salah, Ronald Poppe
Abstract: A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input. To address this challenge, we propose TCNet, a hybrid network that effectively models spatio-temporal information from Trajectories and Correlated regions. TCNet's trajectory module transforms frames into aligned trajectories composed of continuous visual tokens. In addition, for a query token, self-attention is learned along the trajectory. As such, our network can also focus on fine-grained spatio-temporal patterns, such as finger movements, of a specific region in motion. TCNet's correlation module uses a novel dynamic attention mechanism that filters out irrelevant frame regions. Additionally, it assigns dynamic key-value tokens from correlated regions to each query. Both innovations significantly reduce the computation cost and memory. We perform experiments on four large-scale datasets: PHOENIX14, PHOENIX14-T, CSL, and CSL-Daily, respectively. Our results demonstrate that TCNet consistently achieves state-of-the-art performance. For example, we improve over the previous state-of-the-art by 1.5% and 1.0% word error rate on PHOENIX14 and PHOENIX14-T, respectively.
Authors: Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam, Timo Ropinski
Abstract: Recent advances in text-to-image synthesis have been enabled by exploiting a combination of language and vision through foundation models. These models are pre-trained on tremendous amounts of text-image pairs sourced from the World Wide Web or other large-scale databases. As the demand for high-quality image generation shifts towards ensuring content alignment between text and image, novel evaluation metrics have been developed with the aim of mimicking human judgments. Thus, researchers have started to collect datasets with increasingly complex annotations to study the compositionality of vision-language models and their incorporation as a quality measure of compositional alignment between text and image contents. In this work, we provide a comprehensive overview of existing text-to-image evaluation metrics and propose a new taxonomy for categorizing these metrics. We also review frequently adopted text-image benchmark datasets before discussing techniques to optimize text-to-image synthesis models towards quality and human preferences. Ultimately, we derive guidelines for improving text-to-image evaluation and discuss the open challenges and current limitations.
Authors: Lingzhe Zhao, Peng Wang, Peidong Liu
Abstract: While neural rendering has demonstrated impressive capabilities in 3D scene reconstruction and novel view synthesis, it heavily relies on high-quality sharp images and accurate camera poses. Numerous approaches have been proposed to train Neural Radiance Fields (NeRF) with motion-blurred images, commonly encountered in real-world scenarios such as low-light or long-exposure conditions. However, the implicit representation of NeRF struggles to accurately recover intricate details from severely motion-blurred images and cannot achieve real-time rendering. In contrast, recent advancements in 3D Gaussian Splatting achieve high-quality 3D scene reconstruction and real-time rendering by explicitly optimizing point clouds as Gaussian spheres. In this paper, we introduce a novel approach, named BAD-Gaussians (Bundle Adjusted Deblur Gaussian Splatting), which leverages explicit Gaussian representation and handles severe motion-blurred images with inaccurate camera poses to achieve high-quality scene reconstruction. Our method models the physical image formation process of motion-blurred images and jointly learns the parameters of Gaussians while recovering camera motion trajectories during exposure time. In our experiments, we demonstrate that BAD-Gaussians not only achieves superior rendering quality compared to previous state-of-the-art deblur neural rendering methods on both synthetic and real datasets but also enables real-time rendering capabilities.
Authors: Sha Zhang, Di Huang, Jiajun Deng, Shixiang Tang, Wanli Ouyang, Tong He, Yanyong Zhang
Abstract: The ability to understand and reason the 3D real world is a crucial milestone towards artificial general intelligence. The current common practice is to finetune Large Language Models (LLMs) with 3D data and texts to enable 3D understanding. Despite their effectiveness, these approaches are inherently limited by the scale and diversity of the available 3D data. Alternatively, in this work, we introduce Agent3D-Zero, an innovative 3D-aware agent framework addressing the 3D scene understanding in a zero-shot manner. The essence of our approach centers on reconceptualizing the challenge of 3D scene perception as a process of understanding and synthesizing insights from multiple images, inspired by how our human beings attempt to understand 3D scenes. By consolidating this idea, we propose a novel way to make use of a Large Visual Language Model (VLM) via actively selecting and analyzing a series of viewpoints for 3D understanding. Specifically, given an input 3D scene, Agent3D-Zero first processes a bird's-eye view image with custom-designed visual prompts, then iteratively chooses the next viewpoints to observe and summarize the underlying knowledge. A distinctive advantage of Agent3D-Zero is the introduction of novel visual prompts, which significantly unleash the VLMs' ability to identify the most informative viewpoints and thus facilitate observing 3D scenes. Extensive experiments demonstrate the effectiveness of the proposed framework in understanding diverse and previously unseen 3D environments.
Authors: Ziying Song, Lei Yang, Shaoqing Xu, Lin Liu, Dongyang Xu, Caiyan Jia, Feiyang Jia, Li Wang
Abstract: Integrating LiDAR and camera information into Bird's-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing methods are susceptible to the inaccurate calibration relationship between LiDAR and the camera sensor. Such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a robust fusion framework called Graph BEV. Addressing errors caused by inaccurate point cloud projection, we introduce a Local Align module that employs neighbor-aware depth features via Graph matching. Additionally, we propose a Global Align module to rectify the misalignment between LiDAR and camera BEV features. Our Graph BEV framework achieves state-of-the-art performance, with an mAP of 70.1\%, surpassing BEV Fusion by 1.6\% on the nuscenes validation set. Importantly, our Graph BEV outperforms BEV Fusion by 8.3\% under conditions with misalignment noise.
Authors: Mert \"Ozer, Maximilian Weiherer, Martin Hundhausen, Bernhard Egger
Abstract: Neural Radiance Fields (NeRFs) quickly evolved as the new de-facto standard for the task of novel view synthesis when trained on a set of RGB images. In this paper, we conduct a comprehensive evaluation of neural scene representations, such as NeRFs, in the context of multi-modal learning. Specifically, we present four different strategies of how to incorporate a second modality, other than RGB, into NeRFs: (1) training from scratch independently on both modalities; (2) pre-training on RGB and fine-tuning on the second modality; (3) adding a second branch; and (4) adding a separate component to predict (color) values of the additional modality. We chose thermal imaging as second modality since it strongly differs from RGB in terms of radiosity, making it challenging to integrate into neural scene representations. For the evaluation of the proposed strategies, we captured a new publicly available multi-view dataset, ThermalMix, consisting of six common objects and about 360 RGB and thermal images in total. We employ cross-modality calibration prior to data capturing, leading to high-quality alignments between RGB and thermal images. Our findings reveal that adding a second branch to NeRF performs best for novel view synthesis on thermal images while also yielding compelling results on RGB. Finally, we also show that our analysis generalizes to other modalities, including near-infrared images and depth maps. Project page: https://mert-o.github.io/ThermalNeRF/.
Authors: Meilin Wang, Yexing Song, Pengxu Wei, Xiaoyu Xian, Yukai Shi, Liang Lin
Abstract: Deep learning technologies have demonstrated their effectiveness in removing cloud cover from optical remote-sensing images. Convolutional Neural Networks (CNNs) exert dominance in the cloud removal tasks. However, constrained by the inherent limitations of convolutional operations, CNNs can address only a modest fraction of cloud occlusion. In recent years, diffusion models have achieved state-of-the-art (SOTA) proficiency in image generation and reconstruction due to their formidable generative capabilities. Inspired by the rapid development of diffusion models, we first present an iterative diffusion process for cloud removal (IDF-CR), which exhibits a strong generative capabilities to achieve component divide-and-conquer cloud removal. IDF-CR consists of a pixel space cloud removal module (Pixel-CR) and a latent space iterative noise diffusion network (IND). Specifically, IDF-CR is divided into two-stage models that address pixel space and latent space. The two-stage model facilitates a strategic transition from preliminary cloud reduction to meticulous detail refinement. In the pixel space stage, Pixel-CR initiates the processing of cloudy images, yielding a suboptimal cloud removal prior to providing the diffusion model with prior cloud removal knowledge. In the latent space stage, the diffusion model transforms low-quality cloud removal into high-quality clean output. We refine the Stable Diffusion by implementing ControlNet. In addition, an unsupervised iterative noise refinement (INR) module is introduced for diffusion model to optimize the distribution of the predicted noise, thereby enhancing advanced detail recovery. Our model performs best with other SOTA methods, including image reconstruction and optical remote-sensing cloud removal on the optical remote-sensing datasets.
Authors: Jakub Mandula, Jonas K\"uhne, Luca Pascarella, Michele Magno
Abstract: Unmanned Aerial Vehicles (UAVs) are gaining popularity in civil and military applications. However, uncontrolled access to restricted areas threatens privacy and security. Thus, prevention and detection of UAVs are pivotal to guarantee confidentiality and safety. Although active scanning, mainly based on radars, is one of the most accurate technologies, it can be expensive and less versatile than passive inspections, e.g., object recognition. Dynamic vision sensors (DVS) are bio-inspired event-based vision models that leverage timestamped pixel-level brightness changes in fast-moving scenes that adapt well to low-latency object detection. This paper presents F-UAV-D (Fast Unmanned Aerial Vehicle Detector), an embedded system that enables fast-moving drone detection. In particular, we propose a setup to exploit DVS as an alternative to RGB cameras in a real-time and low-power configuration. Our approach leverages the high-dynamic range (HDR) and background suppression of DVS and, when trained with various fast-moving drones, outperforms RGB input in suboptimal ambient conditions such as low illumination and fast-moving scenes. Our results show that F-UAV-D can (i) detect drones by using less than <15 W on average and (ii) perform real-time inference (i.e., <50 ms) by leveraging the CPU and GPU nodes of our edge computer.
Authors: Jiaxiang Tang, Ruijie Lu, Xiaokang Chen, Xiang Wen, Gang Zeng, Ziwei Liu
Abstract: Text-to-texture synthesis has become a new frontier in 3D content creation thanks to the recent advances in text-to-image models. Existing methods primarily adopt a combination of pretrained depth-aware diffusion and inpainting models, yet they exhibit shortcomings such as 3D inconsistency and limited controllability. To address these challenges, we introduce InteX, a novel framework for interactive text-to-texture synthesis. 1) InteX includes a user-friendly interface that facilitates interaction and control throughout the synthesis process, enabling region-specific repainting and precise texture editing. 2) Additionally, we develop a unified depth-aware inpainting model that integrates depth information with inpainting cues, effectively mitigating 3D inconsistencies and improving generation speed. Through extensive experiments, our framework has proven to be both practical and effective in text-to-texture synthesis, paving the way for high-quality 3D content creation.
Authors: Liang Xu, Yizhou Zhou, Yichao Yan, Xin Jin, Wenhan Zhu, Fengyun Rao, Xiaokang Yang, Wenjun Zeng
Abstract: Humans constantly interact with their surrounding environments. Current human-centric generative models mainly focus on synthesizing humans plausibly interacting with static scenes and objects, while the dynamic human action-reaction synthesis for ubiquitous causal human-human interactions is less explored. Human-human interactions can be regarded as asymmetric with actors and reactors in atomic interaction periods. In this paper, we comprehensively analyze the asymmetric, dynamic, synchronous, and detailed nature of human-human interactions and propose the first multi-setting human action-reaction synthesis benchmark to generate human reactions conditioned on given human actions. To begin with, we propose to annotate the actor-reactor order of the interaction sequences for the NTU120, InterHuman, and Chi3D datasets. Based on them, a diffusion-based generative model with a Transformer decoder architecture called ReGenNet together with an explicit distance-based interaction loss is proposed to predict human reactions in an online manner, where the future states of actors are unavailable to reactors. Quantitative and qualitative results show that our method can generate instant and plausible human reactions compared to the baselines, and can generalize to unseen actor motions and viewpoint changes.
Authors: Xiangyu Chen (Perry), Jing Liu (Perry), Ye Wang (Perry), Pu (Perry), Wang, Matthew Brand, Guanghui Wang, Toshiaki Koike-Akino
Abstract: Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision. This paper proposes a generalized framework called SuperLoRA that unifies and extends different LoRA variants, which can be realized under different hyper-parameter settings. Introducing grouping, folding, shuffling, projecting, and tensor factoring, SuperLoRA offers high flexibility compared with other LoRA variants and demonstrates superior performance for transfer learning tasks especially in the extremely few-parameter regimes.
Authors: LI Yang, WU Ruizheng, LI Jiyong, CHEN Ying-cong
Abstract: Learning surfaces from neural radiance field (NeRF) became a rising topic in Multi-View Stereo (MVS). Recent Signed Distance Function (SDF)-based methods demonstrated their ability to reconstruct accurate 3D shapes of Lambertian scenes. However, their results on reflective scenes are unsatisfactory due to the entanglement of specular radiance and complicated geometry. To address the challenges, we propose a Gaussian-based representation of normals in SDF fields. Supervised by polarization priors, this representation guides the learning of geometry behind the specular reflection and captures more details than existing methods. Moreover, we propose a reweighting strategy in the optimization process to alleviate the noise issue of polarization priors. To validate the effectiveness of our design, we capture polarimetric information, and ground truth meshes in additional reflective scenes with various geometry. We also evaluated our framework on the PANDORA dataset. Comparisons prove our method outperforms existing neural 3D reconstruction methods in reflective scenes by a large margin.
Authors: Sibi Catley-Chandar, Richard Shaw, Gregory Slabaugh, Eduardo Perez-Pellitero
Abstract: Recent advances in neural rendering have enabled highly photorealistic 3D scene reconstruction and novel view synthesis. Despite this progress, current state-of-the-art methods struggle to reconstruct high frequency detail, due to factors such as a low-frequency bias of radiance fields and inaccurate camera calibration. One approach to mitigate this issue is to enhance images post-rendering. 2D enhancers can be pre-trained to recover some detail but are agnostic to scene geometry and do not easily generalize to new distributions of image degradation. Conversely, existing 3D enhancers are able to transfer detail from nearby training images in a generalizable manner, but suffer from inaccurate camera calibration and can propagate errors from the geometry into rendered images. We propose a neural rendering enhancer, RoGUENeRF, which exploits the best of both paradigms. Our method is pre-trained to learn a general enhancer while also leveraging information from nearby training images via robust 3D alignment and geometry-aware fusion. Our approach restores high-frequency textures while maintaining geometric consistency and is also robust to inaccurate camera calibration. We show that RoGUENeRF substantially enhances the rendering quality of a wide range of neural rendering baselines, e.g. improving the PSNR of MipNeRF360 by 0.63dB and Nerfacto by 1.34dB on the real world 360v2 dataset.
Authors: Runhui Huang, Kaixin Cai, Jianhua Han, Xiaodan Liang, Renjing Pei, Guansong Lu, Songcen Xu, Wei Zhang, Hang Xu
Abstract: Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital artistry, images are frequently created and manipulated in multiple layers to offer greater flexibility and control. Therefore in this paper, we propose a layer-collaborative diffusion model, named LayerDiff, specifically designed for text-guided, multi-layered, composable image synthesis. The composable image consists of a background layer, a set of foreground layers, and associated mask layers for each foreground element. To enable this, LayerDiff introduces a layer-based generation paradigm incorporating multiple layer-collaborative attention modules to capture inter-layer patterns. Specifically, an inter-layer attention module is designed to encourage information exchange and learning between layers, while a text-guided intra-layer attention module incorporates layer-specific prompts to direct the specific-content generation for each layer. A layer-specific prompt-enhanced module better captures detailed textual cues from the global prompt. Additionally, a self-mask guidance sampling strategy further unleashes the model's ability to generate multi-layered images. We also present a pipeline that integrates existing perceptual and generative models to produce a large dataset of high-quality, text-prompted, multi-layered images. Extensive experiments demonstrate that our LayerDiff model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. Moreover, LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.
Authors: M. Kerem Aydin, Qi Guo, Emma Alexander
Abstract: Hyperspectral cameras face challenging spatial-spectral resolution trade-offs and are more affected by shot noise than RGB photos taken over the same total exposure time. Here, we present a colorization algorithm to reconstruct hyperspectral images from a grayscale guide image and spatially sparse spectral clues. We demonstrate that our algorithm generalizes to varying spectral dimensions for hyperspectral images, and show that colorizing in a low-rank space reduces compute time and the impact of shot noise. To enhance robustness, we incorporate guided sampling, edge-aware filtering, and dimensionality estimation techniques. Our method surpasses previous algorithms in various performance metrics, including SSIM, PSNR, GFC, and EMD, which we analyze as metrics for characterizing hyperspectral image quality. Collectively, these findings provide a promising avenue for overcoming the time-space-wavelength resolution trade-off by reconstructing a dense hyperspectral image from samples obtained by whisk or push broom scanners, as well as hybrid spatial-spectral computational imaging systems.
Authors: Jun Yu, Zhihong Wei, Zhongpeng Cai
Abstract: Facial Expression Recognition (FER) plays a crucial role in computer vision and finds extensive applications across various fields. This paper aims to present our approach for the upcoming 6th Affective Behavior Analysis in-the-Wild (ABAW) competition, scheduled to be held at CVPR2024.. In the facial expression recognition task, The limited size of the FER dataset poses a challenge to the expression recognition model's generalization ability, resulting in subpar recognition performance. To address this problem, we employ a semi-supervised learning technique to generate expression category pseudo-labels for unlabeled face data. At the same time, we uniformly sampled the labeled facial expression samples and implemented a debiased feedback learning strategy to address the problem of category imbalance in the dataset and the possible data bias in semi-supervised learning. Moreover, , to further compensate for the limitation and bias of features obtained only from static images, we introduced a Temporal Encoder to learn and capture temporal relationships between neighboring expression image features. In the 6th ABAW competition, our method achieved outstanding results on the official validation set, a result that fully confirms the effectiveness and competitiveness of our proposed method.
Authors: Tengchuan Kou, Xiaohong Liu, Zicheng Zhang, Chunyi Li, Haoning Wu, Xiongkuo Min, Guangtao Zhai, Ning Liu
Abstract: With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V models have been released for generating high perceptual quality videos, there is still lack of a method to evaluate the quality of these videos quantitatively. To solve this issue, we establish the largest-scale Text-to-Video Quality Assessment DataBase (T2VQA-DB) to date. The dataset is composed of 10,000 videos generated by 9 different T2V models. We also conduct a subjective study to obtain each video's corresponding mean opinion score. Based on T2VQA-DB, we propose a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA). The model extracts features from text-video alignment and video fidelity perspectives, then it leverages the ability of a large language model to give the prediction score. Experimental results show that T2VQA outperforms existing T2V metrics and SOTA video quality assessment models. Quantitative analysis indicates that T2VQA is capable of giving subjective-align predictions, validating its effectiveness. The dataset and code will be released at https://github.com/QMME/T2VQA.
Authors: Hang Wang, Zhi-Qi Cheng, Youtian Du, Lei Zhang
Abstract: Video Action Counting (VAC) is crucial in analyzing sports, fitness, and everyday activities by quantifying repetitive actions in videos. However, traditional VAC methods have overlooked the complexity of action repetitions, such as interruptions and the variability in cycle duration. Our research addresses the shortfall by introducing a novel approach to VAC, called Irregular Video Action Counting (IVAC). IVAC prioritizes modeling irregular repetition patterns in videos, which we define through two primary aspects: Inter-cycle Consistency and Cycle-interval Inconsistency. Inter-cycle Consistency ensures homogeneity in the spatial-temporal representations of cycle segments, signifying action uniformity within cycles. Cycle-interval inconsistency highlights the importance of distinguishing between cycle segments and intervals based on their inherent content differences. To encapsulate these principles, we propose a new methodology that includes consistency and inconsistency modules, supported by a unique pull-push loss (P2L) mechanism. The IVAC-P2L model applies a pull loss to promote coherence among cycle segment features and a push loss to clearly distinguish features of cycle segments from interval segments. Empirical evaluations conducted on the RepCount dataset demonstrate that the IVAC-P2L model sets a new benchmark in VAC task performance. Furthermore, the model demonstrates exceptional adaptability and generalization across various video contents, outperforming existing models on two additional datasets, UCFRep and Countix, without the need for dataset-specific optimization. These results confirm the efficacy of our approach in addressing irregular repetitions in videos and pave the way for further advancements in video analysis and understanding.
Authors: Siying Liu, Pier Luigi Dragotti
Abstract: Deep neural networks for event-based video reconstruction often suffer from a lack of interpretability and have high memory demands. A lightweight network called CISTA-LSTC has recently been introduced showing that high-quality reconstruction can be achieved through the systematic design of its architecture. However, its modelling assumption that input signals and output reconstructed frame share the same sparse representation neglects the displacement caused by motion. To address this, we propose warping the input intensity frames and sparse codes to enhance reconstruction quality. A CISTA-Flow network is constructed by integrating a flow network with CISTA-LSTC for motion compensation. The system relies solely on events, in which predicted flow aids in reconstruction and then reconstructed frames are used to facilitate flow estimation. We also introduce an iterative training framework for this combined system. Results demonstrate that our approach achieves state-of-the-art reconstruction accuracy and simultaneously provides reliable dense flow estimation. Furthermore, our model exhibits flexibility in that it can integrate different flow networks, suggesting its potential for further performance enhancement.
Authors: Jan Krej\v{c}\'i, Oliver Kost, Ond\v{r}ej Straka, Jind\v{r}ich Dun\'ik
Abstract: A first-principle single-object model is proposed for pedestrian tracking. It is assumed that the extent of the moving object can be described via known statistics in 3D, such as pedestrian height. The proposed model thus need not constrain the object motion in 3D to a common ground plane, which is usual in 3D visual tracking applications. A nonlinear filter for this model is implemented using the unscented Kalman filter (UKF) and tested using the publicly available MOT-17 dataset. The proposed solution yields promising results in 3D while maintaining perfect results when projected into the 2D image. Moreover, the estimation error covariance matches the true one. Unlike conventional methods, the introduced model parameters have convenient meaning and can readily be adjusted for a problem.
Authors: Zhaoyang Lyu, Ben Fei, Jinyi Wang, Xudong Xu, Ya Zhang, Weidong Yang, Bo Dai
Abstract: Mesh is a fundamental representation of 3D assets in various industrial applications, and is widely supported by professional softwares. However, due to its irregular structure, mesh creation and manipulation is often time-consuming and labor-intensive. In this paper, we propose a highly controllable generative model, GetMesh, for mesh generation and manipulation across different categories. By taking a varying number of points as the latent representation, and re-organizing them as triplane representation, GetMesh generates meshes with rich and sharp details, outperforming both single-category and multi-category counterparts. Moreover, it also enables fine-grained control over the generation process that previous mesh generative models cannot achieve, where changing global/local mesh topologies, adding/removing mesh parts, and combining mesh parts across categories can be intuitively, efficiently, and robustly accomplished by adjusting the number, positions or features of latent points. Project page is https://getmesh.github.io.
Authors: Ting Yao, Yehao Li, Yingwei Pan, Tao Mei
Abstract: The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two parallel CNN branches in a cost-efficient manner. One high-resolution branch directly takes primary high-resolution features as inputs, but uses less convolution operations. The other low-resolution branch first performs down-sampling and then utilizes more convolution operations over such low-resolution features. Experiments on both recognition task (ImageNet-1K dataset) and dense prediction tasks (COCO and ADE20K datasets) demonstrate the superiority of HIRI-ViT. More remarkably, under comparable computational cost ($\sim$5.0 GFLOPs), HIRI-ViT achieves to-date the best published Top-1 accuracy of 84.3% on ImageNet with 448$\times$448 inputs, which absolutely improves 83.4% of iFormer-S by 0.9% with 224$\times$224 inputs.
Authors: Hyeonho Jeong, Jinho Chang, Geon Yeong Park, Jong Chul Ye
Abstract: Text-driven diffusion-based video editing presents a unique challenge not encountered in image editing literature: establishing real-world motion. Unlike existing video editing approaches, here we focus on score distillation sampling to circumvent the standard reverse diffusion process and initiate optimization from videos that already exhibit natural motion. Our analysis reveals that while video score distillation can effectively introduce new content indicated by target text, it can also cause significant structure and motion deviation. To counteract this, we propose to match space-time self-similarities of the original video and the edited video during the score distillation. Thanks to the use of score distillation, our approach is model-agnostic, which can be applied for both cascaded and non-cascaded video diffusion frameworks. Through extensive comparisons with leading methods, our approach demonstrates its superiority in altering appearances while accurately preserving the original structure and motion.
Authors: Xiaojie Li, Yibo Yang, Xiangtai Li, Jianlong Wu, Yue Yu, Bernard Ghanem, Min Zhang
Abstract: Self-supervised learning has achieved remarkable success in acquiring high-quality representations from unlabeled data. The widely adopted contrastive learning framework aims to learn invariant representations by minimizing the distance between positive views originating from the same image. However, existing techniques to construct positive views highly rely on manual transformations, resulting in limited diversity and potentially false positive pairs. To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics. We develop an adaptive view generation method that dynamically adjusts the noise level in sampling to ensure the preservation of essential semantic meaning while introducing variability. Additionally, we introduce a quality-driven contrastive loss, which assesses the quality of positive pairs by considering both foreground similarity and background diversity. This loss prioritizes the high-quality positive pairs we construct while reducing the influence of low-quality pairs, thereby mitigating potential semantic inconsistencies introduced by generative models and aggressive data augmentation. Thanks to the improved positive view quality and the quality-driven contrastive loss, GenView significantly improves self-supervised learning across various tasks. For instance, GenView improves MoCov2 performance by 2.5%/2.2% on ImageNet linear/semi-supervised classification. Moreover, GenView even performs much better than naively augmenting the ImageNet dataset with Laion400M or ImageNet21K. Code is available at https://github.com/xiaojieli0903/genview.
Authors: Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani
Abstract: We present Stable Video 3D (SV3D) -- a latent video diffusion model for high-resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent work on 3D generation propose techniques to adapt 2D generative models for novel view synthesis (NVS) and 3D optimization. However, these methods have several disadvantages due to either limited views or inconsistent NVS, thereby affecting the performance of 3D object generation. In this work, we propose SV3D that adapts image-to-video diffusion model for novel multi-view synthesis and 3D generation, thereby leveraging the generalization and multi-view consistency of the video models, while further adding explicit camera control for NVS. We also propose improved 3D optimization techniques to use SV3D and its NVS outputs for image-to-3D generation. Extensive experimental results on multiple datasets with 2D and 3D metrics as well as user study demonstrate SV3D's state-of-the-art performance on NVS as well as 3D reconstruction compared to prior works.
Authors: K. P. Santoso, R. V. H. Ginardi, R. A. Sastrowardoyo, F. A. Madany
Abstract: In the realm of skin lesion image classification, the intricate spatial and semantic features pose significant challenges for conventional Convolutional Neural Network (CNN)-based methodologies. These challenges are compounded by the imbalanced nature of skin lesion datasets, which hampers the ability of models to learn minority class features effectively. Despite augmentation strategies, such as those using Generative Adversarial Networks (GANs), previous attempts have not fully addressed these complexities. This study introduces an innovative approach by integrating Graph Neural Networks (GNNs) with Capsule Networks to enhance classification performance. GNNs, known for their proficiency in handling graph-structured data, offer an advanced mechanism for capturing complex patterns and relationships beyond the capabilities of traditional CNNs. Capsule Networks further contribute by providing superior recognition of spatial hierarchies within images. Our research focuses on evaluating and enhancing the Tiny Pyramid Vision GNN (Tiny Pyramid ViG) architecture by incorporating it with a Capsule Network. This hybrid model was applied to the MNIST:HAM10000 dataset, a comprehensive skin lesion dataset designed for benchmarking classification models. After 75 epochs of training, our model achieved a significant accuracy improvement, reaching 89.23% and 95.52%, surpassing established benchmarks such as GoogLeNet (83.94%), InceptionV3 (86.82%), MobileNet V3 (89.87%), EfficientNet-7B (92.07%), ResNet18 (92.22%), ResNet34 (91.90%), ViT-Base (73.70%), and IRv2-SA (93.47%) on the same dataset. This outcome underscores the potential of our approach in overcoming the inherent challenges of skin lesion classification, contributing to the advancement of image-based diagnosis in dermatology.
Authors: Qi Zuo, Xiaodong Gu, Lingteng Qiu, Yuan Dong, Zhengyi Zhao, Weihao Yuan, Rui Peng, Siyu Zhu, Zilong Dong, Liefeng Bo, Qixing Huang
Abstract: Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper introduces a novel framework that makes fundamental contributions to both questions. Unlike leveraging images from 2D diffusion models for training, we propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Images from video generative models are more suitable for multi-view generation because the underlying network architecture that generates them employs a temporal module to enforce frame consistency. Moreover, the video data sets used to train these models are abundant and diverse, leading to a reduced train-finetuning domain gap. To enhance multi-view consistency, we introduce a 3D-Aware Denoising Sampling, which first employs a feed-forward reconstruction module to get an explicit global 3D model, and then adopts a sampling strategy that effectively involves images rendered from the global 3D model into the denoising sampling loop to improve the multi-view consistency of the final images. As a by-product, this module also provides a fast way to create 3D assets represented by 3D Gaussians within a few seconds. Our approach can generate 24 dense views and converges much faster in training than state-of-the-art approaches (4 GPU hours versus many thousand GPU hours) with comparable visual quality and consistency. By further fine-tuning, our approach outperforms existing state-of-the-art methods in both quantitative metrics and visual effects. Our project page is aigc3d.github.io/VideoMV.
Authors: Mengqi Zhang, Yang Fu, Zheng Ding, Sifei Liu, Zhuowen Tu, Xiaolong Wang
Abstract: 3D hand-object interaction data is scarce due to the hardware constraints in scaling up the data collection process. In this paper, we propose HOIDiffusion for generating realistic and diverse 3D hand-object interaction data. Our model is a conditional diffusion model that takes both the 3D hand-object geometric structure and text description as inputs for image synthesis. This offers a more controllable and realistic synthesis as we can specify the structure and style inputs in a disentangled manner. HOIDiffusion is trained by leveraging a diffusion model pre-trained on large-scale natural images and a few 3D human demonstrations. Beyond controllable image synthesis, we adopt the generated 3D data for learning 6D object pose estimation and show its effectiveness in improving perception systems. Project page: https://mq-zhang1.github.io/HOIDiffusion
Authors: Xiao Fu, Wei Yin, Mu Hu, Kaixuan Wang, Yuexin Ma, Ping Tan, Shaojie Shen, Dahua Lin, Xiaoxiao Long
Abstract: We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes, e.g., depth and normals, from single images. While significant research has already been conducted in this area, the progress has been substantially limited by the low diversity and poor quality of publicly available datasets. As a result, the prior works either are constrained to limited scenarios or suffer from the inability to capture geometric details. In this paper, we demonstrate that generative models, as opposed to traditional discriminative models (e.g., CNNs and Transformers), can effectively address the inherently ill-posed problem. We further show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. Specifically, we extend the original stable diffusion model to jointly predict depth and normal, allowing mutual information exchange and high consistency between the two representations. More importantly, we propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions. This strategy enables our model to recognize different scene layouts, capturing 3D geometry with remarkable fidelity. GeoWizard sets new benchmarks for zero-shot depth and normal prediction, significantly enhancing many downstream applications such as 3D reconstruction, 2D content creation, and novel viewpoint synthesis.
Authors: Axel Sauer, Frederic Boesel, Tim Dockhorn, Andreas Blattmann, Patrick Esser, Robin Rombach
Abstract: Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from many-shot to single-step inference, albeit at the cost of expensive and difficult optimization due to its reliance on a fixed pretrained DINOv2 discriminator. We introduce Latent Adversarial Diffusion Distillation (LADD), a novel distillation approach overcoming the limitations of ADD. In contrast to pixel-based ADD, LADD utilizes generative features from pretrained latent diffusion models. This approach simplifies training and enhances performance, enabling high-resolution multi-aspect ratio image synthesis. We apply LADD to Stable Diffusion 3 (8B) to obtain SD3-Turbo, a fast model that matches the performance of state-of-the-art text-to-image generators using only four unguided sampling steps. Moreover, we systematically investigate its scaling behavior and demonstrate LADD's effectiveness in various applications such as image editing and inpainting.
Authors: Yushi Lan, Fangzhou Hong, Shuai Yang, Shangchen Zhou, Xuyi Meng, Bo Dai, Xingang Pan, Chen Change Loy
Abstract: The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled. This paper introduces a novel framework called LN3Diff to address this gap and enable fast, high-quality, and generic conditional 3D generation. Our approach harnesses a 3D-aware architecture and variational autoencoder (VAE) to encode the input image into a structured, compact, and 3D latent space. The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field. Through training a diffusion model on this 3D-aware latent space, our method achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation across various datasets. Moreover, it surpasses existing 3D diffusion methods in terms of inference speed, requiring no per-instance optimization. Our proposed LN3Diff presents a significant advancement in 3D generative modeling and holds promise for various applications in 3D vision and graphics tasks.
Authors: Debidatta Dwibedi, Vidhi Jain, Jonathan Tompson, Andrew Zisserman, Yusuf Aytar
Abstract: We introduce a versatile $\textit{flexible-captioning}$ vision-language model (VLM) capable of generating region-specific descriptions of varying lengths. The model, FlexCap, is trained to produce length-conditioned captions for input bounding boxes, and this allows control over the information density of its output, with descriptions ranging from concise object labels to detailed captions. To achieve this we create large-scale training datasets of image region descriptions of varying length, starting from captioned images. This flexible-captioning capability has several valuable applications. First, FlexCap demonstrates superior performance in dense captioning tasks on the Visual Genome dataset. Second, a visual question answering (VQA) system can be built by employing FlexCap to generate localized descriptions as inputs to a large language model. The resulting system achieves state-of-the-art zero-shot performance on a number of VQA datasets. We also demonstrate a $\textit{localize-then-describe}$ approach with FlexCap can be better at open-ended object detection than a $\textit{describe-then-localize}$ approach with other VLMs. We highlight a novel characteristic of FlexCap, which is its ability to extract diverse visual information through prefix conditioning. Finally, we qualitatively demonstrate FlexCap's broad applicability in tasks such as image labeling, object attribute recognition, and visual dialog. Project webpage: https://flex-cap.github.io .
Authors: Mingjin Chen, Junhao Chen, Xiaojun Ye, Huan-ang Gao, Xiaoxue Chen, Zhaoxin Fan, Hao Zhao
Abstract: 3D human body reconstruction has been a challenge in the field of computer vision. Previous methods are often time-consuming and difficult to capture the detailed appearance of the human body. In this paper, we propose a new method called \emph{Ultraman} for fast reconstruction of textured 3D human models from a single image. Compared to existing techniques, \emph{Ultraman} greatly improves the reconstruction speed and accuracy while preserving high-quality texture details. We present a set of new frameworks for human reconstruction consisting of three parts, geometric reconstruction, texture generation and texture mapping. Firstly, a mesh reconstruction framework is used, which accurately extracts 3D human shapes from a single image. At the same time, we propose a method to generate a multi-view consistent image of the human body based on a single image. This is finally combined with a novel texture mapping method to optimize texture details and ensure color consistency during reconstruction. Through extensive experiments and evaluations, we demonstrate the superior performance of \emph{Ultraman} on various standard datasets. In addition, \emph{Ultraman} outperforms state-of-the-art methods in terms of human rendering quality and speed. Upon acceptance of the article, we will make the code and data publicly available.
Authors: Justin Kay, Timm Haucke, Suzanne Stathatos, Siqi Deng, Erik Young, Pietro Perona, Sara Beery, Grant Van Horn
Abstract: Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, we identify systemic benchmarking pitfalls that call past results into question and hamper further progress: (a) Overestimation of performance due to underpowered baselines, (b) Inconsistent implementation practices preventing transparent comparisons of methods, and (c) Lack of generality due to outdated backbones and lack of diversity in benchmarks. We address these problems by introducing: (1) A unified benchmarking and implementation framework, Align and Distill (ALDI), enabling comparison of DAOD methods and supporting future development, (2) A fair and modern training and evaluation protocol for DAOD that addresses benchmarking pitfalls, (3) A new DAOD benchmark dataset, CFC-DAOD, enabling evaluation on diverse real-world data, and (4) A new method, ALDI++, that achieves state-of-the-art results by a large margin. ALDI++ outperforms the previous state-of-the-art by +3.5 AP50 on Cityscapes to Foggy Cityscapes, +5.7 AP50 on Sim10k to Cityscapes (where ours is the only method to outperform a fair baseline), and +2.0 AP50 on CFC Kenai to Channel. Our framework, dataset, and state-of-the-art method offer a critical reset for DAOD and provide a strong foundation for future research. Code and data are available: https://github.com/justinkay/aldi and https://github.com/visipedia/caltech-fish-counting.
URLs: https://github.com/justinkay/aldi, https://github.com/visipedia/caltech-fish-counting.
Authors: Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan
Abstract: Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the overwriting of old ones. Excessive modification of the network causes forgetting, while minimal adjustments lead to an inadequate fit for new classes. As a result, it is desired to figure out a way of efficient model updating without harming former knowledge. In this paper, we propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. To enable model updating without conflict, we train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. These adapters span a high-dimensional feature space, enabling joint decision-making across multiple subspaces. As data evolves, the expanding subspaces render the old class classifiers incompatible with new-stage spaces. Correspondingly, we design a semantic-guided prototype complement strategy that synthesizes old classes' new features without using any old class instance. Extensive experiments on seven benchmark datasets verify EASE's state-of-the-art performance. Code is available at: https://github.com/sun-hailong/CVPR24-Ease
Authors: Hansheng Chen, Ruoxi Shi, Yulin Liu, Bokui Shen, Jiayuan Gu, Gordon Wetzstein, Hao Su, Leonidas Guibas
Abstract: Open-domain 3D object synthesis has been lagging behind image synthesis due to limited data and higher computational complexity. To bridge this gap, recent works have investigated multi-view diffusion but often fall short in either 3D consistency, visual quality, or efficiency. This paper proposes MVEdit, which functions as a 3D counterpart of SDEdit, employing ancestral sampling to jointly denoise multi-view images and output high-quality textured meshes. Built on off-the-shelf 2D diffusion models, MVEdit achieves 3D consistency through a training-free 3D Adapter, which lifts the 2D views of the last timestep into a coherent 3D representation, then conditions the 2D views of the next timestep using rendered views, without uncompromising visual quality. With an inference time of only 2-5 minutes, this framework achieves better trade-off between quality and speed than score distillation. MVEdit is highly versatile and extendable, with a wide range of applications including text/image-to-3D generation, 3D-to-3D editing, and high-quality texture synthesis. In particular, evaluations demonstrate state-of-the-art performance in both image-to-3D and text-guided texture generation tasks. Additionally, we introduce a method for fine-tuning 2D latent diffusion models on small 3D datasets with limited resources, enabling fast low-resolution text-to-3D initialization.
Authors: Ce Zhang, Simon Stepputtis, Joseph Campbell, Katia Sycara, Yaqi Xie
Abstract: Being able to understand visual scenes is a precursor for many downstream tasks, including autonomous driving, robotics, and other vision-based approaches. A common approach enabling the ability to reason over visual data is Scene Graph Generation (SGG); however, many existing approaches assume undisturbed vision, i.e., the absence of real-world corruptions such as fog, snow, smoke, as well as non-uniform perturbations like sun glare or water drops. In this work, we propose a novel SGG benchmark containing procedurally generated weather corruptions and other transformations over the Visual Genome dataset. Further, we introduce a corresponding approach, Hierarchical Knowledge Enhanced Robust Scene Graph Generation (HiKER-SGG), providing a strong baseline for scene graph generation under such challenging setting. At its core, HiKER-SGG utilizes a hierarchical knowledge graph in order to refine its predictions from coarse initial estimates to detailed predictions. In our extensive experiments, we show that HiKER-SGG does not only demonstrate superior performance on corrupted images in a zero-shot manner, but also outperforms current state-of-the-art methods on uncorrupted SGG tasks. Code is available at https://github.com/zhangce01/HiKER-SGG.
Authors: Junlin Han, Filippos Kokkinos, Philip Torr
Abstract: This paper presents a novel paradigm for building scalable 3D generative models utilizing pre-trained video diffusion models. The primary obstacle in developing foundation 3D generative models is the limited availability of 3D data. Unlike images, texts, or videos, 3D data are not readily accessible and are difficult to acquire. This results in a significant disparity in scale compared to the vast quantities of other types of data. To address this issue, we propose using a video diffusion model, trained with extensive volumes of text, images, and videos, as a knowledge source for 3D data. By unlocking its multi-view generative capabilities through fine-tuning, we generate a large-scale synthetic multi-view dataset to train a feed-forward 3D generative model. The proposed model, VFusion3D, trained on nearly 3M synthetic multi-view data, can generate a 3D asset from a single image in seconds and achieves superior performance when compared to current SOTA feed-forward 3D generative models, with users preferring our results over 70% of the time.
Authors: Bojia Zi, Shihao Zhao, Xianbiao Qi, Jianan Wang, Yukai Shi, Qianyu Chen, Bin Liang, Kam-Fai Wong, Lei Zhang
Abstract: Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks effective techniques for text-guided video inpainting, a stark contrast to the well-explored domain of text-guided image inpainting. To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility. Specifically, we introduce a simple but efficient motion capture module to preserve motion consistency, and design an instance-aware region selection instead of a random region selection to obtain better textual controllability, and utilize a novel strategy to inject some personalized models into our CoCoCo model and thus obtain better model compatibility. Extensive experiments show that our model can generate high-quality video clips. Meanwhile, our model shows better motion consistency, textual controllability and model compatibility. More details are shown in [cococozibojia.github.io](cococozibojia.github.io).
Authors: Gaurav Parmar, Taesung Park, Srinivasa Narasimhan, Jun-Yan Zhu
Abstract: In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning. To tackle these issues, we introduce a general method for adapting a single-step diffusion model to new tasks and domains through adversarial learning objectives. Specifically, we consolidate various modules of the vanilla latent diffusion model into a single end-to-end generator network with small trainable weights, enhancing its ability to preserve the input image structure while reducing overfitting. We demonstrate that, for unpaired settings, our model CycleGAN-Turbo outperforms existing GAN-based and diffusion-based methods for various scene translation tasks, such as day-to-night conversion and adding/removing weather effects like fog, snow, and rain. We extend our method to paired settings, where our model pix2pix-Turbo is on par with recent works like Control-Net for Sketch2Photo and Edge2Image, but with a single-step inference. This work suggests that single-step diffusion models can serve as strong backbones for a range of GAN learning objectives. Our code and models are available at https://github.com/GaParmar/img2img-turbo.
Authors: Enshen Zhou, Yiran Qin, Zhenfei Yin, Yuzhou Huang, Ruimao Zhang, Lu Sheng, Yu Qiao, Jing Shao
Abstract: It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract and sequential natural language instructions. To this end, we introduce MineDreamer, an open-ended embodied agent built upon the challenging Minecraft simulator with an innovative paradigm that enhances instruction-following ability in low-level control signal generation. Specifically, MineDreamer is developed on top of recent advances in Multimodal Large Language Models (MLLMs) and diffusion models, and we employ a Chain-of-Imagination (CoI) mechanism to envision the step-by-step process of executing instructions and translating imaginations into more precise visual prompts tailored to the current state; subsequently, the agent generates keyboard-and-mouse actions to efficiently achieve these imaginations, steadily following the instructions at each step. Extensive experiments demonstrate that MineDreamer follows single and multi-step instructions steadily, significantly outperforming the best generalist agent baseline and nearly doubling its performance. Moreover, qualitative analysis of the agent's imaginative ability reveals its generalization and comprehension of the open world.
Authors: Xinle Cheng, Congyue Deng, Adam Harley, Yixin Zhu, Leonidas Guibas
Abstract: Correspondences emerge from large-scale vision models trained for generative and discriminative tasks. This has been revealed and benchmarked by computing correspondence maps between pairs of images, using nearest neighbors on the feature grids. Existing work has attempted to improve the quality of these correspondence maps by carefully mixing features from different sources, such as by combining the features of different layers or networks. We point out that a better correspondence strategy is available, which directly imposes structure on the correspondence field: the functional map. Wielding this simple mathematical tool, we lift the correspondence problem from the pixel space to the function space and directly optimize for mappings that are globally coherent. We demonstrate that our technique yields correspondences that are not only smoother but also more accurate, with the possibility of better reflecting the knowledge embedded in the large-scale vision models that we are studying. Our approach sets a new state-of-the-art on various dense correspondence tasks. We also demonstrate our effectiveness in keypoint correspondence and affordance map transfer.
Authors: Asaf Shul, Eliahu Horwitz, Yedid Hoshen
Abstract: Dataset distillation aims to compress a dataset into a much smaller one so that a model trained on the distilled dataset achieves high accuracy. Current methods frame this as maximizing the distilled classification accuracy for a budget of K distilled images-per-class, where K is a positive integer. In this paper, we push the boundaries of dataset distillation, compressing the dataset into less than an image-per-class. It is important to realize that the meaningful quantity is not the number of distilled images-per-class but the number of distilled pixels-per-dataset. We therefore, propose Poster Dataset Distillation (PoDD), a new approach that distills the entire original dataset into a single poster. The poster approach motivates new technical solutions for creating training images and learnable labels. Our method can achieve comparable or better performance with less than an image-per-class compared to existing methods that use one image-per-class. Specifically, our method establishes a new state-of-the-art performance on CIFAR-10, CIFAR-100, and CUB200 using as little as 0.3 images-per-class.
Authors: Zixin Zhu, Xuelu Feng, Dongdong Chen, Junsong Yuan, Chunming Qiao, Gang Hua
Abstract: In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed ``VD-IT'', tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifically, VD-IT uses textual information as a conditional input, ensuring semantic consistency across time for precise temporal instance matching. It further incorporates image tokens as supplementary textual inputs, enriching the feature set to generate detailed and nuanced masks.Besides, instead of using the standard Gaussian noise, we propose to predict the video-specific noise with an extra noise prediction module, which can help preserve the feature fidelity and elevates segmentation quality. Through extensive experiments, we surprisingly observe that fixed generative T2V diffusion models, unlike commonly used video backbones (e.g., Video Swin Transformer) pretrained with discriminative image/video pre-tasks, exhibit better potential to maintain semantic alignment and temporal consistency. On existing standard benchmarks, our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods. The code will be available at \url{https://github.com/buxiangzhiren/VD-IT}
Authors: Jay Shah, Md Mahfuzur Rahman Siddiquee, Yi Su, Teresa Wu, Baoxin Li
Abstract: Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at ***.
Authors: Huan-Ke Hsu, I-Chyn Wey, T. Hui Teo
Abstract: Convolution Neural Network (CNN) accelerators have been developed rapidly in recent studies. There are lots of CNN accelerators equipped with a variety of function and algorithm which results in low power and high-speed performances. However, the scale of a PE array in traditional CNN accelerators is too big, which costs the most energy consumption while conducting multiply and accumulation (MAC) computations. The other issue is that due to the advance of CNN models, there are enormous models consist of parallel structures such as residual block in Residual Network (ResNet). The appearance of parallel structure in CNN models gives a challenge to the design of CNN accelerators owing to impacts on both operation and area efficiency. This study proposed SF-MMCN structure. The scale of PE array in proposed designs is reduced by pipeline technique in a PE. Proposed SF structure successfully make proposed SF-MMCN operate in high efficiency when facing parallel structures in CNN models. Proposed design is implemented with TSMC 90nm technology on VGG-16 and ResNet-18 environments. The performance of proposed design achieves 76% energy saving, 55% area saving and increases operation and are efficiency 9.25 times and 4.92 times respectively.
Authors: Kenta Tsukahara, Kanji Tanaka, Daiki Iwata
Abstract: A typical assumption in state-of-the-art self-localization models is that an annotated training dataset is available in the target workspace. However, this does not always hold when a robot travels in a general open-world. This study introduces a novel training scheme for open-world distributed robot systems. In our scheme, a robot ("student") can ask the other robots it meets at unfamiliar places ("teachers") for guidance. Specifically, a pseudo-training dataset is reconstructed from the teacher model and thereafter used for continual learning of the student model. Unlike typical knowledge transfer schemes, our scheme introduces only minimal assumptions on the teacher model, such that it can handle various types of open-set teachers, including uncooperative, untrainable (e.g., image retrieval engines), and blackbox teachers (i.e., data privacy). Rather than relying on the availability of private data of teachers as in existing methods, we propose to exploit an assumption that holds universally in self-localization tasks: "The teacher model is a self-localization system" and to reuse the self-localization system of a teacher as a sole accessible communication channel. We particularly focus on designing an excellent student/questioner whose interactions with teachers can yield effective question-and-answer sequences that can be used as pseudo-training datasets for the student self-localization model. When applied to a generic recursive knowledge distillation scenario, our approach exhibited stable and consistent performance improvement.
Authors: Minjong Cheon, Yo-Hwan Choi, Seon-Yu Kang, Yumi Choi, Jeong-Gil Lee, Daehyun Kang
Abstract: Deep learning-based, data-driven models are gaining prevalence in climate research, particularly for global weather prediction. However, training the global weather data at high resolution requires massive computational resources. Therefore, we present a new model named KARINA to overcome the substantial computational demands typical of this field. This model achieves forecasting accuracy comparable to higher-resolution counterparts with significantly less computational resources, requiring only 4 NVIDIA A100 GPUs and less than 12 hours of training. KARINA combines ConvNext, SENet, and Geocyclic Padding to enhance weather forecasting at a 2.5{\deg} resolution, which could filter out high-frequency noise. Geocyclic Padding preserves pixels at the lateral boundary of the input image, thereby maintaining atmospheric flow continuity in the spherical Earth. SENet dynamically improves feature response, advancing atmospheric process modeling, particularly in the vertical column process as numerous channels. In this vein, KARINA sets new benchmarks in weather forecasting accuracy, surpassing existing models like the ECMWF S2S reforecasts at a lead time of up to 7 days. Remarkably, KARINA achieved competitive performance even when compared to the recently developed models (Pangu-Weather, GraphCast, ClimaX, and FourCastNet) trained with high-resolution data having 100 times larger pixels. Conclusively, KARINA significantly advances global weather forecasting by efficiently modeling Earth's atmosphere with improved accuracy and resource efficiency.
Authors: Long Nguyen-Phuoc, Renald Gaboriau, Dimitri Delacroix, Laurent Navarro
Abstract: In order to provide a more objective and quicker way to diagnose post-traumatic stress disorder (PTSD), we present PTSD-MDNN which merges two unimodal convolutional neural networks and which gives low detection error rate. By taking only videos and audios as inputs, the model could be used in the configuration of teleconsultation sessions, in the optimization of patient journeys or for human-robot interaction.
Authors: Ruixiang Jiang, Lingbo Liu, Changwen Chen
Abstract: Prompt-tuning has demonstrated parameter-efficiency in fusing unimodal foundation models for multimodal tasks. However, its limited adaptivity and expressiveness lead to suboptimal performance when compared with other tuning methods. In this paper, we address this issue by disentangling the vanilla prompts to adaptively capture dataset-level and instance-level features. Building upon this disentanglement, we introduce the mixture of prompt experts (MoPE) technique to enhance expressiveness. MoPE leverages multimodal pairing priors to route the most effective prompt on a per-instance basis. Compared to vanilla prompting, our MoPE-based conditional prompting exhibits greater expressiveness for multimodal fusion, scaling better with the training data and the overall number of trainable parameters. We also study a regularization term for expert routing, leading to emergent expert specialization, where different experts focus on different concepts, enabling interpretable soft prompting. Extensive experiments across three multimodal datasets demonstrate that our method achieves state-of-the-art results, matching or even surpassing the performance of fine-tuning, while requiring only 0.8% of the trainable parameters. Code will be released: https://github.com/songrise/MoPE.
Authors: Atah Nuh Mih, Alireza Rahimi, Asfia Kawnine, Francis Palma, Monica Wachowicz, Rickey Dubay, Hung Cao
Abstract: This paper proposes an optimization of an existing Deep Neural Network (DNN) that improves its hardware utilization and facilitates on-device training for resource-constrained edge environments. We implement efficient parameter reduction strategies on Xception that shrink the model size without sacrificing accuracy, thus decreasing memory utilization during training. We evaluate our model in two experiments: Caltech-101 image classification and PCB defect detection and compare its performance against the original Xception and lightweight models, EfficientNetV2B1 and MobileNetV2. The results of the Caltech-101 image classification show that our model has a better test accuracy (76.21%) than Xception (75.89%), uses less memory on average (847.9MB) than Xception (874.6MB), and has faster training and inference times. The lightweight models overfit with EfficientNetV2B1 having a 30.52% test accuracy and MobileNetV2 having a 58.11% test accuracy. Both lightweight models have better memory usage than our model and Xception. On the PCB defect detection, our model has the best test accuracy (90.30%), compared to Xception (88.10%), EfficientNetV2B1 (55.25%), and MobileNetV2 (50.50%). MobileNetV2 has the least average memory usage (849.4MB), followed by our model (865.8MB), then EfficientNetV2B1 (874.8MB), and Xception has the highest (893.6MB). We further experiment with pre-trained weights and observe that memory usage decreases thereby showing the benefits of transfer learning. A Pareto analysis of the models' performance shows that our optimized model architecture satisfies accuracy and low memory utilization objectives.
Authors: Weixiang Sun, Yixin Liu, Zhiling Yan, Kaidi Xu, Lichao Sun
Abstract: With the rapid growth of artificial intelligence (AI) in healthcare, there has been a significant increase in the generation and storage of sensitive medical data. This abundance of data, in turn, has propelled the advancement of medical AI technologies. However, concerns about unauthorized data exploitation, such as training commercial AI models, often deter researchers from making their invaluable datasets publicly available. In response to the need to protect this hard-to-collect data while still encouraging medical institutions to share it, one promising solution is to introduce imperceptible noise into the data. This method aims to safeguard the data against unauthorized training by inducing degradation in model generalization. Although existing methods have shown commendable data protection capabilities in general domains, they tend to fall short when applied to biomedical data, mainly due to their failure to account for the sparse nature of medical images. To address this problem, we propose the Sparsity-Aware Local Masking (SALM) method, a novel approach that selectively perturbs significant pixel regions rather than the entire image as previous strategies have done. This simple-yet-effective approach significantly reduces the perturbation search space by concentrating on local regions, thereby improving both the efficiency and effectiveness of data protection for biomedical datasets characterized by sparse features. Besides, we have demonstrated that SALM maintains the essential characteristics of the data, ensuring its clinical utility remains uncompromised. Our extensive experiments across various datasets and model architectures demonstrate that SALM effectively prevents unauthorized training of deep-learning models and outperforms previous state-of-the-art data protection methods.
Authors: Haoyue Tang, Tian Xie, Aosong Feng, Hanyu Wang, Chenyang Zhang, Yang Bai
Abstract: Solving image inverse problems (e.g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image). By using the input image as guidance, we can leverage a pretrained diffusion generative model to solve a wide range of image inverse tasks without task specific model fine-tuning. To precisely estimate the guidance score function of the input image, we propose Diffusion Policy Gradient (DPG), a tractable computation method by viewing the intermediate noisy images as policies and the target image as the states selected by the policy. Experiments show that our method is robust to both Gaussian and Poisson noise degradation on multiple linear and non-linear inverse tasks, resulting into a higher image restoration quality on FFHQ, ImageNet and LSUN datasets.
Authors: Xijun Wang, Santiago L\'opez-Tapia, Alice Lucas, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos
Abstract: Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, such as unexpected artifacts and noises. To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process. We extract spatial information from the input data and incorporate it into the training loss, making the corresponding loss a spatially adaptive (SA) one. After that, we utilize it to guide the training process. We will show that the proposed approach is independent of the methods used to extract the spatial information and independent of the SR tasks and models. This method consistently guides the training process towards generating visually pleasing SR images and video frames, substantially mitigating artifacts and noise, ultimately leading to enhanced perceptual quality.
Authors: Yining Jiao, Amy Oldenburg, Yinghan Xu, Srikamal Soundararajan, Carlton Zdanski, Julia Kimbell, Marc Niethammer
Abstract: Optical coherence tomography (OCT) is a popular modality in ophthalmology and is also used intravascularly. Our interest in this work is OCT in the context of airway abnormalities in infants and children where the high resolution of OCT and the fact that it is radiation-free is important. The goal of airway OCT is to provide accurate estimates of airway geometry (in 2D and 3D) to assess airway abnormalities such as subglottic stenosis. We propose $\texttt{NeuralOCT}$, a learning-based approach to process airway OCT images. Specifically, $\texttt{NeuralOCT}$ extracts 3D geometries from OCT scans by robustly bridging two steps: point cloud extraction via 2D segmentation and 3D reconstruction from point clouds via neural fields. Our experiments show that $\texttt{NeuralOCT}$ produces accurate and robust 3D airway reconstructions with an average A-line error smaller than 70 micrometer. Our code will cbe available on GitHub.
Authors: Yuxuan Li, Sarthak Kumar Maharana, Yunhui Guo
Abstract: With the increasing prevalence of Machine Learning as a Service (MLaaS) platforms, there is a growing focus on deep neural network (DNN) watermarking techniques. These methods are used to facilitate the verification of ownership for a target DNN model to protect intellectual property. One of the most widely employed watermarking techniques involves embedding a trigger set into the source model. Unfortunately, existing methodologies based on trigger sets are still susceptible to functionality-stealing attacks, potentially enabling adversaries to steal the functionality of the source model without a reliable means of verifying ownership. In this paper, we first introduce a novel perspective on trigger set-based watermarking methods from a feature learning perspective. Specifically, we demonstrate that by selecting data exhibiting multiple features, also referred to as $\textit{multi-view data}$, it becomes feasible to effectively defend functionality stealing attacks. Based on this perspective, we introduce a novel watermarking technique based on Multi-view dATa, called MAT, for efficiently embedding watermarks within DNNs. This approach involves constructing a trigger set with multi-view data and incorporating a simple feature-based regularization method for training the source model. We validate our method across various benchmarks and demonstrate its efficacy in defending against model extraction attacks, surpassing relevant baselines by a significant margin.
Authors: Jin Yang, Peijie Qiu, Yichi Zhang, Daniel S. Marcus, Aristeidis Sotiras
Abstract: Hierarchical transformers have achieved significant success in medical image segmentation due to their large receptive field and capabilities of effectively leveraging global long-range contextual information. Convolutional neural networks (CNNs) can also deliver a large receptive field by using large kernels, enabling them to achieve competitive performance with fewer model parameters. However, CNNs incorporated with large convolutional kernels remain constrained in adaptively capturing multi-scale features from organs with large variations in shape and size due to the employment of fixed-sized kernels. Additionally, they are unable to utilize global contextual information efficiently. To address these limitations, we propose Dynamic Large Kernel (DLK) and Dynamic Feature Fusion (DFF) modules. The DLK module employs multiple large kernels with varying kernel sizes and dilation rates to capture multi-scale features. Subsequently, a dynamic selection mechanism is utilized to adaptively highlight the most important spatial features based on global information. Additionally, the DFF module is proposed to adaptively fuse multi-scale local feature maps based on their global information. We integrate DLK and DFF in a hierarchical transformer architecture to develop a novel architecture, termed D-Net. D-Net is able to effectively utilize a multi-scale large receptive field and adaptively harness global contextual information. Extensive experimental results demonstrate that D-Net outperforms other state-of-the-art models in the two volumetric segmentation tasks, including abdominal multi-organ segmentation and multi-modality brain tumor segmentation. Our code is available at https://github.com/sotiraslab/DLK.
Authors: Andreas Ziegler, Karl Vetter, Thomas Gossard, Jonas Tebbe, Andreas Zell
Abstract: Table tennis is a fast-paced and exhilarating sport that demands agility, precision, and fast reflexes. In recent years, robotic table tennis has become a popular research challenge for robot perception algorithms. Fast and accurate ball detection is crucial for enabling a robotic arm to rally the ball back successfully. Previous approaches have employed conventional frame-based cameras with Convolutional Neural Networks (CNNs) or traditional computer vision methods. In this paper, we propose a novel solution that combines an event-based camera with Spiking Neural Networks (SNNs) for ball detection. We use multiple state-of-the-art SNN frameworks and develop a SNN architecture for each of them, complying with their corresponding constraints. Additionally, we implement the SNN solution across multiple neuromorphic edge devices, conducting comparisons of their accuracies and run-times. This furnishes robotics researchers with a benchmark illustrating the capabilities achievable with each SNN framework and a corresponding neuromorphic edge device. Next to this comparison of SNN solutions for robots, we also show that an SNN on a neuromorphic edge device is able to run in real-time in a closed loop robotic system, a table tennis robot in our use case.
Authors: Namiko Saito, Joao Moura, Hiroki Uchida, Sethu Vijayakumar
Abstract: Recognising the characteristics of objects while a robot handles them is crucial for adjusting motions that ensure stable and efficient interactions with containers. Ahead of realising stable and efficient robot motions for handling/transferring the containers, this work aims to recognise the latent unobservable object characteristics. While vision is commonly used for object recognition by robots, it is ineffective for detecting hidden objects. However, recognising objects indirectly using other sensors is a challenging task. To address this challenge, we propose a cross-modal transfer learning approach from vision to haptic-audio. We initially train the model with vision, directly observing the target object. Subsequently, we transfer the latent space learned from vision to a second module, trained only with haptic-audio and motor data. This transfer learning framework facilitates the representation of object characteristics using indirect sensor data, thereby improving recognition accuracy. For evaluating the recognition accuracy of our proposed learning framework we selected shape, position, and orientation as the object characteristics. Finally, we demonstrate online recognition of both trained and untrained objects using the humanoid robot Nextage Open.
Authors: Yipeng Sun, Yixing Huang, Linda-Sophie Schneider, Mareike Thies, Mingxuan Gu, Siyuan Mei, Siming Bayer, Andreas Maier
Abstract: Computed Tomography (CT) image reconstruction is crucial for accurate diagnosis and deep learning approaches have demonstrated significant potential in improving reconstruction quality. However, the choice of loss function profoundly affects the reconstructed images. Traditional mean squared error loss often produces blurry images lacking fine details, while alternatives designed to improve may introduce structural artifacts or other undesirable effects. To address these limitations, we propose Eagle-Loss, a novel loss function designed to enhance the visual quality of CT image reconstructions. Eagle-Loss applies spectral analysis of localized features within gradient changes to enhance sharpness and well-defined edges. We evaluated Eagle-Loss on two public datasets across low-dose CT reconstruction and CT field-of-view extension tasks. Our results show that Eagle-Loss consistently improves the visual quality of reconstructed images, surpassing state-of-the-art methods across various network architectures. Code and data are available at \url{https://github.com/sypsyp97/Eagle_Loss}.
Authors: Abigail Julian, Lars Ruthotto
Abstract: Over the past decade, reversed Gradient Polarity (RGP) methods have become a popular approach for correcting susceptibility artifacts in Echo-Planar Imaging (EPI). Although several post-processing tools for RGP are available, their implementations do not fully leverage recent hardware, algorithmic, and computational advances, leading to correction times of several minutes per image volume. To enable 3D RGP correction in seconds, we introduce PyHySCO, a user-friendly EPI distortion correction tool implemented in PyTorch that enables multi-threading and efficient use of graphics processing units (GPUs). PyHySCO uses a time-tested physical distortion model and mathematical formulation and is, therefore, reliable without training. An algorithmic improvement in PyHySCO is its novel initialization scheme that uses 1D optimal transport. PyHySCO is published under the GNU public license and can be used from the command line or its Python interface. Our extensive numerical validation using 3T and 7T data from the Human Connectome Project suggests that PyHySCO achieves accuracy comparable to that of leading RGP tools at a fraction of the cost. We also validate the new initialization scheme, compare different optimization algorithms, and test the algorithm on different hardware and arithmetic precision.
Authors: Christopher Kolios, Yeganeh Bahoo, Sajad Saeedi
Abstract: We present DPPE, a dense pose estimation algorithm that functions over a Plenoxels environment. Recent advances in neural radiance field techniques have shown that it is a powerful tool for environment representation. More recent neural rendering algorithms have significantly improved both training duration and rendering speed. Plenoxels introduced a fully-differentiable radiance field technique that uses Plenoptic volume elements contained in voxels for rendering, offering reduced training times and better rendering accuracy, while also eliminating the neural net component. In this work, we introduce a 6-DoF monocular RGB-only pose estimation procedure for Plenoxels, which seeks to recover the ground truth camera pose after a perturbation. We employ a variation on classical template matching techniques, using stochastic gradient descent to optimize the pose by minimizing errors in re-rendering. In particular, we examine an approach that takes advantage of the rapid rendering speed of Plenoxels to numerically approximate part of the pose gradient, using a central differencing technique. We show that such methods are effective in pose estimation. Finally, we perform ablations over key components of the problem space, with a particular focus on image subsampling and Plenoxel grid resolution. Project website: https://sites.google.com/view/dppe
Authors: Yuwen Chen, Nicholas Konz, Hanxue Gu, Haoyu Dong, Yaqian Chen, Lin Li, Jisoo Lee, Maciej A. Mazurowski
Abstract: Accurately translating medical images across different modalities (e.g., CT to MRI) has numerous downstream clinical and machine learning applications. While several methods have been proposed to achieve this, they often prioritize perceptual quality with respect to output domain features over preserving anatomical fidelity. However, maintaining anatomy during translation is essential for many tasks, e.g., when leveraging masks from the input domain to develop a segmentation model with images translated to the output domain. To address these challenges, we propose ContourDiff, a novel framework that leverages domain-invariant anatomical contour representations of images. These representations are simple to extract from images, yet form precise spatial constraints on their anatomical content. We introduce a diffusion model that converts contour representations of images from arbitrary input domains into images in the output domain of interest. By applying the contour as a constraint at every diffusion sampling step, we ensure the preservation of anatomical content. We evaluate our method by training a segmentation model on images translated from CT to MRI with their original CT masks and testing its performance on real MRIs. Our method outperforms other unpaired image translation methods by a significant margin, furthermore without the need to access any input domain information during training.
Authors: Jiawei Li, Sitong Li, Shanshan Wang, Yicheng Zeng, Falong Tan, Chuanlong Xie
Abstract: Deploying machine learning in open environments presents the challenge of encountering diverse test inputs that differ significantly from the training data. These out-of-distribution samples may exhibit shifts in local or global features compared to the training distribution. The machine learning (ML) community has responded with a number of methods aimed at distinguishing anomalous inputs from original training data. However, the majority of previous studies have primarily focused on the output layer or penultimate layer of pre-trained deep neural networks. In this paper, we propose a novel framework, Multitesting-based Layer-wise Out-of-Distribution (OOD) Detection (MLOD), to identify distributional shifts in test samples at different levels of features through rigorous multiple testing procedure. Our approach distinguishes itself from existing methods as it does not require modifying the structure or fine-tuning of the pre-trained classifier. Through extensive experiments, we demonstrate that our proposed framework can seamlessly integrate with any existing distance-based inspection method while efficiently utilizing feature extractors of varying depths. Our scheme effectively enhances the performance of out-of-distribution detection when compared to baseline methods. In particular, MLOD-Fisher achieves superior performance in general. When trained using KNN on CIFAR10, MLOD-Fisher significantly lowers the false positive rate (FPR) from 24.09% to 7.47% on average compared to merely utilizing the features of the last layer.
Authors: Fan Zhang, Zhaohan Wang, Xin Lyu, Siyuan Zhao, Mengjian Li, Weidong Geng, Naye Ji, Hui Du, Fuxing Gao, Hao Wu, Shunman Li
Abstract: Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture. The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model's superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system's usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology. Supplementary videos and code can be accessed at https://zf223669.github.io/Diffmotion-v2-website/
Authors: Mude Hui, Zihao Wei, Hongru Zhu, Fei Xia, Yuyin Zhou
Abstract: Volumetric optical microscopy using non-diffracting beams enables rapid imaging of 3D volumes by projecting them axially to 2D images but lacks crucial depth information. Addressing this, we introduce MicroDiffusion, a pioneering tool facilitating high-quality, depth-resolved 3D volume reconstruction from limited 2D projections. While existing Implicit Neural Representation (INR) models often yield incomplete outputs and Denoising Diffusion Probabilistic Models (DDPM) excel at capturing details, our method integrates INR's structural coherence with DDPM's fine-detail enhancement capabilities. We pretrain an INR model to transform 2D axially-projected images into a preliminary 3D volume. This pretrained INR acts as a global prior guiding DDPM's generative process through a linear interpolation between INR outputs and noise inputs. This strategy enriches the diffusion process with structured 3D information, enhancing detail and reducing noise in localized 2D images. By conditioning the diffusion model on the closest 2D projection, MicroDiffusion substantially enhances fidelity in resulting 3D reconstructions, surpassing INR and standard DDPM outputs with unparalleled image quality and structural fidelity. Our code and dataset are available at https://github.com/UCSC-VLAA/MicroDiffusion.
Authors: Dongyu Yan, Guanyu Huang, Fengyu Quan, Haoyao Chen
Abstract: Panoramic observation using fisheye cameras is significant in robot perception, reconstruction, and remote operation. However, panoramic images synthesized by traditional methods lack depth information and can only provide three degrees-of-freedom (3DoF) rotation rendering in virtual reality applications. To fully preserve and exploit the parallax information within the original fisheye cameras, we introduce MSI-NeRF, which combines deep learning omnidirectional depth estimation and novel view rendering. We first construct a multi-sphere image as a cost volume through feature extraction and warping of the input images. It is then processed by geometry and appearance decoders, respectively. Unlike methods that regress depth maps directly, we further build an implicit radiance field using spatial points and interpolated 3D feature vectors as input. In this way, we can simultaneously realize omnidirectional depth estimation and 6DoF view synthesis. Our method is trained in a semi-self-supervised manner. It does not require target view images and only uses depth data for supervision. Our network has the generalization ability to reconstruct unknown scenes efficiently using only four images. Experimental results show that our method outperforms existing methods in depth estimation and novel view synthesis tasks.
Authors: Minhyuk Seo, Diganta Misra, Seongwon Cho, Minjae Lee, Jonghyun Choi
Abstract: In real-world scenarios, extensive manual annotation for continual learning is impractical due to prohibitive costs. Although prior arts, influenced by large-scale webly supervised training, suggest leveraging web-scraped data in continual learning, this poses challenges such as data imbalance, usage restrictions, and privacy concerns. Addressing the risks of continual webly supervised training, we present an online continual learning framework - Generative Name only Continual Learning (G-NoCL). The proposed G-NoCL uses a set of generators G along with the learner. When encountering new concepts (i.e., classes), G-NoCL employs the novel sample complexity-guided data ensembling technique DIverSity and COmplexity enhancing ensemBlER (DISCOBER) to optimally sample training data from generated data. Through extensive experimentation, we demonstrate superior performance of DISCOBER in G-NoCL online CL benchmarks, covering both In-Distribution (ID) and Out-of-Distribution (OOD) generalization evaluations, compared to naive generator-ensembling, web-supervised, and manually annotated data.
Authors: Anay Panja, Somenath Kuiry, Alaka Das, Mita Nasipuri, Nibaran Das
Abstract: Since 2019, the global COVID-19 outbreak has emerged as a crucial focus in healthcare research. Although RT-PCR stands as the primary method for COVID-19 detection, its extended detection time poses a significant challenge. Consequently, supplementing RT-PCR with the pathological study of COVID-19 through CT imaging has become imperative. The current segmentation approach based on TVLoss enhances the connectivity of afflicted areas. Nevertheless, it tends to misclassify normal pixels between certain adjacent diseased regions as diseased pixels. The typical Binary cross entropy(BCE) based U-shaped network only concentrates on the entire CT images without emphasizing on the affected regions, which results in hazy borders and low contrast in the projected output. In addition, the fraction of infected pixels in CT images is much less, which makes it a challenge for segmentation models to make accurate predictions. In this paper, we propose COVID-CT-H-UNet, a COVID-19 CT segmentation network to solve these problems. To recognize the unaffected pixels between neighbouring diseased regions, extra visual layer information is captured by combining the attention module on the skip connections with the proposed composite function Bi-category Hybrid Loss. The issue of hazy boundaries and poor contrast brought on by the BCE Loss in conventional techniques is resolved by utilizing the composite function Bi-category Hybrid Loss that concentrates on the pixels in the diseased area. The experiment shows when compared to the previous COVID-19 segmentation networks, the proposed COVID-CT-H-UNet's segmentation impact has greatly improved, and it may be used to identify and study clinical COVID-19.
Authors: Soumyajyoti Dey, Sukanta Chakraborty, Utso Guha Roy, Nibaran Das
Abstract: Automation in medical imaging is quite challenging due to the unavailability of annotated datasets and the scarcity of domain experts. In recent years, deep learning techniques have solved some complex medical imaging tasks like disease classification, important object localization, segmentation, etc. However, most of the task requires a large amount of annotated data for their successful implementation. To mitigate the shortage of data, different generative models are proposed for data augmentation purposes which can boost the classification performances. For this, different synthetic medical image data generation models are developed to increase the dataset. Unpaired image-to-image translation models here shift the source domain to the target domain. In the breast malignancy identification domain, FNAC is one of the low-cost low-invasive modalities normally used by medical practitioners. But availability of public datasets in this domain is very poor. Whereas, for automation of cytology images, we need a large amount of annotated data. Therefore synthetic cytology images are generated by translating breast histopathology samples which are publicly available. In this study, we have explored traditional image-to-image transfer models like CycleGAN, and Neural Style Transfer. Further, it is observed that the generated cytology images are quite similar to real breast cytology samples by measuring FID and KID scores.
Authors: Martin Spitznagel, Janis Keuper
Abstract: Data-driven modeling of complex physical systems is receiving a growing amount of attention in the simulation and machine learning communities. Since most physical simulations are based on compute-intensive, iterative implementations of differential equation systems, a (partial) replacement with learned, 1-step inference models has the potential for significant speedups in a wide range of application areas. In this context, we present a novel benchmark for the evaluation of 1-step generative learning models in terms of speed and physical correctness. Our Urban Sound Propagation benchmark is based on the physically complex and practically relevant, yet intuitively easy to grasp task of modeling the 2d propagation of waves from a sound source in an urban environment. We provide a dataset with 100k samples, where each sample consists of pairs of real 2d building maps drawn from OpenStreetmap, a parameterized sound source, and a simulated ground truth sound propagation for the given scene. The dataset provides four different simulation tasks with increasing complexity regarding reflection, diffraction and source variance. A first baseline evaluation of common generative U-Net, GAN and Diffusion models shows, that while these models are very well capable of modeling sound propagations in simple cases, the approximation of sub-systems represented by higher order equations systematically fails. Information about the dataset, download instructions and source codes are provided on our anonymous website: https://www.urban-sound-data.org.
Authors: Mingzhou Jiang, Jiaying Zhou, Junde Wu, Tianyang Wang, Yueming Jin, Min Xu
Abstract: The Segment Anything Model (SAM) gained significant success in natural image segmentation, and many methods have tried to fine-tune it to medical image segmentation. An efficient way to do so is by using Adapters, specialized modules that learn just a few parameters to tailor SAM specifically for medical images. However, unlike natural images, many tissues and lesions in medical images have blurry boundaries and may be ambiguous. Previous efforts to adapt SAM ignore this challenge and can only predict distinct segmentation.It may mislead clinicians or cause misdiagnosis, especially when encountering rare variants or situations with low model confidence. In this work, we propose a novel module called the Uncertainty-aware Adapter, which efficiently fine-tuning SAM for uncertainty-aware medical image segmentation. Utilizing a conditional variational autoencoder, we encoded stochastic samples to effectively represent the inherent uncertainty in medical imaging. We designed a new module on a standard adapter that utilizes a condition-based strategy to interact with samples to help SAM integrate uncertainty. We evaluated our method on two multi-annotated datasets with different modalities: LIDC-IDRI (lung abnormalities segmentation) and REFUGE2 (optic-cup segmentation). The experimental results show that the proposed model outperforms all the previous methods and achieves the new state-of-the-art (SOTA) on both benchmarks. We also demonstrated that our method can generate diverse segmentation hypotheses that are more realistic as well as heterogeneous.
Authors: Farhad Pakdaman, Moncef Gabbouj
Abstract: The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video compression, and major efforts have been dedicated to improving its compression efficiency. However, most proposed works target compression efficiency by employing more complex DNNS, which contributes to higher computational complexity. Alternatively, this paper proposes to improve compression by fully exploiting the existing DNN capacity. To do so, the latent features are guided to learn a richer and more diverse set of features, which corresponds to better reconstruction. A channel-wise feature decorrelation loss is designed and is integrated into the LC optimization. Three strategies are proposed and evaluated, which optimize (1) the transformation network, (2) the context model, and (3) both networks. Experimental results on two established LC methods show that the proposed method improves the compression with a BD-Rate of up to 8.06%, with no added complexity. The proposed solution can be applied as a plug-and-play solution to optimize any similar LC method.
Authors: Vanessa Wirth, Johanna Br\"aunig, Danti Khouri, Florian Gutsche, Martin Vossiek, Tim Weyrich, Marc Stamminger
Abstract: Despite an emerging interest in MIMO radar, the utilization of its complementary strengths in combination with optical sensors has so far been limited to far-field applications, due to the challenges that arise from mutual sensor calibration in the near field. In fact, most related approaches in the autonomous industry propose target-based calibration methods using corner reflectors that have proven to be unsuitable for the near field. In contrast, we propose a novel, joint calibration approach for optical RGB-D sensors and MIMO radars that is designed to operate in the radar's near-field range, within decimeters from the sensors. Our pipeline consists of a bespoke calibration target, allowing for automatic target detection and localization, followed by the spatial calibration of the two sensor coordinate systems through target registration. We validate our approach using two different depth sensing technologies from the optical domain. The experiments show the efficiency and accuracy of our calibration for various target displacements, as well as its robustness of our localization in terms of signal ambiguities.
Authors: Alexander H. Berger, Nico Stucki, Laurin Lux, Vincent Buergin, Suprosanna Shit, Anna Banaszak, Daniel Rueckert, Ulrich Bauer, Johannes C. Paetzold
Abstract: Topological accuracy in medical image segmentation is a highly important property for downstream applications such as network analysis and flow modeling in vessels or cell counting. Recently, significant methodological advancements have brought well-founded concepts from algebraic topology to binary segmentation. However, these approaches have been underexplored in multi-class segmentation scenarios, where topological errors are common. We propose a general loss function for topologically faithful multi-class segmentation extending the recent Betti matching concept, which is based on induced matchings of persistence barcodes. We project the N-class segmentation problem to N single-class segmentation tasks, which allows us to use 1-parameter persistent homology making training of neural networks computationally feasible. We validate our method on a comprehensive set of four medical datasets with highly variant topological characteristics. Our loss formulation significantly enhances topological correctness in cardiac, cell, artery-vein, and Circle of Willis segmentation.
Authors: Sadaf Khademi, Zohreh Hajiakhondi, Golnaz Vaseghi, Nizal Sarrafzadegan, Arash Mohammadi
Abstract: Familial Hypercholesterolemia (FH) is a genetic disorder characterized by elevated levels of Low-Density Lipoprotein (LDL) cholesterol or its associated genes. Early-stage and accurate categorization of FH is of significance allowing for timely interventions to mitigate the risk of life-threatening conditions. Conventional diagnosis approach, however, is complex, costly, and a challenging interpretation task even for experienced clinicians resulting in high underdiagnosis rates. Although there has been a recent surge of interest in using Machine Learning (ML) models for early FH detection, existing solutions only consider a binary classification task solely using classical ML models. Despite its significance, application of Deep Learning (DL) for FH detection is in its infancy, possibly, due to categorical nature of the underlying clinical data. The paper addresses this gap by introducing the FH-TabNet, which is a multi-stage tabular DL network for multi-class (Definite, Probable, Possible, and Unlikely) FH detection. The FH-TabNet initially involves applying a deep tabular data learning architecture (TabNet) for primary categorization into healthy (Possible/Unlikely) and patient (Probable/Definite) classes. Subsequently, independent TabNet classifiers are applied to each subgroup, enabling refined classification. The model's performance is evaluated through 5-fold cross-validation illustrating superior performance in categorizing FH patients, particularly in the challenging low-prevalence subcategories.
Authors: Che-Yung Shen, Jingxi Li, Tianyi Gan, Yuhang Li, Langxing Bai, Mona Jarrahi, Aydogan Ozcan
Abstract: Quantitative phase imaging (QPI) is a label-free technique that provides optical path length information for transparent specimens, finding utility in biology, materials science, and engineering. Here, we present quantitative phase imaging of a 3D stack of phase-only objects using a wavelength-multiplexed diffractive optical processor. Utilizing multiple spatially engineered diffractive layers trained through deep learning, this diffractive processor can transform the phase distributions of multiple 2D objects at various axial positions into intensity patterns, each encoded at a unique wavelength channel. These wavelength-multiplexed patterns are projected onto a single field-of-view (FOV) at the output plane of the diffractive processor, enabling the capture of quantitative phase distributions of input objects located at different axial planes using an intensity-only image sensor. Based on numerical simulations, we show that our diffractive processor could simultaneously achieve all-optical quantitative phase imaging across several distinct axial planes at the input by scanning the illumination wavelength. A proof-of-concept experiment with a 3D-fabricated diffractive processor further validated our approach, showcasing successful imaging of two distinct phase objects at different axial positions by scanning the illumination wavelength in the terahertz spectrum. Diffractive network-based multiplane QPI designs can open up new avenues for compact on-chip phase imaging and sensing devices.
Authors: Jialu Sui, Xianping Ma, Xiaokang Zhang, Man-On Pun
Abstract: Remote sensing image super-resolution (SR) is a crucial task to restore high-resolution (HR) images from low-resolution (LR) observations. Recently, the Denoising Diffusion Probabilistic Model (DDPM) has shown promising performance in image reconstructions by overcoming problems inherent in generative models, such as over-smoothing and mode collapse. However, the high-frequency details generated by DDPM often suffer from misalignment with HR images due to the model's tendency to overlook long-range semantic contexts. This is attributed to the widely used U-Net decoder in the conditional noise predictor, which tends to overemphasize local information, leading to the generation of noises with significant variances during the prediction process. To address these issues, an adaptive semantic-enhanced DDPM (ASDDPM) is proposed to enhance the detail-preserving capability of the DDPM by incorporating low-frequency semantic information provided by the Transformer. Specifically, a novel adaptive diffusion Transformer decoder (ADTD) is developed to bridge the semantic gap between the encoder and decoder through regulating the noise prediction with the global contextual relationships and long-range dependencies in the diffusion process. Additionally, a residual feature fusion strategy establishes information exchange between the two decoders at multiple levels. As a result, the predicted noise generated by our approach closely approximates that of the real noise distribution.Extensive experiments on two SR and two semantic segmentation datasets confirm the superior performance of the proposed ASDDPM in both SR and the subsequent downstream applications. The source code will be available at https://github.com/littlebeen/ASDDPM-Adaptive-Semantic-Enhanced-DDPM.
URLs: https://github.com/littlebeen/ASDDPM-Adaptive-Semantic-Enhanced-DDPM.
Authors: Liang Zou, Genwei Yan, Ruoyu Wang, Jun Du, Meng Lei, Tian Gao, Xin Fang
Abstract: This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on segment-level predictions, which often providing detailed, fine-grained predictions, particularly for events of brief duration. Although frame-level prediction strategies have been proposed to overcome these limitations, these strategies commonly face difficulties with prediction truncation caused by background noise. To alleviate this issue, we introduces an innovative multitask frame-level SED framework. In addition, we introduce TimeFilterAug, a linear timing mask for data augmentation, to increase the model's robustness and adaptability to diverse acoustic environments. The proposed method achieves a F-score of 63.8%, securing the 1st rank in the few-shot bioacoustic event detection category of the Detection and Classification of Acoustic Scenes and Events Challenge 2023.
Authors: Michael Saxon, Yiran Luo, Sharon Levy, Chitta Baral, Yezhou Yang, William Yang Wang
Abstract: Benchmarks of the multilingual capabilities of text-to-image (T2I) models compare generated images prompted in a test language to an expected image distribution over a concept set. One such benchmark, "Conceptual Coverage Across Languages" (CoCo-CroLa), assesses the tangible noun inventory of T2I models by prompting them to generate pictures from a concept list translated to seven languages and comparing the output image populations. Unfortunately, we find that this benchmark contains translation errors of varying severity in Spanish, Japanese, and Chinese. We provide corrections for these errors and analyze how impactful they are on the utility and validity of CoCo-CroLa as a benchmark. We reassess multiple baseline T2I models with the revisions, compare the outputs elicited under the new translations to those conditioned on the old, and show that a correction's impactfulness on the image-domain benchmark results can be predicted in the text domain with similarity scores. Our findings will guide the future development of T2I multilinguality metrics by providing analytical tools for practical translation decisions.
Authors: Suryam Arnav Kalra, Arindam Biswas, Pabitra Mitra, Biswajit Basu
Abstract: Expansion property of a graph refers to its strong connectivity as well as sparseness. It has been reported that deep neural networks can be pruned to a high degree of sparsity while maintaining their performance. Such pruning is essential for performing real time sequence learning tasks using recurrent neural networks in resource constrained platforms. We prune recurrent networks such as RNNs and LSTMs, maintaining a large spectral gap of the underlying graphs and ensuring their layerwise expansion properties. We also study the time unfolded recurrent network graphs in terms of the properties of their bipartite layers. Experimental results for the benchmark sequence MNIST, CIFAR-10, and Google speech command data show that expander graph properties are key to preserving classification accuracy of RNN and LSTM.
Authors: Kaiqi Zhao, Ming Zhao
Abstract: Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper-parameter tuning to balance the weights of different loss terms, assume the availability of labeled training data, and require complex, computationally intensive training procedures for good performance. To address these limitations, this paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation (SQAKD) framework. SQAKD first unifies the forward and backward dynamics of various quantization functions, making it flexible for incorporating various QAT works. Then it formulates QAT as a co-optimization problem that simultaneously minimizes the KL-Loss between the full-precision and low-bit models for KD and the discretization error for quantization, without supervision from labels. A comprehensive evaluation shows that SQAKD substantially outperforms the state-of-the-art QAT and KD works for a variety of model architectures. Our code is at: https://github.com/kaiqi123/SQAKD.git.
Authors: Mahdie Ahmadi, Nader Karimi, Shadrokh Samavi
Abstract: Accurate and early detection of breast cancer is essential for successful treatment. This paper introduces a novel deep-learning approach for improved breast cancer classification in histopathological images, a crucial step in diagnosis. Our method hinges on the Dense Residual Dual-Shuffle Attention Network (DRDA-Net), inspired by ShuffleNet's efficient architecture. DRDA-Net achieves exceptional accuracy across various magnification levels on the BreaKHis dataset, a breast cancer histopathology analysis benchmark. However, for real-world deployment, computational efficiency is paramount. We integrate a pre-trained MobileNet model renowned for its lightweight design to address computational. MobileNet ensures fast execution even on devices with limited resources without sacrificing performance. This combined approach offers a promising solution for accurate breast cancer diagnosis, paving the way for faster and more accessible screening procedures.
Authors: Chih-Chung Hsu, Chia-Ming Lee, Yang Fan Chiang, Yi-Shiuan Chou, Chih-Yu Jiang, Shen-Chieh Tai, Chi-Han Tsai
Abstract: This study explores the use of deep learning techniques for analyzing lung Computed Tomography (CT) images. Classic deep learning approaches face challenges with varying slice counts and resolutions in CT images, a diversity arising from the utilization of assorted scanning equipment. Typically, predictions are made on single slices which are then combined for a comprehensive outcome. Yet, this method does not incorporate learning features specific to each slice, leading to a compromise in effectiveness. To address these challenges, we propose an advanced Spatial-Slice Feature Learning (SSFL++) framework specifically tailored for CT scans. It aims to filter out out-of-distribution (OOD) data within the entire CT scan, allowing us to select essential spatial-slice features for analysis by reducing data redundancy by 70\%. Additionally, we introduce a Kernel-Density-based slice Sampling (KDS) method to enhance stability during training and inference phases, thereby accelerating convergence and enhancing overall performance. Remarkably, our experiments reveal that our model achieves promising results with a simple EfficientNet-2D (E2D) model. The effectiveness of our approach is confirmed on the COVID-19-CT-DB datasets provided by the DEF-AI-MIA workshop.
Authors: Liren Jin, Haofei Kuang, Yue Pan, Cyrill Stachniss, Marija Popovi\'c
Abstract: Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks in an initially unknown environment. In this work, we propose a novel framework for semantic-targeted active reconstruction using posed RGB-D measurements and 2D semantic labels as input. The key components of our framework are a semantic implicit neural representation and a compatible planning utility function based on semantic rendering and uncertainty estimation, enabling adaptive view planning to target objects of interest. Our planning approach achieves better reconstruction performance in terms of mesh and novel view rendering quality compared to implicit reconstruction baselines that do not consider semantics for view planning. Our framework further outperforms a state-of-the-art semantic-targeted active reconstruction pipeline based on explicit maps, justifying our choice of utilising implicit neural representations to tackle semantic-targeted active reconstruction problems.
Authors: Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Jen-Shiun Chiang
Abstract: The introduction of YOLOv9, the latest version of the You Only Look Once (YOLO) series, has led to its widespread adoption across various scenarios. This paper is the first to apply the YOLOv9 algorithm model to the fracture detection task as computer-assisted diagnosis (CAD) to help radiologists and surgeons to interpret X-ray images. Specifically, this paper trained the model on the GRAZPEDWRI-DX dataset and extended the training set using data augmentation techniques to improve the model performance. Experimental results demonstrate that compared to the mAP 50-95 of the current state-of-the-art (SOTA) model, the YOLOv9 model increased the value from 42.16% to 43.73%, with an improvement of 3.7%. The implementation code is publicly available at https://github.com/RuiyangJu/YOLOv9-Fracture-Detection.
URLs: https://github.com/RuiyangJu/YOLOv9-Fracture-Detection.
Authors: Igor Sterner, Weizhe Lin, Jinghong Chen, Bill Byrne
Abstract: Two approaches have emerged to input images into large language models (LLMs). The first is to caption images into natural language. The second is to map image feature embeddings into the domain of the LLM and pass the mapped embeddings directly to the LLM. The majority of recent few-shot multimodal work reports performance using architectures that employ variations of one of these two approaches. But they overlook an important comparison between them. We design a controlled and focused experiment to compare these two approaches to few-shot visual question answering (VQA) with LLMs. Our findings indicate that for Flan-T5 XL, a 3B parameter LLM, connecting visual embeddings directly to the LLM embedding space does not guarantee improved performance over using image captions. In the zero-shot regime, we find using textual image captions is better. In the few-shot regimes, how the in-context examples are selected determines which is better.
Authors: Fares Bougourzi, Feryal Windal Moula, Halim Benhabiles, Fadi Dornaika, Abdelmalik Taleb-Ahmed
Abstract: Since the emergence of Covid-19 in late 2019, medical image analysis using artificial intelligence (AI) has emerged as a crucial research area, particularly with the utility of CT-scan imaging for disease diagnosis. This paper contributes to the 4th COV19D competition, focusing on Covid-19 Detection and Covid-19 Domain Adaptation Challenges. Our approach centers on lung segmentation and Covid-19 infection segmentation employing the recent CNN-based segmentation architecture PDAtt-Unet, which simultaneously segments lung regions and infections. Departing from traditional methods, we concatenate the input slice (grayscale) with segmented lung and infection, generating three input channels akin to color channels. Additionally, we employ three 3D CNN backbones Customized Hybrid-DeCoVNet, along with pretrained 3D-Resnet-18 and 3D-Resnet-50 models to train Covid-19 recognition for both challenges. Furthermore, we explore ensemble approaches and testing augmentation to enhance performance. Comparison with baseline results underscores the substantial efficiency of our approach, with a significant margin in terms of F1-score (14 %). This study advances the field by presenting a comprehensive methodology for accurate Covid-19 detection and adaptation, leveraging cutting-edge AI techniques in medical image analysis.
Authors: Tushar Kataria, Beatrice Knudsen, Shireen Y. Elhabian
Abstract: Hematoxylin and Eosin (H&E) staining is the most commonly used for disease diagnosis and tumor recurrence tracking. Hematoxylin excels at highlighting nuclei, whereas eosin stains the cytoplasm. However, H&E stain lacks details for differentiating different types of cells relevant to identifying the grade of the disease or response to specific treatment variations. Pathologists require special immunohistochemical (IHC) stains that highlight different cell types. These stains help in accurately identifying different regions of disease growth and their interactions with the cell's microenvironment. The advent of deep learning models has made Image-to-Image (I2I) translation a key research area, reducing the need for expensive physical staining processes. Pix2Pix and CycleGAN are still the most commonly used methods for virtual staining applications. However, both suffer from hallucinations or staining irregularities when H&E stain has less discriminate information about the underlying cells IHC needs to highlight (e.g.,CD3 lymphocytes). Diffusion models are currently the state-of-the-art models for image generation and conditional generation tasks. However, they require extensive and diverse datasets (millions of samples) to converge, which is less feasible for virtual staining applications.Inspired by the success of multitask deep learning models for limited dataset size, we propose StainDiffuser, a novel multitask dual diffusion architecture for virtual staining that converges under a limited training budget. StainDiffuser trains two diffusion processes simultaneously: (a) generation of cell-specific IHC stain from H&E and (b) H&E-based cell segmentation using coarse segmentation only during training. Our results show that StainDiffuser produces high-quality results for easier (CK8/18,epithelial marker) and difficult stains(CD3, Lymphocytes).
Authors: Yihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman
Abstract: An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical effectiveness, the reason behind the success of this technique is poorly understood. The pre-projection representations are not directly optimized by the loss function, raising the question: what makes them better? In this work, we provide a rigorous theoretical answer to this question. We start by examining linear models trained with self-supervised contrastive loss. We reveal that the implicit bias of training algorithms leads to layer-wise progressive feature weighting, where features become increasingly unequal as we go deeper into the layers. Consequently, lower layers tend to have more normalized and less specialized representations. We theoretically characterize scenarios where such representations are more beneficial, highlighting the intricate interplay between data augmentation and input features. Additionally, we demonstrate that introducing non-linearity into the network allows lower layers to learn features that are completely absent in higher layers. Finally, we show how this mechanism improves the robustness in supervised contrastive learning and supervised learning. We empirically validate our results through various experiments on CIFAR-10/100, UrbanCars and shifted versions of ImageNet. We also introduce a potential alternative to projection head, which offers a more interpretable and controllable design.
Authors: Yuting Xiao, Xuan Wang, Jiafei Li, Hongrui Cai, Yanbo Fan, Nan Xue, Minghui Yang, Yujun Shen, Shenghua Gao
Abstract: This is only a preview version of GauMesh. Recently, primitive-based rendering has been proven to achieve convincing results in solving the problem of modeling and rendering the 3D dynamic scene from 2D images. Despite this, in the context of novel view synthesis, each type of primitive has its inherent defects in terms of representation ability. It is difficult to exploit the mesh to depict the fuzzy geometry. Meanwhile, the point-based splatting (e.g. the 3D Gaussian Splatting) method usually produces artifacts or blurry pixels in the area with smooth geometry and sharp textures. As a result, it is difficult, even not impossible, to represent the complex and dynamic scene with a single type of primitive. To this end, we propose a novel approach, GauMesh, to bridge the 3D Gaussian and Mesh for modeling and rendering the dynamic scenes. Given a sequence of tracked mesh as initialization, our goal is to simultaneously optimize the mesh geometry, color texture, opacity maps, a set of 3D Gaussians, and the deformation field. At a specific time, we perform $\alpha$-blending on the RGB and opacity values based on the merged and re-ordered z-buffers from mesh and 3D Gaussian rasterizations. This produces the final rendering, which is supervised by the ground-truth image. Experiments demonstrate that our approach adapts the appropriate type of primitives to represent the different parts of the dynamic scene and outperforms all the baseline methods in both quantitative and qualitative comparisons without losing render speed.
Authors: Debanjali Bhattacharya, Neelam Sinha
Abstract: Recent advances in neuroimaging have enabled studies in functional connectivity (FC) of human brain, alongside investigation of the neuronal basis of cognition. One important FC study is the representation of vision in human brain. The release of publicly available dataset BOLD5000 has made it possible to study the brain dynamics during visual tasks in greater detail. In this paper, a comprehensive analysis of fMRI time series (TS) has been performed to explore different types of visual brain networks (VBN). The novelty of this work lies in (1) constructing VBN with consistently significant direct connectivity using both marginal and partial correlation, which is further analyzed using graph theoretic measures, (2) classification of VBNs as formed by image complexity-specific TS, using graphical features. In image complexity-specific VBN classification, XGBoost yields average accuracy in the range of 86.5% to 91.5% for positively correlated VBN, which is 2% greater than that using negative correlation. This result not only reflects the distinguishing graphical characteristics of each image complexity-specific VBN, but also highlights the importance of studying both positively correlated and negatively correlated VBN to understand the how differently brain functions while viewing different complexities of real-world images.
Authors: Runtian Yuan, Qingqiu Li, Junlin Hou, Jilan Xu, Yuejie Zhang, Rui Feng, Hao Chen
Abstract: In response to the need for rapid and accurate COVID-19 diagnosis during the global pandemic, we present a two-stage framework that leverages pseudo labels for domain adaptation to enhance the detection of COVID-19 from CT scans. By utilizing annotated data from one domain and non-annotated data from another, the model overcomes the challenge of data scarcity and variability, common in emergent health crises. The innovative approach of generating pseudo labels enables the model to iteratively refine its learning process, thereby improving its accuracy and adaptability across different hospitals and medical centres. Experimental results on COV19-CT-DB database showcase the model's potential to achieve high diagnostic precision, significantly contributing to efficient patient management and alleviating the strain on healthcare systems. Our method achieves 0.92 Macro F1 Score on the validation set of Covid-19 domain adaptation challenge.
Authors: Azad Singh, Vandan Gorade, Deepak Mishra
Abstract: Self-supervised learning (SSL) is potentially useful in reducing the need for manual annotation and making deep learning models accessible for medical image analysis tasks. By leveraging the representations learned from unlabeled data, self-supervised models perform well on tasks that require little to no fine-tuning. However, for medical images, like chest X-rays, which are characterized by complex anatomical structures and diverse clinical conditions, there arises a need for representation learning techniques that can encode fine-grained details while preserving the broader contextual information. In this context, we introduce MLVICX (Multi-Level Variance-Covariance Exploration for Chest X-ray Self-Supervised Representation Learning), an approach to capture rich representations in the form of embeddings from chest X-ray images. Central to our approach is a novel multi-level variance and covariance exploration strategy that empowers the model to detect diagnostically meaningful patterns while reducing redundancy effectively. By enhancing the variance and covariance of the learned embeddings, MLVICX promotes the retention of critical medical insights by adapting both global and local contextual details. We demonstrate the performance of MLVICX in advancing self-supervised chest X-ray representation learning through comprehensive experiments. The performance enhancements we observe across various downstream tasks highlight the significance of the proposed approach in enhancing the utility of chest X-ray embeddings for precision medical diagnosis and comprehensive image analysis. For pertaining, we used the NIH-Chest X-ray dataset, while for downstream tasks, we utilized NIH-Chest X-ray, Vinbig-CXR, RSNA pneumonia, and SIIM-ACR Pneumothorax datasets. Overall, we observe more than 3% performance gains over SOTA SSL approaches in various downstream tasks.
Authors: Ramy Farag, Parth Upadhyay, Guilhermen DeSouza
Abstract: Manual diagnosis and analysis of COVID-19 through the examination of lung Computed Tomography (CT) scan images by physicians tends to result in inefficiency, especially with high patient volumes and numerous images per patient. We address the need for automation by developing a deep learning model-based pipeline for COVID-19 detection from CT scan images of the lungs. The Domain adaptation, Explainability, and Fairness in AI for Medical Image Analysis Workshop and COVID-19 Diagnosis Competition (DEF-AI-MIA COV19D) provides an opportunity to assess our designed pipeline for COVID-19 detection from CT scan images. The proposed pipeline incorporates EfficientNet with an Attention mechanism with a pre-processing step. Our pipeline outperforms last year's teams on the validation set of the competition dataset.
Authors: Haoxiang Ma, Ran Qin, Modi shi, Boyang Gao, Di Huang
Abstract: This paper focuses on the sim-to-real issue of RGB-D grasp detection and formulates it as a domain adaptation problem. In this case, we present a global-to-local method to address hybrid domain gaps in RGB and depth data and insufficient multi-modal feature alignment. First, a self-supervised rotation pre-training strategy is adopted to deliver robust initialization for RGB and depth networks. We then propose a global-to-local alignment pipeline with individual global domain classifiers for scene features of RGB and depth images as well as a local one specifically working for grasp features in the two modalities. In particular, we propose a grasp prototype adaptation module, which aims to facilitate fine-grained local feature alignment by dynamically updating and matching the grasp prototypes from the simulation and real-world scenarios throughout the training process. Due to such designs, the proposed method substantially reduces the domain shift and thus leads to consistent performance improvements. Extensive experiments are conducted on the GraspNet-Planar benchmark and physical environment, and superior results are achieved which demonstrate the effectiveness of our method.
Authors: Paul Novello, Joseba Dalmau, L\'eo Andeol
Abstract: Research on Out-Of-Distribution (OOD) detection focuses mainly on building scores that efficiently distinguish OOD data from In Distribution (ID) data. On the other hand, Conformal Prediction (CP) uses non-conformity scores to construct prediction sets with probabilistic coverage guarantees. In this work, we propose to use CP to better assess the efficiency of OOD scores. Specifically, we emphasize that in standard OOD benchmark settings, evaluation metrics can be overly optimistic due to the finite sample size of the test dataset. Based on the work of (Bates et al., 2022), we define new conformal AUROC and conformal FRP@TPR95 metrics, which are corrections that provide probabilistic conservativeness guarantees on the variability of these metrics. We show the effect of these corrections on two reference OOD and anomaly detection benchmarks, OpenOOD (Yang et al., 2022) and ADBench (Han et al., 2022). We also show that the benefits of using OOD together with CP apply the other way around by using OOD scores as non-conformity scores, which results in improving upon current CP methods. One of the key messages of these contributions is that since OOD is concerned with designing scores and CP with interpreting these scores, the two fields may be inherently intertwined.
Authors: Qianyu Zhang, Bolun Zheng, Xinying Chen, Quan Chen, Zhunjie Zhu, Canjin Wang, Zongpeng Li, Chengang Yan
Abstract: Video compression artifacts arise due to the quantization operation in the frequency domain. The goal of video quality enhancement is to reduce compression artifacts and reconstruct a visually-pleasant result. In this work, we propose a hierarchical frequency-based upsampling and refining neural network (HFUR) for compressed video quality enhancement. HFUR consists of two modules: implicit frequency upsampling module (ImpFreqUp) and hierarchical and iterative refinement module (HIR). ImpFreqUp exploits DCT-domain prior derived through implicit DCT transform, and accurately reconstructs the DCT-domain loss via a coarse-to-fine transfer. Consequently, HIR is introduced to facilitate cross-collaboration and information compensation between the scales, thus further refine the feature maps and promote the visual quality of the final output. We demonstrate the effectiveness of the proposed modules via ablation experiments and visualized results. Extensive experiments on public benchmarks show that HFUR achieves state-of-the-art performance for both constant bit rate and constant QP modes.
Authors: Zhizhen Zhou, Yejing Huo, Guoheng Huang, An Zeng, Xuhang Chen, Lian Huang, Zinuo Li
Abstract: The study of music-generated dance is a novel and challenging Image generation task. It aims to input a piece of music and seed motions, then generate natural dance movements for the subsequent music. Transformer-based methods face challenges in time series prediction tasks related to human movements and music due to their struggle in capturing the nonlinear relationship and temporal aspects. This can lead to issues like joint deformation, role deviation, floating, and inconsistencies in dance movements generated in response to the music. In this paper, we propose a Quaternion-Enhanced Attention Network (QEAN) for visual dance synthesis from a quaternion perspective, which consists of a Spin Position Embedding (SPE) module and a Quaternion Rotary Attention (QRA) module. First, SPE embeds position information into self-attention in a rotational manner, leading to better learning of features of movement sequences and audio sequences, and improved understanding of the connection between music and dance. Second, QRA represents and fuses 3D motion features and audio features in the form of a series of quaternions, enabling the model to better learn the temporal coordination of music and dance under the complex temporal cycle conditions of dance generation. Finally, we conducted experiments on the dataset AIST++, and the results show that our approach achieves better and more robust performance in generating accurate, high-quality dance movements. Our source code and dataset can be available from https://github.com/MarasyZZ/QEAN and https://google.github.io/aistplusplus_dataset respectively.
URLs: https://github.com/MarasyZZ/QEAN, https://google.github.io/aistplusplus_dataset
Authors: Zewen Xu, Yijia He, Hao Wei, Bo Xu, BinJian Xie, Yihong Wu
Abstract: Line features are valid complements for point features in man-made environments. 3D-2D constraints provided by line features have been widely used in Visual Odometry (VO) and Structure-from-Motion (SfM) systems. However, how to accurately solve three-view relative motion only with 2D observations of points and lines in real time has not been fully explored. In this paper, we propose a novel three-view pose solver based on rotation-translation decoupled estimation. First, a high-precision rotation estimation method based on normal vector coplanarity constraints that consider the uncertainty of observations is proposed, which can be solved by Levenberg-Marquardt (LM) algorithm efficiently. Second, a robust linear translation constraint that minimizes the degree of the rotation components and feature observation components in equations is elaborately designed for estimating translations accurately. Experiments on synthetic data and real-world data show that the proposed approach improves both rotation and translation accuracy compared to the classical trifocal-tensor-based method and the state-of-the-art two-view algorithm in outdoor and indoor environments.
Authors: Haoyu Zhao, Guyu Liang, Zhou Zhao, Bo Du, Yongchao Xu, Rui Yu
Abstract: In clinical examinations and diagnoses, low-dose computed tomography (LDCT) is crucial for minimizing health risks compared with normal-dose computed tomography (NDCT). However, reducing the radiation dose compromises the signal-to-noise ratio, leading to degraded quality of CT images. To address this, we analyze LDCT denoising task based on experimental results from the frequency perspective, and then introduce a novel self-supervised CT image denoising method called WIA-LD2ND, only using NDCT data. The proposed WIA-LD2ND comprises two modules: Wavelet-based Image Alignment (WIA) and Frequency-Aware Multi-scale Loss (FAM). First, WIA is introduced to align NDCT with LDCT by mainly adding noise to the high-frequency components, which is the main difference between LDCT and NDCT. Second, to better capture high-frequency components and detailed information, Frequency-Aware Multi-scale Loss (FAM) is proposed by effectively utilizing multi-scale feature space. Extensive experiments on two public LDCT denoising datasets demonstrate that our WIA-LD2ND, only uses NDCT, outperforms existing several state-of-the-art weakly-supervised and self-supervised methods.
Authors: Guiyong Zheng, Jinqi Jiang, Chen Feng, Shaojie Shen, Boyu Zhou
Abstract: Surface prediction and completion have been widely studied in various applications. Recently, research in surface completion has evolved from small objects to complex large-scale scenes. As a result, researchers have begun increasing the volume of data and leveraging a greater variety of data modalities including rendered RGB images, descriptive texts, depth images, etc, to enhance algorithm performance. However, existing datasets suffer from a deficiency in the amounts of scene-level models along with the corresponding multi-modal information. Therefore, a method to scale the datasets and generate multi-modal information in them efficiently is essential. To bridge this research gap, we propose MASSTAR: a Multi-modal lArge-scale Scene dataset with a verSatile Toolchain for surfAce pRediction and completion. We develop a versatile and efficient toolchain for processing the raw 3D data from the environments. It screens out a set of fine-grained scene models and generates the corresponding multi-modal data. Utilizing the toolchain, we then generate an example dataset composed of over a thousand scene-level models with partial real-world data added. We compare MASSTAR with the existing datasets, which validates its superiority: the ability to efficiently extract high-quality models from complex scenarios to expand the dataset. Additionally, several representative surface completion algorithms are benchmarked on MASSTAR, which reveals that existing algorithms can hardly deal with scene-level completion. We will release the source code of our toolchain and the dataset. For more details, please see our project page at https://sysu-star.github.io/MASSTAR.
Authors: Haoyu Zhao, Wenhui Dong, Rui Yu, Zhou Zhao, Du Bo, Yongchao Xu
Abstract: The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets. To address the challenge of poor generalization across different domains, we introduce a Plug-and-Play module for data augmentation called MoreStyle. MoreStyle diversifies image styles by relaxing low-frequency constraints in Fourier space, guiding the image reconstruction network. With the help of adversarial learning, MoreStyle further expands the style range and pinpoints the most intricate style combinations within latent features. To handle significant style variations, we introduce an uncertainty-weighted loss. This loss emphasizes hard-to-classify pixels resulting only from style shifts while mitigating true hard-to-classify pixels in both MoreStyle-generated and original images. Extensive experiments on two widely used benchmarks demonstrate that the proposed MoreStyle effectively helps to achieve good domain generalization ability, and has the potential to further boost the performance of some state-of-the-art SDG methods.
Authors: Zhuoyuan Li, Zikun Yuan, Li Li, Dong Liu, Xiaohu Tang, Feng Wu
Abstract: In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex motion fields that are difficult to compactly represent. This problem has been tackled by more flexible block partitioning methods in the Versatile Video Coding (VVC) standard, but the more flexible partitions require more overhead bits to signal and still cannot be made arbitrary shaped. To address this limitation, we propose an object segmentation-assisted inter prediction method (SAIP), where objects in the reference frames are segmented by some advanced technologies. With a proper indication, the object segmentation mask is translated from the reference frame to the current frame as the arbitrary-shaped partition of different regions without any extra signal. Using the segmentation mask, motion compensation is separately performed for different regions, achieving higher prediction accuracy. The segmentation mask is further used to code the motion vectors of different regions more efficiently. Moreover, segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 1.98%, 1.14%, 0.79%, and on average 0.82%, 0.49%, 0.37% BD-rate reduction for common test sequences, under the Low-delay P, Low-delay B, and Random Access configurations, respectively.
Authors: Zhengzheng Tu, Zigang Zhu, Yayang Duan, Bo Jiang, Qishun Wang, Chaoxue Zhang
Abstract: Ultrasound video-based breast lesion segmentation provides a valuable assistance in early breast lesion detection and treatment. However, existing works mainly focus on lesion segmentation based on ultrasound breast images which usually can not be adapted well to obtain desirable results on ultrasound videos. The main challenge for ultrasound video-based breast lesion segmentation is how to exploit the lesion cues of both intra-frame and inter-frame simultaneously. To address this problem, we propose a novel Spatial-Temporal Progressive Fusion Network (STPFNet) for video based breast lesion segmentation problem. The main aspects of the proposed STPFNet are threefold. First, we propose to adopt a unified network architecture to capture both spatial dependences within each ultrasound frame and temporal correlations between different frames together for ultrasound data representation. Second, we propose a new fusion module, termed Multi-Scale Feature Fusion (MSFF), to fuse spatial and temporal cues together for lesion detection. MSFF can help to determine the boundary contour of lesion region to overcome the issue of lesion boundary blurring. Third, we propose to exploit the segmentation result of previous frame as the prior knowledge to suppress the noisy background and learn more robust representation. In particular, we introduce a new publicly available ultrasound video breast lesion segmentation dataset, termed UVBLS200, which is specifically dedicated to breast lesion segmentation. It contains 200 videos, including 80 videos of benign lesions and 120 videos of malignant lesions. Experiments on the proposed dataset demonstrate that the proposed STPFNet achieves better breast lesion detection performance than state-of-the-art methods.
Authors: Zoubida Ameur, Claire-H\'el\`ene Demarty, Daniel Menard, Olivier Le Meur
Abstract: The consumption of a video requires a considerable amount of energy during the various stages of its life-cycle. With a billion hours of video consumed daily, this contributes significantly to the greenhouse gas emission. Therefore, reducing the end-to-end carbon footprint of the video chain, while preserving the quality of experience at the user side, is of high importance. To contribute in an impactful manner, we propose 3R-INN, a single light invertible network that does three tasks at once: given a high-resolution grainy image, it Rescales it to a lower resolution, Removes film grain and Reduces its power consumption when displayed. Providing such a minimum viable quality content contributes to reducing the energy consumption during encoding, transmission, decoding and display. 3R-INN also offers the possibility to restore either the high-resolution grainy original image or a grain-free version, thanks to its invertibility and the disentanglement of the high frequency, and without transmitting auxiliary data. Experiments show that, while enabling significant energy savings for encoding (78%), decoding (77%) and rendering (5% to 20%), 3R-INN outperforms state-of-the-art film grain synthesis and energy-aware methods and achieves state-of-the-art performance on the rescaling task on different test-sets.
Authors: Jonas Schramm, Niclas V\"odisch, K\"ursat Petek, B Ravi Kiran, Senthil Yogamani, Wolfram Burgard, Abhinav Valada
Abstract: Semantic scene segmentation from a bird's-eye-view (BEV) perspective plays a crucial role in facilitating planning and decision-making for mobile robots. Although recent vision-only methods have demonstrated notable advancements in performance, they often struggle under adverse illumination conditions such as rain or nighttime. While active sensors offer a solution to this challenge, the prohibitively high cost of LiDARs remains a limiting factor. Fusing camera data with automotive radars poses a more inexpensive alternative but has received less attention in prior research. In this work, we aim to advance this promising avenue by introducing BEVCar, a novel approach for joint BEV object and map segmentation. The core novelty of our approach lies in first learning a point-based encoding of raw radar data, which is then leveraged to efficiently initialize the lifting of image features into the BEV space. We perform extensive experiments on the nuScenes dataset and demonstrate that BEVCar outperforms the current state of the art. Moreover, we show that incorporating radar information significantly enhances robustness in challenging environmental conditions and improves segmentation performance for distant objects. To foster future research, we provide the weather split of the nuScenes dataset used in our experiments, along with our code and trained models at http://bevcar.cs.uni-freiburg.de.
Authors: Onur Kele\c{s}, A. Murat Tekalp
Abstract: Convolutional neural networks (CNN) are built upon the classical McCulloch-Pitts neuron model, which is essentially a linear model, where the nonlinearity is provided by a separate activation function. Several researchers have proposed enhanced neuron models, including quadratic neurons, generalized operational neurons, generative neurons, and super neurons, with stronger nonlinearity than that provided by the pointwise activation function. There has also been a proposal to use Pade approximation as a generalized activation function. In this paper, we introduce a brand new neuron model called Pade neurons (Paons), inspired by the Pade approximants, which is the best mathematical approximation of a transcendental function as a ratio of polynomials with different orders. We show that Paons are a super set of all other proposed neuron models. Hence, the basic neuron in any known CNN model can be replaced by Paons. In this paper, we extend the well-known ResNet to PadeNet (built by Paons) to demonstrate the concept. Our experiments on the single-image super-resolution task show that PadeNets can obtain better results than competing architectures.
Authors: Ashesh Ashesh, Florian Jug
Abstract: In this work we present denoiSplit, a method to tackle a new analysis task, i.e. the challenge of joint semantic image splitting and unsupervised denoising. This dual approach has important applications in fluorescence microscopy, where semantic image splitting has important applications but noise does generally hinder the downstream analysis of image content. Image splitting involves dissecting an image into its distinguishable semantic structures. We show that the current state-of-the-art method for this task struggles in the presence of image noise, inadvertently also distributing the noise across the predicted outputs. The method we present here can deal with image noise by integrating an unsupervised denoising sub-task. This integration results in improved semantic image unmixing, even in the presence of notable and realistic levels of imaging noise. A key innovation in denoiSplit is the use of specifically formulated noise models and the suitable adjustment of KL-divergence loss for the high-dimensional hierarchical latent space we are training. We showcase the performance of denoiSplit across 4 tasks on real-world microscopy images. Additionally, we perform qualitative and quantitative evaluations and compare results to existing benchmarks, demonstrating the effectiveness of using denoiSplit: a single Variational Splitting Encoder-Decoder (VSE) Network using two suitable noise models to jointly perform semantic splitting and denoising.
Authors: Yuxuan Wang, Xuanyu Yi, Zike Wu, Na Zhao, Long Chen, Hanwang Zhang
Abstract: The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes.
Authors: Shubhra Aich, Wenshan Wang, Parv Maheshwari, Matthew Sivaprakasam, Samuel Triest, Cherie Ho, Jason M. Gregory, John G. Rogers III, Sebastian Scherer
Abstract: The limited sensing resolution of resource-constrained off-road vehicles poses significant challenges towards reliable off-road autonomy. To overcome this limitation, we propose a general framework based on fusing the future information (i.e. future fusion) for self-supervision. Recent approaches exploit this future information alongside the hand-crafted heuristics to directly supervise the targeted downstream tasks (e.g. traversability estimation). However, in this paper, we opt for a more general line of development - time-efficient completion of the highest resolution (i.e. 2cm per pixel) BEV map in a self-supervised manner via future fusion, which can be used for any downstream tasks for better longer range prediction. To this end, first, we create a high-resolution future-fusion dataset containing pairs of (RGB / height) raw sparse and noisy inputs and map-based dense labels. Next, to accommodate the noise and sparsity of the sensory information, especially in the distal regions, we design an efficient realization of the Bayes filter onto the vanilla convolutional network via the recurrent mechanism. Equipped with the ideas from SOTA generative models, our Bayesian structure effectively predicts high-quality BEV maps in the distal regions. Extensive evaluation on both the quality of completion and downstream task on our future-fusion dataset demonstrates the potential of our approach.
Authors: Kevin Xu, Yeganeh Kordi, Kate Sanders, Yizhong Wang, Adam Byerly, Jack Zhang, Benjamin Van Durme, Daniel Khashabi
Abstract: Recent chatbots have demonstrated impressive ability to understand and communicate in raw-text form. However, there is more to the world than raw text. For example, humans spend long hours of their time on web pages, where text is intertwined with other modalities and tasks are accomplished in the form of various complex interactions. Can state-of-the-art multi-modal models generalize to such complex domains? To address this question, we introduce TurkingBench, a benchmark of tasks formulated as web pages containing textual instructions with multi-modal context. Unlike existing work which employs artificially synthesized web pages, here we use natural HTML pages that were originally designed for crowdsourcing workers for various annotation purposes. The HTML instructions of each task are also instantiated with various values (obtained from the crowdsourcing tasks) to form new instances of the task. This benchmark contains 32.2K instances distributed across 158 tasks. Additionally, to facilitate the evaluation on TurkingBench, we develop an evaluation framework that connects the responses of chatbots to modifications on web pages (modifying a text box, checking a radio, etc.). We evaluate the performance of state-of-the-art models, including language-only, vision-only, and layout-only models, and their combinations, on this benchmark. Our findings reveal that these models perform significantly better than random chance, yet considerable room exists for improvement. We hope this benchmark will help facilitate the evaluation and development of web-based agents.
Authors: Hamza Kheddar, Yassine Himeur, Abbes Amira, Rachik Soualah
Abstract: In recent times, the fields of high-energy physics (HEP) experimentation and phenomenological studies have seen the integration of machine learning (ML) and its specialized branch, deep learning (DL). This survey offers a comprehensive assessment of these applications within the realm of various DL approaches. The initial segment of the paper introduces the fundamentals encompassing diverse particle physics types and establishes criteria for evaluating particle physics in tandem with learning models. Following this, a comprehensive taxonomy is presented for representing HEP images, encompassing accessible datasets, intricate details of preprocessing techniques, and methods of feature extraction and selection. Subsequently, the focus shifts to an exploration of available artificial intelligence (AI) models tailored to HEP images, along with a concentrated examination of HEP image classification pertaining to Jet particles. Within this review, a profound investigation is undertaken into distinct ML and DL proposed state-of-the art (SOTA) techniques, underscoring their implications for HEP inquiries. The discussion delves into specific applications in substantial detail, including Jet tagging, Jet tracking, particle classification, and more. The survey culminates with an analysis concerning the present status of HEP grounded in DL methodologies, encompassing inherent challenges and prospective avenues for future research endeavors.
Authors: Kanchan Poudel, Lisasha Poudel, Prabin Raj Shakya, Atit Poudel, Archana Shrestha, Bishesh Khanal
Abstract: Visual Inspection with Acetic Acid (VIA) remains the most feasible cervical cancer screening test in resource-constrained settings of low- and middle-income countries (LMICs), which are often performed screening camps or primary/community health centers by nurses instead of the preferred but unavailable expert Gynecologist. To address the highly subjective nature of the test, various handheld devices integrating cameras or smartphones have been recently explored to capture cervical images during VIA and aid decision-making via telemedicine or AI models. Most studies proposing AI models retrospectively use a relatively small number of already collected images from specific devices, digital cameras, or smartphones; the challenges and protocol for quality image acquisition during VIA in resource-constrained camp settings, challenges in getting gold standard, data imbalance, etc. are often overlooked. We present a novel approach and describe the end-to-end design process to build a robust smartphone-based AI-assisted system that does not require buying a separate integrated device: the proposed protocol for quality image acquisition in resource-constrained settings, dataset collected from 1,430 women during VIA performed by nurses in screening camps, preprocessing pipeline, and training and evaluation of a deep-learning-based classification model aimed to identify (pre)cancerous lesions. Our work shows that the readily available smartphones and a suitable protocol can capture the cervix images with the required details for the VIA test well; the deep-learning-based classification model provides promising results to assist nurses in VIA screening; and provides a direction for large-scale data collection and validation in resource-constrained settings.
Authors: Qingqiu Li, Runtian Yuan, Junlin Hou, Jilan Xu, Yuejie Zhang, Rui Feng, Hao Chen
Abstract: To make a more accurate diagnosis of COVID-19, we propose a straightforward yet effective model. Firstly, we analyse the characteristics of 3D CT scans and remove the non-lung parts, facilitating the model to focus on lesion-related areas and reducing computational cost. We use ResNeSt50 as the strong feature extractor, initializing it with pretrained weights which have COVID-19-specific prior knowledge. Our model achieves a Macro F1 Score of 0.94 on the validation set of the 4th COV19D Competition Challenge $\mathrm{I}$, surpassing the baseline by 16%. This indicates its effectiveness in distinguishing between COVID-19 and non-COVID-19 cases, making it a robust method for COVID-19 detection.
Authors: Yang Li, Qiuyi Huang, Chong Zhong, Danjuan Yang, Meiyan Li, A. H. Welsh, Aiyi Liu, Bo Fu, Catherien C. Liu, Xingtao Zhou
Abstract: Myopia screening using cutting-edge ultra-widefield (UWF) fundus imaging is potentially significant for ophthalmic outcomes. Current multidisciplinary research between ophthalmology and deep learning (DL) concentrates primarily on disease classification and diagnosis using single-eye images, largely ignoring joint modeling and prediction for Oculus Uterque (OU, both eyes). Inspired by the complex relationships between OU and the high correlation between the (continuous) outcome labels (Spherical Equivalent and Axial Length), we propose a framework of copula-enhanced adapter convolutional neural network (CNN) learning with OU UWF fundus images (OUCopula) for joint prediction of multiple clinical scores. We design a novel bi-channel multi-label CNN that can (1) take bi-channel image inputs subject to both high correlation and heterogeneity (by sharing the same backbone network and employing adapters to parameterize the channel-wise discrepancy), and (2) incorporate correlation information between continuous output labels (using a copula). Solid experiments show that OUCopula achieves satisfactory performance in myopia score prediction compared to backbone models. Moreover, OUCopula can far exceed the performance of models constructed for single-eye inputs. Importantly, our study also hints at the potential extension of the bi-channel model to a multi-channel paradigm and the generalizability of OUCopula across various backbone CNNs.
Authors: Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
Abstract: We present a certified defense to clean-label poisoning attacks. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain $p$-norm bounded adversarial perturbations into the training data to induce a targeted misclassification of a test-time input. Inspired by the adversarial robustness achieved by $denoised$ $smoothing$, we show how an off-the-shelf diffusion model can sanitize the tampered training data. We extensively test our defense against seven clean-label poisoning attacks and reduce their attack success to 0-16% with only a negligible drop in the test time accuracy. We compare our defense with existing countermeasures against clean-label poisoning, showing that the defense reduces the attack success the most and offers the best model utility. Our results highlight the need for future work on developing stronger clean-label attacks and using our certified yet practical defense as a strong baseline to evaluate these attacks.
Authors: Kung-Hsiang Huang, Hou Pong Chan, Yi R. Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, Heng Ji
Abstract: Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Automatic chart understanding has witnessed significant advancements with the rise of large foundation models in recent years. Foundation models, such as large language models (LLMs), have revolutionized various natural language processing (NLP) tasks and are increasingly being applied to chart understanding tasks. This survey paper provides a comprehensive overview of the recent developments, challenges, and future directions in chart understanding within the context of these foundation models. The paper begins by defining chart understanding, outlining problem formulations, and discussing fundamental building blocks crucial for studying chart understanding tasks. In the section on tasks and datasets, we explore various tasks within chart understanding and discuss their evaluation metrics and sources of both charts and textual inputs. Modeling strategies are then examined, encompassing both classification-based and generation-based approaches, along with tool augmentation techniques that enhance chart understanding performance. Furthermore, we discuss the state-of-the-art performance of each task and discuss how we can improve the performance. Challenges and future directions are addressed in a dedicated section, highlighting issues such as domain-specific charts, lack of efforts in evaluation, and agent-oriented settings. This survey paper serves to provide valuable insights and directions for future research in chart understanding leveraging large foundation models. The studies mentioned in this paper, along with emerging new research, will be continually updated at: https://github.com/khuangaf/Awesome-Chart-Understanding.
URLs: https://github.com/khuangaf/Awesome-Chart-Understanding.
Authors: Jiawei Zhang, Yuzhen Jin, Jilan Xu, Xiaowei Xu, Yanchun Zhang
Abstract: Biomedical image segmentation plays a central role in quantitative analysis, clinical diagnosis, and medical intervention. In the light of the fully convolutional networks (FCN) and U-Net, deep convolutional networks (DNNs) have made significant contributions to biomedical image segmentation applications. In this paper, we propose three different multi-scale dense connections (MDC) for the encoder, the decoder of U-shaped architectures, and across them. Based on three dense connections, we propose a multi-scale densely connected U-Net (MDU-Net) for biomedical image segmentation. MDU-Net directly fuses the neighboring feature maps with different scales from both higher layers and lower layers to strengthen feature propagation in the current layer. Multi-scale dense connections, which contain shorter connections between layers close to the input and output, also make a much deeper U-Net possible. Besides, we introduce quantization to alleviate the potential overfitting in dense connections, and further improve the segmentation performance. We evaluate our proposed model on the MICCAI 2015 Gland Segmentation (GlaS) dataset. The three MDC improve U-Net performance by up to 1.8% on test A and 3.5% on test B in the MICCAI Gland dataset. Meanwhile, the MDU-Net with quantization obviously improves the segmentation performance of original U-Net.
Authors: Huaizu Jiang, Erik Learned-Miller
Abstract: The cost volume, capturing the similarity of possible correspondences across two input images, is a key ingredient in state-of-the-art optical flow approaches. When sampling correspondences to build the cost volume, a large neighborhood radius is required to deal with large displacements, introducing a significant computational burden. To address this, coarse-to-fine or recurrent processing of the cost volume is usually adopted, where correspondence sampling in a local neighborhood with a small radius suffices. In this paper, we propose an alternative by constructing cost volumes with different dilation factors to capture small and large displacements simultaneously. A U-Net with skip connections is employed to convert the dilated cost volumes into interpolation weights between all possible captured displacements to get the optical flow. Our proposed model DCVNet only needs to process the cost volume once in a simple feedforward manner and does not rely on the sequential processing strategy. DCVNet obtains comparable accuracy to existing approaches and achieves real-time inference (30 fps on a mid-end 1080ti GPU). The code and model weights are available at https://github.com/neu-vi/ezflow.
Authors: Sucheng Ren, Qiang Wen, Nanxuan Zhao, Guoqiang Han, Shengfeng He
Abstract: The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers. With the global view in very shallow layers, the transformer encoder preserves more local representations to recover the spatial details in final saliency maps. Besides, as each layer can capture a global view of its previous layer, adjacent layers can implicitly maximize the representation differences and minimize the redundant features, making that every output feature of transformer layers contributes uniquely for final prediction. To decode features from the transformer, we propose a simple yet effective deeply-transformed decoder. The decoder densely decodes and upsamples the transformer features, generating the final saliency map with less noise injection. Experimental results demonstrate that our method significantly outperforms other FCN-based and transformer-based methods in five benchmarks by a large margin, with an average of 12.17% improvement in terms of Mean Absolute Error (MAE). Code will be available at https://github.com/OliverRensu/GLSTR.
Authors: Xue-Feng Zhu, Tianyang Xu, Xiao-Jun Wu
Abstract: The development of visual object tracking has continued for decades. Recent years, as the wide accessibility of the low-cost RGBD sensors, the task of visual object tracking on RGB-D videos has drawn much attention. Compared to conventional RGB-only tracking, the RGB-D videos can provide more information that facilitates objecting tracking in some complicated scenarios. The goal of this review is to summarize the relative knowledge of the research filed of RGB-D tracking. To be specific, we will generalize the related RGB-D tracking benchmarking datasets as well as the corresponding performance measurements. Besides, the existing RGB-D tracking methods are summarized in the paper. Moreover, we discuss the possible future direction in the field of RGB-D tracking.
Authors: Yunke Wang, Bo Du, Wenyuan Wang, Chang Xu
Abstract: Recently, Vision Transformer (ViT) has achieved promising performance in image recognition and gradually serves as a powerful backbone in various vision tasks. To satisfy the sequential input of Transformer, the tail of ViT first splits each image into a sequence of visual tokens with a fixed length. Then the following self-attention layers constructs the global relationship between tokens to produce useful representation for the downstream tasks. Empirically, representing the image with more tokens leads to better performance, yet the quadratic computational complexity of self-attention layer to the number of tokens could seriously influence the efficiency of ViT's inference. For computational reduction, a few pruning methods progressively prune uninformative tokens in the Transformer encoder, while leaving the number of tokens before the Transformer untouched. In fact, fewer tokens as the input for the Transformer encoder can directly reduce the following computational cost. In this spirit, we propose a Multi-Tailed Vision Transformer (MT-ViT) in the paper. MT-ViT adopts multiple tails to produce visual sequences of different lengths for the following Transformer encoder. A tail predictor is introduced to decide which tail is the most efficient for the image to produce accurate prediction. Both modules are optimized in an end-to-end fashion, with the Gumbel-Softmax trick. Experiments on ImageNet-1K demonstrate that MT-ViT can achieve a significant reduction on FLOPs with no degradation of the accuracy and outperform other compared methods in both accuracy and FLOPs.
Authors: Vladimir Guzov, Julian Chibane, Riccardo Marin, Yannan He, Yunus Saracoglu, Torsten Sattler, Gerard Pons-Moll
Abstract: Our world is not static and humans naturally cause changes in their environments through interactions, e.g., opening doors or moving furniture. Modeling changes caused by humans is essential for building digital twins, e.g., in the context of shared physical-virtual spaces (metaverses) and robotics. In order for widespread adoption of such emerging applications, the sensor setup used to capture the interactions needs to be inexpensive and easy-to-use for non-expert users. I.e., interactions should be captured and modeled by simple ego-centric sensors such as a combination of cameras and IMU sensors, not relying on any external cameras or object trackers. Yet, to the best of our knowledge, no work tackling the challenging problem of modeling human-scene interactions via such an ego-centric sensor setup exists. This paper closes this gap in the literature by developing a novel approach that combines visual localization of humans in the scene with contact-based reasoning about human-scene interactions from IMU data. Interestingly, we can show that even without visual observations of the interactions, human-scene contacts and interactions can be realistically predicted from human pose sequences. Our method, iReplica (Interaction Replica), is an essential first step towards the egocentric capture of human interactions and modeling of dynamic scenes, which is required for future AR/VR applications in immersive virtual universes and for training machines to behave like humans. Our code, data and model are available on our project page at http://virtualhumans.mpi-inf.mpg.de/ireplica/
Authors: Haimei Zhao, Jing Zhang, Zhuo Chen, Bo Yuan, Dacheng Tao
Abstract: Remarkable progress has been made in self-supervised monocular depth estimation (SS-MDE) by exploring cross-view consistency, e.g., photometric consistency and 3D point cloud consistency. However, they are very vulnerable to illumination variance, occlusions, texture-less regions, as well as moving objects, making them not robust enough to deal with various scenes. To address this challenge, we study two kinds of robust cross-view consistency in this paper. Firstly, the spatial offset field between adjacent frames is obtained by reconstructing the reference frame from its neighbors via deformable alignment, which is used to align the temporal depth features via a Depth Feature Alignment (DFA) loss. Secondly, the 3D point clouds of each reference frame and its nearby frames are calculated and transformed into voxel space, where the point density in each voxel is calculated and aligned via a Voxel Density Alignment (VDA) loss. In this way, we exploit the temporal coherence in both depth feature space and 3D voxel space for SS-MDE, shifting the "point-to-point" alignment paradigm to the "region-to-region" one. Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges. Experimental results on several outdoor benchmarks show that our method outperforms current state-of-the-art techniques. Extensive ablation study and analysis validate the effectiveness of the proposed losses, especially in challenging scenes. The code and models are available at https://github.com/sunnyHelen/RCVC-depth.
Authors: Minh Tran, Khoa Vo, Kashu Yamazaki, Arthur Fernandes, Michael Kidd, Ngan Le
Abstract: Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown promising results, they are unable to model high-level features coherence due to the limited receptive field. The most recent transformer-based models show impressive performance on vision tasks, even better than Convolution Neural Networks (CNN). In this work, we present AISFormer, an AIS framework, with a Transformer-based mask head. AISFormer explicitly models the complex coherence between occluder, visible, amodal, and invisible masks within an object's regions of interest by treating them as learnable queries. Specifically, AISFormer contains four modules: (i) feature encoding: extract ROI and learn both short-range and long-range visual features. (ii) mask transformer decoding: generate the occluder, visible, and amodal mask query embeddings by a transformer decoder (iii) invisible mask embedding: model the coherence between the amodal and visible masks, and (iv) mask predicting: estimate output masks including occluder, visible, amodal and invisible. We conduct extensive experiments and ablation studies on three challenging benchmarks i.e. KINS, D2SA, and COCOA-cls to evaluate the effectiveness of AISFormer. The code is available at: https://github.com/UARK-AICV/AISFormer
Authors: Xuanjun Chen, Haibin Wu, Chung-Che Wang, Hung-yi Lee, Jyh-Shing Roger Jang
Abstract: Audio-visual synchronization aims to determine whether the mouth movements and speech in the video are synchronized. VocaLiST reaches state-of-the-art performance by incorporating multimodal Transformers to model audio-visual interact information. However, it requires high computing resources, making it impractical for real-world applications. This paper proposed an MTDVocaLiST model, which is trained by our proposed multimodal Transformer distillation (MTD) loss. MTD loss enables MTDVocaLiST model to deeply mimic the cross-attention distribution and value-relation in the Transformer of VocaLiST. Additionally, we harness uncertainty weighting to fully exploit the interaction information across all layers. Our proposed method is effective in two aspects: From the distillation method perspective, MTD loss outperforms other strong distillation baselines. From the distilled model's performance perspective: 1) MTDVocaLiST outperforms similar-size SOTA models, SyncNet, and Perfect Match models by 15.65% and 3.35%; 2) MTDVocaLiST reduces the model size of VocaLiST by 83.52%, yet still maintaining similar performance.
Authors: Libo Zhang, Wenzhang Zhou, Heng Fan, Tiejian Luo, Haibin Ling
Abstract: Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. However, they neglect the relationship between multiple granularities and different features in alignment, degrading detection. Addressing this, we introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning. The key is to encode the dependencies across different granularities including pixel-, instance-, and category-levels simultaneously to align two domains. Specifically, based on pixel-level features, we first develop an omni-scale gated fusion (OSGF) module to aggregate discriminative representations of instances with scale-aware convolutions, leading to robust multi-scale detection. Besides, we introduce multi-granularity discriminators to identify where, either source or target domains, different granularities of samples come from. Note that, MGA not only leverages instance discriminability in different categories but also exploits category consistency between two domains for detection. Furthermore, we present an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness. Extensive experiments on multiple domain adaption scenarios validate the superiority of MGA over other approaches on FCOS and Faster R-CNN detectors. Code will be released at https://github.com/tiankongzhang/MGA.
Authors: Xinge Yang, Qiang Fu, Wolfgang Heidrich
Abstract: Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective. However, it has been limited to either simple optical systems consisting of a single element such as a diffractive optical element (DOE) or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a DeepLens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces without human intervention, therefore overcoming the need for a good initial design. We demonstrate the effectiveness of our approach by fully automatically designing both classical imaging lenses and a large field-of-view extended depth-of-field computational lens in a cellphone-style form factor, with highly aspheric surfaces and a short back focal length.
Authors: Tiago Cortinhal, Eren Erdal Aksoy
Abstract: This work presents a new depth- and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation in a multi-modal setup between LiDAR and camera sensors. The proposed model leverages scene semantics as a mid-level representation and is able to translate raw LiDAR point clouds to RGB-D camera images by solely relying on semantic scene segments. We claim that this is the first framework of its kind and it has practical applications in autonomous vehicles such as providing a fail-safe mechanism and augmenting available data in the target image domain. The proposed model is evaluated on the large-scale and challenging Semantic-KITTI dataset, and experimental findings show that it considerably outperforms the original TITAN-Net and other strong baselines by 23.7$\%$ margin in terms of IoU.
Authors: Xinyu Huang, Youcai Zhang, Jinyu Ma, Weiwei Tian, Rui Feng, Yuejie Zhang, Yaqian Li, Yandong Guo, Lei Zhang
Abstract: This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features. In contrast to prior works which utilize object tags either manually labeled or automatically detected with an off-the-shelf detector with limited performance, our approach explicitly learns an image tagger using tags parsed from image-paired text and thus provides a strong semantic guidance to vision-language models. In this way, Tag2Text can utilize large-scale annotation-free image tags in accordance with image-text pairs, and provides more diverse tag categories beyond objects. As a result, Tag2Text demonstrates the ability of a foundational image tagging model, with superior zero-shot performance even comparable to fully supervised models. Moreover, by leveraging the tagging guidance, Tag2Text effectively enhances the performance of vision-language models on both generation-based and alignment-based tasks. Across a wide range of downstream benchmarks, Tag2Text achieves state-of-the-art results with similar model sizes and data scales, demonstrating the efficacy of the proposed tagging guidance. Code, demo and pre-trained models are available at https://github.com/xinyu1205/recognize-anything.
Authors: Zhipeng Luo, Gongjie Zhang, Changqing Zhou, Zhonghua Wu, Qingyi Tao, Lewei Lu, Shijian Lu
Abstract: The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling within only two successive frames, thereby overlooking the long-range continuous motion property of objects in 3D space. To address this issue, this paper presents a novel approach that views each tracklet as a continuous stream: at each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank, enabling efficient exploitation of sequential information. To achieve effective cross-frame message passing, a hybrid attention mechanism is designed to account for both long-range relation modeling and local geometric feature extraction. Furthermore, to enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed, which uses ground truth tracklets to augment training sequences and promote discrimination against false positives in a contrastive manner. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art method by significant margins on multiple benchmarks.
Authors: Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo A. Vargas Hakim, David Osowiechi, Ismail Ben Ayed, Christian Desrosiers
Abstract: Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such models that the source and target data come from the same i.i.d. distribution. Recently, Vision Transformers (ViTs) have shown outstanding performance for a broad range of computer vision tasks. However, very few studies have investigated their ability to generalize to new domains. This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains. Our approach transforms token features by mixing the normalization statistics of images from different domains. We further improve this approach with a novel strategy for attention-aware stylization, which uses the attention maps of class (CLS) tokens to compute and mix normalization statistics of tokens corresponding to different image regions. The proposed method is flexible to the choice of backbone model and can be easily applied to any ViT-based architecture with a negligible increase in computational complexity. Comprehensive experiments show that our approach is able to achieve state-of-the-art performance on five challenging benchmarks for domain generalization, and demonstrate its ability to deal with different types of domain shifts. The implementation is available at: https://github.com/Mehrdad-Noori/TFS-ViT_Token-level_Feature_Stylization.
URLs: https://github.com/Mehrdad-Noori/TFS-ViT_Token-level_Feature_Stylization.
Authors: Yuwei Sun, Hideya Ochiai, Jun Sakuma
Abstract: Trojan attacks embed perturbations in input data leading to malicious behavior in neural network models. A combination of various Trojans in different modalities enables an adversary to mount a sophisticated attack on multimodal learning such as Visual Question Answering (VQA). However, multimodal Trojans in conventional methods are susceptible to parameter adjustment during processes such as fine-tuning. To this end, we propose an instance-level multimodal Trojan attack on VQA that efficiently adapts to fine-tuned models through a dual-modality adversarial learning method. This method compromises two specific neurons in a specific perturbation layer in the pretrained model to produce overly large neuron activations. Then, a malicious correlation between these overactive neurons and the malicious output of a fine-tuned model is established through adversarial learning. Extensive experiments are conducted using the VQA-v2 dataset, based on a wide range of metrics including sample efficiency, stealthiness, and robustness. The proposed attack demonstrates enhanced performance with diverse vision and text Trojans tailored for each sample. We demonstrate that the proposed attack can be efficiently adapted to different fine-tuned models, by injecting only a few shots of Trojan samples. Moreover, we investigate the attack performance under conventional defenses, where the defenses cannot effectively mitigate the attack.
Authors: Francesco Ragusa, Giovanni Maria Farinella, Antonino Furnari
Abstract: Anticipation problem has been studied considering different aspects such as predicting humans' locations, predicting hands and objects trajectories, and forecasting actions and human-object interactions. In this paper, we studied the short-term object interaction anticipation problem from the egocentric point of view, proposing a new end-to-end architecture named StillFast. Our approach simultaneously processes a still image and a video detecting and localizing next-active objects, predicting the verb which describes the future interaction and determining when the interaction will start. Experiments on the large-scale egocentric dataset EGO4D show that our method outperformed state-of-the-art approaches on the considered task. Our method is ranked first in the public leaderboard of the EGO4D short term object interaction anticipation challenge 2022. Please see the project web page for code and additional details: https://iplab.dmi.unict.it/stillfast/.
Authors: Pedro Conde, Tiago Barros, Rui L. Lopes, Cristiano Premebida, Urbano J. Nunes
Abstract: With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models. This requires a thorough look not only at the accuracy of such systems, but also at their predictive uncertainty. Hence, we propose a novel technique (with two different variations, named M-ATTA and V-ATTA) based on test time augmentation, to improve the uncertainty calibration of deep models for image classification. By leveraging na adaptive weighting system, M/V-ATTA improves uncertainty calibration without affecting the model's accuracy. The performance of these techniques is evaluated by considering diverse metrics related to uncertainty calibration, demonstrating their robustness. Empirical results, obtained on CIFAR-10, CIFAR-100, Aerial Image Dataset, as well as in two different scenarios under distribution-shift, indicate that the proposed methods outperform several state-of-the-art post-hoc calibration techniques. Furthermore, the methods proposed also show improvements in terms of predictive entropy on out-of-distribution samples. Code for M/V-ATTA available at: https://github.com/pedrormconde/MV-ATTA
Authors: Tomas Jakab, Ruining Li, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
Abstract: We present Farm3D, a method for learning category-specific 3D reconstructors for articulated objects, relying solely on "free" virtual supervision from a pre-trained 2D diffusion-based image generator. Recent approaches can learn a monocular network that predicts the 3D shape, albedo, illumination, and viewpoint of any object occurrence, given a collection of single-view images of an object category. However, these approaches heavily rely on manually curated clean training data, which are expensive to obtain. We propose a framework that uses an image generator, such as Stable Diffusion, to generate synthetic training data that are sufficiently clean and do not require further manual curation, enabling the learning of such a reconstruction network from scratch. Additionally, we incorporate the diffusion model as a score to enhance the learning process. The idea involves randomizing certain aspects of the reconstruction, such as viewpoint and illumination, generating virtual views of the reconstructed 3D object, and allowing the 2D network to assess the quality of the resulting image, thus providing feedback to the reconstructor. Unlike work based on distillation, which produces a single 3D asset for each textual prompt, our approach yields a monocular reconstruction network capable of outputting a controllable 3D asset from any given image, whether real or generated, in a single forward pass in a matter of seconds. Our network can be used for analysis, including monocular reconstruction, or for synthesis, generating articulated assets for real-time applications such as video games.
Authors: Haian Jin, Isabella Liu, Peijia Xu, Xiaoshuai Zhang, Songfang Han, Sai Bi, Xiaowei Zhou, Zexiang Xu, Hao Su
Abstract: We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields. Unlike previous works that use purely MLP-based neural fields, thus suffering from low capacity and high computation costs, we extend TensoRF, a state-of-the-art approach for radiance field modeling, to estimate scene geometry, surface reflectance, and environment illumination from multi-view images captured under unknown lighting conditions. Our approach jointly achieves radiance field reconstruction and physically-based model estimation, leading to photo-realistic novel view synthesis and relighting results. Benefiting from the efficiency and extensibility of the TensoRF-based representation, our method can accurately model secondary shading effects (like shadows and indirect lighting) and generally support input images captured under single or multiple unknown lighting conditions. The low-rank tensor representation allows us to not only achieve fast and compact reconstruction but also better exploit shared information under an arbitrary number of capturing lighting conditions. We demonstrate the superiority of our method to baseline methods qualitatively and quantitatively on various challenging synthetic and real-world scenes.
Authors: Suhyeon Lee, Won Jun Kim, Jinho Chang, Jong Chul Ye
Abstract: Following the impressive development of LLMs, vision-language alignment in LLMs is actively being researched to enable multimodal reasoning and visual IO. This direction of research is particularly relevant to medical imaging because medical image analysis and generation consist of reasoning based on a combination of visual features and prior knowledge. Many recent works have focused on training adapter networks that serve as an information bridge between image processing networks and LLMs; but presumably, in order to achieve maximum reasoning potential of LLMs on visual information as well, visual and language features should be allowed to interact more freely. This is especially important in the medical domain because understanding and generating medical images such as chest X-rays (CXR) require not only accurate visual and language-based reasoning but also a more intimate mapping between the two modalities. Thus, taking inspiration from previous work on the transformer and VQ-GAN combination for bidirectional image and text generation, we build upon this approach and develop a method for instruction-tuning an LLM pre-trained only on text to gain vision-language capabilities for medical images. Specifically, we leverage a pretrained LLM's existing question-answering and instruction-following abilities to teach it to understand visual inputs by instructing it to answer questions about image inputs and, symmetrically, output both text and image responses appropriate to a given query by tuning the LLM with diverse tasks that encompass image-based text-generation and text-based image-generation. We show that our model, LLM-CXR, trained in this approach shows better image-text alignment in both CXR understanding and generation tasks while being smaller in size compared to previously developed models that perform a narrower range of tasks. The code is at https://github.com/hyn2028/llm-cxr.
Authors: Yuta Mimura
Abstract: Generative models excel in creating realistic images, yet their dependency on extensive datasets for training presents significant challenges, especially in domains where data collection is costly or challenging. Current data-efficient methods largely focus on GAN architectures, leaving a gap in training other types of generative models. Our study introduces "phased data augmentation" as a novel technique that addresses this gap by optimizing training in limited data scenarios without altering the inherent data distribution. By limiting the augmentation intensity throughout the learning phases, our method enhances the model's ability to learn from limited data, thus maintaining fidelity. Applied to a model integrating PixelCNNs with VQ-VAE-2, our approach demonstrates superior performance in both quantitative and qualitative evaluations across diverse datasets. This represents an important step forward in the efficient training of likelihood-based models, extending the usefulness of data augmentation techniques beyond just GANs.
Authors: Amogh Joshi, Adarsh Kosta, Wachirawit Ponghiran, Manish Nagaraj, Kaushik Roy
Abstract: The ability of resource-constrained biological systems such as fruitflies to perform complex and high-speed maneuvers in cluttered environments has been one of the prime sources of inspiration for developing vision-based autonomous systems. To emulate this capability, the perception pipeline of such systems must integrate information cues from tasks including optical flow and depth estimation, object detection and tracking, and segmentation, among others. However, the conventional approach of employing slow, synchronous inputs from standard frame-based cameras constrains these perception capabilities, particularly during high-speed maneuvers. Recently, event-based sensors have emerged as low latency and low energy alternatives to standard frame-based cameras for capturing high-speed motion, effectively speeding up perception and hence navigation. For coherence, all the perception tasks must be trained on the same input data. However, present-day datasets are curated mainly for a single or a handful of tasks and are limited in the rate of the provided ground truths. To address these limitations, we present Flying Event Dataset fOr Reactive behAviour (FEDORA) - a fully synthetic dataset for perception tasks, with raw data from frame-based cameras, event-based cameras, and Inertial Measurement Units (IMU), along with ground truths for depth, pose, and optical flow at a rate much higher than existing datasets.
Authors: Tung Le, Khai Nguyen, Shanlin Sun, Kun Han, Nhat Ho, Xiaohui Xie
Abstract: Mesh deformation plays a pivotal role in many 3D vision tasks including dynamic simulations, rendering, and reconstruction. However, defining an efficient discrepancy between predicted and target meshes remains an open problem. A prevalent approach in current deep learning is the set-based approach which measures the discrepancy between two surfaces by comparing two randomly sampled point-clouds from the two meshes with Chamfer pseudo-distance. Nevertheless, the set-based approach still has limitations such as lacking a theoretical guarantee for choosing the number of points in sampled point-clouds, and the pseudo-metricity and the quadratic complexity of the Chamfer divergence. To address these issues, we propose a novel metric for learning mesh deformation. The metric is defined by sliced Wasserstein distance on meshes represented as probability measures that generalize the set-based approach. By leveraging probability measure space, we gain flexibility in encoding meshes using diverse forms of probability measures, such as continuous, empirical, and discrete measures via varifold representation. After having encoded probability measures, we can compare meshes by using the sliced Wasserstein distance which is an effective optimal transport distance with linear computational complexity and can provide a fast statistical rate for approximating the surface of meshes. To the end, we employ a neural ordinary differential equation (ODE) to deform the input surface into the target shape by modeling the trajectories of the points on the surface. Our experiments on cortical surface reconstruction demonstrate that our approach surpasses other competing methods in multiple datasets and metrics.
Authors: Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, Dacheng Tao
Abstract: End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. In addition, our models are also compatible with line annotations, which require much less annotation cost than polygons. The code is available at \url{https://github.com/ViTAE-Transformer/DeepSolo}.
Authors: Wentao Wu, Aleksei Timofeev, Chen Chen, Bowen Zhang, Kun Duan, Shuangning Liu, Yantao Zheng, Jonathon Shlens, Xianzhi Du, Zhe Gan, Yinfei Yang
Abstract: We present MOFI, Manifold OF Images, a new vision foundation model designed to learn image representations from noisy entity annotated images. MOFI differs from previous work in two key aspects: (i) pre-training data, and (ii) training recipe. Regarding data, we introduce a new approach to automatically assign entity labels to images from noisy image-text pairs. Our approach involves employing a named entity recognition model to extract entities from the alt-text, and then using a CLIP model to select the correct entities as labels of the paired image. It's a simple, cost-effective method that can scale to handle billions of web-mined image-text pairs. Through this method, we have created Image-to-Entities (I2E), a new dataset with 1 billion images and 2 million distinct entities, covering rich visual concepts in the wild. Building upon the I2E dataset, we study different training recipes like supervised pre-training, contrastive pre-training, and multi-task learning. For contrastive pre-training, we treat entity names as free-form text, and further enrich them with entity descriptions. Experiments show that supervised pre-training with large-scale fine-grained entity labels is highly effective for image retrieval tasks, and multi-task training further improves the performance. The final MOFI model achieves 86.66% mAP on the challenging GPR1200 dataset, surpassing the previous state-of-the-art performance of 72.19% from OpenAI's CLIP model. Further experiments on zero-shot and linear probe image classification also show that MOFI outperforms a CLIP model trained on the original image-text data, demonstrating the effectiveness of the I2E dataset in learning strong image representations. We release our code and model weights at https://github.com/apple/ml-mofi.
Authors: Yaqi Zhang, Di Huang, Bin Liu, Shixiang Tang, Yan Lu, Lu Chen, Lei Bai, Qi Chu, Nenghai Yu, Wanli Ouyang
Abstract: Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Visit our webpage at https://qiqiapink.github.io/MotionGPT/.
Authors: Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, Rongrong Ji
Abstract: Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to fully reflect the performance of MLLM, lacking a comprehensive evaluation. In this paper, we fill in this blank, presenting the first comprehensive MLLM Evaluation benchmark MME. It measures both perception and cognition abilities on a total of 14 subtasks. In order to avoid data leakage that may arise from direct use of public datasets for evaluation, the annotations of instruction-answer pairs are all manually designed. The concise instruction design allows us to fairly compare MLLMs, instead of struggling in prompt engineering. Besides, with such an instruction, we can also easily carry out quantitative statistics. A total of 30 advanced MLLMs are comprehensively evaluated on our MME, which not only suggests that existing MLLMs still have a large room for improvement, but also reveals the potential directions for the subsequent model optimization. The data application manner and online leaderboards are released at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation.
URLs: https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation.
Authors: Yanhui Guo, Fangzhou Luo, Xiaolin Wu
Abstract: Image signal processing (ISP) pipeline plays a fundamental role in digital cameras, which converts raw Bayer sensor data to RGB images. However, ISP-generated images usually suffer from imperfections due to the compounded degradations that stem from sensor noises, demosaicing noises, compression artifacts, and possibly adverse effects of erroneous ISP hyperparameter settings such as ISO and gamma values. In a general sense, these ISP imperfections can be considered as degradations. The highly complex mechanisms of ISP degradations, some of which are even unknown, pose great challenges to the generalization capability of deep neural networks (DNN) for image restoration and to their adaptability to downstream tasks. To tackle the issues, we propose a novel DNN approach to learn degradation-independent representations (DiR) through the refinement of a self-supervised learned baseline representation. The proposed DiR learning technique has remarkable domain generalization capability and consequently, it outperforms state-of-the-art methods across various downstream tasks, including blind image restoration, object detection, and instance segmentation, as verified in our experiments.
Authors: Haixing Dai, Chong Ma, Zhiling Yan, Zhengliang Liu, Enze Shi, Yiwei Li, Peng Shu, Xiaozheng Wei, Lin Zhao, Zihao Wu, Fang Zeng, Dajiang Zhu, Wei Liu, Quanzheng Li, Lichao Sun, Shu Zhang Tianming Liu, Xiang Li
Abstract: This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about the user's intention to SAM. Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts. By incorporating these extra points, SAM can generate augmented segmentation masks based on both the augmented point prompts and the initial prompt, resulting in improved segmentation performance. We conducted evaluations using four different point augmentation strategies: random sampling, sampling based on maximum difference entropy, maximum distance, and saliency. Experiment results on the COCO, Fundus, COVID QUEx, and ISIC2018 datasets show that SAMAug can boost SAM's segmentation results, especially using the maximum distance and saliency. SAMAug demonstrates the potential of visual prompt augmentation for computer vision. Codes of SAMAug are available at github.com/yhydhx/SAMAug
Authors: Sen Lu, Abhronil Sengupta
Abstract: Spike-Timing-Dependent Plasticity (STDP) is an unsupervised learning mechanism for Spiking Neural Networks (SNNs) that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve $24.56\%$ higher accuracy and $3.5\times$ faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a $k$-means clustering approach.
Authors: Ranjan Sapkota, Dawood Ahmed, Manoj Karkee
Abstract: This research investigated the role of artificial intelligence (AI), specifically the DALL.E model by OpenAI, in advancing data generation and visualization techniques in agriculture. DALL.E, an advanced AI image generator, works alongside ChatGPT's language processing to transform text descriptions and image clues into realistic visual representations of the content. The study used both approaches of image generation: text-to-image and image-to image (variation). Six types of datasets depicting fruit crop environment were generated. These AI-generated images were then compared against ground truth images captured by sensors in real agricultural fields. The comparison was based on Peak Signal-to-Noise Ratio (PSNR) and Feature Similarity Index (FSIM) metrics. The image-to-image generation exhibited a 5.78% increase in average PSNR over text-to-image methods, signifying superior image clarity and quality. However, this method also resulted in a 10.23% decrease in average FSIM, indicating a diminished structural and textural similarity to the original images. Similar to these measures, human evaluation also showed that images generated using image-to-image-based method were more realistic compared to those generated with text-to-image approach. The results highlighted DALL.E's potential in generating realistic agricultural image datasets and thus accelerating the development and adoption of imaging-based precision agricultural solutions.
Authors: Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang
Abstract: Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better performance is still an open question. This paper draws inspiration from the human visual perception process: when classifying an object, humans first infer contextual attributes (e.g., background and orientation) which help separate the foreground object from the background, and then classify the object based on this information. Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features. We also observe that CLIP itself can reasonably infer the attributes from an image. With these observations, we propose a training-free, two-step zero-shot classification method PerceptionCLIP. Given an image, it first infers contextual attributes (e.g., background) and then performs object classification conditioning on them. Our experiments show that PerceptionCLIP achieves better generalization, group robustness, and interoperability. Our code is available at https://github.com/umd-huang-lab/perceptionCLIP
Authors: Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu, Lin Wang
Abstract: In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular, due to the distinct modality gap with the image-text data and the lack of large-scale datasets, learning a common representation space for images, texts, and events is non-trivial.Intuitively, we need to address two key challenges: 1) how to generalize CLIP's visual encoder to event data while fully leveraging events' unique properties, e.g., sparsity and high temporal resolution; 2) how to effectively align the multi-modal embeddings, i.e., image, text, and events. Accordingly, we first introduce a novel event encoder that subtly models the temporal information from events and meanwhile, generates event prompts for modality bridging. We then design a text encoder that generates content prompts and utilizes hybrid text prompts to enhance EventBind's generalization ability across diverse datasets.With the proposed event encoder, text encoder, and image encoder, a novel Hierarchical Triple Contrastive Alignment (HTCA) module is introduced to jointly optimize the correlation and enable efficient knowledge transfer among the three modalities. We evaluate various settings, including fine-tuning and few-shot on three benchmarks, and our EventBind achieves new state-of-the-art accuracy compared with the previous methods, such as on N-Caltech101 (+5.34% and +1.70%) and N-Imagenet (+5.65% and +1.99%) with fine-tuning and 20-shot settings, respectively. Moreover, our EventBind can be flexibly extended to the event retrieval task using text or image queries, showing plausible performance. Our project code will be made publicly available.
Authors: Melissa Hall, Candace Ross, Adina Williams, Nicolas Carion, Michal Drozdzal, Adriana Romero Soriano
Abstract: The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to understand their potential biases. In this work, we introduce three indicators to evaluate the realism, diversity and prompt-generation consistency of text-to-image generative systems when prompted to generate objects from across the world. Our indicators complement qualitative analysis of the broader impact of such systems by enabling automatic and efficient benchmarking of geographic disparities, an important step towards building responsible visual content creation systems. We use our proposed indicators to analyze potential geographic biases in state-of-the-art visual content creation systems and find that: (1) models have less realism and diversity of generations when prompting for Africa and West Asia than Europe, (2) prompting with geographic information comes at a cost to prompt-consistency and diversity of generated images, and (3) models exhibit more region-level disparities for some objects than others. Perhaps most interestingly, our indicators suggest that progress in image generation quality has come at the cost of real-world geographic representation. Our comprehensive evaluation constitutes a crucial step towards ensuring a positive experience of visual content creation for everyone.
Authors: Xiuwei Chen, Xiaobin Chang
Abstract: Class incremental learning (CIL) aims to recognize both the old and new classes along the increment tasks. Deep neural networks in CIL suffer from catastrophic forgetting and some approaches rely on saving exemplars from previous tasks, known as the exemplar-based setting, to alleviate this problem. On the contrary, this paper focuses on the Exemplar-Free setting with no old class sample preserved. Balancing the plasticity and stability in deep feature learning with only supervision from new classes is more challenging. Most existing Exemplar-Free CIL methods report the overall performance only and lack further analysis. In this work, different methods are examined with complementary metrics in greater detail. Moreover, we propose a simple CIL method, Rotation Augmented Distillation (RAD), which achieves one of the top-tier performances under the Exemplar-Free setting. Detailed analysis shows our RAD benefits from the superior balance between plasticity and stability. Finally, more challenging exemplar-free settings with fewer initial classes are undertaken for further demonstrations and comparisons among the state-of-the-art methods.
Authors: Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, Xiao Yang
Abstract: We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt. Learning from both 2D and 3D data, a multi-view diffusion model can achieve the generalizability of 2D diffusion models and the consistency of 3D renderings. We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods. It can also learn new concepts from a few 2D examples, akin to DreamBooth, but for 3D generation.
Authors: Pedro Conde, Rui L. Lopes, Cristiano Premebida
Abstract: The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains, making the problem of uncertainty calibration pivotal when considering the future of deep learning. This is especially true when considering object detection systems, that are commonly present in safety-critical applications such as autonomous driving, robotics and medical diagnosis. For this reason, this work presents a novel theoretical and practical framework to evaluate object detection systems in the context of uncertainty calibration. This encompasses a new comprehensive formulation of this concept through distinct formal definitions, and also three novel evaluation metrics derived from such theoretical foundation. The robustness of the proposed uncertainty calibration metrics is shown through a series of representative experiments.
Authors: Nicolas Schischka, Hannah Schieber, Mert Asim Karaoglu, Melih G\"org\"ul\"u, Florian Gr\"otzner, Alexander Ladikos, Daniel Roth, Nassir Navab, Benjamin Busam
Abstract: The accurate reconstruction of dynamic scenes with neural radiance fields is significantly dependent on the estimation of camera poses. Widely used structure-from-motion pipelines encounter difficulties in accurately tracking the camera trajectory when faced with separate dynamics of the scene content and the camera movement. To address this challenge, we propose DynaMoN. DynaMoN utilizes semantic segmentation and generic motion masks to handle dynamic content for initial camera pose estimation and statics-focused ray sampling for fast and accurate novel-view synthesis. Our novel iterative learning scheme switches between training the NeRF and updating the pose parameters for an improved reconstruction and trajectory estimation quality. The proposed pipeline shows significant acceleration of the training process. We extensively evaluate our approach on two real-world dynamic datasets, the TUM RGB-D and the BONN RGB-D Dynamic dataset. DynaMoN improves over the state-of-the-art both in terms of reconstruction quality and trajectory accuracy. We plan to make our code public to enhance research in this area.
Authors: Shiwen Zhang, Shuai Xiao, Weilin Huang
Abstract: Text-guided image editing on real or synthetic images, given only the original image itself and the target text prompt as inputs, is a very general and challenging task. It requires an editing model to estimate by itself which part of the image should be edited, and then perform either rigid or non-rigid editing while preserving the characteristics of original image. In this paper, we design a novel text-guided image editing method, named as Forgedit. First, we propose a vision-language joint optimization framework capable of reconstructing the original image in 30 seconds, much faster than previous SOTA and much less overfitting. Then we propose a novel vector projection mechanism in text embedding space of Diffusion Models, which is capable to control the identity similarity and editing strength seperately. Finally, we discovered a general property of UNet in Diffusion Models, i.e., Unet encoder learns space and structure, Unet decoder learns appearance and identity. With such a property, we design forgetting mechanisms to successfully tackle the fatal and inevitable overfitting issues when fine-tuning Diffusion Models on one image, thus significantly boosting the editing capability of Diffusion Models. Our method, Forgedit, built on Stable Diffusion, achieves new state-of-the-art results on the challenging text-guided image editing benchmark: TEdBench, surpassing the previous SOTA methods such as Imagic with Imagen, in terms of both CLIP score and LPIPS score. Codes are available at https://github.com/witcherofresearch/Forgedit
Authors: Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, Li Yi
Abstract: This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DreamLLM operates on two fundamental principles. The first focuses on the generative modeling of both language and image posteriors by direct sampling in the raw multimodal space. This approach circumvents the limitations and information loss inherent to external feature extractors like CLIP, and a more thorough multimodal understanding is obtained. Second, DreamLLM fosters the generation of raw, interleaved documents, modeling both text and image contents, along with unstructured layouts. This allows DreamLLM to learn all conditional, marginal, and joint multimodal distributions effectively. As a result, DreamLLM is the first MLLM capable of generating free-form interleaved content. Comprehensive experiments highlight DreamLLM's superior performance as a zero-shot multimodal generalist, reaping from the enhanced learning synergy. Project page: https://dreamllm.github.io.
Authors: Nakyeong Yang, Minsung Kim, Seunghyun Yoon, Joongbo Shin, Kyomin Jung
Abstract: With the explosion of multimedia content in recent years, Video Corpus Moment Retrieval (VCMR), which aims to detect a video moment that matches a given natural language query from multiple videos, has become a critical problem. However, existing VCMR studies have a significant limitation since they have regarded all videos not paired with a specific query as negative, neglecting the possibility of including false negatives when constructing the negative video set. In this paper, we propose an MVMR (Massive Videos Moment Retrieval) task that aims to localize video frames within a massive video set, mitigating the possibility of falsely distinguishing positive and negative videos. For this task, we suggest an automatic dataset construction framework by employing textual and visual semantic matching evaluation methods on the existing video moment search datasets and introduce three MVMR datasets. To solve MVMR task, we further propose a strong method, CroCs, which employs cross-directional contrastive learning that selectively identifies the reliable and informative negatives, enhancing the robustness of a model on MVMR task. Experimental results on the introduced datasets reveal that existing video moment search models are easily distracted by negative video frames, whereas our model shows significant performance.
Authors: Yulu Gan, Sungwoo Park, Alexander Schubert, Anthony Philippakis, Ahmed M. Alaa
Abstract: Recent advances in generative diffusion models have enabled text-controlled synthesis of realistic and diverse images with impressive quality. Despite these remarkable advances, the application of text-to-image generative models in computer vision for standard visual recognition tasks remains limited. The current de facto approach for these tasks is to design model architectures and loss functions that are tailored to the task at hand. In this paper, we develop a unified language interface for computer vision tasks that abstracts away task-specific design choices and enables task execution by following natural language instructions. Our approach involves casting multiple computer vision tasks as text-to-image generation problems. Here, the text represents an instruction describing the task, and the resulting image is a visually-encoded task output. To train our model, we pool commonly-used computer vision datasets covering a range of tasks, including segmentation, object detection, depth estimation, and classification. We then use a large language model to paraphrase prompt templates that convey the specific tasks to be conducted on each image, and through this process, we create a multi-modal and multi-task training dataset comprising input and output images along with annotated instructions. Following the InstructPix2Pix architecture, we apply instruction-tuning to a text-to-image diffusion model using our constructed dataset, steering its functionality from a generative model to an instruction-guided multi-task vision learner. Experiments demonstrate that our model, dubbed InstructCV, performs competitively compared to other generalist and task-specific vision models. Moreover, it exhibits compelling generalization capabilities to unseen data, categories, and user instructions.
Authors: Kaizhi Zheng, Xuehai He, Xin Eric Wang
Abstract: The effectiveness of Multimodal Large Language Models (MLLMs) demonstrates a profound capability in multimodal understanding. However, the simultaneous generation of images with coherent texts is still underdeveloped. Addressing this, we introduce a novel interleaved vision-and-language generation method, centered around the concept of ``generative vokens". These vokens serve as pivotal elements contributing to coherent image-text outputs. Our method is marked by a unique two-stage training strategy for description-free multimodal generation, which does not necessitate extensive descriptions of images. We integrate classifier-free guidance to enhance the alignment of generated images and texts, ensuring more seamless and contextually relevant multimodal interactions. Our model, MiniGPT-5, exhibits substantial improvement over the baseline models on multimodal generation datasets, including MMDialog and VIST. The human evaluation shows MiniGPT-5 is better than the baseline model on more than 56\% cases for multimodal generation, highlighting its efficacy across diverse benchmarks.
Authors: Zahra Kadkhodaie, Florentin Guth, Eero P. Simoncelli, St\'ephane Mallat
Abstract: Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem to imply an escape from the curse of dimensionality, but recent reports of memorization of the training set raise the question of whether these networks are learning the "true" continuous density of the data. Here, we show that two DNNs trained on non-overlapping subsets of a dataset learn nearly the same score function, and thus the same density, when the number of training images is large enough. In this regime of strong generalization, diffusion-generated images are distinct from the training set, and are of high visual quality, suggesting that the inductive biases of the DNNs are well-aligned with the data density. We analyze the learned denoising functions and show that the inductive biases give rise to a shrinkage operation in a basis adapted to the underlying image. Examination of these bases reveals oscillating harmonic structures along contours and in homogeneous regions. We demonstrate that trained denoisers are inductively biased towards these geometry-adaptive harmonic bases since they arise not only when the network is trained on photographic images, but also when it is trained on image classes supported on low-dimensional manifolds for which the harmonic basis is suboptimal. Finally, we show that when trained on regular image classes for which the optimal basis is known to be geometry-adaptive and harmonic, the denoising performance of the networks is near-optimal.
Authors: Hye Bin Yoo, Hyun Min Han, Sung Soo Hwang, Il Yong Chun
Abstract: Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and sampling is performed around there only. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.
Authors: Jiyuan Wang, Chunyu Lin, Lang Nie, Shujun Huang, Yao Zhao, Xing Pan, Rui Ai
Abstract: Depth estimation models have shown promising performance on clear scenes but fail to generalize to adverse weather conditions due to illumination variations, weather particles, etc. In this paper, we propose WeatherDepth, a self-supervised robust depth estimation model with curriculum contrastive learning, to tackle performance degradation in complex weather conditions. Concretely, we first present a progressive curriculum learning scheme with three simple-to-complex curricula to gradually adapt the model from clear to relative adverse, and then to adverse weather scenes. It encourages the model to gradually grasp beneficial depth cues against the weather effect, yielding smoother and better domain adaption. Meanwhile, to prevent the model from forgetting previous curricula, we integrate contrastive learning into different curricula. By drawing reference knowledge from the previous course, our strategy establishes a depth consistency constraint between different courses toward robust depth estimation in diverse weather. Besides, to reduce manual intervention and better adapt to different models, we designed an adaptive curriculum scheduler to automatically search for the best timing for course switching. In the experiment, the proposed solution is proven to be easily incorporated into various architectures and demonstrates state-of-the-art (SoTA) performance on both synthetic and real weather datasets. Source code and data are available at \url{https://github.com/wangjiyuan9/WeatherDepth}.
Authors: Ziyao Guo, Kai Wang, George Cazenavette, Hui Li, Kaipeng Zhang, Yang You
Abstract: The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset. Until now, no method of Dataset Distillation has reached this completely lossless goal, in part due to the fact that previous methods only remain effective when the total number of synthetic samples is extremely small. Since only so much information can be contained in such a small number of samples, it seems that to achieve truly loss dataset distillation, we must develop a distillation method that remains effective as the size of the synthetic dataset grows. In this work, we present such an algorithm and elucidate why existing methods fail to generate larger, high-quality synthetic sets. Current state-of-the-art methods rely on trajectory-matching, or optimizing the synthetic data to induce similar long-term training dynamics as the real data. We empirically find that the training stage of the trajectories we choose to match (i.e., early or late) greatly affects the effectiveness of the distilled dataset. Specifically, early trajectories (where the teacher network learns easy patterns) work well for a low-cardinality synthetic set since there are fewer examples wherein to distribute the necessary information. Conversely, late trajectories (where the teacher network learns hard patterns) provide better signals for larger synthetic sets since there are now enough samples to represent the necessary complex patterns. Based on our findings, we propose to align the difficulty of the generated patterns with the size of the synthetic dataset. In doing so, we successfully scale trajectory matching-based methods to larger synthetic datasets, achieving lossless dataset distillation for the very first time. Code and distilled datasets are available at https://gzyaftermath.github.io/DATM.
Authors: Ziyang Song, Ruijie Zhu, Chuxin Wang, Jiacheng Deng, Jianfeng He, Tianzhu Zhang
Abstract: Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and tested on standard datasets, overlooking the impact of various adverse conditions prevalent in real-world applications, such as rainy days. As a result, it is commonly observed that these methods struggle to handle these challenging scenarios. To address this issue, we present EC-Depth, a novel self-supervised two-stage framework to achieve a robust depth estimation. In the first stage, we propose depth consistency regularization to propagate reliable supervision from standard to challenging scenes. In the second stage, we adopt the Mean Teacher paradigm and propose a novel consistency-based pseudo-label filtering strategy to improve the quality of pseudo-labels, further improving both the accuracy and robustness of our model. Extensive experiments demonstrate that our method achieves accurate and consistent depth predictions in both standard and challenging scenarios, surpassing existing state-of-the-art methods on KITTI, KITTI-C, DrivingStereo, and NuScenes-Night benchmarks.
Authors: Sangwon Lim, Karim El-Basyouny, Yee Hong Yang
Abstract: While recent advancements in deep-learning point cloud upsampling methods have improved the input to intelligent transportation systems, they still suffer from issues of domain dependency between synthetic and real-scanned point clouds. This paper addresses the above issues by proposing a new ray-based upsampling approach with an arbitrary rate, where a depth prediction is made for each query ray and its corresponding patch. Our novel method simulates the sphere-tracing ray marching algorithm on the neural implicit surface defined with an unsigned distance function (UDF) to achieve more precise and stable ray-depth predictions by training a point-transformer-based network. The rule-based mid-point query sampling method generates more evenly distributed points without requiring an end-to-end model trained using a nearest-neighbor-based reconstruction loss function, which may be biased towards the training dataset. Self-supervised learning becomes possible with accurate ground truths within the input point cloud. The results demonstrate the method's versatility across domains and training scenarios with limited computational resources and training data. Comprehensive analyses of synthetic and real-scanned applications provide empirical evidence for the significance of the upsampling task across the computer vision and graphics domains to real-world applications of ITS.
Authors: Xinhua Cheng, Tianyu Yang, Jianan Wang, Yu Li, Lei Zhang, Jian Zhang, Li Yuan
Abstract: Recent text-to-3D generation methods achieve impressive 3D content creation capacity thanks to the advances in image diffusion models and optimizing strategies. However, current methods struggle to generate correct 3D content for a complex prompt in semantics, i.e., a prompt describing multiple interacted objects binding with different attributes. In this work, we propose a general framework named Progressive3D, which decomposes the entire generation into a series of locally progressive editing steps to create precise 3D content for complex prompts, and we constrain the content change to only occur in regions determined by user-defined region prompts in each editing step. Furthermore, we propose an overlapped semantic component suppression technique to encourage the optimization process to focus more on the semantic differences between prompts. Extensive experiments demonstrate that the proposed Progressive3D framework generates precise 3D content for prompts with complex semantics and is general for various text-to-3D methods driven by different 3D representations.
Authors: Zhen Yang, Ganggui Ding, Wen Wang, Hao Chen, Bohan Zhuang, Chunhua Shen
Abstract: By comparing the original and target prompts, we can obtain numerous editing pairs, each comprising an object and its corresponding editing target. To allow editability while maintaining fidelity to the input image, existing editing methods typically involve a fixed number of inversion steps that project the whole input image to its noisier latent representation, followed by a denoising process guided by the target prompt. However, we find that the optimal number of inversion steps for achieving ideal editing results varies significantly among different editing pairs, owing to varying editing difficulties. Therefore, the current literature, which relies on a fixed number of inversion steps, produces sub-optimal generation quality, especially when handling multiple editing pairs in a natural image. To this end, we propose a new image editing paradigm, dubbed Object-aware Inversion and Reassembly (OIR), to enable object-level fine-grained editing. Specifically, we design a new search metric, which determines the optimal inversion steps for each editing pair, by jointly considering the editability of the target and the fidelity of the non-editing region. We use our search metric to find the optimal inversion step for each editing pair when editing an image. We then edit these editing pairs separately to avoid concept mismatch. Subsequently, we propose an additional reassembly step to seamlessly integrate the respective editing results and the non-editing region to obtain the final edited image. To systematically evaluate the effectiveness of our method, we collect two datasets called OIRBench for benchmarking single- and multi-object editing, respectively. Experiments demonstrate that our method achieves superior performance in editing object shapes, colors, materials, categories, etc., especially in multi-object editing scenarios.
Authors: Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang
Abstract: Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods are trained in a closed-set setting and treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. This paper proposes to learn heterogeneous anomaly distributions using the limited anomaly examples to address this issue. To this end, we introduce a novel approach, namely Anomaly Heterogeneity Learning (AHL), that simulates a diverse set of heterogeneous anomaly distributions and then utilizes them to learn a unified heterogeneous abnormality model in surrogate open-set environments. Further, AHL is a generic framework that existing OSAD models can plug and play for enhancing their abnormality modeling. Extensive experiments on nine real-world anomaly detection datasets show that AHL can 1) substantially enhance different state-of-the-art OSAD models in detecting seen and unseen anomalies, and 2) effectively generalize to unseen anomalies in new domains. Code is available at https://github.com/mala-lab/AHL.
Authors: Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, Dinesh Manocha, Tianyi Zhou
Abstract: We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmark comprises 346 images paired with 1129 questions, all meticulously crafted by human experts. We introduce a novel structure for these visual questions designed to establish control groups. This structure enables us to conduct a quantitative analysis of the models' response tendencies, logical consistency, and various failure modes. In our evaluation on HallusionBench, we benchmarked 15 different models, highlighting a 31.42% question-pair accuracy achieved by the state-of-the-art GPT-4V. Notably, all other evaluated models achieve accuracy below 16%. Moreover, our analysis not only highlights the observed failure modes, including language hallucination and visual illusion, but also deepens an understanding of these pitfalls. Our comprehensive case studies within HallusionBench shed light on the challenges of hallucination and illusion in LVLMs. Based on these insights, we suggest potential pathways for their future improvement. The benchmark and codebase can be accessed at https://github.com/tianyi-lab/HallusionBench.
Authors: Lennart Alexander Van der Goten, Kevin Smith
Abstract: MRI scans provide valuable medical information, however they also contain sensitive and personally identifiable information that needs to be protected. Whereas MRI metadata is easily sanitized, MRI image data is a privacy risk because it contains information to render highly-realistic 3D visualizations of a patient's head, enabling malicious actors to possibly identify the subject by cross-referencing a database. Data anonymization and de-identification is concerned with ensuring the privacy and confidentiality of individuals' personal information. Traditional MRI de-identification methods remove privacy-sensitive parts (e.g. eyes, nose etc.) from a given scan. This comes at the expense of introducing a domain shift that can throw off downstream analyses. In this work, we propose CP-MAE, a model that de-identifies the face by remodeling it (e.g. changing the face) rather than by removing parts using masked autoencoders. CP-MAE outperforms all previous approaches in terms of downstream task performance as well as de-identification. With our method we are able to synthesize high-fidelity scans of resolution up to $256^3$ -- compared to $128^3$ with previous approaches -- which constitutes an eight-fold increase in the number of voxels.
Authors: Niki Maria Foteinopoulou, Ioannis Patras
Abstract: Facial Expression Recognition (FER) is a crucial task in affective computing, but its conventional focus on the seven basic emotions limits its applicability to the complex and expanding emotional spectrum. To address the issue of new and unseen emotions present in dynamic in-the-wild FER, we propose a novel vision-language model that utilises sample-level text descriptions (i.e. captions of the context, expressions or emotional cues) as natural language supervision, aiming to enhance the learning of rich latent representations, for zero-shot classification. To test this, we evaluate using zero-shot classification of the model trained on sample-level descriptions on four popular dynamic FER datasets. Our findings show that this approach yields significant improvements when compared to baseline methods. Specifically, for zero-shot video FER, we outperform CLIP by over 10\% in terms of Weighted Average Recall and 5\% in terms of Unweighted Average Recall on several datasets. Furthermore, we evaluate the representations obtained from the network trained using sample-level descriptions on the downstream task of mental health symptom estimation, achieving performance comparable or superior to state-of-the-art methods and strong agreement with human experts. Namely, we achieve a Pearson's Correlation Coefficient of up to 0.85 on schizophrenia symptom severity estimation, which is comparable to human experts' agreement. The code is publicly available at: https://github.com/NickyFot/EmoCLIP.
Authors: Chengyao Duan, Zhiliu Yang
Abstract: Previous attempts to integrate Neural Radiance Fields (NeRF) into the Simultaneous Localization and Mapping (SLAM) framework either rely on the assumption of static scenes or require the ground truth camera poses, which impedes their application in real-world scenarios. In this paper, we propose a time-varying representation to track and reconstruct the dynamic scenes. Firstly, two processes, tracking process and mapping process, are simultaneously maintained in our framework. For the tracking process, all input images are uniformly sampled, then progressively trained in a self-supervised paradigm. For the mapping process, we leverage motion masks to distinguish dynamic objects from static background, and sample more pixels from dynamic areas. Secondly, the parameter optimization for both processes consists of two stages: the first stage associates time with 3D positions to convert the deformation field to the canonical field. And the second stage associates time with the embeddings of canonical field to obtain colors and Signed Distance Function (SDF). Lastly, we propose a novel keyframe selection strategy based on the overlapping rate. We evaluate our approach on two synthetic datasets and one real-world dataset. And the experiments validate that our method achieves competitive results in both tracking and mapping when compared to existing state-of-the-art NeRF-based methods.
Authors: Zhaoyuan Yang, Zhengyang Yu, Zhiwei Xu, Jaskirat Singh, Jing Zhang, Dylan Campbell, Peter Tu, Richard Hartley
Abstract: We present a diffusion-based image morphing approach with perceptually-uniform sampling (IMPUS) that produces smooth, direct and realistic interpolations given an image pair. The embeddings of two images may lie on distinct conditioned distributions of a latent diffusion model, especially when they have significant semantic difference. To bridge this gap, we interpolate in the locally linear and continuous text embedding space and Gaussian latent space. We first optimize the endpoint text embeddings and then map the images to the latent space using a probability flow ODE. Unlike existing work that takes an indirect morphing path, we show that the model adaptation yields a direct path and suppresses ghosting artifacts in the interpolated images. To achieve this, we propose a heuristic bottleneck constraint based on a novel relative perceptual path diversity score that automatically controls the bottleneck size and balances the diversity along the path with its directness. We also propose a perceptually-uniform sampling technique that enables visually smooth changes between the interpolated images. Extensive experiments validate that our IMPUS can achieve smooth, direct, and realistic image morphing and is adaptable to several other generative tasks.
Authors: Pranav Singh, Raviteja Chukkapalli, Shravan Chaudhari, Luoyao Chen, Mei Chen, Jinqian Pan, Craig Smuda, Jacopo Cirrone
Abstract: Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages the advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, thus simplifying the scaling of machine supervision compared to fully-supervised methods. Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks. Notably, we observed that self-supervised learning significantly surpassed the performance of supervised methods in the classification of all evaluated datasets. Remarkably, the semi-supervised approach demonstrated superior outcomes in segmentation, outperforming fully-supervised methods while using 50% fewer labels across all datasets. In line with our commitment to contributing to the scientific community, we have made the S4MI code openly accessible, allowing for broader application and further development of these methods.
Authors: Yichi Zhang, Shiyao Hu, Sijie Ren, Chen Jiang, Yuan Cheng, Yuan Qi
Abstract: The Segment Anything Model (SAM) has recently emerged as a groundbreaking foundation model for prompt-driven image segmentation tasks. However, both the original SAM and its medical variants require slice-by-slice manual prompting of target structures, which directly increase the burden for applications. Despite attempts of auto-prompting to turn SAM into a fully automatic manner, it still exhibits subpar performance and lacks of reliability especially in the field of medical imaging. In this paper, we propose UR-SAM, an uncertainty rectified SAM framework to enhance the reliability for auto-prompting medical image segmentation. Building upon a localization framework for automatic prompt generation, our method incorporates a prompt augmentation module to obtain a series of input prompts for SAM for uncertainty estimation and an uncertainty-based rectification module to further utilize the distribution of estimated uncertainty to improve the segmentation performance. Extensive experiments on two public 3D medical datasets covering the segmentation of 35 organs demonstrate that without supplementary training or fine-tuning, our method further improves the segmentation performance with up to 10.7 % and 13.8 % in dice similarity coefficient, demonstrating efficiency and broad capabilities for medical image segmentation without manual prompting.
Authors: Delin Qu, Chi Yan, Dong Wang, Jie Yin, Dan Xu, Bin Zhao, Xuelong Li
Abstract: Implicit neural SLAM has achieved remarkable progress recently. Nevertheless, existing methods face significant challenges in non-ideal scenarios, such as motion blur or lighting variation, which often leads to issues like convergence failures, localization drifts, and distorted mapping. To address these challenges, we propose EN-SLAM, the first event-RGBD implicit neural SLAM framework, which effectively leverages the high rate and high dynamic range advantages of event data for tracking and mapping. Specifically, EN-SLAM proposes a differentiable CRF (Camera Response Function) rendering technique to generate distinct RGB and event camera data via a shared radiance field, which is optimized by learning a unified implicit representation with the captured event and RGBD supervision. Moreover, based on the temporal difference property of events, we propose a temporal aggregating optimization strategy for the event joint tracking and global bundle adjustment, capitalizing on the consecutive difference constraints of events, significantly enhancing tracking accuracy and robustness. Finally, we construct the simulated dataset DEV-Indoors and real captured dataset DEV-Reals containing 6 scenes, 17 sequences with practical motion blur and lighting changes for evaluations. Experimental results show that our method outperforms the SOTA methods in both tracking ATE and mapping ACC with a real-time 17 FPS in various challenging environments. Project page: https://delinqu.github.io/EN-SLAM.
Authors: S\'ebastien Henry, John A. Christian
Abstract: This work proposes a non-iterative, scalable, and statistically optimal way to triangulate called \texttt{LOSTU}. Unlike triangulation algorithms that minimize the reprojection ($L_2$) error, LOSTU will still provide the maximum likelihood estimate when there are errors in camera pose or parameters. This generic framework is used to contextualize other triangulation methods like the direct linear transform (DLT) or the midpoint. Synthetic experiments show that LOSTU can be substantially faster than using uncertainty-aware Levenberg-Marquardt (or similar) optimization schemes, while providing results of comparable precision. Finally, LOSTU is implemented in sequential reconstruction in conjunction with uncertainty-aware pose estimation, where it yields better reconstruction metrics.
Authors: Jia Yu, Lichao Zhang, Zijie Chen, Fayu Pan, MiaoMiao Wen, Yuming Yan, Fangsheng Weng, Shuai Zhang, Lili Pan, Zhenzhong Lan
Abstract: The fusion of AI and fashion design has emerged as a promising research area. However, the lack of extensive, interrelated data on clothing and try-on stages has hindered the full potential of AI in this domain. Addressing this, we present the Fashion-Diffusion dataset, a product of multiple years' rigorous effort. This dataset, the first of its kind, comprises over a million high-quality fashion images, paired with detailed text descriptions. Sourced from a diverse range of geographical locations and cultural backgrounds, the dataset encapsulates global fashion trends. The images have been meticulously annotated with fine-grained attributes related to clothing and humans, simplifying the fashion design process into a Text-to-Image (T2I) task. The Fashion-Diffusion dataset not only provides high-quality text-image pairs and diverse human-garment pairs but also serves as a large-scale resource about humans, thereby facilitating research in T2I generation. Moreover, to foster standardization in the T2I-based fashion design field, we propose a new benchmark comprising multiple datasets for evaluating the performance of fashion design models. This work represents a significant leap forward in the realm of AI-driven fashion design, setting a new standard for future research in this field.
Authors: Bowen Fu, Gu Wang, Chenyangguang Zhang, Yan Di, Ziqin Huang, Zhiying Leng, Fabian Manhardt, Xiangyang Ji, Federico Tombari
Abstract: Reconstructing hand-held objects from a single RGB image is a challenging task in computer vision. In contrast to prior works that utilize deterministic modeling paradigms, we employ a point cloud denoising diffusion model to account for the probabilistic nature of this problem. In the core, we introduce centroid-fixed dual-stream conditional diffusion for monocular hand-held object reconstruction (D-SCo), tackling two predominant challenges. First, to avoid the object centroid from deviating, we utilize a novel hand-constrained centroid fixing paradigm, enhancing the stability of diffusion and reverse processes and the precision of feature projection. Second, we introduce a dual-stream denoiser to semantically and geometrically model hand-object interactions with a novel unified hand-object semantic embedding, enhancing the reconstruction performance of the hand-occluded region of the object. Experiments on the synthetic ObMan dataset and three real-world datasets HO3D, MOW and DexYCB demonstrate that our approach can surpass all other state-of-the-art methods. Codes will be released.
Authors: Ziqing Wang, Yuetong Fang, Jiahang Cao, Renjing Xu
Abstract: Spiking Neural Networks (SNNs) have emerged as a promising energy-efficient alternative to traditional Artificial Neural Networks (ANNs). Despite this, bridging the performance gap with ANNs in practical scenarios remains a significant challenge. This paper focuses on addressing the dual objectives of enhancing the performance and efficiency of SNNs through the established SNN Calibration conversion framework. Inspired by the biological nervous system, we propose a novel Adaptive-Firing Neuron Model (AdaFire) that dynamically adjusts firing patterns across different layers, substantially reducing conversion errors within limited timesteps. Moreover, to meet our efficiency objectives, we propose two novel strategies: an Sensitivity Spike Compression (SSC) technique and an Input-aware Adaptive Timesteps (IAT) technique. These techniques synergistically reduce both energy consumption and latency during the conversion process, thereby enhancing the overall efficiency of SNNs. Extensive experiments demonstrate our approach outperforms state-of-the-art SNNs methods, showcasing superior performance and efficiency in 2D, 3D, and event-driven classification, as well as object detection and segmentation tasks.
Authors: Shivam Aggarwal, Kuluhan Binici, Tulika Mitra
Abstract: Machine learning pipelines for classification tasks often train a universal model to achieve accuracy across a broad range of classes. However, a typical user encounters only a limited selection of classes regularly. This disparity provides an opportunity to enhance computational efficiency by tailoring models to focus on user-specific classes. Existing works rely on unstructured pruning, which introduces randomly distributed non-zero values in the model, making it unsuitable for hardware acceleration. Alternatively, some approaches employ structured pruning, such as channel pruning, but these tend to provide only minimal compression and may lead to reduced model accuracy. In this work, we propose CRISP, a novel pruning framework leveraging a hybrid structured sparsity pattern that combines both fine-grained N:M structured sparsity and coarse-grained block sparsity. Our pruning strategy is guided by a gradient-based class-aware saliency score, allowing us to retain weights crucial for user-specific classes. CRISP achieves high accuracy with minimal memory consumption for popular models like ResNet-50, VGG-16, and MobileNetV2 on ImageNet and CIFAR-100 datasets. Moreover, CRISP delivers up to 14$\times$ reduction in latency and energy consumption compared to existing pruning methods while maintaining comparable accuracy. Our code is available at https://github.com/shivmgg/CRISP/.
Authors: Yuxuan Xiao, Yao Li, Chengzhen Meng, Xingchen Li, Jianmin Ji, Yanyong Zhang
Abstract: The fusion of LiDARs and cameras has been increasingly adopted in autonomous driving for perception tasks. The performance of such fusion-based algorithms largely depends on the accuracy of sensor calibration, which is challenging due to the difficulty of identifying common features across different data modalities. Previously, many calibration methods involved specific targets and/or manual intervention, which has proven to be cumbersome and costly. Learning-based online calibration methods have been proposed, but their performance is barely satisfactory in most cases. These methods usually suffer from issues such as sparse feature maps, unreliable cross-modality association, inaccurate calibration parameter regression, etc. In this paper, to address these issues, we propose CalibFormer, an end-to-end network for automatic LiDAR-camera calibration. We aggregate multiple layers of camera and LiDAR image features to achieve high-resolution representations. A multi-head correlation module is utilized to identify correlations between features more accurately. Lastly, we employ transformer architectures to estimate accurate calibration parameters from the correlation information. Our method achieved a mean translation error of $0.8751 \mathrm{cm}$ and a mean rotation error of $0.0562 ^{\circ}$ on the KITTI dataset, surpassing existing state-of-the-art methods and demonstrating strong robustness, accuracy, and generalization capabilities.
Authors: Xiaohan Ding, Yiyuan Zhang, Yixiao Ge, Sijie Zhao, Lin Song, Xiangyu Yue, Ying Shan
Abstract: Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or transformers, while the architectural design for large-kernel ConvNets remains under-addressed. 2) As transformers have dominated multiple modalities, it remains to be investigated whether ConvNets also have a strong universal perception ability in domains beyond vision. In this paper, we contribute from two aspects. 1) We propose four architectural guidelines for designing large-kernel ConvNets, the core of which is to exploit the essential characteristics of large kernels that distinguish them from small kernels - they can see wide without going deep. Following such guidelines, our proposed large-kernel ConvNet shows leading performance in image recognition (ImageNet accuracy of 88.0%, ADE20K mIoU of 55.6%, and COCO box AP of 56.4%), demonstrating better performance and higher speed than the recent powerful competitors. 2) We discover large kernels are the key to unlocking the exceptional performance of ConvNets in domains where they were originally not proficient. With certain modality-related preprocessing approaches, the proposed model achieves state-of-the-art performance on time-series forecasting and audio recognition tasks even without modality-specific customization to the architecture. All the code and models are publicly available on GitHub and Huggingface.
Authors: Zongwei Wu, Jilai Zheng, Xiangxuan Ren, Florin-Alexandru Vasluianu, Chao Ma, Danda Pani Paudel, Luc Van Gool, Radu Timofte
Abstract: In the realm of video object tracking, auxiliary modalities such as depth, thermal, or event data have emerged as valuable assets to complement the RGB trackers. In practice, most existing RGB trackers learn a single set of parameters to use them across datasets and applications. However, a similar single-model unification for multi-modality tracking presents several challenges. These challenges stem from the inherent heterogeneity of inputs -- each with modality-specific representations, the scarcity of multi-modal datasets, and the absence of all the modalities at all times. In this work, we introduce Un-Track, a Unified Tracker of a single set of parameters for any modality. To handle any modality, our method learns their common latent space through low-rank factorization and reconstruction techniques. More importantly, we use only the RGB-X pairs to learn the common latent space. This unique shared representation seamlessly binds all modalities together, enabling effective unification and accommodating any missing modality, all within a single transformer-based architecture. Our Un-Track achieves +8.1 absolute F-score gain, on the DepthTrack dataset, by introducing only +2.14 (over 21.50) GFLOPs with +6.6M (over 93M) parameters, through a simple yet efficient prompting strategy. Extensive comparisons on five benchmark datasets with different modalities show that Un-Track surpasses both SOTA unified trackers and modality-specific counterparts, validating our effectiveness and practicality. The source code is publicly available at https://github.com/Zongwei97/UnTrack.
Authors: Shitong Shao, Zeyuan Yin, Muxin Zhou, Xindong Zhang, Zhiqiang Shen
Abstract: The lightweight "local-match-global" matching introduced by SRe2L successfully creates a distilled dataset with comprehensive information on the full 224x224 ImageNet-1k. However, this one-sided approach is limited to a particular backbone, layer, and statistics, which limits the improvement of the generalization of a distilled dataset. We suggest that sufficient and various "local-match-global" matching are more precise and effective than a single one and has the ability to create a distilled dataset with richer information and better generalization. We call this perspective "generalized matching" and propose Generalized Various Backbone and Statistical Matching (G-VBSM) in this work, which aims to create a synthetic dataset with densities, ensuring consistency with the complete dataset across various backbones, layers, and statistics. As experimentally demonstrated, G-VBSM is the first algorithm to obtain strong performance across both small-scale and large-scale datasets. Specifically, G-VBSM achieves a performance of 38.7% on CIFAR-100 with 128-width ConvNet, 47.6% on Tiny-ImageNet with ResNet18, and 31.4% on the full 224x224 ImageNet-1k with ResNet18, under images per class (IPC) 10, 50, and 10, respectively. These results surpass all SOTA methods by margins of 3.9%, 6.5%, and 10.1%, respectively.
Authors: Haoyang Liu, Yijiang Li, Tiancheng Xing, Vibhu Dalal, Luwei Li, Jingrui He, Haohan Wang
Abstract: Dataset Distillation (DD) emerges as a powerful strategy to encapsulate the expansive information of large datasets into significantly smaller, synthetic equivalents, thereby preserving model performance with reduced computational overhead. Pursuing this objective, we introduce the Wasserstein distance, a metric grounded in optimal transport theory, to enhance distribution matching in DD. Our approach employs the Wasserstein barycenter to provide a geometrically meaningful method for quantifying distribution differences and capturing the centroid of distribution sets efficiently. By embedding synthetic data in the feature spaces of pretrained classification models, we facilitate effective distribution matching that leverages prior knowledge inherent in these models. Our method not only maintains the computational advantages of distribution matching-based techniques but also achieves new state-of-the-art performance across a range of high-resolution datasets. Extensive testing demonstrates the effectiveness and adaptability of our method, underscoring the untapped potential of Wasserstein metrics in dataset distillation.
Authors: Ping Chen, Xingpeng Zhang, Chengtao Zhou, Dichao Fan, Peng Tu, Le Zhang, Yanlin Qian
Abstract: Convolution neural network is successful in pervasive vision tasks, including label distribution learning, which usually takes the form of learning an injection from the non-linear visual features to the well-defined labels. However, how the discrepancy between features is mapped to the label discrepancy is ambient, and its correctness is not guaranteed.To address these problems, we study the mathematical connection between feature and its label, presenting a general and simple framework for label distribution learning. We propose a so-called Triangular Distribution Transform (TDT) to build an injective function between feature and label, guaranteeing that any symmetric feature discrepancy linearly reflects the difference between labels. The proposed TDT can be used as a plug-in in mainstream backbone networks to address different label distribution learning tasks. Experiments on Facial Age Recognition, Illumination Chromaticity Estimation, and Aesthetics assessment show that TDT achieves on-par or better results than the prior arts.
Authors: Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Tao Gong, Bin Liu, Shengwei Xu, Nenghai Yu
Abstract: The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline.Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.
Authors: Zheng Lian, Licai Sun, Haiyang Sun, Kang Chen, Zhuofan Wen, Hao Gu, Bin Liu, Jianhua Tao
Abstract: Recently, GPT-4 with Vision (GPT-4V) has demonstrated remarkable visual capabilities across various tasks, but its performance in emotion recognition has not been fully evaluated. To bridge this gap, we present the quantitative evaluation results of GPT-4V on 21 benchmark datasets covering 6 tasks: visual sentiment analysis, tweet sentiment analysis, micro-expression recognition, facial emotion recognition, dynamic facial emotion recognition, and multimodal emotion recognition. This paper collectively refers to these tasks as ``Generalized Emotion Recognition (GER)''. Through experimental analysis, we observe that GPT-4V exhibits strong visual understanding capabilities in GER tasks. Meanwhile, GPT-4V shows the ability to integrate multimodal clues and exploit temporal information, which is also critical for emotion recognition. However, it's worth noting that GPT-4V is primarily designed for general domains and cannot recognize micro-expressions that require specialized knowledge. To the best of our knowledge, this paper provides the first quantitative assessment of GPT-4V for GER tasks. We have open-sourced the code and encourage subsequent researchers to broaden the evaluation scope by including more tasks and datasets. Our code and evaluation results are available at: https://github.com/zeroQiaoba/gpt4v-emotion.
Authors: Yikai Wang, Chenjie Cao, Ke Fan Xiangyang Xue Yanwei Fu
Abstract: Recent progress in inpainting increasingly relies on generative models, leveraging their strong generation capabilities for addressing large irregular masks. However, this enhanced generation often introduces context-instability, leading to arbitrary object generation within masked regions. This paper proposes a balanced solution, emphasizing the importance of unmasked regions in guiding inpainting while preserving generation capacity. Our approach, Aligned Stable Inpainting with UnKnown Areas Prior (ASUKA), employs a Masked Auto-Encoder (MAE) to produce reconstruction-based prior. Aligned with the powerful Stable Diffusion inpainting model (SD), ASUKA significantly improves context stability. ASUKA further adopts an inpainting-specialized decoder, highly reducing the color inconsistency issue of SD and thus ensuring more visual-consistent inpainting. We validate effectiveness of inpainting algorithms on benchmark dataset Places 2 and a collection of several existing datasets, dubbed MISATO, across diverse domains and masking scenarios. Results on these benchmark datasets confirm ASUKA's efficacy in both context-stability and visual-consistency compared to SD and other inpainting algorithms.
Authors: Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang
Abstract: Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing conventional pruning techniques can remarkably reduce data requirements but would suffer from a degradation in performance. To address this challenging trade-off, we introduce SlimSAM, a novel data-efficient SAM compression method that achieves superior performance with extremely less training data. The essence of SlimSAM is encapsulated in the alternate slimming framework which effectively enhances knowledge inheritance under severely limited training data availability and exceptional pruning ratio. Diverging from prior techniques, our framework progressively compresses the model by alternately pruning and distilling distinct, decoupled sub-structures. Disturbed Taylor pruning is also proposed to address the misalignment between the pruning objective and training target, thereby boosting the post-distillation after pruning. SlimSAM yields significant performance improvements while demanding over 10 times less training data than any other existing compression methods. Even when compared to the original SAM, SlimSAM achieves approaching performance while reducing parameter counts to merely 1.4% (9.1M), MACs to 0.8% (23G), and requiring only 0.1% (10k) of the SAM training data. The code is available at http://github.com/czg1225/SlimSAM.
Authors: Rongkun Zheng, Lu Qi, Xi Chen, Yi Wang, Kun Wang, Yu Qiao, Hengshuang Zhao
Abstract: Training on large-scale datasets can boost the performance of video instance segmentation while the annotated datasets for VIS are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggregation of datasets to enhance data volume and diversity. However, due to the heterogeneity in category space, as mask precision increases with the data volume, simply utilizing multiple datasets will dilute the attention of models on different taxonomies. Thus, increasing the data scale and enriching taxonomy space while improving classification precision is important. In this work, we analyze that providing extra taxonomy information can help models concentrate on specific taxonomy, and propose our model named Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation (TMT-VIS) to address this vital challenge. Specifically, we design a two-stage taxonomy aggregation module that first compiles taxonomy information from input videos and then aggregates these taxonomy priors into instance queries before the transformer decoder. We conduct extensive experimental evaluations on four popular and challenging benchmarks, including YouTube-VIS 2019, YouTube-VIS 2021, OVIS, and UVO. Our model shows significant improvement over the baseline solutions, and sets new state-of-the-art records on all benchmarks. These appealing and encouraging results demonstrate the effectiveness and generality of our approach. The code is available at https://github.com/rkzheng99/TMT-VIS .
Authors: Zehuan Huang, Hao Wen, Junting Dong, Yaohui Wang, Yangguang Li, Xinyuan Chen, Yan-Pei Cao, Ding Liang, Yu Qiao, Bo Dai, Lu Sheng
Abstract: Generating multiview images from a single view facilitates the rapid generation of a 3D mesh conditioned on a single image. Recent methods that introduce 3D global representation into diffusion models have shown the potential to generate consistent multiviews, but they have reduced generation speed and face challenges in maintaining generalizability and quality. To address this issue, we propose EpiDiff, a localized interactive multiview diffusion model. At the core of the proposed approach is to insert a lightweight epipolar attention block into the frozen diffusion model, leveraging epipolar constraints to enable cross-view interaction among feature maps of neighboring views. The newly initialized 3D modeling module preserves the original feature distribution of the diffusion model, exhibiting compatibility with a variety of base diffusion models. Experiments show that EpiDiff generates 16 multiview images in just 12 seconds, and it surpasses previous methods in quality evaluation metrics, including PSNR, SSIM and LPIPS. Additionally, EpiDiff can generate a more diverse distribution of views, improving the reconstruction quality from generated multiviews. Please see our project page at https://huanngzh.github.io/EpiDiff/.
Authors: Jingyang Xiang, Siqi Li, Junhao Chen, Zhuangzhi Chen, Tianxin Huang, Linpeng Peng, Yong Liu
Abstract: N:M sparsity has received increasing attention due to its remarkable performance and latency trade-off compared with structured and unstructured sparsity. However, existing N:M sparsity methods do not differentiate the relative importance of weights among blocks and leave important weights underappreciated. Besides, they directly apply N:M sparsity to the whole network, which will cause severe information loss. Thus, they are still sub-optimal. In this paper, we propose an efficient and effective Multi-Axis Query methodology, dubbed as MaxQ, to rectify these problems. During the training, MaxQ employs a dynamic approach to generate soft N:M masks, considering the weight importance across multiple axes. This method enhances the weights with more importance and ensures more effective updates. Meanwhile, a sparsity strategy that gradually increases the percentage of N:M weight blocks is applied, which allows the network to heal from the pruning-induced damage progressively. During the runtime, the N:M soft masks can be precomputed as constants and folded into weights without causing any distortion to the sparse pattern and incurring additional computational overhead. Comprehensive experiments demonstrate that MaxQ achieves consistent improvements across diverse CNN architectures in various computer vision tasks, including image classification, object detection and instance segmentation. For ResNet50 with 1:16 sparse pattern, MaxQ can achieve 74.6\% top-1 accuracy on ImageNet and improve by over 2.8\% over the state-of-the-art. Codes and checkpoints are available at \url{https://github.com/JingyangXiang/MaxQ}.
Authors: Shivangi Aneja, Justus Thies, Angela Dai, Matthias Nie{\ss}ner
Abstract: We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from input audio signal. To capture the expressive, detailed nature of human heads, including hair, ears, and finer-scale eye movements, we propose to couple speech signal with the latent space of neural parametric head models to create high-fidelity, temporally coherent motion sequences. We propose a new latent diffusion model for this task, operating in the expression space of neural parametric head models, to synthesize audio-driven realistic head sequences. In the absence of a dataset with corresponding NPHM expressions to audio, we optimize for these correspondences to produce a dataset of temporally-optimized NPHM expressions fit to audio-video recordings of people talking. To the best of our knowledge, this is the first work to propose a generative approach for realistic and high-quality motion synthesis of volumetric human heads, representing a significant advancement in the field of audio-driven 3D animation. Notably, our approach stands out in its ability to generate plausible motion sequences that can produce high-fidelity head animation coupled with the NPHM shape space. Our experimental results substantiate the effectiveness of FaceTalk, consistently achieving superior and visually natural motion, encompassing diverse facial expressions and styles, outperforming existing methods by 75% in perceptual user study evaluation.
Authors: Rongsheng Wang, Qingsong Yao, Haoran Lai, Zhiyang He, Xiaodong Tao, Zihang Jiang, S. Kevin Zhou
Abstract: Despite significant advancements in medical vision-language pre-training, existing methods have largely overlooked the inherent entity-specific context within radiology reports and the complex cross-modality contextual relationships between text and images. To close this gap, we propose a novel Entity-centered Context-aware Medical Vision-language Pre-training (ECAMP) framework, which is designed to enable a more entity-centered and context-sensitive interpretation of medical data. Utilizing the recent powerful large language model, we distill entity-centered context from medical reports, which enables ECAMP to gain more effective supervision from the text modality. By further pre-training our model with carefully designed entity-aware, context-enhanced masked language modeling and context-guided super-resolution tasks, ECAMP significantly refines the interplay between text and image modalities, leading to an enhanced ability to extract entity-centered contextual features. Besides, our proposed multi-scale context fusion design also improves the semantic integration of both coarse and fine-level image representations, prompting better performance for multi-scale downstream applications. Combining these components leads to significant performance leaps over current state-of-the-art methods and establishes a new standard for cross-modality learning in medical imaging, whose effectiveness is demonstrated by our extensive experiments on various tasks including classification, segmentation, and detection across several public datasets. Code and models are available at https://github.com/ToniChopp/ECAMP.
Authors: Hayk Manukyan, Andranik Sargsyan, Barsegh Atanyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
Abstract: Recent progress in text-guided image inpainting, based on the unprecedented success of text-to-image diffusion models, has led to exceptionally realistic and visually plausible results. However, there is still significant potential for improvement in current text-to-image inpainting models, particularly in better aligning the inpainted area with user prompts and performing high-resolution inpainting. Therefore, we introduce HD-Painter, a training free approach that accurately follows prompts and coherently scales to high resolution image inpainting. To this end, we design the Prompt-Aware Introverted Attention (PAIntA) layer enhancing self-attention scores by prompt information resulting in better text aligned generations. To further improve the prompt coherence we introduce the Reweighting Attention Score Guidance (RASG) mechanism seamlessly integrating a post-hoc sampling strategy into the general form of DDIM to prevent out-of-distribution latent shifts. Moreover, HD-Painter allows extension to larger scales by introducing a specialized super-resolution technique customized for inpainting, enabling the completion of missing regions in images of up to 2K resolution. Our experiments demonstrate that HD-Painter surpasses existing state-of-the-art approaches quantitatively and qualitatively across multiple metrics and a user study. Code is publicly available at: https://github.com/Picsart-AI-Research/HD-Painter
Authors: Xiaoxu Chen, Jingfan Tan, Tao Wang, Kaihao Zhang, Wenhan Luo, Xiaochun Cao
Abstract: Blind face restoration is an important task in computer vision and has gained significant attention due to its wide-range applications. Previous works mainly exploit facial priors to restore face images and have demonstrated high-quality results. However, generating faithful facial details remains a challenging problem due to the limited prior knowledge obtained from finite data. In this work, we delve into the potential of leveraging the pretrained Stable Diffusion for blind face restoration. We propose BFRffusion which is thoughtfully designed to effectively extract features from low-quality face images and could restore realistic and faithful facial details with the generative prior of the pretrained Stable Diffusion. In addition, we build a privacy-preserving face dataset called PFHQ with balanced attributes like race, gender, and age. This dataset can serve as a viable alternative for training blind face restoration networks, effectively addressing privacy and bias concerns usually associated with the real face datasets. Through an extensive series of experiments, we demonstrate that our BFRffusion achieves state-of-the-art performance on both synthetic and real-world public testing datasets for blind face restoration and our PFHQ dataset is an available resource for training blind face restoration networks. The codes, pretrained models, and dataset are released at https://github.com/chenxx89/BFRffusion.
Authors: Ximing Xing, Haitao Zhou, Chuang Wang, Jing Zhang, Dong Xu, Qian Yu
Abstract: Recently, text-guided scalable vector graphics (SVGs) synthesis has shown promise in domains such as iconography and sketch. However, existing text-to-SVG generation methods lack editability and struggle with visual quality and result diversity. To address these limitations, we propose a novel text-guided vector graphics synthesis method called SVGDreamer. SVGDreamer incorporates a semantic-driven image vectorization (SIVE) process that enables the decomposition of synthesis into foreground objects and background, thereby enhancing editability. Specifically, the SIVE process introduce attention-based primitive control and an attention-mask loss function for effective control and manipulation of individual elements. Additionally, we propose a Vectorized Particle-based Score Distillation (VPSD) approach to tackle the challenges of color over-saturation, vector primitives over-smoothing, and limited result diversity in existing text-to-SVG generation methods. Furthermore, on the basis of VPSD, we introduce Reward Feedback Learning (ReFL) to accelerate VPSD convergence and improve aesthetic appeal. Extensive experiments have been conducted to validate the effectiveness of SVGDreamer, demonstrating its superiority over baseline methods in terms of editability, visual quality, and diversity. The code and demo of SVGDreamer can be found at https://ximinng.github.io/SVGDreamer-project/
Authors: Yuyang Yin, Dejia Xu, Zhangyang Wang, Yao Zhao, Yunchao Wei
Abstract: Aided by text-to-image and text-to-video diffusion models, existing 4D content creation pipelines utilize score distillation sampling to optimize the entire dynamic 3D scene. However, as these pipelines generate 4D content from text or image inputs, they incur significant time and effort in prompt engineering through trial and error. This work introduces 4DGen, a novel, holistic framework for grounded 4D content creation that decomposes the 4D generation task into multiple stages. We identify static 3D assets and monocular video sequences as key components in constructing the 4D content. Our pipeline facilitates conditional 4D generation, enabling users to specify geometry (3D assets) and motion (monocular videos), thus offering superior control over content creation. Furthermore, we construct our 4D representation using dynamic 3D Gaussians, which permits efficient, high-resolution supervision through rendering during training, thereby facilitating high-quality 4D generation. Additionally, we employ spatial-temporal pseudo labels on anchor frames, along with seamless consistency priors implemented through 3D-aware score distillation sampling and smoothness regularizations. Compared to existing baselines, our approach yields competitive results in faithfully reconstructing input signals and realistically inferring renderings from novel viewpoints and timesteps. Most importantly, our method supports grounded generation, offering users enhanced control, a feature difficult to achieve with previous methods. Project page: https://vita-group.github.io/4DGen/
Authors: Zhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan, Wangmeng Zuo
Abstract: It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments. Although multi-image processing methods (using burst, dual-exposure, or multi-exposure images) have made significant progress in addressing this issue, they typically focus on specific restoration or enhancement problems, being insufficient in exploiting multi-image. Motivated by that multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution, we propose to utilize exposure bracketing photography to unify restoration and enhancement tasks in this work. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data and then adapts it to real-world unlabeled images. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed. Moreover, we construct a data simulation pipeline to synthesize pairs and collect real-world images from 200 nighttime scenarios. Experiments on both datasets show that our method performs favorably against the state-of-the-art multi-image processing ones. The dataset, code, and pre-trained models are available at https://github.com/cszhilu1998/BracketIRE.
Authors: Hao Yang, Hong-Yu Zhou, Cheng Li, Weijian Huang, Jiarun Liu, Yong Liang, Shanshan Wang
Abstract: Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient annotation information is lacking. Nonetheless, localizing diseases accurately without detailed positional annotations remains a challenge. Although existing methods have attempted to utilize local information to achieve fine-grained semantic alignment, their capability in extracting the fine-grained semantics of the comprehensive context within reports is limited. To address this problem, a new method is introduced that takes full sentences from textual reports as the basic units for local semantic alignment. This approach combines chest X-ray images with their corresponding textual reports, performing contrastive learning at both global and local levels. The leading results obtained by this method on multiple datasets confirm its efficacy in the task of lesion localization.
Authors: Hao Yang, Hong-Yu Zhou, Zhihuan Li, Yuanxu Gao, Cheng Li, Weijian Huang, Jiarun Liu, Hairong Zheng, Kang Zhang, Shanshan Wang
Abstract: Defining pathologies automatically from medical images aids the understanding of the emergence and progression of diseases, and such an ability is crucial in clinical diagnostics. However, existing deep learning models heavily rely on expert annotations and lack generalization capabilities in open clinical environments. In this study, we present a generalizable vision-language pre-training model for Annotation-Free pathological lesions Localization (AFLoc). The core strength of AFLoc lies in its extensive multi-level semantic structure-based contrastive learning, which comprehensively aligns multi-granularity medical concepts from reports with abundant image features, to adapt to the diverse expressions of pathologies and unseen pathologies without the reliance on image annotations from experts. We demonstrate the proof of concept on CXR images, with extensive experimental validation across 4 distinct external datasets, encompassing 11 types of chest pathologies. The results demonstrate that AFLoc surpasses 6 state-of-the-art methods and even outperforms the human benchmark in locating 5 different pathologies. We further verify its generalization ability in retinal fundus image pathological lesions localization. Our approach showcases AFLoc versatilities and underscores its suitability in complex clinical environments.
Authors: Shuhao Chen, Yulong Zhang, Weisen Jiang, Jiangang Lu, Yu Zhang
Abstract: Recent advances achieved by deep learning models rely on the independent and identically distributed assumption, hindering their applications in real-world scenarios with domain shifts. To tackle this issue, cross-domain learning aims at extracting domain-invariant knowledge to reduce the domain shift between training and testing data. However, in visual cross-domain learning, traditional methods concentrate solely on the image modality, disregarding the potential benefits of incorporating the text modality. In this work, we propose VLLaVO, combining Vision language models and Large Language models as Visual cross-dOmain learners. VLLaVO uses vision-language models to convert images into detailed textual descriptions. A large language model is then finetuned on textual descriptions of the source/target domain generated by a designed instruction template. Extensive experimental results under domain generalization and unsupervised domain adaptation settings demonstrate the effectiveness of the proposed method.
Authors: Xiangtao Kong, Chao Dong, Lei Zhang
Abstract: While single task image restoration (IR) has achieved significant successes, it remains a challenging issue to train a single model which can tackle multiple IR tasks. In this work, we investigate in-depth the multiple-in-one (MiO) IR problem, which comprises seven popular IR tasks. We point out that MiO IR faces two pivotal challenges: the optimization of diverse objectives and the adaptation to multiple tasks. To tackle these challenges, we present two simple yet effective strategies. The first strategy, referred to as sequential learning, attempts to address how to optimize the diverse objectives, which guides the network to incrementally learn individual IR tasks in a sequential manner rather than mixing them together. The second strategy, i.e., prompt learning, attempts to address how to adapt to the different IR tasks, which assists the network to understand the specific task and improves the generalization ability. By evaluating on 19 test sets, we demonstrate that the sequential and prompt learning strategies can significantly enhance the MiO performance of commonly used CNN and Transformer backbones. Our experiments also reveal that the two strategies can supplement each other to learn better degradation representations and enhance the model robustness. It is expected that our proposed MiO IR formulation and strategies could facilitate the research on how to train IR models with higher generalization capabilities.
Authors: Peter Lorenz, Ricard Durall, Janis Keuper
Abstract: In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their generative capabilities to encompass various vision applications, such as image inpainting, segmentation, adversarial robustness, among others. This study is dedicated to the investigation of adversarial attacks through the lens of diffusion models. However, our objective does not involve enhancing the adversarial robustness of image classifiers. Instead, our focus lies in utilizing the diffusion model to detect and analyze the anomalies introduced by these attacks on images. To that end, we systematically examine the alignment of the distributions of adversarial examples when subjected to the process of transformation using diffusion models. The efficacy of this approach is assessed across CIFAR-10 and ImageNet datasets, including varying image sizes in the latter. The results demonstrate a notable capacity to discriminate effectively between benign and attacked images, providing compelling evidence that adversarial instances do not align with the learned manifold of the DMs.
Authors: Seok-Hwan Oh, Guil Jung, Myeong-Gee Kim, Sang-Yun Kim, Young-Min Kim, Hyeon-Jik Lee, Hyuk-Sool Kwon, Hyeon-Min Bae
Abstract: In this paper, we introduce a Key-point-guided Diffusion probabilistic Model (KDM) that gains precise control over images by manipulating the object's key-point. We propose a two-stage generative model incorporating an optical flow map as an intermediate output. By doing so, a dense pixel-wise understanding of the semantic relation between the image and sparse key point is configured, leading to more realistic image generation. Additionally, the integration of optical flow helps regulate the inter-frame variance of sequential images, demonstrating an authentic sequential image generation. The KDM is evaluated with diverse key-point conditioned image synthesis tasks, including facial image generation, human pose synthesis, and echocardiography video prediction, demonstrating the KDM is proving consistency enhanced and photo-realistic images compared with state-of-the-art models.
Authors: Quang-Trung Truong, Duc Thanh Nguyen, Binh-Son Hua, Sai-Kit Yeung
Abstract: Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video data, attention maps may not well align with the objects of interest across video frames, causing accumulated errors in long-term video processing. In addition, existing techniques have utilised complex architectures, requiring highly computational complexity and hence limiting the ability to integrate video object segmentation into low-powered devices. To address these issues, we propose a new method for self-supervised video object segmentation based on distillation learning of deformable attention. Specifically, we devise a lightweight architecture for video object segmentation that is effectively adapted to temporal changes. This is enabled by deformable attention mechanism, where the keys and values capturing the memory of a video sequence in the attention module have flexible locations updated across frames. The learnt object representations are thus adaptive to both the spatial and temporal dimensions. We train the proposed architecture in a self-supervised fashion through a new knowledge distillation paradigm where deformable attention maps are integrated into the distillation loss. We qualitatively and quantitatively evaluate our method and compare it with existing methods on benchmark datasets including DAVIS 2016/2017 and YouTube-VOS 2018/2019. Experimental results verify the superiority of our method via its achieved state-of-the-art performance and optimal memory usage.
Authors: Yiyuan Zhang, Xiaohan Ding, Kaixiong Gong, Yixiao Ge, Ying Shan, Xiangyu Yue
Abstract: We propose to improve transformers of a specific modality with irrelevant data from other modalities, e.g., improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target modality are irrelevant to the other modalities, which distinguishes our method from other works utilizing paired (e.g., CLIP) or interleaved data of different modalities. We propose a methodology named Multimodal Pathway - given a target modality and a transformer designed for it, we use an auxiliary transformer trained with data of another modality and construct pathways to connect components of the two models so that data of the target modality can be processed by both models. In this way, we utilize the universal sequence-to-sequence modeling abilities of transformers obtained from two modalities. As a concrete implementation, we use a modality-specific tokenizer and task-specific head as usual but utilize the transformer blocks of the auxiliary model via a proposed method named Cross-Modal Re-parameterization, which exploits the auxiliary weights without any inference costs. On the image, point cloud, video, and audio recognition tasks, we observe significant and consistent performance improvements with irrelevant data from other modalities. The code and models are available at https://github.com/AILab-CVC/M2PT.
Authors: Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu
Abstract: Current image manipulation primarily centers on static manipulation, such as replacing specific regions within an image or altering its overall style. In this paper, we introduce an innovative dynamic manipulation task, subject repositioning. This task involves relocating a user-specified subject to a desired position while preserving the image's fidelity. Our research reveals that the fundamental sub-tasks of subject repositioning, which include filling the void left by the repositioned subject, reconstructing obscured portions of the subject and blending the subject to be consistent with surrounding areas, can be effectively reformulated as a unified, prompt-guided inpainting task. Consequently, we can employ a single diffusion generative model to address these sub-tasks using various task prompts learned through our proposed task inversion technique. Additionally, we integrate pre-processing and post-processing techniques to further enhance the quality of subject repositioning. These elements together form our SEgment-gEnerate-and-bLEnd (SEELE) framework. To assess SEELE's effectiveness in subject repositioning, we assemble a real-world subject repositioning dataset called ReS. Results of SEELE on ReS demonstrate its efficacy.
Authors: Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, Pengfeng Xiao
Abstract: The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain.
Authors: Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, Rakesh Ranjan
Abstract: This paper presents a neural architecture MVDiffusion++ for 3D object reconstruction that synthesizes dense and high-resolution views of an object given one or a few images without camera poses. MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time. We use the Objaverse for training and the Google Scanned Objects for evaluation with standard novel view synthesis and 3D reconstruction metrics, where MVDiffusion++ significantly outperforms the current state of the arts. We also demonstrate a text-to-3D application example by combining MVDiffusion++ with a text-to-image generative model. The project page is at https://mvdiffusion-plusplus.github.io.
Authors: Mehdi Azarafza, Mojtaba Nayyeri, Charles Steinmetz, Steffen Staab, Achim Rettberg
Abstract: Large Language Models (LLMs) have garnered significant attention for their ability to understand text and images, generate human-like text, and perform complex reasoning tasks. However, their ability to generalize this advanced reasoning with a combination of natural language text for decision-making in dynamic situations requires further exploration. In this study, we investigate how well LLMs can adapt and apply a combination of arithmetic and common-sense reasoning, particularly in autonomous driving scenarios. We hypothesize that LLMs hybrid reasoning abilities can improve autonomous driving by enabling them to analyze detected object and sensor data, understand driving regulations and physical laws, and offer additional context. This addresses complex scenarios, like decisions in low visibility (due to weather conditions), where traditional methods might fall short. We evaluated Large Language Models (LLMs) based on accuracy by comparing their answers with human-generated ground truth inside CARLA. The results showed that when a combination of images (detected objects) and sensor data is fed into the LLM, it can offer precise information for brake and throttle control in autonomous vehicles across various weather conditions. This formulation and answers can assist in decision-making for auto-pilot systems.
Authors: Feng Lu, Lijun Zhang, Xiangyuan Lan, Shuting Dong, Yaowei Wang, Chun Yuan
Abstract: Recent studies show that vision models pre-trained in generic visual learning tasks with large-scale data can provide useful feature representations for a wide range of visual perception problems. However, few attempts have been made to exploit pre-trained foundation models in visual place recognition (VPR). Due to the inherent difference in training objectives and data between the tasks of model pre-training and VPR, how to bridge the gap and fully unleash the capability of pre-trained models for VPR is still a key issue to address. To this end, we propose a novel method to realize seamless adaptation of pre-trained models for VPR. Specifically, to obtain both global and local features that focus on salient landmarks for discriminating places, we design a hybrid adaptation method to achieve both global and local adaptation efficiently, in which only lightweight adapters are tuned without adjusting the pre-trained model. Besides, to guide effective adaptation, we propose a mutual nearest neighbor local feature loss, which ensures proper dense local features are produced for local matching and avoids time-consuming spatial verification in re-ranking. Experimental results show that our method outperforms the state-of-the-art methods with less training data and training time, and uses about only 3% retrieval runtime of the two-stage VPR methods with RANSAC-based spatial verification. It ranks 1st on the MSLS challenge leaderboard (at the time of submission). The code is released at https://github.com/Lu-Feng/SelaVPR.
Authors: Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu
Abstract: Recently, Multimodal LLMs (MLLMs) have shown a great ability to understand images. However, like traditional vision models, they are still vulnerable to adversarial images. Meanwhile, Chain-of-Thought (CoT) reasoning has been widely explored on MLLMs, which not only improves model's performance, but also enhances model's explainability by giving intermediate reasoning steps. Nevertheless, there is still a lack of study regarding MLLMs' adversarial robustness with CoT and an understanding of what the rationale looks like when MLLMs infer wrong answers with adversarial images. Our research evaluates the adversarial robustness of MLLMs when employing CoT reasoning, finding that CoT marginally improves adversarial robustness against existing attack methods. Moreover, we introduce a novel stop-reasoning attack technique that effectively bypasses the CoT-induced robustness enhancements. Finally, we demonstrate the alterations in CoT reasoning when MLLMs confront adversarial images, shedding light on their reasoning process under adversarial attacks.
Authors: Francis Engelmann, Ayca Takmaz, Jonas Schult, Elisabetta Fedele, Johanna Wald, Songyou Peng, Xi Wang, Or Litany, Siyu Tang, Federico Tombari, Marc Pollefeys, Leonidas Guibas, Hongbo Tian, Chunjie Wang, Xiaosheng Yan, Bingwen Wang, Xuanyang Zhang, Xiao Liu, Phuc Nguyen, Khoi Nguyen, Anh Tran, Cuong Pham, Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, Joan Lasenby
Abstract: This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this workshop series is to provide a platform for exploration and discussion of open-vocabulary 3D scene understanding tasks, including but not limited to segmentation, detection and mapping. We provide an overview of the challenge hosted at the workshop, present the challenge dataset, the evaluation methodology, and brief descriptions of the winning methods. For additional details, please see https://opensun3d.github.io/index_iccv23.html.
Authors: Feng Lu, Shuting Dong, Lijun Zhang, Bingxi Liu, Xiangyuan Lan, Dongmei Jiang, Chun Yuan
Abstract: Visual place recognition (VPR) is a fundamental task for many applications such as robot localization and augmented reality. Recently, the hierarchical VPR methods have received considerable attention due to the trade-off between accuracy and efficiency. They usually first use global features to retrieve the candidate images, then verify the spatial consistency of matched local features for re-ranking. However, the latter typically relies on the RANSAC algorithm for fitting homography, which is time-consuming and non-differentiable. This makes existing methods compromise to train the network only in global feature extraction. Here, we propose a transformer-based deep homography estimation (DHE) network that takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Moreover, we design a re-projection error of inliers loss to train the DHE network without additional homography labels, which can also be jointly trained with the backbone network to help it extract the features that are more suitable for local matching. Extensive experiments on benchmark datasets show that our method can outperform several state-of-the-art methods. And it is more than one order of magnitude faster than the mainstream hierarchical VPR methods using RANSAC. The code is released at https://github.com/Lu-Feng/DHE-VPR.
Authors: Qixuan Zheng, Ming Zhang, Hong Yan
Abstract: To achieve greater accuracy, hypergraph matching algorithms require exponential increases in computational resources. Recent kd-tree-based approximate nearest neighbor (ANN) methods, despite the sparsity of their compatibility tensor, still require exhaustive calculations for large-scale graph matching. This work utilizes CUR tensor decomposition and introduces a novel cascaded second and third-order hypergraph matching framework (CURSOR) for efficient hypergraph matching. A CUR-based second-order graph matching algorithm is used to provide a rough match, and then the core of CURSOR, a fiber-CUR-based tensor generation method, directly calculates entries of the compatibility tensor by leveraging the initial second-order match result. This significantly decreases the time complexity and tensor density. A probability relaxation labeling (PRL)-based matching algorithm, especially suitable for sparse tensors, is developed. Experiment results on large-scale synthetic datasets and widely-adopted benchmark sets demonstrate the superiority of CURSOR over existing methods. The tensor generation method in CURSOR can be integrated seamlessly into existing hypergraph matching methods to improve their performance and lower their computational costs.
Authors: Yi Huang, Jiancheng Huang, Yifan Liu, Mingfu Yan, Jiaxi Lv, Jianzhuang Liu, Wei Xiong, He Zhang, Shifeng Chen, Liangliang Cao
Abstract: Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning to reverse the process of gradually adding noise to images, allowing them to generate high-quality samples from a complex distribution. In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field. We delve into a thorough analysis and categorization of these works from multiple perspectives, including learning strategies, user-input conditions, and the array of specific editing tasks that can be accomplished. In addition, we pay special attention to image inpainting and outpainting, and explore both earlier traditional context-driven and current multimodal conditional methods, offering a comprehensive analysis of their methodologies. To further evaluate the performance of text-guided image editing algorithms, we propose a systematic benchmark, EditEval, featuring an innovative metric, LMM Score. Finally, we address current limitations and envision some potential directions for future research. The accompanying repository is released at https://github.com/SiatMMLab/Awesome-Diffusion-Model-Based-Image-Editing-Methods.
URLs: https://github.com/SiatMMLab/Awesome-Diffusion-Model-Based-Image-Editing-Methods.
Authors: Gao Yu, Qiu Xuchong, Ye Zihan
Abstract: Message hiding, a technique that conceals secret message bits within a cover image, aims to achieve an optimal balance among message capacity, recovery accuracy, and imperceptibility. While convolutional neural networks have notably improved message capacity and imperceptibility, achieving high recovery accuracy remains challenging. This challenge arises because convolutional operations struggle to preserve the sequential order of message bits and effectively address the discrepancy between these two modalities. To address this, we propose StegaFormer, an innovative MLP-based framework designed to preserve bit order and enable global fusion between modalities. Specifically, StegaFormer incorporates three crucial components: Order-Preserving Message Encoder (OPME), Decoder (OPMD) and Global Message-Image Fusion (GMIF). OPME and OPMD aim to preserve the order of message bits by segmenting the entire sequence into equal-length segments and incorporating sequential information during encoding and decoding. Meanwhile, GMIF employs a cross-modality fusion mechanism to effectively fuse the features from the two uncorrelated modalities. Experimental results on the COCO and DIV2K datasets demonstrate that StegaFormer surpasses existing state-of-the-art methods in terms of recovery accuracy, message capacity, and imperceptibility. We will make our code publicly available.
Authors: Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, Lei Li, Sishuo Chen, Xu Sun, Lu Hou
Abstract: Recently, there is a surge in interest surrounding video large language models (Video LLMs). However, existing benchmarks fail to provide a comprehensive feedback on the temporal perception ability of Video LLMs. On the one hand, most of them are unable to distinguish between different temporal aspects (e.g., speed, direction) and thus cannot reflect the nuanced performance on these specific aspects. On the other hand, they are limited in the diversity of task formats (e.g., only multi-choice QA), which hinders the understanding of how temporal perception performance may vary across different types of tasks. Motivated by these two problems, we propose the \textbf{TempCompass} benchmark, which introduces a diversity of temporal aspects and task formats. To collect high-quality test data, we devise two novel strategies: (1) In video collection, we construct conflicting videos that share the same static content but differ in a specific temporal aspect, which prevents Video LLMs from leveraging single-frame bias or language priors. (2) To collect the task instructions, we propose a paradigm where humans first annotate meta-information for a video and then an LLM generates the instruction. We also design an LLM-based approach to automatically and accurately evaluate the responses from Video LLMs. Based on TempCompass, we comprehensively evaluate 8 state-of-the-art (SOTA) Video LLMs and 3 Image LLMs, and reveal the discerning fact that these models exhibit notably poor temporal perception ability. The data and evaluation code are available at https://github.com/llyx97/TempCompass.
Authors: Venkatesh Jatla, Sravani Teeparthi, Ugesh Egala, Sylvia Celedon Pattichis, Marios S. Patticis
Abstract: Research on video activity detection has primarily focused on identifying well-defined human activities in short video segments. The majority of the research on video activity recognition is focused on the development of large parameter systems that require training on large video datasets. This paper develops a low-parameter, modular system with rapid inferencing capabilities that can be trained entirely on limited datasets without requiring transfer learning from large-parameter systems. The system can accurately detect and associate specific activities with the students who perform the activities in real-life classroom videos. Additionally, the paper develops an interactive web-based application to visualize human activity maps over long real-life classroom videos.
Authors: Aisha L. Shuaibu, Ivor J. A. Simpson
Abstract: Methods for medical image registration infer geometric transformations that align pairs/groups of images by maximising an image similarity metric. This problem is ill-posed as several solutions may have equivalent likelihoods, also optimising purely for image similarity can yield implausible transformations. For these reasons regularization terms are essential to obtain meaningful registration results. However, this requires the introduction of at least one hyperparameter often termed $\lambda$, that serves as a tradeoff between loss terms. In some situations, the quality of the estimated transformation greatly depends on hyperparameter choice, and different choices may be required depending on the characteristics of the data. Analyzing the effect of these hyperparameters requires labelled data, which is not commonly available at test-time. In this paper, we propose a method for evaluating the influence of hyperparameters and subsequently selecting an optimal value for given image pairs. Our approach which we call HyperPredict, implements a Multi-Layer Perceptron that learns the effect of selecting particular hyperparameters for registering an image pair by predicting the resulting segmentation overlap and measure of deformation smoothness. This approach enables us to select optimal hyperparameters at test time without requiring labelled data, removing the need for a one-size-fits-all cross-validation approach. Furthermore, the criteria used to define optimal hyperparameter is flexible post-training, allowing us to efficiently choose specific properties. We evaluate our proposed method on the OASIS brain MR dataset using a recent deep learning approach(cLapIRN) and an algorithmic method(Niftyreg). Our results demonstrate good performance in predicting the effects of regularization hyperparameters and highlight the benefits of our image-pair specific approach to hyperparameter selection.
Authors: Tianxiang Chen, Zhentao Tan, Tao Gong, Qi Chu, Yue Wu, Bin Liu, Jieping Ye, Nenghai Yu
Abstract: Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the structures combining convolutional networks with transformers can successfully extract both local and global features. However, the disadvantage of the transformer is also inherited, i.e., the quadratic computational complexity to the length of the sequence. Inspired by the recent basic model with linear complexity for long-distance modeling, called Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper. However, directly applying Mamba achieves poor performance since local features, which are critical to detecting small targets, cannot be fully exploited. Instead, we tailor a Mamba-in-Mamba (MiM-ISTD) structure for efficient ISTD. Specifically, we treat the local patches as "visual sentences" and use the Outer Mamba to explore the global information. We then decompose each visual sentence into sub-patches as "visual words" and use the Inner Mamba to further explore the local information among words in the visual sentence with negligible computational costs. By aggregating the word and sentence features, the MiM-ISTD can effectively explore both global and local information. Experiments on NUAA-SIRST and IRSTD-1k show the superior accuracy and efficiency of our method. Specifically, MiM-ISTD is $10 \times$ faster than the SOTA method and reduces GPU memory usage by 73.4$\%$ when testing on $2048 \times 2048$ image, overcoming the computation and memory constraints on high-resolution infrared images. Source code is available at https://github.com/txchen-USTC/MiM-ISTD.
Authors: Ruizhuo Song, Beiming Yuan
Abstract: This paper achieves significant progress in the field of abstract reasoning, particularly in addressing Raven's Progressive Matrices (RPM) and Bongard-Logo problems. We propose the D2C approach, which redefines conceptual boundaries in these domains and bridges the gap between high-level concepts and their low-dimensional representations. Based on this, we further introduce the D3C method that handles Bongard-Logo problems and significantly improves reasoning accuracy by estimating the distribution of image representations and measuring their Sinkhorn distance. To enhance computational efficiency, we introduce the D3C-cos variant, which provides an efficient and accurate solution for RPM problems by constraining distribution distances. Additionally, we present Lico-Net, a network that combines D3C and D3C-cos to achieve state-of-the-art performance in both problem-solving and interpretability. Finally, we extend our approach to D4C, employing adversarial strategies to further refine conceptual boundaries and demonstrate notable improvements for both RPM and Bongard-Logo problems. Overall, our contributions offer a new perspective and practical solutions to the field of abstract reasoning.
Authors: Jinfeng Wang, Sifan Song, Xinkun Wang, Yiyi Wang, Yiyi Miao, Jionglong Su, S. Kevin Zhou
Abstract: With the proposal of the Segment Anything Model (SAM), fine-tuning SAM for medical image segmentation (MIS) has become popular. However, due to the large size of the SAM model and the significant domain gap between natural and medical images, fine-tuning-based strategies are costly with potential risk of instability, feature damage and catastrophic forgetting. Furthermore, some methods of transferring SAM to a domain-specific MIS through fine-tuning strategies disable the model's prompting capability, severely limiting its utilization scenarios. In this paper, we propose an Auto-Prompting Module (APM), which provides SAM-based foundation model with Euclidean adaptive prompts in the target domain. Our experiments demonstrate that such adaptive prompts significantly improve SAM's non-fine-tuned performance in MIS. In addition, we propose a novel non-invasive method called Incremental Pattern Shifting (IPS) to adapt SAM to specific medical domains. Experimental results show that the IPS enables SAM to achieve state-of-the-art or competitive performance in MIS without the need for fine-tuning. By coupling these two methods, we propose ProMISe, an end-to-end non-fine-tuned framework for Promptable Medical Image Segmentation. Our experiments demonstrate that both using our methods individually or in combination achieves satisfactory performance in low-cost pattern shifting, with all of SAM's parameters frozen.
Authors: Yao Jiang, Xinyu Yan, Ge-Peng Ji, Keren Fu, Meijun Sun, Huan Xiong, Deng-Ping Fan, Fahad Shahbaz Khan
Abstract: The advent of large vision-language models (LVLMs) represents a noteworthy advancement towards the pursuit of artificial general intelligence. However, the extent of their efficacy across both specialized and general tasks warrants further investigation. This article endeavors to evaluate the competency of popular LVLMs in specialized and general tasks, respectively, aiming to offer a comprehensive comprehension of these innovative methodologies. To gauge their efficacy in specialized tasks, we tailor a comprehensive testbed comprising three distinct scenarios: natural, healthcare, and industrial, encompassing six challenging tasks. These tasks include salient, camouflaged, and transparent object detection, as well as polyp and skin lesion detection, alongside industrial anomaly detection. We examine the performance of three recent open-source LVLMs -- MiniGPT-v2, LLaVA-1.5, and Shikra -- in the realm of visual recognition and localization. Moreover, we conduct empirical investigations utilizing the aforementioned models alongside GPT-4V, assessing their multi-modal understanding capacities in general tasks such as object counting, absurd question answering, affordance reasoning, attribute recognition, and spatial relation reasoning. Our investigations reveal that these models demonstrate limited proficiency not only in specialized tasks but also in general tasks. We delve deeper into this inadequacy and suggest several potential factors, including limited cognition in specialized tasks, object hallucination, text-to-image interference, and decreased robustness in complex problems. We hope this study would provide valuable insights for the future development of LVLMs, augmenting their power in coping with both general and specialized applications.
Authors: Junsong Chen, Chongjian Ge, Enze Xie, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, Zhenguo Li
Abstract: In this paper, we introduce PixArt-\Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-\Sigma represents a significant advancement over its predecessor, PixArt-\alpha, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-\Sigma is its training efficiency. Leveraging the foundational pre-training of PixArt-\alpha, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term "weak-to-strong training". The advancements in PixArt-\Sigma are twofold: (1) High-Quality Training Data: PixArt-\Sigma incorporates superior-quality image data, paired with more precise and detailed image captions. (2) Efficient Token Compression: we propose a novel attention module within the DiT framework that compresses both keys and values, significantly improving efficiency and facilitating ultra-high-resolution image generation. Thanks to these improvements, PixArt-\Sigma achieves superior image quality and user prompt adherence capabilities with significantly smaller model size (0.6B parameters) than existing text-to-image diffusion models, such as SDXL (2.6B parameters) and SD Cascade (5.1B parameters). Moreover, PixArt-\Sigma's capability to generate 4K images supports the creation of high-resolution posters and wallpapers, efficiently bolstering the production of high-quality visual content in industries such as film and gaming.
Authors: Xiang Huang, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Wangmeng Xiang, Baigui Sun, Xiao Wu
Abstract: The advancement of autonomous driving systems hinges on the ability to achieve low-latency and high-accuracy perception. To address this critical need, this paper introduces Dynamic Routering Network (DyRoNet), a low-rank enhanced dynamic routing framework designed for streaming perception in autonomous driving systems. DyRoNet integrates a suite of pre-trained branch networks, each meticulously fine-tuned to function under distinct environmental conditions. At its core, the framework offers a speed router module, developed to assess and route input data to the most suitable branch for processing. This approach not only addresses the inherent limitations of conventional models in adapting to diverse driving conditions but also ensures the balance between performance and efficiency. Extensive experimental evaluations demonstrating the adaptability of DyRoNet to diverse branch selection strategies, resulting in significant performance enhancements across different scenarios. This work not only establishes a new benchmark for streaming perception but also provides valuable engineering insights for future work.
Authors: Linwei Chen, Lin Gu, Ying Fu
Abstract: Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three strategies to improve individual phases of dilated convolution from the view of spectrum analysis. Departing from the conventional practice of fixing a global dilation rate as a hyperparameter, we introduce Frequency-Adaptive Dilated Convolution (FADC), which dynamically adjusts dilation rates spatially based on local frequency components. Subsequently, we design two plug-in modules to directly enhance effective bandwidth and receptive field size. The Adaptive Kernel (AdaKern) module decomposes convolution weights into low-frequency and high-frequency components, dynamically adjusting the ratio between these components on a per-channel basis. By increasing the high-frequency part of convolution weights, AdaKern captures more high-frequency components, thereby improving effective bandwidth. The Frequency Selection (FreqSelect) module optimally balances high- and low-frequency components in feature representations through spatially variant reweighting. It suppresses high frequencies in the background to encourage FADC to learn a larger dilation, thereby increasing the receptive field for an expanded scope. Extensive experiments on segmentation and object detection consistently validate the efficacy of our approach. The code is publicly available at \url{https://github.com/Linwei-Chen/FADC}.
Authors: Ruinan Jin, Wenlong Deng, Minghui Chen, Xiaoxiao Li
Abstract: In the era of Foundation Models' (FMs) rising prominence in AI, our study addresses the challenge of biases in medical images while using FM API, particularly spurious correlations between pixels and sensitive attributes. Traditional methods for bias mitigation face limitations due to the restricted access to web-hosted FMs and difficulties in addressing the underlying bias encoded within the FM API. We propose an U(niversal) D(ebiased) E(diting) strategy, termed UDE, which generates UDE noise to mask such spurious correlation. UDE is capable of mitigating bias both within the FM API embedding and the images themselves. Furthermore, UDE is suitable for both white-box and black-box FM APIs, where we introduced G(reedy) (Z)eroth-O(rder) (GeZO) optimization for it when the gradient is inaccessible in black-box APIs. Our whole pipeline enables fairness-aware image editing that can be applied across various medical contexts without requiring direct model manipulation or significant computational resources. Our empirical results demonstrate the method's effectiveness in maintaining fairness and utility across different patient groups and diseases. In the era of AI-driven medicine, this work contributes to making healthcare diagnostics more equitable, showcasing a practical solution for bias mitigation in pre-trained image FMs.
Authors: Jiuming Liu, Ruiji Yu, Yian Wang, Yu Zheng, Tianchen Deng, Weicai Ye, Hesheng Wang
Abstract: Recently, state space model (SSM) has gained great attention due to its promising performance, linear complexity, and long sequence modeling ability in both language and image domains. However, it is non-trivial to extend SSM to the point cloud field, because of the causality requirement of SSM and the disorder and irregularity nature of point clouds. In this paper, we propose a novel SSM-based point cloud processing backbone, named Point Mamba, with a causality-aware ordering mechanism. To construct the causal dependency relationship, we design an octree-based ordering strategy on raw irregular points, globally sorting points in a z-order sequence and also retaining their spatial proximity. Our method achieves state-of-the-art performance compared with transformer-based counterparts, with 93.4% accuracy and 75.7 mIOU respectively on the ModelNet40 classification dataset and ScanNet semantic segmentation dataset. Furthermore, our Point Mamba has linear complexity, which is more efficient than transformer-based methods. Our method demonstrates the great potential that SSM can serve as a generic backbone in point cloud understanding. Codes are released at https://github.com/IRMVLab/Point-Mamba.
Authors: Jiawen Zhu, Guansong Pang
Abstract: This paper explores the problem of Generalist Anomaly Detection (GAD), aiming to train one single detection model that can generalize to detect anomalies in diverse datasets from different application domains without any further training on the target data. Some recent studies have shown that large pre-trained Visual-Language Models (VLMs) like CLIP have strong generalization capabilities on detecting industrial defects from various datasets, but their methods rely heavily on handcrafted text prompts about defects, making them difficult to generalize to anomalies in other applications, e.g., medical image anomalies or semantic anomalies in natural images. In this work, we propose to train a GAD model with few-shot normal images as sample prompts for AD on diverse datasets on the fly. To this end, we introduce a novel approach that learns an in-context residual learning model for GAD, termed InCTRL. It is trained on an auxiliary dataset to discriminate anomalies from normal samples based on a holistic evaluation of the residuals between query images and few-shot normal sample prompts. Regardless of the datasets, per definition of anomaly, larger residuals are expected for anomalies than normal samples, thereby enabling InCTRL to generalize across different domains without further training. Comprehensive experiments on nine AD datasets are performed to establish a GAD benchmark that encapsulate the detection of industrial defect anomalies, medical anomalies, and semantic anomalies in both one-vs-all and multi-class setting, on which InCTRL is the best performer and significantly outperforms state-of-the-art competing methods. Code is available at https://github.com/mala-lab/InCTRL.
Authors: Zijian Chen, Mei Wang, Weihong Deng, Hongzhi Shi, Dongchao Wen, Yingjie Zhang, Xingchen Cui, Jian Zhao
Abstract: 2D face recognition encounters challenges in unconstrained environments due to varying illumination, occlusion, and pose. Recent studies focus on RGB-D face recognition to improve robustness by incorporating depth information. However, collecting sufficient paired RGB-D training data is expensive and time-consuming, hindering wide deployment. In this work, we first construct a diverse depth dataset generated by 3D Morphable Models for depth model pre-training. Then, we propose a domain-independent pre-training framework that utilizes readily available pre-trained RGB and depth models to separately perform face recognition without needing additional paired data for retraining. To seamlessly integrate the two distinct networks and harness the complementary benefits of RGB and depth information for improved accuracy, we propose an innovative Adaptive Confidence Weighting (ACW). This mechanism is designed to learn confidence estimates for each modality to achieve modality fusion at the score level. Our method is simple and lightweight, only requiring ACW training beyond the backbone models. Experiments on multiple public RGB-D face recognition benchmarks demonstrate state-of-the-art performance surpassing previous methods based on depth estimation and feature fusion, validating the efficacy of our approach.
Authors: Zeyu Zhang, Akide Liu, Ian Reid, Richard Hartley, Bohan Zhuang, Hao Tang
Abstract: Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have showcased considerable promise in long sequence modeling with an efficient hardware-aware design, which appears to be a promising direction to build motion generation model upon it. Nevertheless, adapting SSMs to motion generation faces hurdles since the lack of a specialized design architecture to model motion sequence. To address these challenges, we propose Motion Mamba, a simple and efficient approach that presents the pioneering motion generation model utilized SSMs. Specifically, we design a Hierarchical Temporal Mamba (HTM) block to process temporal data by ensemble varying numbers of isolated SSM modules across a symmetric U-Net architecture aimed at preserving motion consistency between frames. We also design a Bidirectional Spatial Mamba (BSM) block to bidirectionally process latent poses, to enhance accurate motion generation within a temporal frame. Our proposed method achieves up to 50% FID improvement and up to 4 times faster on the HumanML3D and KIT-ML datasets compared to the previous best diffusion-based method, which demonstrates strong capabilities of high-quality long sequence motion modeling and real-time human motion generation. See project website https://steve-zeyu-zhang.github.io/MotionMamba/
Authors: Honghao Chen, Xiangxiang Chu, Yongjian Ren, Xin Zhao, Kaiqi Huang
Abstract: Recently, some large kernel convnets strike back with appealing performance and efficiency. However, given the square complexity of convolution, scaling up kernels can bring about an enormous amount of parameters and the proliferated parameters can induce severe optimization problem. Due to these issues, current CNNs compromise to scale up to 51x51 in the form of stripe convolution (i.e., 51x5 + 5x51) and start to saturate as the kernel size continues growing. In this paper, we delve into addressing these vital issues and explore whether we can continue scaling up kernels for more performance gains. Inspired by human vision, we propose a human-like peripheral convolution that efficiently reduces over 90% parameter count of dense grid convolution through parameter sharing, and manage to scale up kernel size to extremely large. Our peripheral convolution behaves highly similar to human, reducing the complexity of convolution from O(K^2) to O(logK) without backfiring performance. Built on this, we propose Parameter-efficient Large Kernel Network (PeLK). Our PeLK outperforms modern vision Transformers and ConvNet architectures like Swin, ConvNeXt, RepLKNet and SLaK on various vision tasks including ImageNet classification, semantic segmentation on ADE20K and object detection on MS COCO. For the first time, we successfully scale up the kernel size of CNNs to an unprecedented 101x101 and demonstrate consistent improvements.
Authors: Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon
Abstract: We present "SemCity," a 3D diffusion model for semantic scene generation in real-world outdoor environments. Most 3D diffusion models focus on generating a single object, synthetic indoor scenes, or synthetic outdoor scenes, while the generation of real-world outdoor scenes is rarely addressed. In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset. In contrast to synthetic data, real-outdoor datasets often contain more empty spaces due to sensor limitations, causing challenges in learning real-outdoor distributions. To address this issue, we exploit a triplane representation as a proxy form of scene distributions to be learned by our diffusion model. Furthermore, we propose a triplane manipulation that integrates seamlessly with our triplane diffusion model. The manipulation improves our diffusion model's applicability in a variety of downstream tasks related to outdoor scene generation such as scene inpainting, scene outpainting, and semantic scene completion refinements. In experimental results, we demonstrate that our triplane diffusion model shows meaningful generation results compared with existing work in a real-outdoor dataset, SemanticKITTI. We also show our triplane manipulation facilitates seamlessly adding, removing, or modifying objects within a scene. Further, it also enables the expansion of scenes toward a city-level scale. Finally, we evaluate our method on semantic scene completion refinements where our diffusion model enhances predictions of semantic scene completion networks by learning scene distribution. Our code is available at https://github.com/zoomin-lee/SemCity.
Authors: Yusuke Marumo, Kazuhiko Kawamoto, Hiroshi Kera
Abstract: Not identical but similar objects are everywhere in the world. Examples include four-legged animals such as dogs and cats, cars of different models, akin flowers in various colors, and countless others. In this study, we address a novel task of matching such non-identical objects. We propose a simple weighting scheme of descriptors that enhances various sparse image matching methods, which were originally designed for matching identical objects captured from different perspectives, and achieve semantically robust matching. The experiments show successful matching between non-identical objects in various cases including domain shift. Further, we present a first evaluation of the robustness of the image matching methods under common corruptions, which is a sort of domain shift, and the proposed method improves the matching in this case as well.
Authors: Zhonghan Zhao, Kewei Chen, Dongxu Guo, Wenhao Chai, Tian Ye, Yanting Zhang, Gaoang Wang
Abstract: Due to the dynamic and unpredictable open-world setting, navigating complex environments in Minecraft poses significant challenges for multi-agent systems. Agents must interact with the environment and coordinate their actions with other agents to achieve common objectives. However, traditional approaches often struggle to efficiently manage inter-agent communication and task distribution, crucial for effective multi-agent navigation. Furthermore, processing and integrating multi-modal information (such as visual, textual, and auditory data) is essential for agents to comprehend their goals and navigate the environment successfully and fully. To address this issue, we design the HAS framework to auto-organize groups of LLM-based agents to complete navigation tasks. In our approach, we devise a hierarchical auto-organizing navigation system, which is characterized by 1) a hierarchical system for multi-agent organization, ensuring centralized planning and decentralized execution; 2) an auto-organizing and intra-communication mechanism, enabling dynamic group adjustment under subtasks; 3) a multi-modal information platform, facilitating multi-modal perception to perform the three navigation tasks with one system. To assess organizational behavior, we design a series of navigation tasks in the Minecraft environment, which includes searching and exploring. We aim to develop embodied organizations that push the boundaries of embodied AI, moving it towards a more human-like organizational structure.
Authors: Matteo Taiana, Matteo Toso, Stuart James, Alessio Del Bue
Abstract: Robustly estimating camera poses from a set of images is a fundamental task which remains challenging for differentiable methods, especially in the case of small and sparse camera pose graphs. To overcome this challenge, we propose Pose-refined Rotation Averaging Graph Optimization (PRAGO). From a set of objectness detections on unordered images, our method reconstructs the rotational pose, and in turn, the absolute pose, in a differentiable manner benefiting from the optimization of a sequence of geometrical tasks. We show how our objectness pose-refinement module in PRAGO is able to refine the inherent ambiguities in pairwise relative pose estimation without removing edges and avoiding making early decisions on the viability of graph edges. PRAGO then refines the absolute rotations through iterative graph construction, reweighting the graph edges to compute the final rotational pose, which can be converted into absolute poses using translation averaging. We show that PRAGO is able to outperform non-differentiable solvers on small and sparse scenes extracted from 7-Scenes achieving a relative improvement of 21% for rotations while achieving similar translation estimates.
Authors: Dali Zhu, Wenli Zhang, Hualin Zeng, Xiaohao Liu, Long Yang, Jiaqi Zheng
Abstract: Remote photoplethysmography (rPPG) technique extracts blood volume pulse (BVP) signals from subtle pixel changes in video frames. This study introduces rFaceNet, an advanced rPPG method that enhances the extraction of facial BVP signals with a focus on facial contours. rFaceNet integrates identity-specific facial contour information and eliminates redundant data. It efficiently extracts facial contours from temporally normalized frame inputs through a Temporal Compressor Unit (TCU) and steers the model focus to relevant facial regions by using the Cross-Task Feature Combiner (CTFC). Through elaborate training, the quality and interpretability of facial physiological signals extracted by rFaceNet are greatly improved compared to previous methods. Moreover, our novel approach demonstrates superior performance than SOTA methods in various heart rate estimation benchmarks.
Authors: Linwei Chen, Lin Gu, Ying Fu
Abstract: Despite recent advancements in semantic segmentation, where and what pixels are hard to segment remains largely unexplored. Existing research only separates an image into easy and hard regions and empirically observes the latter are associated with object boundaries. In this paper, we conduct a comprehensive analysis of hard pixel errors, categorizing them into three types: false responses, merging mistakes, and displacements. Our findings reveal a quantitative association between hard pixels and aliasing, which is distortion caused by the overlapping of frequency components in the Fourier domain during downsampling. To identify the frequencies responsible for aliasing, we propose using the equivalent sampling rate to calculate the Nyquist frequency, which marks the threshold for aliasing. Then, we introduce the aliasing score as a metric to quantify the extent of aliasing. While positively correlated with the proposed aliasing score, three types of hard pixels exhibit different patterns. Here, we propose two novel de-aliasing filter (DAF) and frequency mixing (FreqMix) modules to alleviate aliasing degradation by accurately removing or adjusting frequencies higher than the Nyquist frequency. The DAF precisely removes the frequencies responsible for aliasing before downsampling, while the FreqMix dynamically selects high-frequency components within the encoder block. Experimental results demonstrate consistent improvements in semantic segmentation and low-light instance segmentation tasks. The code is available at: https://github.com/Linwei-Chen/Seg-Aliasing.
Authors: Hongchen Luo, Kai Zhu, Wei Zhai, Yang Cao
Abstract: Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages action intention consisting of human movement and action description as view-independent representation to guide video generation, preserving the consistency of content and motion. Specifically, the egocentric head trajectory is first estimated through multi-view stereo matching. Then, cross-view feature perception module is introduced to establish correspondences between exo- and ego- views, guiding the trajectory transformation module to infer human full-body movement from the head trajectory. Meanwhile, we present an action description unit that maps the action semantics into the feature space consistent with the exocentric image. Finally, the inferred human movement and high-level action descriptions jointly guide the generation of exocentric motion and interaction content (i.e., corresponding optical flow and occlusion maps) in the backward process of the diffusion model, ultimately warping them into the corresponding exocentric video. We conduct extensive experiments on the relevant dataset with diverse exo-ego video pairs, and our IDE outperforms state-of-the-art models in both subjective and objective assessments, demonstrating its efficacy in ego-to-exo video generation.
Authors: Yanfei Song, Bangzheng Pu, Peng Wang, Hongxu Jiang, Dong Dong, Yongxiang Cao, Yiqing Shen
Abstract: Segment Anything Model (SAM) has garnered significant attention in segmentation tasks due to their zero-shot generalization ability. However, a broader application of SAMs to real-world practice has been restricted by their low inference speed and high computational memory demands, which mainly stem from the attention mechanism. Existing work concentrated on optimizing the encoder, yet has not adequately addressed the inefficiency of the attention mechanism itself, even when distilled to a smaller model, which thus leaves space for further improvement. In response, we introduce SAM-Lightening, a variant of SAM, that features a re-engineered attention mechanism, termed Dilated Flash Attention. It not only facilitates higher parallelism, enhancing processing efficiency but also retains compatibility with the existing FlashAttention. Correspondingly, we propose a progressive distillation to enable an efficient knowledge transfer from the vanilla SAM without costly training from scratch. Experiments on COCO and LVIS reveal that SAM-Lightening significantly outperforms the state-of-the-art methods in both run-time efficiency and segmentation accuracy. Specifically, it can achieve an inference speed of 7 milliseconds (ms) per image, for images of size 1024*1024 pixels, which is 30.1 times faster than the vanilla SAM and 2.1 times than the state-of-the-art. Moreover, it takes only 244MB memory, which is 3.5\% of the vanilla SAM. The code and weights are available at https://anonymous.4open.science/r/SAM-LIGHTENING-BC25/.
URLs: https://anonymous.4open.science/r/SAM-LIGHTENING-BC25/.
Authors: Hong Liu, Haosen Yang, Paul J. van Diest, Josien P. W. Pluim, Mitko Veta
Abstract: The Segment Anything Model (SAM) marks a significant advancement in segmentation models, offering robust zero-shot abilities and dynamic prompting. However, existing medical SAMs are not suitable for the multi-scale nature of whole-slide images (WSIs), restricting their effectiveness. To resolve this drawback, we present WSI-SAM, enhancing SAM with precise object segmentation capabilities for histopathology images using multi-resolution patches, while preserving its efficient, prompt-driven design, and zero-shot abilities. To fully exploit pretrained knowledge while minimizing training overhead, we keep SAM frozen, introducing only minimal extra parameters and computational overhead. In particular, we introduce High-Resolution (HR) token, Low-Resolution (LR) token and dual mask decoder. This decoder integrates the original SAM mask decoder with a lightweight fusion module that integrates features at multiple scales. Instead of predicting a mask independently, we integrate HR and LR token at intermediate layer to jointly learn features of the same object across multiple resolutions. Experiments show that our WSI-SAM outperforms state-of-the-art SAM and its variants. In particular, our model outperforms SAM by 4.1 and 2.5 percent points on a ductal carcinoma in situ (DCIS) segmentation tasks and breast cancer metastasis segmentation task (CAMELYON16 dataset). The code will be available at https://github.com/HongLiuuuuu/WSI-SAM.
Authors: Tingtian Li, Zixun Sun, Xinyu Xiao
Abstract: Identifying highlight moments of raw video materials is crucial for improving the efficiency of editing videos that are pervasive on internet platforms. However, the extensive work of manually labeling footage has created obstacles to applying supervised methods to videos of unseen categories. The absence of an audio modality that contains valuable cues for highlight detection in many videos also makes it difficult to use multimodal strategies. In this paper, we propose a novel model with cross-modal perception for unsupervised highlight detection. The proposed model learns representations with visual-audio level semantics from image-audio pair data via a self-reconstruction task. To achieve unsupervised highlight detection, we investigate the latent representations of the network and propose the representation activation sequence learning (RASL) module with k-point contrastive learning to learn significant representation activations. To connect the visual modality with the audio modality, we use the symmetric contrastive learning (SCL) module to learn the paired visual and audio representations. Furthermore, an auxiliary task of masked feature vector sequence (FVS) reconstruction is simultaneously conducted during pretraining for representation enhancement. During inference, the cross-modal pretrained model can generate representations with paired visual-audio semantics given only the visual modality. The RASL module is used to output the highlight scores. The experimental results show that the proposed framework achieves superior performance compared to other state-of-the-art approaches.
Authors: Minyoung Oh, Jae-Young Sim
Abstract: Lifelong person re-identification (LReID) assumes a practical scenario where the model is sequentially trained on continuously incoming datasets while alleviating the catastrophic forgetting in the old datasets. However, not only the training datasets but also the gallery images are incrementally accumulated, that requires a huge amount of computational complexity and storage space to extract the features at the inference phase. In this paper, we address the above mentioned problem by incorporating the backward-compatibility to LReID for the first time. We train the model using the continuously incoming datasets while maintaining the model's compatibility toward the previously trained old models without re-computing the features of the old gallery images. To this end, we devise the cross-model compatibility loss based on the contrastive learning with respect to the replay features across all the old datasets. Moreover, we also develop the knowledge consolidation method based on the part classification to learn the shared representation across different datasets for the backward-compatibility. We suggest a more practical methodology for performance evaluation as well where all the gallery and query images are considered together. Experimental results demonstrate that the proposed method achieves a significantly higher performance of the backward-compatibility compared with the existing methods. It is a promising tool for more practical scenarios of LReID.
Authors: Bejamin A. Huerfano, Fernando Jimenez
Abstract: Digital image processing (DIP) is of great importance in validating and guaranteeing parameters that ensure the quality of mass-produced products. Therefore, this article focused on developing an industrial automation method for a zone of a production line model using the DIP. The neo-cascade methodology employed allowed for defining each of the stages in an adequate way, ensuring the inclusion of the relevant methods for its development, which finally incurred in the modeling, design, implementation, and testing of an optimal route generation system for a warehouse area, using DIP with optimization guidelines, in conjunction with an embedded platform and the connection to programmable logic controllers (PLCs) for its execution. The system was based on the OpenCV library; tool focused on artificial vision, which was implemented on an object-oriented programming (OOP) platform based on Java language. It generated the optimal route for the automation of processes in a scale warehouse area, using the segmentation of objects and the optimization of flow in networks as pillars, ending with the connection to PLCs as a method of action, which in case of implementation would eliminate constraints such as process inefficiency, the use of manpower to perform these tasks, inadequate use of resources, among others
Authors: Alhassan Mumuni, Fuseini Mumuni, Nana Kobina Gerrar
Abstract: The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task. However, in many scenarios, it is often challenging to obtain sufficient image data for the target task. Data augmentation is a way to mitigate this challenge. A common practice is to explicitly transform existing images in desired ways so as to create the required volume and variability of training data necessary to achieve good generalization performance. In situations where data for the target domain is not accessible, a viable workaround is to synthesize training data from scratch--i.e., synthetic data augmentation. This paper presents an extensive review of synthetic data augmentation techniques. It covers data synthesis approaches based on realistic 3D graphics modeling, neural style transfer (NST), differential neural rendering, and generative artificial intelligence (AI) techniques such as generative adversarial networks (GANs) and variational autoencoders (VAEs). For each of these classes of methods, we focus on the important data generation and augmentation techniques, general scope of application and specific use-cases, as well as existing limitations and possible workarounds. Additionally, we provide a summary of common synthetic datasets for training computer vision models, highlighting the main features, application domains and supported tasks. Finally, we discuss the effectiveness of synthetic data augmentation methods. Since this is the first paper to explore synthetic data augmentation methods in great detail, we are hoping to equip readers with the necessary background information and in-depth knowledge of existing methods and their attendant issues.
Authors: Juan Carlos Ruiz-Garcia, Ruben Tolosana, Ruben Vera-Rodriguez, Julian Fierrez, Jaime Herreros-Rodriguez
Abstract: This article presents a comprehensive analysis of the different tests proposed in the recent ChildCI framework, proving its potential for generating a better understanding of children's neuromotor and cognitive development along time, as well as their possible application in other research areas such as e-Health and e-Learning. In particular, we propose a set of over 100 global features related to motor and cognitive aspects of the children interaction with mobile devices, some of them collected and adapted from the literature. Furthermore, we analyse the robustness and discriminative power of the proposed feature set including experimental results for the task of children age group detection based on their motor and cognitive behaviours. Two different scenarios are considered in this study: i) single-test scenario, and ii) multiple-test scenario. Results over 93% accuracy are achieved using the publicly available ChildCIdb_v1 database (over 400 children from 18 months to 8 years old), proving the high correlation of children's age with the way they interact with mobile devices.
Authors: Yunchao Zhang, Zonglin Di, Kaiwen Zhou, Cihang Xie, Xin Eric Wang
Abstract: Federated embodied agent learning protects the data privacy of individual visual environments by keeping data locally at each client (the individual environment) during training. However, since the local data is inaccessible to the server under federated learning, attackers may easily poison the training data of the local client to build a backdoor in the agent without notice. Deploying such an agent raises the risk of potential harm to humans, as the attackers may easily navigate and control the agent as they wish via the backdoor. Towards Byzantine-robust federated embodied agent learning, in this paper, we study the attack and defense for the task of vision-and-language navigation (VLN), where the agent is required to follow natural language instructions to navigate indoor environments. First, we introduce a simple but effective attack strategy, Navigation as Wish (NAW), in which the malicious client manipulates local trajectory data to implant a backdoor into the global model. Results on two VLN datasets (R2R and RxR) show that NAW can easily navigate the deployed VLN agent regardless of the language instruction, without affecting its performance on normal test sets. Then, we propose a new Prompt-Based Aggregation (PBA) to defend against the NAW attack in federated VLN, which provides the server with a ''prompt'' of the vision-and-language alignment variance between the benign and malicious clients so that they can be distinguished during training. We validate the effectiveness of the PBA method on protecting the global model from the NAW attack, which outperforms other state-of-the-art defense methods by a large margin in the defense metrics on R2R and RxR.
Authors: Soroosh Tayebi Arasteh, Alexander Ziller, Christiane Kuhl, Marcus Makowski, Sven Nebelung, Rickmer Braren, Daniel Rueckert, Daniel Truhn, Georgios Kaissis
Abstract: Artificial intelligence (AI) models are increasingly used in the medical domain. However, as medical data is highly sensitive, special precautions to ensure its protection are required. The gold standard for privacy preservation is the introduction of differential privacy (DP) to model training. Prior work indicates that DP has negative implications on model accuracy and fairness, which are unacceptable in medicine and represent a main barrier to the widespread use of privacy-preserving techniques. In this work, we evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training. For this, we used two datasets: (1) A large dataset (N=193,311) of high quality clinical chest radiographs, and (2) a dataset (N=1,625) of 3D abdominal computed tomography (CT) images, with the task of classifying the presence of pancreatic ductal adenocarcinoma (PDAC). Both were retrospectively collected and manually labeled by experienced radiologists. We then compared non-private deep convolutional neural networks (CNNs) and privacy-preserving (DP) models with respect to privacy-utility trade-offs measured as area under the receiver-operator-characteristic curve (AUROC), and privacy-fairness trade-offs, measured as Pearson's r or Statistical Parity Difference. We found that, while the privacy-preserving trainings yielded lower accuracy, they did largely not amplify discrimination against age, sex or co-morbidity. Our study shows that -- under the challenging realistic circumstances of a real-life clinical dataset -- the privacy-preserving training of diagnostic deep learning models is possible with excellent diagnostic accuracy and fairness.
Authors: Hongyi Yuan, Songchi Zhou, Sheng Yu
Abstract: Electronic health records (EHR) contain a wealth of biomedical information, serving as valuable resources for the development of precision medicine systems. However, privacy concerns have resulted in limited access to high-quality and large-scale EHR data for researchers, impeding progress in methodological development. Recent research has delved into synthesizing realistic EHR data through generative modeling techniques, where a majority of proposed methods relied on generative adversarial networks (GAN) and their variants for EHR synthesis. Despite GAN-based methods attaining state-of-the-art performance in generating EHR data, these approaches are difficult to train and prone to mode collapse. Recently introduced in generative modeling, diffusion models have established cutting-edge performance in image generation, but their efficacy in EHR data synthesis remains largely unexplored. In this study, we investigate the potential of diffusion models for EHR data synthesis and introduce a novel method, EHRDiff. Through extensive experiments, EHRDiff establishes new state-of-the-art quality for synthetic EHR data, protecting private information in the meanwhile.
Authors: Yuheng Li, Jacob Wynne, Jing Wang, Richard L. J. Qiu, Justin Roper, Shaoyan Pan, Ashesh B. Jani, Tian Liu, Pretesh R. Patel, Hui Mao, Xiaofeng Yang
Abstract: Biparametric magnetic resonance imaging (bpMRI) has demonstrated promising results in prostate cancer (PCa) detection using convolutional neural networks (CNNs). Recently, transformers have achieved competitive performance compared to CNNs in computer vision. Large scale transformers need abundant annotated data for training, which are difficult to obtain in medical imaging. Self-supervised learning (SSL) utilizes unlabeled data to generate meaningful semantic representations without the need for costly annotations, enhancing model performance on tasks with limited labeled data. We introduce a novel end-to-end Cross-Shaped windows (CSwin) transformer UNet model, CSwin UNet, to detect clinically significant prostate cancer (csPCa) in prostate bi-parametric MR imaging (bpMRI) and demonstrate the effectiveness of our proposed self-supervised pre-training framework. Using a large prostate bpMRI dataset with 1500 patients, we first pretrain CSwin transformer using multi-task self-supervised learning to improve data-efficiency and network generalizability. We then finetune using lesion annotations to perform csPCa detection. Five-fold cross validation shows that self-supervised CSwin UNet achieves 0.888 AUC and 0.545 Average Precision (AP), significantly outperforming four comparable models (Swin UNETR, DynUNet, Attention UNet, UNet). Using a separate bpMRI dataset with 158 patients, we evaluate our method robustness to external hold-out data. Self-supervised CSwin UNet achieves 0.79 AUC and 0.45 AP, still outperforming all other comparable methods and demonstrating good generalization to external data.
Authors: Hayeong Song, Gonzalo Ramos, Peter Bodik
Abstract: Creating Computer Vision (CV) models remains a complex practice, despite their ubiquity. Access to data, the requirement for ML expertise, and model opacity are just a few points of complexity that limit the ability of end-users to build, inspect, and improve these models. Interactive ML perspectives have helped address some of these issues by considering a teacher in the loop where planning, teaching, and evaluating tasks take place. We present and evaluate two interactive visualizations in the context of Sprite, a system for creating CV classification and detection models for images originating from videos. We study how these visualizations help Sprite's users identify (evaluate) and select (plan) images where a model is struggling and can lead to improved performance, compared to a baseline condition where users used a query language. We found that users who had used the visualizations found more images across a wider set of potential types of model errors.
Authors: Sven Dummer, Nicola Strisciuglio, Christoph Brune
Abstract: Diffeomorphic registration frameworks such as Large Deformation Diffeomorphic Metric Mapping (LDDMM) are used in computer graphics and the medical domain for atlas building, statistical latent modeling, and pairwise and groupwise registration. In recent years, researchers have developed neural network-based approaches regarding diffeomorphic registration to improve the accuracy and computational efficiency of traditional methods. In this work, we focus on a limitation of neural network-based atlas building and statistical latent modeling methods, namely that they either are (i) resolution dependent or (ii) disregard any data/problem-specific geometry needed for proper mean-variance analysis. In particular, we overcome this limitation by designing a novel encoder based on resolution-independent implicit neural representations. The encoder achieves resolution invariance for LDDMM-based statistical latent modeling. Additionally, the encoder adds LDDMM Riemannian geometry to resolution-independent deep learning models for statistical latent modeling. We showcase that the Riemannian geometry aspect improves latent modeling and is required for a proper mean-variance analysis. Furthermore, to showcase the benefit of resolution independence for LDDMM-based data variability modeling, we show that our approach outperforms another neural network-based LDDMM latent code model. Our work paves a way to more research into how Riemannian geometry, shape/image analysis, and deep learning can be combined.
Authors: Chanwut Kittivorawong, Yongming Ge, Yousef Helal, Alvin Cheung
Abstract: Videos that are shot using commodity hardware such as phones and surveillance cameras record various metadata such as time and location. We encounter such geospatial videos on a daily basis and such videos have been growing in volume significantly. Yet, we do not have data management systems that allow users to interact with such data effectively. In this paper, we describe Spatialyze, a new framework for end-to-end querying of geospatial videos. Spatialyze comes with a domain-specific language where users can construct geospatial video analytic workflows using a 3-step, declarative, build-filter-observe paradigm. Internally, Spatialyze leverages the declarative nature of such workflows, the temporal-spatial metadata stored with videos, and physical behavior of real-world objects to optimize the execution of workflows. Our results using real-world videos and workflows show that Spatialyze can reduce execution time by up to 5.3x, while maintaining up to 97.1% accuracy compared to unoptimized execution.
Authors: Mojtaba Yeganejou, Kimia Honari, Ryan Kluzinski, Scott Dick, Michael Lipsett, James Miller
Abstract: A key challenge in eXplainable Artificial Intelligence is the well-known tradeoff between the transparency of an algorithm (i.e., how easily a human can directly understand the algorithm, as opposed to receiving a post-hoc explanation), and its accuracy. We report on the design of a new deep network that achieves improved transparency without sacrificing accuracy. We design a deep convolutional neuro-fuzzy inference system (DCNFIS) by hybridizing fuzzy logic and deep learning models and show that DCNFIS performs as accurately as existing convolutional neural networks on four well-known datasets and 3 famous architectures. Our performance comparison with available fuzzy methods show that DCNFIS is now state-of-the-art fuzzy system and outperforms other shallow and deep fuzzy methods to the best of our knowledge. At the end, we exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in the network to take benefit of fuzzy logic upon regular deep learning methods. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset.
Authors: Jiajia Li, Mingle Xu, Lirong Xiang, Dong Chen, Weichao Zhuang, Xunyuan Yin, Zhaojian Li
Abstract: The past decade has witnessed the rapid development and adoption of ML & DL methodologies in agricultural systems, showcased by great successes in agricultural applications. However, these conventional ML/DL models have certain limitations: they heavily rely on large, costly-to-acquire labeled datasets for training, require specialized expertise for development and maintenance, and are mostly tailored for specific tasks, thus lacking generalizability. Recently, large pre-trained models, also known as FMs, have demonstrated remarkable successes in language, vision, and decision-making tasks across various domains. These models are trained on a large amount of data from multiple domains and modalities. Once trained, they can accomplish versatile tasks with just minor fine-tuning and minimal task-specific labeled data. Despite their proven effectiveness and huge potential, there has been little exploration of applying FMs to agriculture AI. Thus, this study aims to explore the potential of FMs in the field of smart agriculture. In particular, conceptual tools and technical background are presented to help the understanding of the problem space and uncover new research directions. To this end, recent FMs in the general CS domain are reviewed, and the models are categorized into four categories: language FMs, vision FMs, multimodal FMs, and reinforcement learning FMs. Then, the steps of developing agriculture FMs (AFMs) are outlined and potential applications in smart agriculture are discussed. Moreover, challenges and risks associated with developing AFMs are discussed, including model training, validation, and deployment. In summary, the advancement of AI in agriculture is explored by introducing AFMs as a promising paradigm that can significantly mitigate the reliance on extensive labeled datasets and enhance the efficiency, effectiveness, and generalization of agricultural AI systems.
Authors: Diganta Misra, Muawiz Chaudhary, Agam Goyal, Bharat Runwal, Pin Yu Chen
Abstract: In an age dominated by resource-intensive foundation models, the ability to efficiently adapt to downstream tasks is crucial. Visual Prompting (VP), drawing inspiration from the prompting techniques employed in Large Language Models (LLMs), has emerged as a pivotal method for transfer learning in the realm of computer vision. As the importance of efficiency continues to rise, research into model compression has become indispensable in alleviating the computational burdens associated with training and deploying over-parameterized neural networks. A primary objective in model compression is to develop sparse and/or quantized models capable of matching or even surpassing the performance of their over-parameterized, full-precision counterparts. Although previous studies have explored the effects of model compression on transfer learning, its impact on visual prompting-based transfer remains unclear. This study aims to bridge this gap, shedding light on the fact that model compression detrimentally impacts the performance of visual prompting-based transfer, particularly evident in scenarios with low data volume. Furthermore, our findings underscore the adverse influence of sparsity on the calibration of downstream visual-prompted models. However, intriguingly, we also illustrate that such negative effects on calibration are not present when models are compressed via quantization. This empirical investigation underscores the need for a nuanced understanding beyond mere accuracy in sparse and quantized settings, thereby paving the way for further exploration in Visual Prompting techniques tailored for sparse and quantized models.
Authors: Ashmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya, Yaman K Singla, Somesh Singh, Uttaran Bhattacharya, Ishita Dasgupta, Stefano Petrangeli, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy
Abstract: Shannon and Weaver's seminal information theory divides communication into three levels: technical, semantic, and effectiveness. While the technical level deals with the accurate reconstruction of transmitted symbols, the semantic and effectiveness levels deal with the inferred meaning and its effect on the receiver. Large Language Models (LLMs), with their wide generalizability, make some progress towards the second level. However, LLMs and other communication models are not conventionally designed for predicting and optimizing communication for desired receiver behaviors and intents. As a result, the effectiveness level remains largely untouched by modern communication systems. In this paper, we introduce the receivers' "behavior tokens," such as shares, likes, clicks, purchases, and retweets, in the LLM's training corpora to optimize content for the receivers and predict their behaviors. Other than showing similar performance to LLMs on content understanding tasks, our trained models show generalization capabilities on the behavior dimension for behavior simulation, content simulation, behavior understanding, and behavior domain adaptation. We show results on all these capabilities using a wide range of tasks on three corpora. We call these models Large Content and Behavior Models (LCBMs). Further, to spur more research on LCBMs, we release our new Content Behavior Corpus (CBC), a repository containing communicator, message, and corresponding receiver behavior (https://behavior-in-the-wild.github.io/LCBM).
Authors: Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, Huaxiu Yao
Abstract: Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination, which is the problem of generating descriptions that include objects that do not actually exist in the images. This can negatively impact many vision-language tasks, such as visual summarization and reasoning. To address this issue, we propose a simple yet powerful algorithm, LVLM Hallucination Revisor (LURE), to post-hoc rectify object hallucination in LVLMs by reconstructing less hallucinatory descriptions. LURE is grounded in a rigorous statistical analysis of the key factors underlying object hallucination, including co-occurrence (the frequent appearance of certain objects alongside others in images), uncertainty (objects with higher uncertainty during LVLM decoding), and object position (hallucination often appears in the later part of the generated text). LURE can also be seamlessly integrated with any LVLMs. We evaluate LURE on six open-source LVLMs, achieving a 23% improvement in general object hallucination evaluation metrics over the previous best approach. In both GPT and human evaluations, LURE consistently ranks at the top. Our data and code are available at https://github.com/YiyangZhou/LURE.
Authors: Shutong Jin, Ruiyu Wang, Muhammad Zahid, Florian T. Pokorny
Abstract: As model and dataset sizes continue to scale in robot learning, the need to understand what is the specific factor in the dataset that affects model performance becomes increasingly urgent to ensure cost-effective data collection and model performance. In this work, we empirically investigate how physics attributes (color, friction coefficient, shape) and scene background characteristics, such as the complexity and dynamics of interactions with background objects, influence the performance of Video Transformers in predicting planar pushing trajectories. We aim to investigate three primary questions: How do physics attributes and background scene characteristics influence model performance? What kind of changes in attributes are most detrimental to model generalization? What proportion of fine-tuning data is required to adapt models to novel scenarios? To facilitate this research, we present CloudGripper-Push-1K, a large real-world vision-based robot pushing dataset comprising 1278 hours and 460,000 videos of planar pushing interactions with objects with different physics and background attributes. We also propose Video Occlusion Transformer (VOT), a generic modular video-transformer-based trajectory prediction framework which features 3 choices of 2D-spatial encoders as the subject of our case study. Dataset and codes will be available at https://cloudgripper.org.
Authors: Yuhang Hu, Zhizhuo Zhang, Xinyue Zhu, Ruibo Liu, Philippe Wyder, Hod Lipson
Abstract: Addressing the challenge of organizing scattered items in domestic spaces is complicated by the diversity and subjective nature of tidiness. Just as the complexity of human language allows for multiple expressions of the same idea, household tidiness preferences and organizational patterns vary widely, so presetting object locations would limit the adaptability to new objects and environments. Inspired by advancements in natural language processing (NLP), this paper introduces a self-supervised learning framework that allows robots to understand and replicate the concept of tidiness from demonstrations of well-organized layouts, akin to using conversational datasets to train Large Language Models(LLM). We leverage a transformer neural network to predict the placement of subsequent objects. We demonstrate a ``knolling'' system with a robotic arm and an RGB camera to organize items of varying sizes and quantities on a table. Our method not only trains a generalizable concept of tidiness, enabling the model to provide diverse solutions and adapt to different numbers of objects, but it can also incorporate human preferences to generate customized tidy tables without explicit target positions for each object.
Authors: Jonathan Vacher, Pascal Mamassian
Abstract: Perception is often viewed as a process that transforms physical variables, external to an observer, into internal psychological variables. Such a process can be modeled by a function coined perceptual scale. The perceptual scale can be deduced from psychophysical measurements that consist in comparing the relative differences between stimuli (i.e. difference scaling experiments). However, this approach is often overlooked by the modeling and experimentation communities. Here, we demonstrate the value of measuring the perceptual scale of classical (spatial frequency, orientation) and less classical physical variables (interpolation between textures) by embedding it in recent probabilistic modeling of perception. First, we show that the assumption that an observer has an internal representation of univariate parameters such as spatial frequency or orientation while stimuli are high-dimensional does not lead to contradictory predictions when following the theoretical framework. Second, we show that the measured perceptual scale corresponds to the transduction function hypothesized in this framework. In particular, we demonstrate that it is related to the Fisher information of the generative model that underlies perception and we test the predictions given by the generative model of different stimuli in a set a of difference scaling experiments. Our main conclusion is that the perceptual scale is mostly driven by the stimulus power spectrum. Finally, we propose that this measure of perceptual scale is a way to push further the notion of perceptual distances by estimating the perceptual geometry of images i.e. the path between images instead of simply the distance between those.
Authors: Qianxu Wang, Haotong Zhang, Congyue Deng, Yang You, Hao Dong, Yixin Zhu, Leonidas Guibas
Abstract: Humans demonstrate remarkable skill in transferring manipulation abilities across objects of varying shapes, poses, and appearances, a capability rooted in their understanding of semantic correspondences between different instances. To equip robots with a similar high-level comprehension, we present SparseDFF, a novel DFF for 3D scenes utilizing large 2D vision models to extract semantic features from sparse RGBD images, a domain where research is limited despite its relevance to many tasks with fixed-camera setups. SparseDFF generates view-consistent 3D DFFs, enabling efficient one-shot learning of dexterous manipulations by mapping image features to a 3D point cloud. Central to SparseDFF is a feature refinement network, optimized with a contrastive loss between views and a point-pruning mechanism for feature continuity. This facilitates the minimization of feature discrepancies w.r.t. end-effector parameters, bridging demonstrations and target manipulations. Validated in real-world scenarios with a dexterous hand, SparseDFF proves effective in manipulating both rigid and deformable objects, demonstrating significant generalization capabilities across object and scene variations.
Authors: Chawin Sitawarin, Jaewon Chang, David Huang, Wesson Altoyan, David Wagner
Abstract: Adversarial attacks have been a looming and unaddressed threat in the industry. However, through a decade-long history of the robustness evaluation literature, we have learned that mounting a strong or optimal attack is challenging. It requires both machine learning and domain expertise. In other words, the white-box threat model, religiously assumed by a large majority of the past literature, is unrealistic. In this paper, we propose a new practical threat model where the adversary relies on transfer attacks through publicly available surrogate models. We argue that this setting will become the most prevalent for security-sensitive applications in the future. We evaluate the transfer attacks in this setting and propose a specialized defense method based on a game-theoretic perspective. The defenses are evaluated under 24 public models and 11 attack algorithms across three datasets (CIFAR-10, CIFAR-100, and ImageNet). Under this threat model, our defense, PubDef, outperforms the state-of-the-art white-box adversarial training by a large margin with almost no loss in the normal accuracy. For instance, on ImageNet, our defense achieves 62% accuracy under the strongest transfer attack vs only 36% of the best adversarially trained model. Its accuracy when not under attack is only 2% lower than that of an undefended model (78% vs 80%). We release our code at https://github.com/wagner-group/pubdef.
Authors: Iu Yahiro, Takashi Ishida, Naoto Yokoya
Abstract: Generative Adversarial Networks (GANs) have shown remarkable performance in image generation. However, GAN training suffers from the problem of instability. One of the main approaches to address this problem is to modify the loss function, often using regularization terms in addition to changing the type of adversarial losses. This paper focuses on directly regularizing the adversarial loss function. We propose a method that applies flooding, an overfitting suppression method in supervised learning, to GANs to directly prevent the discriminator's loss from becoming excessively low. Flooding requires tuning the flood level, but when applied to GANs, we propose that the appropriate range of flood level settings is determined by the adversarial loss function, supported by theoretical analysis of GANs using the binary cross entropy loss. We experimentally verify that flooding stabilizes GAN training and can be combined with other stabilization techniques. We also show that by restricting the discriminator's loss to be no less than the flood level, the training proceeds stably even when the flood level is somewhat high.
Authors: Kuancheng Wang, Hai Siong Tan, Rafe Mcbeth
Abstract: The field of Radiation Oncology is uniquely positioned to benefit from the use of artificial intelligence to fully automate the creation of radiation treatment plans for cancer therapy. This time-consuming and specialized task combines patient imaging with organ and tumor segmentation to generate a 3D radiation dose distribution to meet clinical treatment goals, similar to voxel-level dense prediction. In this work, we propose Swin UNETR++, that contains a lightweight 3D Dual Cross-Attention (DCA) module to capture the intra and inter-volume relationships of each patient's unique anatomy, which fully convolutional neural networks lack. Our model was trained, validated, and tested on the Open Knowledge-Based Planning dataset. In addition to metrics of Dose Score $\overline{S_{\text{Dose}}}$ and DVH Score $\overline{S_{\text{DVH}}}$ that quantitatively measure the difference between the predicted and ground-truth 3D radiation dose distribution, we propose the qualitative metrics of average volume-wise acceptance rate $\overline{R_{\text{VA}}}$ and average patient-wise clinical acceptance rate $\overline{R_{\text{PA}}}$ to assess the clinical reliability of the predictions. Swin UNETR++ demonstrates near-state-of-the-art performance on validation and test dataset (validation: $\overline{S_{\text{DVH}}}$=1.492 Gy, $\overline{S_{\text{Dose}}}$=2.649 Gy, $\overline{R_{\text{VA}}}$=88.58%, $\overline{R_{\text{PA}}}$=100.0%; test: $\overline{S_{\text{DVH}}}$=1.634 Gy, $\overline{S_{\text{Dose}}}$=2.757 Gy, $\overline{R_{\text{VA}}}$=90.50%, $\overline{R_{\text{PA}}}$=98.0%), establishing a basis for future studies to translate 3D dose predictions into a deliverable treatment plan, facilitating full automation.
Authors: Jamil Fayyad, Shadi Alijani, Homayoun Najjaran
Abstract: Background and objective: Uncertainty quantification is a pivotal field that contributes to realizing reliable and robust systems. It becomes instrumental in fortifying safe decisions by providing complementary information, particularly within high-risk applications. existing studies have explored various methods that often operate under specific assumptions or necessitate substantial modifications to the network architecture to effectively account for uncertainties. The objective of this paper is to study Conformal Prediction, an emerging distribution-free uncertainty quantification technique, and provide a comprehensive understanding of the advantages and limitations inherent in various methods within the medical imaging field. Methods: In this study, we developed Conformal Prediction, Monte Carlo Dropout, and Evidential Deep Learning approaches to assess uncertainty quantification in deep neural networks. The effectiveness of these methods is evaluated using three public medical imaging datasets focused on detecting pigmented skin lesions and blood cell types. Results: The experimental results demonstrate a significant enhancement in uncertainty quantification with the utilization of the Conformal Prediction method, surpassing the performance of the other two methods. Furthermore, the results present insights into the effectiveness of each uncertainty method in handling Out-of-Distribution samples from domain-shifted datasets. Our code is available at: Conclusions: Our conclusion highlights a robust and consistent performance of conformal prediction across diverse testing conditions. This positions it as the preferred choice for decision-making in safety-critical applications.
Authors: Hongyuan Wang, Lizhi Wang, Jiang Xu, Chang Chen, Xue Hu, Fenglong Song, Youliang Yan
Abstract: Spectral super-resolution that aims to recover hyperspectral image (HSI) from easily obtainable RGB image has drawn increasing interest in the field of computational photography. The crucial aspect of spectral super-resolution lies in exploiting the correlation within HSIs. However, two types of bottlenecks in existing Transformers limit performance improvement and practical applications. First, existing Transformers often separately emphasize either spatial-wise or spectral-wise correlation, disrupting the 3D features of HSI and hindering the exploitation of unified spatial-spectral correlation. Second, existing self-attention mechanism always establishes full-rank correlation matrix by learning the correlation between pairs of tokens, leading to its inability to describe linear dependence widely existing in HSI among multiple tokens. To address these issues, we propose a novel Exhaustive Correlation Transformer (ECT) for spectral super-resolution. First, we propose a Spectral-wise Discontinuous 3D (SD3D) splitting strategy, which models unified spatial-spectral correlation by integrating spatial-wise continuous splitting strategy and spectral-wise discontinuous splitting strategy. Second, we propose a Dynamic Low-Rank Mapping (DLRM) model, which captures linear dependence among multiple tokens through a dynamically calculated low-rank dependence map. By integrating unified spatial-spectral attention and linear dependence, our ECT can model exhaustive correlation within HSI. The experimental results on both simulated and real data indicate that our method achieves state-of-the-art performance. Codes and pretrained models will be available later.
Authors: Tao Huang, Guangqi Jiang, Yanjie Ze, Huazhe Xu
Abstract: Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning tasks. In this work, we propose Diffusion Reward, a novel framework that learns rewards from expert videos via conditional video diffusion models for solving complex visual RL problems. Our key insight is that lower generative diversity is observed when conditioned on expert trajectories. Diffusion Reward is accordingly formalized by the negative of conditional entropy that encourages productive exploration of expert-like behaviors. We show the efficacy of our method over 10 robotic manipulation tasks from MetaWorld and Adroit with visual input and sparse reward. Moreover, Diffusion Reward could even solve unseen tasks successfully and effectively, largely surpassing baseline methods. Project page and code: https://diffusion-reward.github.io/.
Authors: Tsachi Blau, Sharon Fogel, Roi Ronen, Alona Golts, Roy Ganz, Elad Ben Avraham, Aviad Aberdam, Shahar Tsiper, Ron Litman
Abstract: The increasing use of transformer-based large language models brings forward the challenge of processing long sequences. In document visual question answering (DocVQA), leading methods focus on the single-page setting, while documents can span hundreds of pages. We present GRAM, a method that seamlessly extends pre-trained single-page models to the multi-page setting, without requiring computationally-heavy pretraining. To do so, we leverage a single-page encoder for local page-level understanding, and enhance it with document-level designated layers and learnable tokens, facilitating the flow of information across pages for global reasoning. To enforce our model to utilize the newly introduced document tokens, we propose a tailored bias adaptation method. For additional computational savings during decoding, we introduce an optional compression stage using our compression-transformer (C-Former),reducing the encoded sequence length, thereby allowing a tradeoff between quality and latency. Extensive experiments showcase GRAM's state-of-the-art performance on the benchmarks for multi-page DocVQA, demonstrating the effectiveness of our approach.
Authors: Annika Thomas, Jouko Kinnari, Parker Lusk, Kota Kondo, Jonathan P. How
Abstract: We present SOS-Match, a novel framework for detecting and matching objects in unstructured environments. Our system consists of 1) a front-end mapping pipeline using a zero-shot segmentation model to extract object masks from images and track them across frames and 2) a frame alignment pipeline that uses the geometric consistency of object relationships to efficiently localize across a variety of conditions. We evaluate SOS-Match on the Batvik seasonal dataset which includes drone flights collected over a coastal plot of southern Finland during different seasons and lighting conditions. Results show that our approach is more robust to changes in lighting and appearance than classical image feature-based approaches or global descriptor methods, and it provides more viewpoint invariance than learning-based feature detection and description approaches. SOS-Match localizes within a reference map up to 46x faster than other feature-based approaches and has a map size less than 0.5% the size of the most compact other maps. SOS-Match is a promising new approach for landmark detection and correspondence search in unstructured environments that is robust to changes in lighting and appearance and is more computationally efficient than other approaches, suggesting that the geometric arrangement of segments is a valuable localization cue in unstructured environments. We release our datasets at https://acl.mit.edu/SOS-Match/.
Authors: Ge Zhang, Xinrun Du, Bei Chen, Yiming Liang, Tongxu Luo, Tianyu Zheng, Kang Zhu, Yuyang Cheng, Chunpu Xu, Shuyue Guo, Haoran Zhang, Xingwei Qu, Junjie Wang, Ruibin Yuan, Yizhi Li, Zekun Wang, Yudong Liu, Yu-Hsuan Tsai, Fengji Zhang, Chenghua Lin, Wenhao Huang, Wenhu Chen, Jie Fu
Abstract: As the capabilities of large multimodal models (LMMs) continue to advance, evaluating the performance of LMMs emerges as an increasing need. Additionally, there is an even larger gap in evaluating the advanced knowledge and reasoning abilities of LMMs in non-English contexts such as Chinese. We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context. CMMMU is inspired by and strictly follows the annotation and analysis pattern of MMMU. CMMMU includes 12k manually collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering, like its companion, MMMU. These questions span 30 subjects and comprise 39 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. CMMMU focuses on complex perception and reasoning with domain-specific knowledge in the Chinese context. We evaluate 11 open-source LLMs and one proprietary GPT-4V(ision). Even GPT-4V only achieves accuracies of 42%, indicating a large space for improvement. CMMMU will boost the community to build the next-generation LMMs towards expert artificial intelligence and promote the democratization of LMMs by providing diverse language contexts.
Authors: Rui Qiao, Bryan Kian Hsiang Low
Abstract: Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks. To better understand this phenomenon, we investigate whether there are benefits of DG algorithms over ERM through the lens of label noise. Specifically, our finite-sample analysis reveals that label noise exacerbates the effect of spurious correlations for ERM, undermining generalization. Conversely, we illustrate that DG algorithms exhibit implicit label-noise robustness during finite-sample training even when spurious correlation is present. Such desirable property helps mitigate spurious correlations and improve generalization in synthetic experiments. However, additional comprehensive experiments on real-world benchmark datasets indicate that label-noise robustness does not necessarily translate to better performance compared to ERM. We conjecture that the failure mode of ERM arising from spurious correlations may be less pronounced in practice.
Authors: Sheng Li, Geng Yuan, Yawen Wu, Yue Dai, Chao Wu, Alex K. Jones, Jingtong Hu, Yanzhi Wang, Xulong Tang
Abstract: Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes. Online model fine-tuning is widely adopted to satisfy these needs. However, an inappropriate fine-tuning scheme could involve significant energy consumption, making it challenging to deploy on edge devices. In this paper, we propose EdgeOL, an edge online learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy.
Authors: Pranav Kulkarni, Andrew Chan, Nithya Navarathna, Skylar Chan, Paul H. Yi, Vishwa S. Parekh
Abstract: The proliferation of artificial intelligence (AI) in radiology has shed light on the risk of deep learning (DL) models exacerbating clinical biases towards vulnerable patient populations. While prior literature has focused on quantifying biases exhibited by trained DL models, demographically targeted adversarial bias attacks on DL models and its implication in the clinical environment remains an underexplored field of research in medical imaging. In this work, we demonstrate that demographically targeted label poisoning attacks can introduce undetectable underdiagnosis bias in DL models. Our results across multiple performance metrics and demographic groups like sex, age, and their intersectional subgroups show that adversarial bias attacks demonstrate high-selectivity for bias in the targeted group by degrading group model performance without impacting overall model performance. Furthermore, our results indicate that adversarial bias attacks result in biased DL models that propagate prediction bias even when evaluated with external datasets.
Authors: Collin Hague, Nick Kakavitsas, Jincheng Zhang, Chris Beam, Andrew Willis, Artur Wolek
Abstract: This paper describes the hardware design and flight demonstration of a small quadrotor with imaging sensors for urban mapping, hazard avoidance, and target tracking research. The vehicle is equipped with five cameras, including two pairs of fisheye stereo cameras that enable a nearly omnidirectional view and a two-axis gimbaled camera. An onboard NVIDIA Jetson Orin Nano computer running the Robot Operating System software is used for data collection. An autonomous tracking behavior was implemented to coordinate the motion of the quadrotor and gimbaled camera to track a moving GPS coordinate. The data collection system was demonstrated through a flight test that tracked a moving GPS-tagged vehicle through a series of roads and parking lots. A map of the environment was reconstructed from the collected images using the Direct Sparse Odometry (DSO) algorithm. The performance of the quadrotor was also characterized by acoustic noise, communication range, battery voltage in hover, and maximum speed tests.
Authors: Xinjie Zhang, Ren Yang, Dailan He, Xingtong Ge, Tongda Xu, Yan Wang, Hongwei Qin, Jun Zhang
Abstract: Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capabilities, primarily due to inadequate alignment of intermediate features during target frame decoding. This paper introduces a universal boosting framework for current implicit video representation approaches. Specifically, we utilize a conditional decoder with a temporal-aware affine transform module, which uses the frame index as a prior condition to effectively align intermediate features with target frames. Besides, we introduce a sinusoidal NeRV-like block to generate diverse intermediate features and achieve a more balanced parameter distribution, thereby enhancing the model's capacity. With a high-frequency information-preserving reconstruction loss, our approach successfully boosts multiple baseline INRs in the reconstruction quality and convergence speed for video regression, and exhibits superior inpainting and interpolation results. Further, we integrate a consistent entropy minimization technique and develop video codecs based on these boosted INRs. Experiments on the UVG dataset confirm that our enhanced codecs significantly outperform baseline INRs and offer competitive rate-distortion performance compared to traditional and learning-based codecs. Code is available at https://github.com/Xinjie-Q/Boosting-NeRV.
Authors: Fatemeh Ahmadi, Mohamad Ebrahim Shiri, Behroz Bidabad, Maral Sedaghat, Pooran Memari
Abstract: Automated feature extraction from MRI brain scans and diagnosis of Alzheimer's disease are ongoing challenges. With advances in 3D imaging technology, 3D data acquisition is becoming more viable and efficient than its 2D counterpart. Rather than using feature-based vectors, in this paper, for the first time, we suggest a pipeline to extract novel covariance-based descriptors from the cortical surface using the Ricci energy optimization. The covariance descriptors are components of the nonlinear manifold of symmetric positive-definite matrices, thus we focus on using the Gaussian radial basis function to apply manifold-based classification to the 3D shape problem. Applying this novel signature to the analysis of abnormal cortical brain morphometry allows for diagnosing Alzheimer's disease. Experimental studies performed on about two hundred 3D MRI brain models, gathered from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate the effectiveness of our descriptors in achieving remarkable classification accuracy.
Authors: Zihao Tang, Zheqi Lv, Shengyu Zhang, Yifan Zhou, Xinyu Duan, Fei Wu, Kun Kuang
Abstract: Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation (DFKD) methods have emerged as direct solutions. However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain). The degradation stems from the portions of teachers' knowledge that are not applicable to the student domain. They are specific to the teacher domain and would undermine students' performance. Hence, selectively transferring teachers' appropriate knowledge becomes the primary challenge in DFKD. In this work, we propose a simple but effective method AuG-KD. It utilizes an uncertainty-guided and sample-specific anchor to align student-domain data with the teacher domain and leverages a generative method to progressively trade off the learning process between OOD knowledge distillation and domain-specific information learning via mixup learning. Extensive experiments in 3 datasets and 8 settings demonstrate the stability and superiority of our approach. Code available at https://github.com/IshiKura-a/AuG-KD .
Authors: Ivo M. Baltruschat, Parvaneh Janbakhshi, Matthias Lenga
Abstract: This work addresses the Brain Magnetic Resonance Image Synthesis for Tumor Segmentation (BraSyn) challenge, which was hosted as part of the Brain Tumor Segmentation (BraTS) challenge in 2023. In this challenge, researchers are invited to synthesize a missing magnetic resonance image sequence, given other available sequences, to facilitate tumor segmentation pipelines trained on complete sets of image sequences. This problem can be tackled using deep learning within the framework of paired image-to-image translation. In this study, we propose investigating the effectiveness of a commonly used deep learning framework, such as Pix2Pix, trained under the supervision of different image-quality loss functions. Our results indicate that the use of different loss functions significantly affects the synthesis quality. We systematically study the impact of various loss functions in the multi-sequence MR image synthesis setting of the BraSyn challenge. Furthermore, we demonstrate how image synthesis performance can be optimized by combining different learning objectives beneficially.
Authors: Lipei Zhang, Yanqi Cheng, Lihao Liu, Carola-Bibiane Sch\"onlieb, Angelica I Aviles-Rivero
Abstract: Recent advancements in deep learning have significantly improved brain tumour segmentation techniques; however, the results still lack confidence and robustness as they solely consider image data without biophysical priors or pathological information. Integrating biophysics-informed regularisation is one effective way to change this situation, as it provides an prior regularisation for automated end-to-end learning. In this paper, we propose a novel approach that designs brain tumour growth Partial Differential Equation (PDE) models as a regularisation with deep learning, operational with any network model. Our method introduces tumour growth PDE models directly into the segmentation process, improving accuracy and robustness, especially in data-scarce scenarios. This system estimates tumour cell density using a periodic activation function. By effectively integrating this estimation with biophysical models, we achieve a better capture of tumour characteristics. This approach not only aligns the segmentation closer to actual biological behaviour but also strengthens the model's performance under limited data conditions. We demonstrate the effectiveness of our framework through extensive experiments on the BraTS 2023 dataset, showcasing significant improvements in both precision and reliability of tumour segmentation.
Authors: Zhikang Wang, Yumeng Zhang, Yingxue Xu, Seiya Imoto, Hao Chen, Jiangning Song
Abstract: Histo-genomic multi-modal methods have recently emerged as a powerful paradigm, demonstrating significant potential for improving cancer prognosis. However, genome sequencing, unlike histopathology imaging, is still not widely accessible in underdeveloped regions, limiting the application of these multi-modal approaches in clinical settings. To address this, we propose a novel Genome-informed Hyper-Attention Network, termed G-HANet, which is capable of effectively distilling the histo-genomic knowledge during training to elevate uni-modal whole slide image (WSI)-based inference for the first time. Compared with traditional knowledge distillation methods (i.e., teacher-student architecture) in other tasks, our end-to-end model is superior in terms of training efficiency and learning cross-modal interactions. Specifically, the network comprises the cross-modal associating branch (CAB) and hyper-attention survival branch (HSB). Through the genomic data reconstruction from WSIs, CAB effectively distills the associations between functional genotypes and morphological phenotypes and offers insights into the gene expression profiles in the feature space. Subsequently, HSB leverages the distilled histo-genomic associations as well as the generated morphology-based weights to achieve the hyper-attention modeling of the patients from both histopathology and genomic perspectives to improve cancer prognosis. Extensive experiments are conducted on five TCGA benchmarking datasets and the results demonstrate that G-HANet significantly outperforms the state-of-the-art WSI-based methods and achieves competitive performance with genome-based and multi-modal methods. G-HANet is expected to be explored as a useful tool by the research community to address the current bottleneck of insufficient histo-genomic data pairing in the context of cancer prognosis and precision oncology.