Authors: Zeyi Sun, Tong Wu, Pan Zhang, Yuhang Zang, Xiaoyi Dong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
Abstract: Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical bottleneck is the scarcity of high-quality 3D assets with detailed captions. To address this challenge, we propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images to assist in training multi-view diffusion models. Specifically, we introduce a data generation pipeline that employs (1) 2D and video diffusion models to generate multi-view images based on constructed text prompts, and (2) our fine-tuned 3D-aware MV-LLaVA for filtering high-quality data and rewriting inaccurate captions. Leveraging this pipeline, we have generated 1 million high-quality synthetic multi-view images with dense descriptive captions to address the shortage of high-quality 3D data. Furthermore, we present a Training Timestep Reschedule (TTR) strategy that leverages the denoising process to learn multi-view consistency while maintaining the original 2D diffusion prior. Extensive experiments demonstrate that Bootstrap3D can generate high-quality multi-view images with superior aesthetic quality, image-text alignment, and maintained view consistency.
Authors: Tiancheng Shen, Jun Hao Liew, Long Mai, Lu Qi, Jiashi Feng, Jiaya Jia
Abstract: Advances in text-based image generation and editing have revolutionized content creation, enabling users to create impressive content from imaginative text prompts. However, existing methods are not designed to work well with the oversimplified prompts that are often encountered in typical scenarios when users start their editing with only vague or abstract purposes in mind. Those scenarios demand elaborate ideation efforts from the users to bridge the gap between such vague starting points and the detailed creative ideas needed to depict the desired results. In this paper, we introduce the task of Image Editing Recommendation (IER). This task aims to automatically generate diverse creative editing instructions from an input image and a simple prompt representing the users' under-specified editing purpose. To this end, we introduce Creativity-Vision Language Assistant~(Creativity-VLA), a multimodal framework designed specifically for edit-instruction generation. We train Creativity-VLA on our edit-instruction dataset specifically curated for IER. We further enhance our model with a novel 'token-for-localization' mechanism, enabling it to support both global and local editing operations. Our experimental results demonstrate the effectiveness of \ours{} in suggesting instructions that not only contain engaging creative elements but also maintain high relevance to both the input image and the user's initial hint.
Authors: Youssef Mohamed, Zeyad Youssef, Ahmed Heakl, Ahmed Zaky
Abstract: Biometric identification is a reliable method to verify individuals based on their unique physical or behavioral traits, offering a secure alternative to traditional methods like passwords or PINs. This study focuses on ear biometric identification, exploiting its distinctive features for enhanced accuracy, reliability, and usability. While past studies typically investigate face recognition and fingerprint analysis, our research demonstrates the effectiveness of ear biometrics in overcoming limitations such as variations in facial expressions and lighting conditions. We utilized two datasets: AMI (700 images from 100 individuals) and EarNV1.0 (28,412 images from 164 individuals). To improve the accuracy and robustness of our ear biometric identification system, we applied various techniques including data preprocessing and augmentation. Our models achieved a testing accuracy of 99.35% on the AMI Dataset and 98.1% on the EarNV1.0 dataset, showcasing the effectiveness of our approach in precisely identifying individuals based on ear biometric characteristics.
Authors: Xiaolong Sun, Liushuai Shi, Le Wang, Sanping Zhou, Kun Xia, Yabing Wang, Gang Hua
Abstract: Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer from overlapped and redundant proposals, leading to inaccurate predictions. We attribute this limitation to the lack of task-related guidance for the learnable queries to serve a specific mode. Furthermore, the complex solution space generated by variable and open-vocabulary language descriptions exacerbates the optimization difficulty, making it harder for learnable queries to distinguish each other adaptively. To tackle this limitation, we present a Region-Guided TRansformer (RGTR) for temporal sentence grounding, which diversifies moment queries to eliminate overlapped and redundant predictions. Instead of using learnable queries, RGTR adopts a set of anchor pairs as moment queries to introduce explicit regional guidance. Each anchor pair takes charge of moment prediction for a specific temporal region, which reduces the optimization difficulty and ensures the diversity of the final predictions. In addition, we design an IoU-aware scoring head to improve proposal quality. Extensive experiments demonstrate the effectiveness of RGTR, outperforming state-of-the-art methods on QVHighlights, Charades-STA and TACoS datasets.
Authors: Zhengang Li, Yan Kang, Yuchen Liu, Difan Liu, Tobias Hinz, Feng Liu, Yanzhi Wang
Abstract: While AI-generated content has garnered significant attention, achieving photo-realistic video synthesis remains a formidable challenge. Despite the promising advances in diffusion models for video generation quality, the complex model architecture and substantial computational demands for both training and inference create a significant gap between these models and real-world applications. This paper presents SNED, a superposition network architecture search method for efficient video diffusion model. Our method employs a supernet training paradigm that targets various model cost and resolution options using a weight-sharing method. Moreover, we propose the supernet training sampling warm-up for fast training optimization. To showcase the flexibility of our method, we conduct experiments involving both pixel-space and latent-space video diffusion models. The results demonstrate that our framework consistently produces comparable results across different model options with high efficiency. According to the experiment for the pixel-space video diffusion model, we can achieve consistent video generation results simultaneously across 64 x 64 to 256 x 256 resolutions with a large range of model sizes from 640M to 1.6B number of parameters for pixel-space video diffusion models.
Authors: Jinchao Zhu, Yuxuan Wang, Siyuan Pan, Pengfei Wan, Di Zhang, Gao Huang
Abstract: The Stable Diffusion Model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these approaches typically maintain the original network architecture. The extensive parameter scale and substantial computational demands have limited research into adjusting the model architecture. 1) For the tuning method, we design a model assembly strategy to reconstruct a lightweight model while preserving performance through distillation. Second, to mitigate performance loss due to pruning, we incorporate multi-expert conditional convolution (ME-CondConv) into compressed UNets to enhance network performance by increasing capacity without sacrificing speed. Third, we validate the effectiveness of the multi-UNet switching method for improving network speed. 2) For the tuning-free method, we propose a feature inheritance strategy to accelerate inference by skipping local computations at the block, layer, or unit level within the network structure. We also examine multiple sampling modes for feature inheritance at the time-step level. Experiments demonstrate that both the proposed tuning and the tuning-free methods can improve the speed and performance of the SDM. The lightweight model reconstructed by the model assembly strategy increases generation speed by $22.4\%$, while the feature inheritance strategy enhances the SDM generation speed by $40.0\%$.
Authors: Bimsara Pathiraja, Caleb Liu, Ransalu Senanayake
Abstract: The deployment of autonomous vehicles (AVs) is rapidly expanding to numerous cities. At the heart of AVs, the object detection module assumes a paramount role, directly influencing all downstream decision-making tasks by considering the presence of nearby pedestrians, vehicles, and more. Despite high accuracy of pedestrians detected on held-out datasets, the potential presence of algorithmic bias in such object detectors, particularly in challenging weather conditions, remains unclear. This study provides a comprehensive empirical analysis of fairness in detecting pedestrians in a state-of-the-art transformer-based object detector. In addition to classical metrics, we introduce novel probability-based metrics to measure various intricate properties of object detection. Leveraging the state-of-the-art FACET dataset and the Carla high-fidelity vehicle simulator, our analysis explores the effect of protected attributes such as gender, skin tone, and body size on object detection performance in varying environmental conditions such as ambient darkness and fog. Our quantitative analysis reveals how the previously overlooked yet intuitive factors, such as the distribution of demographic groups in the scene, the severity of weather, the pedestrians' proximity to the AV, among others, affect object detection performance. Our code is available at https://github.com/bimsarapathiraja/fair-AV.
Authors: Haoan Feng, Xin Xu, Leila De Floriani
Abstract: Digital terrain models (DTMs) are pivotal in remote sensing, cartography, and landscape management, requiring accurate surface representation and topological information restoration. While topology analysis traditionally relies on smooth manifolds, the absence of an easy-to-use continuous surface model for a large terrain results in a preference for discrete meshes. Structural representation based on topology provides a succinct surface description, laying the foundation for many terrain analysis applications. However, on discrete meshes, numerical issues emerge, and complex algorithms are designed to handle them. This paper brings the context of terrain data analysis back to the continuous world and introduces ImplicitTerrain (Project homepage available at https://fengyee.github.io/implicit-terrain/), an implicit neural representation (INR) approach for modeling high-resolution terrain continuously and differentiably. Our comprehensive experiments demonstrate superior surface fitting accuracy, effective topological feature retrieval, and various topographical feature extraction that are implemented over this compact representation in parallel. To our knowledge, ImplicitTerrain pioneers a feasible continuous terrain surface modeling pipeline that provides a new research avenue for our community.
Authors: Nurul Rafi, Pablo Rivas
Abstract: Research in neural models inspired by mammal's visual cortex has led to many spiking neural networks such as pulse-coupled neural networks (PCNNs). These models are oscillating, spatio-temporal models stimulated with images to produce several time-based responses. This paper reviews PCNN's state of the art, covering its mathematical formulation, variants, and other simplifications found in the literature. We present several applications in which PCNN architectures have successfully addressed some fundamental image processing and computer vision challenges, including image segmentation, edge detection, medical imaging, image fusion, image compression, object recognition, and remote sensing. Results achieved in these applications suggest that the PCNN architecture generates useful perceptual information relevant to a wide variety of computer vision tasks.
Authors: Jihao Qiu, Yuan Zhang, Xi Tang, Lingxi Xie, Tianren Ma, Pengyu Yan, David Doermann, Qixiang Ye, Yunjie Tian
Abstract: Videos carry rich visual information including object description, action, interaction, etc., but the existing multimodal large language models (MLLMs) fell short in referential understanding scenarios such as video-based referring. In this paper, we present Artemis, an MLLM that pushes video-based referential understanding to a finer level. Given a video, Artemis receives a natural-language question with a bounding box in any video frame and describes the referred target in the entire video. The key to achieving this goal lies in extracting compact, target-specific video features, where we set a solid baseline by tracking and selecting spatiotemporal features from the video. We train Artemis on the newly established VideoRef45K dataset with 45K video-QA pairs and design a computationally efficient, three-stage training procedure. Results are promising both quantitatively and qualitatively. Additionally, we show that \model can be integrated with video grounding and text summarization tools to understand more complex scenarios. Code and data are available at https://github.com/qiujihao19/Artemis.
Authors: Zhengqing Wang, Jiacheng Chen, Yasutaka Furukawa
Abstract: This paper proposes a novel "auto-agglomerative" 3D fracture assembly method, PuzzleFusion++, resembling how humans solve challenging spatial puzzles. Starting from individual fragments, the approach 1) aligns and merges fragments into larger groups akin to agglomerative clustering and 2) repeats the process iteratively in completing the assembly akin to auto-regressive methods. Concretely, a diffusion model denoises the 6-DoF alignment parameters of the fragments simultaneously, and a transformer model verifies and merges pairwise alignments into larger ones, whose process repeats iteratively. Extensive experiments on the Breaking Bad dataset show that PuzzleFusion++ outperforms all other state-of-the-art techniques by significant margins across all metrics, in particular by over 10% in part accuracy and 50% in Chamfer distance. The code will be available on our project page: https://puzzlefusion-plusplus.github.io.
Authors: Raehyuk Jung, Sungmin Cho, Junseok Kwon
Abstract: We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected based methods.
Authors: AmirHossein Zamani, Amir G. Aghdam, Tiberiu Popa, Eugene Belilovsky
Abstract: Image generation and editing have seen a great deal of advancements with the rise of large-scale diffusion models that allow user control of different modalities such as text, mask, depth maps, etc. However, controlled editing of videos still lags behind. Prior work in this area has focused on using 2D diffusion models to globally change the style of an existing video. On the other hand, in many practical applications, editing localized parts of the video is critical. In this work, we propose a method to edit videos using a pre-trained inpainting image diffusion model. We systematically redesign the forward path of the model by replacing the self-attention modules with an extended version of attention modules that creates frame-level dependencies. In this way, we ensure that the edited information will be consistent across all the video frames no matter what the shape and position of the masked area is. We qualitatively compare our results with state-of-the-art in terms of accuracy on several video editing tasks like object retargeting, object replacement, and object removal tasks. Simulations demonstrate the superior performance of the proposed strategy.
Authors: Songhua Liu, Xin Jin, Xingyi Yang, Jingwen Ye, Xinchao Wang
Abstract: Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain, making it a highly ambitious and challenging task. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data and thus increase robustness. Nevertheless, they have largely overlooked the underlying coherence between the augmented domains, which in turn leads to inferior results in real-world scenarios. In this paper, we propose a simple yet effective scheme, termed as \emph{StyDeSty}, to explicitly account for the alignment of the source and pseudo domains in the process of data augmentation, enabling them to interact with each other in a self-consistent manner and further giving rise to a latent domain with strong generalization power. The heart of StyDeSty lies in the interaction between a \emph{stylization} module for generating novel stylized samples using the source domain, and a \emph{destylization} module for transferring stylized and source samples to a latent domain to learn content-invariant features. The stylization and destylization modules work adversarially and reinforce each other. During inference, the destylization module transforms the input sample with an arbitrary style shift to the latent domain, in which the downstream tasks are carried out. Specifically, the location of the destylization layer within the backbone network is determined by a dedicated neural architecture search (NAS) strategy. We evaluate StyDeSty on multiple benchmarks and demonstrate that it yields encouraging results, outperforming the state of the art by up to {13.44%} on classification accuracy. Codes are available here: https://github.com/Huage001/StyDeSty.
Authors: Chengzeng You, Zhongyuan Hau, Binbin Xu, Soteris Demetriou
Abstract: LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of reducing the required spoofing area through a novel object-hiding strategy based on virtual patches (VPs). We first manually design VPs (MVPs) and show that VP-focused attacks can achieve similar success rates with prior work but with a fraction of the required spoofing area. Then we design a framework Saliency-LiDAR (SALL), which can identify critical regions for LiDAR objects using Integrated Gradients. VPs crafted on critical regions (CVPs) reduce object detection recall by at least 15% compared to our baseline with an approximate 50% reduction in the spoofing area for vehicles of average size.
Authors: Steven A. Grosz, Anil K. Jain
Abstract: The scarcity of large-scale palmprint databases poses a significant bottleneck to advancements in contactless palmprint recognition. To address this, researchers have turned to synthetic data generation. While Generative Adversarial Networks (GANs) have been widely used, they suffer from instability and mode collapse. Recently, diffusion probabilistic models have emerged as a promising alternative, offering stable training and better distribution coverage. This paper introduces a novel palmprint generation method using diffusion probabilistic models, develops an end-to-end framework for synthesizing multiple palm identities, and validates the realism and utility of the generated palmprints. Experimental results demonstrate the effectiveness of our approach in generating palmprint images which enhance contactless palmprint recognition performance across several test databases utilizing challenging cross-database and time-separated evaluation protocols.
Authors: Eduardo Reis, Thangarajah Akilan, Mohammed Khalid
Abstract: Recent research in deep learning (DL) has investigated the use of the Fast Fourier Transform (FFT) to accelerate the computations involved in Convolutional Neural Networks (CNNs) by replacing spatial convolution with element-wise multiplications on the spectral domain. These approaches mainly rely on the FFT to reduce the number of operations, which can be further decreased by adopting the Real-Valued FFT. In this paper, we propose using the phasor form, a polar representation of complex numbers, as a more efficient alternative to the traditional approach. The experimental results, evaluated on the CIFAR-10, demonstrate that our method achieves superior speed improvements of up to a factor of 1.376 (average of 1.316) during training and up to 1.390 (average of 1.321) during inference when compared to the traditional rectangular form employed in modern CNN architectures. Similarly, when evaluated on the CIFAR-100, our method achieves superior speed improvements of up to a factor of 1.375 (average of 1.299) during training and up to 1.387 (average of 1.300) during inference. Most importantly, given the modular aspect of our approach, the proposed method can be applied to any existing convolution-based DL model without design changes.
Authors: Khoa Vo, Thinh Phan, Kashu Yamazaki, Minh Tran, Ngan Le
Abstract: Video-Language Models (VLMs), pre-trained on large-scale video-caption datasets, are now standard for robust visual-language representation and downstream tasks. However, their reliance on global contrastive alignment limits their ability to capture fine-grained interactions between visual and textual elements. To address these challenges, we introduce HENASY (Hierarchical ENtities ASsemblY), a novel framework designed for egocentric video analysis that enhances the granularity of video content representations. HENASY employs a compositional approach using an enhanced slot-attention and grouping mechanisms for videos, assembling dynamic entities from video patches. It integrates a local entity encoder for dynamic modeling, a global encoder for broader contextual understanding, and an entity-aware decoder for late-stage fusion, enabling effective video scene dynamics modeling and granular-level alignment between visual entities and text. By incorporating innovative contrastive losses, HENASY significantly improves entity and activity recognition, delivering superior performance on benchmarks such as Ego4D and EpicKitchen, and setting new standards in both zero-shot and extensive video understanding tasks. Our results confirm groundbreaking capabilities of HENASY and establish it as a significant advancement in video-language multimodal research.
Authors: Raul Steinmetz, Victor A. Kich, Henrique Krever, Joao D. Rigo Mazzarolo, Ricardo B. Grando, Vinicius Marini, Celio Trois, Ard Nieuwenhuizen
Abstract: Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classification accuracy. In this work, we introduce a comprehensive dataset for training neural networks to detect weeds and soy plants through instance segmentation. Our dataset covers various stages of soy growth, offering a chronological perspective on weed invasion's impact, with 1,000 meticulously annotated images. We also provide 6 state of the art models, trained in this dataset, that can understand and detect soy and weed in every stage of the plantation process. By using this dataset for weed and soy segmentation, we achieved a segmentation average precision of 79.1% and an average recall of 69.2% across all plant classes, with the YOLOv8X model. Moreover, the YOLOv8M model attained 78.7% mean average precision (mAp-50) in caruru weed segmentation, 69.7% in grassy weed segmentation, and 90.1% in soy plant segmentation.
Authors: Yixiong Chen, Zongwei Zhou, Alan Yuille
Abstract: An increasing number of public datasets have shown a transformative impact on automated medical segmentation. However, these datasets are often with varying label quality, ranging from manual expert annotations to AI-generated pseudo-annotations. There is no systematic, reliable, and automatic quality control (QC). To fill in this bridge, we introduce a regression model, Quality Sentinel, to estimate label quality compared with manual annotations in medical segmentation datasets. This regression model was trained on over 4 million image-label pairs created by us. Each pair presents a varying but quantified label quality based on manual annotations, which enable us to predict the label quality of any image-label pairs in the inference. Our Quality Sentinel can predict the label quality of 142 body structures. The predicted label quality quantified by Dice Similarity Coefficient (DSC) shares a strong correlation with ground truth quality, with a positive correlation coefficient (r=0.902). Quality Sentinel has found multiple impactful use cases. (I) We evaluated label quality in publicly available datasets, where quality highly varies across different datasets. Our analysis also uncovers that male and younger subjects exhibit significantly higher quality. (II) We identified and corrected poorly annotated labels, achieving 1/3 reduction in annotation costs with optimal budgeting on TotalSegmentator. (III) We enhanced AI training efficiency and performance by focusing on high-quality pseudo labels, resulting in a 33%--88% performance boost over entropy-based methods, with a cost of 31% time and 4.5% memory. The data and model are released.
Authors: Yiwei Ma, Jiayi Ji, Xiaoshuai Sun, Yiyi Zhou, Xiaopeng Hong, Yongjian Wu, Rongrong Ji
Abstract: This paper explores a novel dynamic network for vision and language tasks, where the inferring structure is customized on the fly for different inputs. Most previous state-of-the-art approaches are static and hand-crafted networks, which not only heavily rely on expert knowledge, but also ignore the semantic diversity of input samples, therefore resulting in suboptimal performance. To address these issues, we propose a novel Dynamic Transformer Network (DTNet) for image captioning, which dynamically assigns customized paths to different samples, leading to discriminative yet accurate captions. Specifically, to build a rich routing space and improve routing efficiency, we introduce five types of basic cells and group them into two separate routing spaces according to their operating domains, i.e., spatial and channel. Then, we design a Spatial-Channel Joint Router (SCJR), which endows the model with the capability of path customization based on both spatial and channel information of the input sample. To validate the effectiveness of our proposed DTNet, we conduct extensive experiments on the MS-COCO dataset and achieve new state-of-the-art performance on both the Karpathy split and the online test server.
Authors: Zhi Zhou, Ming Yang, Jiang-Xin Shi, Lan-Zhe Guo, Yu-Feng Li
Abstract: Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies evaluate the performance of learned prompts separately on base and new classes. This evaluation lacks practicality for real-world applications since downstream tasks cannot determine whether the data belongs to base or new classes in advance. In this paper, we explore a problem setting called Open-world Prompt Tuning (OPT), which involves tuning prompts on base classes and evaluating on a combination of base and new classes. By introducing Decomposed Prompt Tuning framework (DePT), we theoretically demonstrate that OPT can be solved by incorporating out-of-distribution detection into prompt tuning, thereby enhancing the base-to-new discriminability. Based on DePT, we present a novel prompt tuning approach, namely, Decomposed Context Optimization (DeCoOp), which introduces new-class detectors and sub-classifiers to further enhance the base-class and new-class discriminability. Experimental results on 11 benchmark datasets validate the effectiveness of DePT and demonstrate that DeCoOp outperforms current state-of-the-art methods, providing a significant 2% average accuracy improvement.
Authors: Cheng Xu, Fei Hou, Wencheng Wang, Hong Qin, Zhebin Zhang, Ying He
Abstract: While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and a UDF-tailored method for extracting iso-surface with non-constant iso-values. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces. We will make the source code publicly available.
Authors: Hanxiao Wang, Mingyang Zhao, Weize Quan, Zhen Chen, Dong-ming Yan, Peter Wonka
Abstract: Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in inefficient learning of symmetric patterns. To address this issue, we propose E3-Net to achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work and improves the accuracy. Further, we design a Gaussian-weighted loss function and a receptive-aware inference strategy that effectively utilizes the local properties of point clouds. Our method achieves superior results on both synthetic and real-world datasets, and outperforms current state-of-the-art techniques by a substantial margin. We improve RMSE by 4% on the PCPNet dataset, 2.67% on the SceneNN dataset, and 2.44% on the FamousShape dataset.
Authors: Wadii Boulila, Eman Alshanqiti, Ayyub Alzahem, Anis Koubaa, Nabil Mlaiki
Abstract: The growing interest in satellite imagery has triggered the need for efficient mechanisms to extract valuable information from these vast data sources, providing deeper insights. Even though deep learning has shown significant progress in satellite image classification. Nevertheless, in the literature, only a few results can be found on weight initialization techniques. These techniques traditionally involve initializing the networks' weights before training on extensive datasets, distinct from fine-tuning the weights of pre-trained networks. In this study, a novel weight initialization method is proposed in the context of satellite image classification. The proposed weight initialization method is mathematically detailed during the forward and backward passes of the convolutional neural network (CNN) model. Extensive experiments are carried out using six real-world datasets. Comparative analyses with existing weight initialization techniques made on various well-known CNN models reveal that the proposed weight initialization technique outperforms the previous competitive techniques in classification accuracy. The complete code of the proposed technique, along with the obtained results, is available at https://github.com/WadiiBoulila/Weight-Initialization
Authors: Baoyue Zhang, Yajing Zheng, Shiyan Chen, Jiyuan Zhang, Kang Chen, Zhaofei Yu, Tiejun Huang
Abstract: The amplification of high-speed micro-motions holds significant promise, with applications spanning fault detection in fast-paced industrial environments to refining precision in medical procedures. However, conventional motion magnification algorithms often encounter challenges in high-speed scenarios due to low sampling rates or motion blur. In recent years, spike cameras have emerged as a superior alternative for visual tasks in such environments, owing to their unique capability to capture temporal and spatial frequency domains with exceptional fidelity. Unlike conventional cameras, which operate at fixed, low frequencies, spike cameras emulate the functionality of the retina, asynchronously capturing photon changes at each pixel position using spike streams. This innovative approach comprehensively records temporal and spatial visual information, rendering it particularly suitable for magnifying high-speed micro-motions.This paper introduces SpikeMM, a pioneering spike-based algorithm tailored specifically for high-speed motion magnification. SpikeMM integrates multi-level information extraction, spatial upsampling, and motion magnification modules, offering a self-supervised approach adaptable to a wide range of scenarios. Notably, SpikeMM facilitates seamless integration with high-performance super-resolution and motion magnification algorithms. We substantiate the efficacy of SpikeMM through rigorous validation using scenes captured by spike cameras, showcasing its capacity to magnify motions in real-world high-frequency settings.
Authors: Matan Rusanovsky, Or Hirschorn, Shai Avidan
Abstract: Conventional 2D pose estimation models are constrained by their design to specific object categories. This limits their applicability to predefined objects. To overcome these limitations, category-agnostic pose estimation (CAPE) emerged as a solution. CAPE aims to facilitate keypoint localization for diverse object categories using a unified model, which can generalize from minimal annotated support images. Recent CAPE works have produced object poses based on arbitrary keypoint definitions annotated on a user-provided support image. Our work departs from conventional CAPE methods, which require a support image, by adopting a text-based approach instead of the support image. Specifically, we use a pose-graph, where nodes represent keypoints that are described with text. This representation takes advantage of the abstraction of text descriptions and the structure imposed by the graph. Our approach effectively breaks symmetry, preserves structure, and improves occlusion handling. We validate our novel approach using the MP-100 benchmark, a comprehensive dataset spanning over 100 categories and 18,000 images. Under a 1-shot setting, our solution achieves a notable performance boost of 1.07\%, establishing a new state-of-the-art for CAPE. Additionally, we enrich the dataset by providing text description annotations, further enhancing its utility for future research.
Authors: Nhi Ngoc-Yen Nguyen, Le-Huy Tu, Dieu-Phuong Nguyen, Nhat-Tan Do, Minh Triet Thai, Bao-Thien Nguyen-Tat
Abstract: Purpose: Our study presents an enhanced approach to medical image caption generation by integrating concept detection into attention mechanisms. Method: This method utilizes sophisticated models to identify critical concepts within medical images, which are then refined and incorporated into the caption generation process. Results: Our concept detection task, which employed the Swin-V2 model, achieved an F1 score of 0.58944 on the validation set and 0.61998 on the private test set, securing the third position. For the caption prediction task, our BEiT+BioBart model, enhanced with concept integration and post-processing techniques, attained a BERTScore of 0.60589 on the validation set and 0.5794 on the private test set, placing ninth. Conclusion: These results underscore the efficacy of concept-aware algorithms in generating precise and contextually appropriate medical descriptions. The findings demonstrate that our approach significantly improves the quality of medical image captions, highlighting its potential to enhance medical image interpretation and documentation, thereby contributing to improved healthcare outcomes.
Authors: Mazen Balat, Youssef Mohamed, Ahmed Heakl, Ahmed Zaky
Abstract: This study thoroughly investigates how well deep learning models can recognize Arabic handwritten text for person biometric identification. It compares three advanced architectures -- ResNet50, MobileNetV2, and EfficientNetB7 -- using three widely recognized datasets: AHAWP, Khatt, and LAMIS-MSHD. Results show that EfficientNetB7 outperforms the others, achieving test accuracies of 98.57\%, 99.15\%, and 99.79\% on AHAWP, Khatt, and LAMIS-MSHD datasets, respectively. EfficientNetB7's exceptional performance is credited to its innovative techniques, including compound scaling, depth-wise separable convolutions, and squeeze-and-excitation blocks. These features allow the model to extract more abstract and distinctive features from handwritten text images. The study's findings hold significant implications for enhancing identity verification and authentication systems, highlighting the potential of deep learning in Arabic handwritten text recognition for person biometric identification.
Authors: Luis Rei, Dunja Mladeni\'c, Mareike Dorozynski, Franz Rottensteiner, Thomas Schleider, Rapha\"el Troncy, Jorge Sebasti\'an Lozano, Mar Gait\'an Salvatella
Abstract: We develop a multimodal classifier for the cultural heritage domain using a late fusion approach and introduce a novel dataset. The three modalities are Image, Text, and Tabular data. We based the image classifier on a ResNet convolutional neural network architecture and the text classifier on a multilingual transformer architecture (XML-Roberta). Both are trained as multitask classifiers and use the focal loss to handle class imbalance. Tabular data and late fusion are handled by Gradient Tree Boosting. We also show how we leveraged specific data models and taxonomy in a Knowledge Graph to create the dataset and to store classification results. All individual classifiers accurately predict missing properties in the digitized silk artifacts, with the multimodal approach providing the best results.
Authors: Shuoxi Zhang, Hanpeng Liu, Stephen Lin, Kun He
Abstract: The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among patchified image tokens. While self-attention modules empower ViTs to capture long-range dependencies, the computational complexity grows quadratically with the number of tokens, which is a major hindrance to the practical application of ViTs. Moreover, the self-attention mechanism in deep ViTs is also susceptible to the attention saturation issue. Accordingly, we argue against the necessity of computing the attention scores in every layer, and we propose the Less-Attention Vision Transformer (LaViT), which computes only a few attention operations at each stage and calculates the subsequent feature alignments in other layers via attention transformations that leverage the previously calculated attention scores. This novel approach can mitigate two primary issues plaguing traditional self-attention modules: the heavy computational burden and attention saturation. Our proposed architecture offers superior efficiency and ease of implementation, merely requiring matrix multiplications that are highly optimized in contemporary deep learning frameworks. Moreover, our architecture demonstrates exceptional performance across various vision tasks including classification, detection and segmentation.
Authors: Zheng Qin, Le Wang, Sanping Zhou, Panpan Fu, Gang Hua, Wei Tang
Abstract: Multi-Object Tracking MOT encompasses various tracking scenarios, each characterized by unique traits. Effective trackers should demonstrate a high degree of generalizability across diverse scenarios. However, existing trackers struggle to accommodate all aspects or necessitate hypothesis and experimentation to customize the association information motion and or appearance for a given scenario, leading to narrowly tailored solutions with limited generalizability. In this paper, we investigate the factors that influence trackers generalization to different scenarios and concretize them into a set of tracking scenario attributes to guide the design of more generalizable trackers. Furthermore, we propose a point-wise to instance-wise relation framework for MOT, i.e., GeneralTrack, which can generalize across diverse scenarios while eliminating the need to balance motion and appearance. Thanks to its superior generalizability, our proposed GeneralTrack achieves state-of-the-art performance on multiple benchmarks and demonstrates the potential for domain generalization. https://github.com/qinzheng2000/GeneralTrack.git
Authors: Xing Cui, Peipei Li, Zekun Li, Xuannan Liu, Yueying Zou, Zhaofeng He
Abstract: Flexible and accurate drag-based editing is a challenging task that has recently garnered significant attention. Current methods typically model this problem as automatically learning ``how to drag'' through point dragging and often produce one deterministic estimation, which presents two key limitations: 1) Overlooking the inherently ill-posed nature of drag-based editing, where multiple results may correspond to a given input, as illustrated in Fig.1; 2) Ignoring the constraint of image quality, which may lead to unexpected distortion. To alleviate this, we propose LucidDrag, which shifts the focus from ``how to drag'' to a paradigm of ``what-then-how''. LucidDrag comprises an intention reasoner and a collaborative guidance sampling mechanism. The former infers several optimal editing strategies, identifying what content and what semantic direction to be edited. Based on the former, the latter addresses "how to drag" by collaboratively integrating existing editing guidance with the newly proposed semantic guidance and quality guidance. Specifically, semantic guidance is derived by establishing a semantic editing direction based on reasoned intentions, while quality guidance is achieved through classifier guidance using an image fidelity discriminator. Both qualitative and quantitative comparisons demonstrate the superiority of LucidDrag over previous methods. The code will be released.
Authors: Qingming Liu, Yuan Liu, Jiepeng Wang, Xianqiang Lv, Peng Wang, Wenping Wang, Junhui Hou
Abstract: In this paper, we propose MoDGS, a new pipeline to render novel-view images in dynamic scenes using only casually captured monocular videos. Previous monocular dynamic NeRF or Gaussian Splatting methods strongly rely on the rapid movement of input cameras to construct multiview consistency but fail to reconstruct dynamic scenes on casually captured input videos whose cameras are static or move slowly. To address this challenging task, MoDGS adopts recent single-view depth estimation methods to guide the learning of the dynamic scene. Then, a novel 3D-aware initialization method is proposed to learn a reasonable deformation field and a new robust depth loss is proposed to guide the learning of dynamic scene geometry. Comprehensive experiments demonstrate that MoDGS is able to render high-quality novel view images of dynamic scenes from just a casually captured monocular video, which outperforms baseline methods by a significant margin.
Authors: X. Li, Y. Cheng, X. Ren, H. Jia, D. Xu, W. Zhu, Y. Yan
Abstract: 4D head capture aims to generate dynamic topological meshes and corresponding texture maps from videos, which is widely utilized in movies and games for its ability to simulate facial muscle movements and recover dynamic textures in pore-squeezing. The industry often adopts the method involving multi-view stereo and non-rigid alignment. However, this approach is prone to errors and heavily reliant on time-consuming manual processing by artists. To simplify this process, we propose Topo4D, a novel framework for automatic geometry and texture generation, which optimizes densely aligned 4D heads and 8K texture maps directly from calibrated multi-view time-series images. Specifically, we first represent the time-series faces as a set of dynamic 3D Gaussians with fixed topology in which the Gaussian centers are bound to the mesh vertices. Afterward, we perform alternative geometry and texture optimization frame-by-frame for high-quality geometry and texture learning while maintaining temporal topology stability. Finally, we can extract dynamic facial meshes in regular wiring arrangement and high-fidelity textures with pore-level details from the learned Gaussians. Extensive experiments show that our method achieves superior results than the current SOTA face reconstruction methods both in the quality of meshes and textures. Project page: https://xuanchenli.github.io/Topo4D/.
Authors: Feiyu Zhu, Yuming Zhang, Changpeng Cai, Guinan Guo, Jiao Li, Xiuyuan Guo, Quanwei Zhang, Peizhe Wang, Chenghao He, Junhao Su
Abstract: Traditional deep neural networks typically use end-to-end backpropagation, which often places a big burden on GPU memory. Another promising training method is local learning, which involves splitting the network into blocks and training them in parallel with the help of an auxiliary network. Local learning has been widely studied and applied to image classification tasks, and its performance is comparable to that of end-to-end method. However, different image tasks often rely on different feature representations, which is difficult for typical auxiliary networks to adapt to. To solve this problem, we propose the construction method of Global-Local Collaborative Auxiliary Network (GLCAN), which provides a macroscopic design approach for auxiliary networks. This is the first demonstration that local learning methods can be successfully applied to other tasks such as object detection and super-resolution. GLCAN not only saves a lot of GPU memory, but also has comparable performance to an end-to-end approach on data sets for multiple different tasks.
Authors: Ahmed Heakl, Fatma Youssef, Victor Parque, Walid Gomaa
Abstract: This paper introduces DroneVis, a novel library designed to automate computer vision algorithms on Parrot drones. DroneVis offers a versatile set of features and provides a diverse range of computer vision tasks along with a variety of models to choose from. Implemented in Python, the library adheres to high-quality code standards, facilitating effortless customization and feature expansion according to user requirements. In addition, comprehensive documentation is provided, encompassing usage guidelines and illustrative use cases. Our documentation, code, and examples are available in https://github.com/ahmedheakl/drone-vis.
Authors: Yuehao Wang, Chaoyi Wang, Bingchen Gong, Tianfan Xue
Abstract: Neural Radiance Fields (NeRF) achieves unprecedented performance in synthesizing novel view synthesis, utilizing multi-view consistency. When capturing multiple inputs, image signal processing (ISP) in modern cameras will independently enhance them, including exposure adjustment, color correction, local tone mapping, etc. While these processings greatly improve image quality, they often break the multi-view consistency assumption, leading to "floaters" in the reconstructed radiance fields. To address this concern without compromising visual aesthetics, we aim to first disentangle the enhancement by ISP at the NeRF training stage and re-apply user-desired enhancements to the reconstructed radiance fields at the finishing stage. Furthermore, to make the re-applied enhancements consistent between novel views, we need to perform imaging signal processing in 3D space (i.e. "3D ISP"). For this goal, we adopt the bilateral grid, a locally-affine model, as a generalized representation of ISP processing. Specifically, we optimize per-view 3D bilateral grids with radiance fields to approximate the effects of camera pipelines for each input view. To achieve user-adjustable 3D finishing, we propose to learn a low-rank 4D bilateral grid from a given single view edit, lifting photo enhancements to the whole 3D scene. We demonstrate our approach can boost the visual quality of novel view synthesis by effectively removing floaters and performing enhancements from user retouching. The source code and our data are available at: https://bilarfpro.github.io.
Authors: Hidir Yesiltepe, Yusuf Dalva, Pinar Yanardag
Abstract: Diffusion models have become prominent in creating high-quality images. However, unlike GAN models celebrated for their ability to edit images in a disentangled manner, diffusion-based text-to-image models struggle to achieve the same level of precise attribute manipulation without compromising image coherence. In this paper, CLIP which is often used in popular text-to-image diffusion models such as Stable Diffusion is capable of performing disentangled editing in a zero-shot manner. Through both qualitative and quantitative comparisons with state-of-the-art editing methods, we show that our approach yields competitive results. This insight may open opportunities for applying this method to various tasks, including image and video editing, providing a lightweight and efficient approach for disentangled editing.
Authors: Mustafa Sakhai, Szymon Mazurek, Jakub Caputa, Jan K. Argasi\'nski, Maciej Wielgosz
Abstract: This study examines the effectiveness of Spiking Neural Networks (SNNs) paired with Dynamic Vision Sensors (DVS) to improve pedestrian detection in adverse weather, a significant challenge for autonomous vehicles. Utilizing the high temporal resolution and low latency of DVS, which excels in dynamic, low-light, and high-contrast environments, we assess the efficiency of SNNs compared to traditional Convolutional Neural Networks (CNNs). Our experiments involved testing across diverse weather scenarios using a custom dataset from the CARLA simulator, mirroring real-world variability. SNN models, enhanced with Temporally Effective Batch Normalization, were trained and benchmarked against state-of-the-art CNNs to demonstrate superior accuracy and computational efficiency in complex conditions such as rain and fog. The results indicate that SNNs, integrated with DVS, significantly reduce computational overhead and improve detection accuracy in challenging conditions compared to CNNs. This highlights the potential of DVS combined with bio-inspired SNN processing to enhance autonomous vehicle perception and decision-making systems, advancing intelligent transportation systems' safety features in varying operational environments. Additionally, our research indicates that SNNs perform more efficiently in handling long perception windows and prediction tasks, rather than simple pedestrian detection.
Authors: Zimin Xia, Yujiao Shi, Hongdong Li, Julian F. P. Kooij
Abstract: Given a ground-level query image and a geo-referenced aerial image that covers the query's local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works have focused on developing advanced networks trained with accurate ground truth (GT) locations of ground images. However, the trained models always suffer a performance drop when applied to images in a new target area that differs from training. In most deployment scenarios, acquiring fine GT, i.e. accurate GT locations, for target-area images to re-train the network can be expensive and sometimes infeasible. In contrast, collecting images with noisy GT with errors of tens of meters is often easy. Motivated by this, our paper focuses on improving the performance of a trained model in a new target area by leveraging only the target-area images without fine GT. We propose a weakly supervised learning approach based on knowledge self-distillation. This approach uses predictions from a pre-trained model as pseudo GT to supervise a copy of itself. Our approach includes a mode-based pseudo GT generation for reducing uncertainty in pseudo GT and an outlier filtering method to remove unreliable pseudo GT. Our approach is validated using two recent state-of-the-art models on two benchmarks. The results demonstrate that it consistently and considerably boosts the localization accuracy in the target area.
Authors: Duojun Huang, Xinyu Xiong, Jie Ma, Jichang Li, Zequn Jie, Lin Ma, Guanbin Li
Abstract: Powered by massive curated training data, Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. However, the vanilla SAM is class agnostic and heavily relies on user-provided prompts to segment objects of interest. Adapting this method to diverse tasks is crucial for accurate target identification and to avoid suboptimal segmentation results. In this paper, we propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context through reinforcement learning. Anchored by an agent, AlignSAM enables the generality of the SAM model across diverse downstream tasks while keeping its parameters frozen. Specifically, AlignSAM initiates a prompting agent to iteratively refine segmentation predictions by interacting with the foundational model. It integrates a reinforcement learning policy network to provide informative prompts to the foundational models. Additionally, a semantic recalibration module is introduced to provide fine-grained labels of prompts, enhancing the model's proficiency in handling tasks encompassing explicit and implicit semantics. Experiments conducted on various challenging segmentation tasks among existing foundation models demonstrate the superiority of the proposed AlignSAM over state-of-the-art approaches. Project page: \url{https://github.com/Duojun-Huang/AlignSAM-CVPR2024}.
Authors: Manogna Sreenivas, Soma Biswas
Abstract: We propose a novel framework to address the real-world challenging task of Single Image Test Time Adaptation in an open and dynamic environment. We leverage large scale Vision Language Models like CLIP to enable real time adaptation on a per-image basis without access to source data or ground truth labels. Since the deployed model can also encounter unseen classes in an open world, we first employ a simple and effective Out of Distribution (OOD) detection module to distinguish between weak and strong OOD samples. We propose a novel contrastive learning based objective to enhance the discriminability between weak and strong OOD samples by utilizing small, dynamically updated feature banks. Finally, we also employ a classification objective for adapting the model using the reliable weak OOD samples. The proposed framework ROSITA combines these components, enabling continuous online adaptation of Vision Language Models on a single image basis. Extensive experimentation on diverse domain adaptation benchmarks validates the effectiveness of the proposed framework. Our code can be found at the project site https://manogna-s.github.io/rosita/
Authors: Jingyu Zhang, Jin Cao, Jinghao Chang, Xinjin Li, Houze Liu, Zhenglin Li
Abstract: This research aims to explore the application of deep learning in autonomous driving computer vision technology and its impact on improving system performance. By using advanced technologies such as convolutional neural networks (CNN), multi-task joint learning methods, and deep reinforcement learning, this article analyzes in detail the application of deep learning in image recognition, real-time target tracking and classification, environment perception and decision support, and path planning and navigation. Application process in key areas. Research results show that the proposed system has an accuracy of over 98% in image recognition, target tracking and classification, and also demonstrates efficient performance and practicality in environmental perception and decision support, path planning and navigation. The conclusion points out that deep learning technology can significantly improve the accuracy and real-time response capabilities of autonomous driving systems. Although there are still challenges in environmental perception and decision support, with the advancement of technology, it is expected to achieve wider applications and greater capabilities in the future. potential.
Authors: Biao Wu, Diankai Zhang, Si Gao, Chengjian Zheng, Shaoli Liu, Ning Wang
Abstract: Video Panoptic Segmentation (VPS) is a challenging task that is extends from image panoptic segmentation.VPS aims to simultaneously classify, track, segment all objects in a video, including both things and stuff. Due to its wide application in many downstream tasks such as video understanding, video editing, and autonomous driving. In order to deal with the task of video panoptic segmentation in the wild, we propose a robust integrated video panoptic segmentation solution. We use DVIS++ framework as our baseline to generate the initial masks. Then,we add an additional image semantic segmentation model to further improve the performance of semantic classes.Finally, our method achieves state-of-the-art performance with a VPQ score of 56.36 and 57.12 in the development and test phases, respectively, and ultimately ranked 2nd in the VPS track of the PVUW Challenge at CVPR2024.
Authors: Luigi Capogrosso, Federico Girella, Francesco Taioli, Michele Dalla Chiara, Muhammad Aqeel, Franco Fummi, Francesco Setti, Marco Cristani
Abstract: In this study, we show that diffusion models can be used in industrial scenarios to improve the data augmentation procedure in the context of surface defect detection. In general, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. For these reasons, state-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples. This leads to out-of-distribution augmented data so that the classification system learns what is not a normal sample but does not know what a defect really is. We show that diffusion models overcome this situation, providing more realistic in-distribution defects so that the model can learn the defect's genuine appearance. We propose a novel approach for data augmentation that mixes out-of-distribution with in-distribution samples, which we call In&Out. The approach can deal with two data augmentation setups: i) when no defects are available (zero-shot data augmentation) and ii) when defects are available, which can be in a small number (few-shot) or a large one (full-shot). We focus the experimental part on the most challenging benchmark in the state-of-the-art, i.e., the Kolektor Surface-Defect Dataset 2, defining the new state-of-the-art classification AP score under weak supervision of .782. The code is available at https://github.com/intelligolabs/in_and_out.
Authors: Jun Young Koh, Sang Hyun Park, Joy Song
Abstract: The recent emergence of latent diffusion models such as SDXL and SD 1.5 has shown significant capability in generating highly detailed and realistic images. Despite their remarkable ability to produce images, generating accurate text within images still remains a challenging task. In this paper, we examine the validity of fine-tuning approaches in generating legible text within the image. We propose a low-cost approach by leveraging SDXL without any time-consuming training on large-scale datasets. The proposed strategy employs a fine-tuning technique that examines the effects of data refinement levels and synthetic captions. Moreover, our results demonstrate how our small scale fine-tuning approach can improve the accuracy of text generation in different scenarios without the need of additional multimodal encoders. Our experiments show that with the addition of random letters to our raw dataset, our model's performance improves in producing well-formed visual text.
Authors: Yixuan Zhu, Wenliang Zhao, Ao Li, Yansong Tang, Jie Zhou, Jiwen Lu
Abstract: Image enhancement holds extensive applications in real-world scenarios due to complex environments and limitations of imaging devices. Conventional methods are often constrained by their tailored models, resulting in diminished robustness when confronted with challenging degradation conditions. In response, we propose FlowIE, a simple yet highly effective flow-based image enhancement framework that estimates straight-line paths from an elementary distribution to high-quality images. Unlike previous diffusion-based methods that suffer from long-time inference, FlowIE constructs a linear many-to-one transport mapping via conditioned rectified flow. The rectification straightens the trajectories of probability transfer, accelerating inference by an order of magnitude. This design enables our FlowIE to fully exploit rich knowledge in the pre-trained diffusion model, rendering it well-suited for various real-world applications. Moreover, we devise a faster inference algorithm, inspired by Lagrange's Mean Value Theorem, harnessing midpoint tangent direction to optimize path estimation, ultimately yielding visually superior results. Thanks to these designs, our FlowIE adeptly manages a diverse range of enhancement tasks within a concise sequence of fewer than 5 steps. Our contributions are rigorously validated through comprehensive experiments on synthetic and real-world datasets, unveiling the compelling efficacy and efficiency of our proposed FlowIE. Code is available at https://github.com/EternalEvan/FlowIE.
Authors: Jiaming Li, Jiacheng Zhang, Jichang Li, Ge Li, Si Liu, Liang Lin, Guanbin Li
Abstract: Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable of recognizing objects from both base and novel categories. Recent advances leverage knowledge distillation to transfer insightful knowledge from pre-trained large-scale vision-language models to the task of object detection, significantly generalizing the powerful capabilities of the detector to identify more unknown object categories. However, these methods face significant challenges in background interpretation and model overfitting and thus often result in the loss of crucial background knowledge, giving rise to sub-optimal inference performance of the detector. To mitigate these issues, we present a novel OVD framework termed LBP to propose learning background prompts to harness explored implicit background knowledge, thus enhancing the detection performance w.r.t. base and novel categories. Specifically, we devise three modules: Background Category-specific Prompt, Background Object Discovery, and Inference Probability Rectification, to empower the detector to discover, represent, and leverage implicit object knowledge explored from background proposals. Evaluation on two benchmark datasets, OV-COCO and OV-LVIS, demonstrates the superiority of our proposed method over existing state-of-the-art approaches in handling the OVD tasks.
Authors: Marcos Faundez-Zanuy, Moises Diaz
Abstract: This paper investigates the impact of different approximation methods in feature extraction for pattern recognition applications, specifically focused on delta and delta-delta parameters. Using MCYT330 online signature data-base, our experiments show that 11-point approximation outperforms 1-point approximation, resulting in a 1.4% improvement in identification rate, 36.8% reduction in random forgeries and 2.4% reduction in skilled forgeries
Authors: Xinyue Chen, Miaojing Shi
Abstract: The performance of supervised semantic segmentation methods highly relies on the availability of large-scale training data. To alleviate this dependence, few-shot semantic segmentation (FSS) is introduced to leverage the model trained on base classes with sufficient data into the segmentation of novel classes with few data. FSS methods face the challenge of model generalization on novel classes due to the distribution shift between base and novel classes. To overcome this issue, we propose a class-shared memory (CSM) module consisting of a set of learnable memory vectors. These memory vectors learn elemental object patterns from base classes during training whilst re-encoding query features during both training and inference, thereby improving the distribution alignment between base and novel classes. Furthermore, to cope with the performance degradation resulting from the intra-class variance across images, we introduce an uncertainty-based feature augmentation (UFA) module to produce diverse query features during training for improving the model's robustness. We integrate CSM and UFA into representative FSS works, with experimental results on the widely-used PASCAL-5$^i$ and COCO-20$^i$ datasets demonstrating the superior performance of ours over state of the art.
Authors: Elisha Dayag, Kevin Bui, Fredrick Park, Jack Xin
Abstract: Based on transformed $\ell_1$ regularization, transformed total variation (TTV) has robust image recovery that is competitive with other nonconvex total variation (TV) regularizers, such as TV$^p$, $0
Authors: Biao Wu, Diankai Zhang, Si Gao, Chengjian Zheng, Shaoli Liu, Ning Wang
Abstract: Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction,because the real-world is actually video-based rather than a static state. In this paper, we adopt semi-supervised video semantic segmentation method based on unreliable pseudo labels. Then, We ensemble the teacher network model with the student network model to generate pseudo labels and retrain the student network. Our method achieves the mIoU scores of 63.71% and 67.83% on development test and final test respectively. Finally, we obtain the 1st place in the Video Scene Parsing in the Wild Challenge at CVPR 2024.
Authors: Zhuang Qi, Junlin Zhang, Xin Qi
Abstract: Visual tracking fundamentally involves regressing the state of the target in each frame of a video. Despite significant progress, existing regression-based trackers still tend to experience failures and inaccuracies. To enhance the precision of target estimation, this paper proposes a tracking technique based on robust regression. Firstly, we introduce a novel robust linear regression estimator, which achieves favorable performance when the error vector follows i.i.d Gaussian-Laplacian distribution. Secondly, we design an iterative process to quickly solve the problem of outliers. In fact, the coefficients are obtained by Iterative Gradient Descent and Threshold Selection algorithm (IGDTS). In addition, we expend IGDTS to a generative tracker, and apply IGDTS-distance to measure the deviation between the sample and the model. Finally, we propose an update scheme to capture the appearance changes of the tracked object and ensure that the model is updated correctly. Experimental results on several challenging image sequences show that the proposed tracker outperformance existing trackers.
Authors: Austin Peng
Abstract: Novel view synthesis (NVS) is a challenge in computer vision and graphics, focusing on generating realistic images of a scene from unobserved camera poses, given a limited set of authentic input images. Neural radiance fields (NeRF) achieved impressive results in rendering quality by utilizing volumetric rendering. However, NeRF and its variants are unsuitable for mobile devices due to the high computational cost of volumetric rendering. Emerging research in neural light fields (NeLF) eliminates the need for volumetric rendering by directly learning a mapping from ray representation to pixel color. NeLF has demonstrated its capability to achieve results similar to NeRF but requires a more extensive, computationally intensive network that is not mobile-friendly. Unlike existing works, this research builds upon the novel network architecture introduced by MobileR2L and aggressively applies a compression technique (channel-wise structure pruning) to produce a model that runs efficiently on mobile devices with lower latency and smaller sizes, with a slight decrease in performance.
Authors: Minjong Cheon
Abstract: In this research, we propose the first approach for integrating the Kolmogorov-Arnold Network (KAN) with various pre-trained Convolutional Neural Network (CNN) models for remote sensing (RS) scene classification tasks using the EuroSAT dataset. Our novel methodology, named KCN, aims to replace traditional Multi-Layer Perceptrons (MLPs) with KAN to enhance classification performance. We employed multiple CNN-based models, including VGG16, MobileNetV2, EfficientNet, ConvNeXt, ResNet101, and Vision Transformer (ViT), and evaluated their performance when paired with KAN. Our experiments demonstrated that KAN achieved high accuracy with fewer training epochs and parameters. Specifically, ConvNeXt paired with KAN showed the best performance, achieving 94% accuracy in the first epoch, which increased to 96% and remained consistent across subsequent epochs. The results indicated that KAN and MLP both achieved similar accuracy, with KAN performing slightly better in later epochs. By utilizing the EuroSAT dataset, we provided a robust testbed to investigate whether KAN is suitable for remote sensing classification tasks. Given that KAN is a novel algorithm, there is substantial capacity for further development and optimization, suggesting that KCN offers a promising alternative for efficient image analysis in the RS field.
Authors: Yuan Shen, Duygu Ceylan, Paul Guerrero, Zexiang Xu, Niloy J. Mitra, Shenlong Wang, Anna Fr\"ust\"uck
Abstract: We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet match the quality of their counterparts in image and video domains. We demonstrate that it is possible to directly repurpose existing (pretrained) video models for 3D super-resolution and thus sidestep the problem of the shortage of large repositories of high-quality 3D training models. We describe how to repurpose video upsampling models, which are not 3D consistent, and combine them with 3D consolidation to produce 3D-consistent results. As output, we produce high quality Gaussian Splat models, which are object centric and effective. Our method is category agnostic and can be easily incorporated into existing 3D workflows. We evaluate our proposed SuperGaussian on a variety of 3D inputs, which are diverse both in terms of complexity and representation (e.g., Gaussian Splats or NeRFs), and demonstrate that our simple method significantly improves the fidelity of the final 3D models. Check our project website for details: supergaussian.github.io
Authors: Xingrui Wang, Wufei Ma, Angtian Wang, Shuo Chen, Adam Kortylewski, Alan Yuille
Abstract: For vision-language models (VLMs), understanding the dynamic properties of objects and their interactions within 3D scenes from video is crucial for effective reasoning. In this work, we introduce a video question answering dataset SuperCLEVR-Physics that focuses on the dynamics properties of objects. We concentrate on physical concepts -- velocity, acceleration, and collisions within 4D scenes, where the model needs to fully understand these dynamics properties and answer the questions built on top of them. From the evaluation of a variety of current VLMs, we find that these models struggle with understanding these dynamic properties due to the lack of explicit knowledge about the spatial structure in 3D and world dynamics in time variants. To demonstrate the importance of an explicit 4D dynamics representation of the scenes in understanding world dynamics, we further propose NS-4Dynamics, a Neural-Symbolic model for reasoning on 4D Dynamics properties under explicit scene representation from videos. Using scene rendering likelihood combining physical prior distribution, the 4D scene parser can estimate the dynamics properties of objects over time to and interpret the observation into 4D scene representation as world states. By further incorporating neural-symbolic reasoning, our approach enables advanced applications in future prediction, factual reasoning, and counterfactual reasoning. Our experiments show that our NS-4Dynamics suppresses previous VLMs in understanding the dynamics properties and answering questions about factual queries, future prediction, and counterfactual reasoning. Moreover, based on the explicit 4D scene representation, our model is effective in reconstructing the 4D scenes and re-simulate the future or counterfactual events.
Authors: Yun Peng, Xiao Lin, Nachuan Ma, Jiayuan Du, Chuangwei Liu, Chengju Liu, Qijun Chen
Abstract: Visual anomaly detection is vital in real-world applications, such as industrial defect detection and medical diagnosis. However, most existing methods focus on local structural anomalies and fail to detect higher-level functional anomalies under logical conditions. Although recent studies have explored logical anomaly detection, they can only address simple anomalies like missing or addition and show poor generalizability due to being heavily data-driven. To fill this gap, we propose SAM-LAD, a zero-shot, plug-and-play framework for logical anomaly detection in any scene. First, we obtain a query image's feature map using a pre-trained backbone. Simultaneously, we retrieve the reference images and their corresponding feature maps via the nearest neighbor search of the query image. Then, we introduce the Segment Anything Model (SAM) to obtain object masks of the query and reference images. Each object mask is multiplied with the entire image's feature map to obtain object feature maps. Next, an Object Matching Model (OMM) is proposed to match objects in the query and reference images. To facilitate object matching, we further propose a Dynamic Channel Graph Attention (DCGA) module, treating each object as a keypoint and converting its feature maps into feature vectors. Finally, based on the object matching relations, an Anomaly Measurement Model (AMM) is proposed to detect objects with logical anomalies. Structural anomalies in the objects can also be detected. We validate our proposed SAM-LAD using various benchmarks, including industrial datasets (MVTec Loco AD, MVTec AD), and the logical dataset (DigitAnatomy). Extensive experimental results demonstrate that SAM-LAD outperforms existing SoTA methods, particularly in detecting logical anomalies.
Authors: Cong Wang, Jinshan Pan, Wei Wang, Gang Fu, Siyuan Liang, Mengzhu Wang, Xiao-Ming Wu, Jun Liu
Abstract: This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high features and reconstructs the residual images, while the latter explores more representative features learning from the high-resolution ones to facilitate better restoration. To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one. To that end, we propose two new modules: Dual-path Correlation Matching Transformation module (DualCMT) and Adaptive Channel Modulator (ACM). The DualCMT selects top C/r (r is greater or equal to 1 which controls the squeezing level) correlation channels from the max-pooling/mean-pooling high-resolution features to replace low-resolution ones in Transformers, which can effectively squeeze useless content to improve the feature representation in low-resolution space to facilitate better recovery. The ACM is exploited to adaptively modulate multi-level high-resolution features, enabling to provide more useful features to low-resolution space for better learning. Experimental results show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes will be made available at https://github.com/supersupercong/UHDformer.
Authors: Jiaying Zhou, Mingzhou Jiang, Junde Wu, Jiayuan Zhu, Ziyue Wang, Yueming Jin
Abstract: Medicine is inherently a multimodal discipline. Medical images can reflect the pathological changes of cancer and tumors, while the expression of specific genes can influence their morphological characteristics. However, most deep learning models employed for these medical tasks are unimodal, making predictions using either image data or genomic data exclusively. In this paper, we propose a multimodal pre-training framework that jointly incorporates genomics and medical images for downstream tasks. To address the issues of high computational complexity and difficulty in capturing long-range dependencies in genes sequence modeling with MLP or Transformer architectures, we utilize Mamba to model these long genomic sequences. We aligns medical images and genes using a self-supervised contrastive learning approach which combines the Mamba as a genetic encoder and the Vision Transformer (ViT) as a medical image encoder. We pre-trained on the TCGA dataset using paired gene expression data and imaging data, and fine-tuned it for downstream tumor segmentation tasks. The results show that our model outperformed a wide range of related methods.
Authors: Yukai Shi, Yupei Lin, Pengxu Wei, Xiaoyu Xian, Tianshui Chen, Liang Lin
Abstract: Recently, researchers have proposed various deep learning methods to accurately detect infrared targets with the characteristics of indistinct shape and texture. Due to the limited variety of infrared datasets, training deep learning models with good generalization poses a challenge. To augment the infrared dataset, researchers employ data augmentation techniques, which often involve generating new images by combining images from different datasets. However, these methods are lacking in two respects. In terms of realism, the images generated by mixup-based methods lack realism and are difficult to effectively simulate complex real-world scenarios. In terms of diversity, compared with real-world scenes, borrowing knowledge from another dataset inherently has a limited diversity. Currently, the diffusion model stands out as an innovative generative approach. Large-scale trained diffusion models have a strong generative prior that enables real-world modeling of images to generate diverse and realistic images. In this paper, we propose Diff-Mosaic, a data augmentation method based on the diffusion model. This model effectively alleviates the challenge of diversity and realism of data augmentation methods via diffusion prior. Specifically, our method consists of two stages. Firstly, we introduce an enhancement network called Pixel-Prior, which generates highly coordinated and realistic Mosaic images by harmonizing pixels. In the second stage, we propose an image enhancement strategy named Diff-Prior. This strategy utilizes diffusion priors to model images in the real-world scene, further enhancing the diversity and realism of the images. Extensive experiments have demonstrated that our approach significantly improves the performance of the detection network. The code is available at https://github.com/YupeiLin2388/Diff-Mosaic
Authors: Taeryung Lee, Fabien Baradel, Thomas Lucas, Kyoung Mu Lee, Gregory Rogez
Abstract: In this paper, we address the challenging problem of long-term 3D human motion generation. Specifically, we aim to generate a long sequence of smoothly connected actions from a stream of multiple sentences (i.e., paragraph). Previous long-term motion generating approaches were mostly based on recurrent methods, using previously generated motion chunks as input for the next step. However, this approach has two drawbacks: 1) it relies on sequential datasets, which are expensive; 2) these methods yield unrealistic gaps between motions generated at each step. To address these issues, we introduce simple yet effective T2LM, a continuous long-term generation framework that can be trained without sequential data. T2LM comprises two components: a 1D-convolutional VQVAE, trained to compress motion to sequences of latent vectors, and a Transformer-based Text Encoder that predicts a latent sequence given an input text. At inference, a sequence of sentences is translated into a continuous stream of latent vectors. This is then decoded into a motion by the VQVAE decoder; the use of 1D convolutions with a local temporal receptive field avoids temporal inconsistencies between training and generated sequences. This simple constraint on the VQ-VAE allows it to be trained with short sequences only and produces smoother transitions. T2LM outperforms prior long-term generation models while overcoming the constraint of requiring sequential data; it is also competitive with SOTA single-action generation models.
Authors: Chunjin Song, Zhijie Wu, Bastian Wandt, Leonid Sigal, Helge Rhodin
Abstract: For reconstructing high-fidelity human 3D models from monocular videos, it is crucial to maintain consistent large-scale body shapes along with finely matched subtle wrinkles. This paper explores the observation that the per-frame rendering results can be factorized into a pose-independent component and a corresponding pose-dependent equivalent to facilitate frame consistency. Pose adaptive textures can be further improved by restricting frequency bands of these two components. In detail, pose-independent outputs are expected to be low-frequency, while highfrequency information is linked to pose-dependent factors. We achieve a coherent preservation of both coarse body contours across the entire input video and finegrained texture features that are time variant with a dual-branch network with distinct frequency components. The first branch takes coordinates in canonical space as input, while the second branch additionally considers features outputted by the first branch and pose information of each frame. Our network integrates the information predicted by both branches and utilizes volume rendering to generate photo-realistic 3D human images. Through experiments, we demonstrate that our network surpasses the neural radiance fields (NeRF) based state-of-the-art methods in preserving high-frequency details and ensuring consistent body contours.
Authors: Haojun Xu, Yan Gao, Jie Li, Xinbo Gao
Abstract: Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial distributions. However, these methods extract semantic features simply. They ignore that proper prompt design for rich and fine-grained action cues can provide robust representation space clustering. In order to alleviate the problem of insufficient information available for skeleton sequences, we design an information compensation learning framework from an information-theoretic perspective to improve zero-shot action recognition accuracy with a multi-granularity semantic interaction mechanism. Inspired by ensemble learning, we propose a multi-level alignment (MLA) approach to compensate information for action classes. MLA aligns multi-granularity embeddings with visual embedding through a multi-head scoring mechanism to distinguish semantically similar action names and visually similar actions. Furthermore, we introduce a new loss function sampling method to obtain a tight and robust representation. Finally, these multi-granularity semantic embeddings are synthesized to form a proper decision surface for classification. Significant action recognition performance is achieved when evaluated on the challenging NTU RGB+D, NTU RGB+D 120, and PKU-MMD benchmarks and validate that multi-granularity semantic features facilitate the differentiation of action clusters with similar visual features.
Authors: Jun Li, Tongkun Su, Baoliang Zhao, Faqin Lv, Qiong Wang, Nassir Navab, Ying Hu, Zhongliang Jiang
Abstract: Automatic report generation has arisen as a significant research area in computer-aided diagnosis, aiming to alleviate the burden on clinicians by generating reports automatically based on medical images. In this work, we propose a novel framework for automatic ultrasound report generation, leveraging a combination of unsupervised and supervised learning methods to aid the report generation process. Our framework incorporates unsupervised learning methods to extract potential knowledge from ultrasound text reports, serving as the prior information to guide the model in aligning visual and textual features, thereby addressing the challenge of feature discrepancy. Additionally, we design a global semantic comparison mechanism to enhance the performance of generating more comprehensive and accurate medical reports. To enable the implementation of ultrasound report generation, we constructed three large-scale ultrasound image-text datasets from different organs for training and validation purposes. Extensive evaluations with other state-of-the-art approaches exhibit its superior performance across all three datasets. Code and dataset are valuable at this link.
Authors: Benjamin Towle, Xin Chen, Ke Zhou
Abstract: The recently released Segment Anything Model (SAM) has shown powerful zero-shot segmentation capabilities through a semi-automatic annotation setup in which the user can provide a prompt in the form of clicks or bounding boxes. There is growing interest around applying this to medical imaging, where the cost of obtaining expert annotations is high, privacy restrictions may limit sharing of patient data, and model generalisation is often poor. However, there are large amounts of inherent uncertainty in medical images, due to unclear object boundaries, low-contrast media, and differences in expert labelling style. Currently, SAM is known to struggle in a zero-shot setting to adequately annotate the contours of the structure of interest in medical images, where the uncertainty is often greatest, thus requiring significant manual correction. To mitigate this, we introduce \textbf{Sim}ulated Interaction for \textbf{S}egment \textbf{A}nything \textbf{M}odel (\textsc{\textbf{SimSAM}}), an approach that leverages simulated user interaction to generate an arbitrary number of candidate masks, and uses a novel aggregation approach to output the most compatible mask. Crucially, our method can be used during inference directly on top of SAM, without any additional training requirement. Quantitatively, we evaluate our method across three publicly available medical imaging datasets, and find that our approach leads to up to a 15.5\% improvement in contour segmentation accuracy compared to zero-shot SAM. Our code is available at \url{https://github.com/BenjaminTowle/SimSAM}.
Authors: Yunheng Li, ZhongYu Li, Quansheng Zeng, Qibin Hou, Ming-Ming Cheng
Abstract: Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features from the last layer to align with text embeddings, while they neglect the crucial information in intermediate layers that contain rich object details. However, we find that directly aggregating the multi-level visual features weakens the zero-shot ability for novel classes. The large differences between the visual features from different layers make these features hard to align well with the text embeddings. We resolve this problem by introducing a series of independent decoders to align the multi-level visual features with the text embeddings in a cascaded way, forming a novel but simple framework named Cascade-CLIP. Our Cascade-CLIP is flexible and can be easily applied to existing zero-shot semantic segmentation methods. Experimental results show that our simple Cascade-CLIP achieves superior zero-shot performance on segmentation benchmarks, like COCO-Stuff, Pascal-VOC, and Pascal-Context. Our code is available at: https://github.com/HVision-NKU/Cascade-CLIP
Authors: Xuenian Wang, Shanshan Shi, Renao Yan, Qiehe Sun, Lianghui Zhu, Tian Guan, Yonghong He
Abstract: In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation reveals that discriminative embeddings are crucial for aggregation to the final prediction. Among all feature updating strategies, task-oriented ones can capture characteristics specifically for certain tasks. However, they can be prone to overfitting and contaminated by samples assigned with noisy labels. To address this issue, we propose a heuristic clustering-driven feature fine-tuning method (HC-FT) to enhance the performance of multiple instance learning by providing purified positive and hard negative samples. Our method first employs a well-trained MIL model to evaluate the confidence of patches. Then, patches with high confidence are marked as positive samples, while the remaining patches are used to identify crucial negative samples. After two rounds of heuristic clustering and selection, purified positive and hard negative samples are obtained to facilitate feature fine-tuning. The proposed method is evaluated on both CAMELYON16 and BRACS datasets, achieving an AUC of 97.13% and 85.85%, respectively, consistently outperforming all compared methods.
Authors: Hao Liu, Yang Yang, Yunxia Liu
Abstract: Face Super-Resolution (FSR) aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Despite the progress made by convolutional neural networks in FSR, the results of existing approaches are not ideal due to their low reconstruction efficiency and insufficient utilization of prior information. Considering that faces are highly structured objects, effectively leveraging facial priors to improve FSR results is a worthwhile endeavor. This paper proposes a novel network architecture called W-Net to address this challenge. W-Net leverages meticulously designed Parsing Block to fully exploit the resolution potential of LR image. We use this parsing map as an attention prior, effectively integrating information from both the parsing map and LR images. Simultaneously, we perform multiple fusions in various dimensions through the W-shaped network structure combined with the LPF(LR-Parsing Map Fusion Module). Additionally, we utilize a facial parsing graph as a mask, assigning different weights and loss functions to key facial areas to balance the performance of our reconstructed facial images between perceptual quality and pixel accuracy. We conducted extensive comparative experiments, not only limited to conventional facial super-resolution metrics but also extending to downstream tasks such as facial recognition and facial keypoint detection. The experiments demonstrate that W-Net exhibits outstanding performance in quantitative metrics, visual quality, and downstream tasks.
Authors: Haisu Guan, Huanxin Yang, Xinyu Wang, Shengwei Han, Yongge Liu, Lianwen Jin, Xiang Bai, Yuliang Liu
Abstract: Originating from China's Shang Dynasty approximately 3,000 years ago, the Oracle Bone Script (OBS) is a cornerstone in the annals of linguistic history, predating many established writing systems. Despite the discovery of thousands of inscriptions, a vast expanse of OBS remains undeciphered, casting a veil of mystery over this ancient language. The emergence of modern AI technologies presents a novel frontier for OBS decipherment, challenging traditional NLP methods that rely heavily on large textual corpora, a luxury not afforded by historical languages. This paper introduces a novel approach by adopting image generation techniques, specifically through the development of Oracle Bone Script Decipher (OBSD). Utilizing a conditional diffusion-based strategy, OBSD generates vital clues for decipherment, charting a new course for AI-assisted analysis of ancient languages. To validate its efficacy, extensive experiments were conducted on an oracle bone script dataset, with quantitative results demonstrating the effectiveness of OBSD. Code and decipherment results will be made available at https://github.com/guanhaisu/OBSD.
Authors: Jiacheng Zhang, Feng Liu, Dawei Zhou, Jingfeng Zhang, Tongliang Liu
Abstract: Adversarial training (AT) trains models using adversarial examples (AEs), which are natural images modified with specific perturbations to mislead the model. These perturbations are constrained by a predefined perturbation budget $\epsilon$ and are equally applied to each pixel within an image. However, in this paper, we discover that not all pixels contribute equally to the accuracy on AEs (i.e., robustness) and accuracy on natural images (i.e., accuracy). Motivated by this finding, we propose Pixel-reweighted AdveRsarial Training (PART), a new framework that partially reduces $\epsilon$ for less influential pixels, guiding the model to focus more on key regions that affect its outputs. Specifically, we first use class activation mapping (CAM) methods to identify important pixel regions, then we keep the perturbation budget for these regions while lowering it for the remaining regions when generating AEs. In the end, we use these pixel-reweighted AEs to train a model. PART achieves a notable improvement in accuracy without compromising robustness on CIFAR-10, SVHN and TinyImagenet-200, justifying the necessity to allocate distinct weights to different pixel regions in robust classification.
Authors: Ohad Rahamim, Hilit Segev, Idan Achituve, Yuval Atzmon, Yoni Kasten, Gal Chechik
Abstract: Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects. Here we introduce Lay-A-Scene, which solves the task of Open-set 3D Object Arrangement, effectively arranging unseen objects. Given a set of 3D objects, the task is to find a plausible arrangement of these objects in a scene. We address this task by leveraging pre-trained text-to-image models. We personalize the model and explain how to generate images of a scene that contains multiple predefined objects without neglecting any of them. Then, we describe how to infer the 3D poses and arrangement of objects from a 2D generated image by finding a consistent projection of objects onto the 2D scene. We evaluate the quality of Lay-A-Scene using 3D objects from Objaverse and human raters and find that it often generates coherent and feasible 3D object arrangements.
Authors: Belal Ahmad, Mohd Usama, Tanvir Ahmad, Adnan Saeed, Shabnam Khatoon, Long Hu
Abstract: In this study, we proposed a model for skin disease classification using a Bilinear Convolutional Neural Network (BCNN) with a Constrained Triplet Network (CTN). BCNN can capture rich spatial interactions between features in image data. This computes the outer product of feature vectors from two different CNNs by a bilinear pooling. The resulting features encode second-order statistics, enabling the network to capture more complex relationships between different channels and spatial locations. The CTN employs the Triplet Loss Function (TLF) by using a new loss layer that is added at the end of the architecture called the Constrained Triplet Loss (CTL) layer. This is done to obtain two significant learning objectives: inter-class categorization and intra-class concentration with their deep features as often as possible, which can be effective for skin disease classification. The proposed model is trained to extract the intra-class features from a deep network and accordingly increases the distance between these features, improving the model's performance. The model achieved a mean accuracy of 93.72%.
Authors: Yuan Xiao, Shiqing Ma, Juan Zhai, Chunrong Fang, Jinyuan Jia, Zhenyu Chen
Abstract: The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classification result. It is challenging due to nonlinear components, such as MaxPool. At present, many verification methods are sound but risk losing some precision to enhance efficiency and scalability, and thus, a certified lower bound is a crucial criterion for evaluating the performance of verification tools. In this paper, we present MaxLin, a robustness verifier for MaxPool-based CNNs with tight linear approximation. By tightening the linear approximation of the MaxPool function, we can certify larger certified lower bounds of CNNs. We evaluate MaxLin with open-sourced benchmarks, including LeNet and networks trained on the MNIST, CIFAR-10, and Tiny ImageNet datasets. The results show that MaxLin outperforms state-of-the-art tools with up to 110.60% improvement regarding the certified lower bound and 5.13 $\times$ speedup for the same neural networks. Our code is available at https://github.com/xiaoyuanpigo/maxlin.
Authors: Ylva Gr{\o}nnings{\ae}ter, Halvor S. Sm{\o}rvik, Ole-Christoffer Granmo
Abstract: The Tsetlin Machine (TM) has achieved competitive results on several image classification benchmarks, including MNIST, K-MNIST, F-MNIST, and CIFAR-2. However, color image classification is arguably still in its infancy for TMs, with CIFAR-10 being a focal point for tracking progress. Over the past few years, TM's CIFAR-10 accuracy has increased from around 61% in 2020 to 75.1% in 2023 with the introduction of Drop Clause. In this paper, we leverage the recently proposed TM Composites architecture and introduce a range of TM Specialists that use various image processing techniques. These include Canny edge detection, Histogram of Oriented Gradients, adaptive mean thresholding, adaptive Gaussian thresholding, Otsu's thresholding, color thermometers, and adaptive color thermometers. In addition, we conduct a rigorous hyperparameter search, where we uncover optimal hyperparameters for several of the TM Specialists. The result is a toolbox that provides new state-of-the-art results on CIFAR-10 for TMs with an accuracy of 82.8%. In conclusion, our toolbox of TM Specialists forms a foundation for new TM applications and a landmark for further research on TM Composites in image analysis.
Authors: Di Wu, Feng Yang, Benlian Xu, Pan Liao, Bo Liu
Abstract: With the rapid advancement of autonomous driving technology, there is a growing need for enhanced safety and efficiency in the automatic environmental perception of vehicles during their operation. In modern vehicle setups, cameras and mmWave radar (radar), being the most extensively employed sensors, demonstrate complementary characteristics, inherently rendering them conducive to fusion and facilitating the achievement of both robust performance and cost-effectiveness. This paper focuses on a comprehensive survey of radar-vision (RV) fusion based on deep learning methods for 3D object detection in autonomous driving. We offer a comprehensive overview of each RV fusion category, specifically those employing region of interest (ROI) fusion and end-to-end fusion strategies. As the most promising fusion strategy at present, we provide a deeper classification of end-to-end fusion methods, including those 3D bounding box prediction based and BEV based approaches. Moreover, aligning with recent advancements, we delineate the latest information on 4D radar and its cutting-edge applications in autonomous vehicles (AVs). Finally, we present the possible future trends of RV fusion and summarize this paper.
Authors: Cong Wang, Wei Wang, Chengjin Yu, Jie Mu
Abstract: Patch-level non-local self-similarity is an important property of natural images. However, most existing methods do not consider this property into neural networks for image deraining, thus affecting recovery performance. Motivated by this property, we find that there exists significant patch recurrence property of a rainy image, that is, similar patches tend to recur many times in one image and its multi-scale images and external images. To better model this property for image detaining, we develop a multi-scale graph network with exemplars, called MSGNN, that contains two branches: 1) internal data-based supervised branch is used to model the internal relations of similar patches from the rainy image itself and its multi-scale images and 2) external data-participated unsupervised branch is used to model the external relations of the similar patches in the rainy image and exemplar. Specifically, we construct a graph model by searching the k-nearest neighboring patches from both the rainy images in a multi-scale framework and the exemplar. After obtaining the corresponding k neighboring patches from the multi-scale images and exemplar, we build a graph and aggregate them in an attentional manner so that the graph can provide more information from similar patches for image deraining. We embed the proposed graph in a deep neural network and train it in an end-to-end manner. Extensive experiments demonstrate that the proposed algorithm performs favorably against eight state-of-the-art methods on five public synthetic datasets and one real-world dataset. The source codes will be available at https://github.com/supersupercong/MSGNN.
Authors: Pranav Singh Chib, Pravendra Singh
Abstract: Accurately predicting future pedestrian trajectories is crucial across various domains. Due to the uncertainty in future pedestrian trajectories, it is important to learn complex spatio-temporal representations in multi-agent scenarios. To address this, we propose a novel Cross-Correction Framework (CCF) to learn spatio-temporal representations of pedestrian trajectories better. Our framework consists of two trajectory prediction models, known as subnets, which share the same architecture and are trained with both cross-correction loss and trajectory prediction loss. Cross-correction leverages the learning from both subnets and enables them to refine their underlying representations of trajectories through a mutual correction mechanism. Specifically, we use the cross-correction loss to learn how to correct each other through an inter-subnet interaction. To induce diverse learning among the subnets, we use the transformed observed trajectories produced by a neural network as input to one subnet and the original observed trajectories as input to the other subnet. We utilize transformer-based encoder-decoder architecture for each subnet to capture motion and social interaction among pedestrians. The encoder of the transformer captures motion patterns in trajectories, while the decoder focuses on pedestrian interactions with neighbors. Each subnet performs the primary task of predicting future trajectories (a regression task) along with the secondary task of classifying the predicted trajectories (a classification task). Extensive experiments on real-world benchmark datasets such as ETH-UCY and SDD demonstrate the efficacy of our proposed framework, CCF, in precisely predicting pedestrian future trajectories. We also conducted several ablation experiments to demonstrate the effectiveness of various modules and loss functions used in our approach.
Authors: Wenqiang Sun, Zhengyi Wang, Shuo Chen, Yikai Wang, Zilong Chen, Jun Zhu, Jun Zhang
Abstract: Creating 3D assets from single-view images is a complex task that demands a deep understanding of the world. Recently, feed-forward 3D generative models have made significant progress by training large reconstruction models on extensive 3D datasets, with triplanes being the preferred 3D geometry representation. However, effectively utilizing the geometric priors of triplanes, while minimizing artifacts caused by generated inconsistent multi-view images, remains a challenge. In this work, we present \textbf{Fre}quency modulat\textbf{e}d tri\textbf{plane} (\textbf{Freeplane}), a simple yet effective method to improve the generation quality of feed-forward models without additional training. We first analyze the role of triplanes in feed-forward methods and find that the inconsistent multi-view images introduce high-frequency artifacts on triplanes, leading to low-quality 3D meshes. Based on this observation, we propose strategically filtering triplane features and combining triplanes before and after filtering to produce high-quality textured meshes. These techniques incur no additional cost and can be seamlessly integrated into pre-trained feed-forward models to enhance their robustness against the inconsistency of generated multi-view images. Both qualitative and quantitative results demonstrate that our method improves the performance of feed-forward models by simply modulating triplanes. All you need is to modulate the triplanes during inference.
Authors: Cristiano Patr\'icio, Carlo Alberto Barbano, Attilio Fiandrotti, Riccardo Renzulli, Marco Grangetto, Luis F. Teixeira, Jo\~ao C. Neves
Abstract: Contrastive Analysis (CA) regards the problem of identifying patterns in images that allow distinguishing between a background (BG) dataset (i.e. healthy subjects) and a target (TG) dataset (i.e. unhealthy subjects). Recent works on this topic rely on variational autoencoders (VAE) or contrastive learning strategies to learn the patterns that separate TG samples from BG samples in a supervised manner. However, the dependency on target (unhealthy) samples can be challenging in medical scenarios due to their limited availability. Also, the blurred reconstructions of VAEs lack utility and interpretability. In this work, we redefine the CA task by employing a self-supervised contrastive encoder to learn a latent representation encoding only common patterns from input images, using samples exclusively from the BG dataset during training, and approximating the distribution of the target patterns by leveraging data augmentation techniques. Subsequently, we exploit state-of-the-art generative methods, i.e. diffusion models, conditioned on the learned latent representation to produce a realistic (healthy) version of the input image encoding solely the common patterns. Thorough validation on a facial image dataset and experiments across three brain MRI datasets demonstrate that conditioning the generative process of state-of-the-art generative methods with the latent representation from our self-supervised contrastive encoder yields improvements in the generated image quality and in the accuracy of image classification. The code is available at https://github.com/CristianoPatricio/unsupervised-contrastive-cond-diff.
URLs: https://github.com/CristianoPatricio/unsupervised-contrastive-cond-diff.
Authors: Yuxiang Ji, Boyong He, Chenyuan Qu, Zhuoyue Tan, Chuan Qin, Liaoni Wu
Abstract: Pre-trained diffusion models have demonstrated remarkable proficiency in synthesizing images across a wide range of scenarios with customizable prompts, indicating their effective capacity to capture universal features. Motivated by this, our study delves into the utilization of the implicit knowledge embedded within diffusion models to address challenges in cross-domain semantic segmentation. This paper investigates the approach that leverages the sampling and fusion techniques to harness the features of diffusion models efficiently. Contrary to the simplistic migration applications characterized by prior research, our finding reveals that the multi-step diffusion process inherent in the diffusion model manifests more robust semantic features. We propose DIffusion Feature Fusion (DIFF) as a backbone use for extracting and integrating effective semantic representations through the diffusion process. By leveraging the strength of text-to-image generation capability, we introduce a new training framework designed to implicitly learn posterior knowledge from it. Through rigorous evaluation in the contexts of domain generalization semantic segmentation, we establish that our methodology surpasses preceding approaches in mitigating discrepancies across distinct domains and attains the state-of-the-art (SOTA) benchmark. Within the synthetic-to-real (syn-to-real) context, our method significantly outperforms ResNet-based and transformer-based backbone methods, achieving an average improvement of $3.84\%$ mIoU across various datasets. The implementation code will be released soon.
Authors: Li Lin, Santosh, Xin Wang, Shu Hu
Abstract: AI-generated faces have enriched human life, such as entertainment, education, and art. However, they also pose misuse risks. Therefore, detecting AI-generated faces becomes crucial, yet current detectors show biased performance across different demographic groups. Mitigating biases can be done by designing algorithmic fairness methods, which usually require demographically annotated face datasets for model training. However, no existing dataset comprehensively encompasses both demographic attributes and diverse generative methods, which hinders the development of fair detectors for AI-generated faces. In this work, we introduce the AI-Face dataset, the first million-scale demographically annotated AI-generated face image dataset, including real faces, faces from deepfake videos, and faces generated by Generative Adversarial Networks and Diffusion Models. Based on this dataset, we conduct the first comprehensive fairness benchmark to assess various AI face detectors and provide valuable insights and findings to promote the future fair design of AI face detectors. Our AI-Face dataset and benchmark code are publicly available at https://github.com/Purdue-M2/AI-Face-FairnessBench.
Authors: Lei Liu, Zhihao Hu, Zhenghao Chen
Abstract: Point cloud compression has garnered significant interest in computer vision. However, existing algorithms primarily cater to human vision, while most point cloud data is utilized for machine vision tasks. To address this, we propose a point cloud compression framework that simultaneously handles both human and machine vision tasks. Our framework learns a scalable bit-stream, using only subsets for different machine vision tasks to save bit-rate, while employing the entire bit-stream for human vision tasks. Building on mainstream octree-based frameworks like VoxelContext-Net, OctAttention, and G-PCC, we introduce a new octree depth-level predictor. This predictor adaptively determines the optimal depth level for each octree constructed from a point cloud, controlling the bit-rate for machine vision tasks. For simpler tasks (\textit{e.g.}, classification) or objects/scenarios, we use fewer depth levels with fewer bits, saving bit-rate. Conversely, for more complex tasks (\textit{e.g}., segmentation) or objects/scenarios, we use deeper depth levels with more bits to enhance performance. Experimental results on various datasets (\textit{e.g}., ModelNet10, ModelNet40, ShapeNet, ScanNet, and KITTI) show that our point cloud compression approach improves performance for machine vision tasks without compromising human vision quality.
Authors: Yeonsung Jung, Heecheol Yun, Joonhyung Park, Jin-Hwa Kim, Eunho Yang
Abstract: Neural Radiance Fields (NeRF) have shown remarkable performance in learning 3D scenes. However, NeRF exhibits vulnerability when confronted with distractors in the training images -- unexpected objects are present only within specific views, such as moving entities like pedestrians or birds. Excluding distractors during dataset construction is a straightforward solution, but without prior knowledge of their types and quantities, it becomes prohibitively expensive. In this paper, we propose PruNeRF, a segment-centric dataset pruning framework via 3D spatial consistency, that effectively identifies and prunes the distractors. We first examine existing metrics for measuring pixel-wise distraction and introduce Influence Functions for more accurate measurements. Then, we assess 3D spatial consistency using a depth-based reprojection technique to obtain 3D-aware distraction. Furthermore, we incorporate segmentation for pixel-to-segment refinement, enabling more precise identification. Our experiments on benchmark datasets demonstrate that PruNeRF consistently outperforms state-of-the-art methods in robustness against distractors.
Authors: Hadrien Reynaud, Qingjie Meng, Mischa Dombrowski, Arijit Ghosh, Thomas Day, Alberto Gomez, Paul Leeson, Bernhard Kainz
Abstract: To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data. Until now, generative methods have faced constraints in terms of fidelity, spatio-temporal coherence, and the length of generation, failing to capture the complete details of dataset distributions. We present a model designed to produce high-fidelity, long and complete data samples with near-real-time efficiency and explore our approach on a challenging task: generating echocardiogram videos. We develop our generation method based on diffusion models and introduce a protocol for medical video dataset anonymization. As an exemplar, we present EchoNet-Synthetic, a fully synthetic, privacy-compliant echocardiogram dataset with paired ejection fraction labels. As part of our de-identification protocol, we evaluate the quality of the generated dataset and propose to use clinical downstream tasks as a measurement on top of widely used but potentially biased image quality metrics. Experimental outcomes demonstrate that EchoNet-Synthetic achieves comparable dataset fidelity to the actual dataset, effectively supporting the ejection fraction regression task. Code, weights and dataset are available at https://github.com/HReynaud/EchoNet-Synthetic.
Authors: Nurit Spingarn-Eliezer, Tomer Michaeli
Abstract: Training deep neural networks requires significant computational resources and large datasets that are often confidential or expensive to collect. As a result, owners tend to protect their models by allowing access only via an API. Many works demonstrated the possibility of stealing such protected models by repeatedly querying the API. However, to date, research has predominantly focused on stealing classification models, for which a very large number of queries has been found necessary. In this paper, we study the possibility of stealing image-to-image models. Surprisingly, we find that many such models can be stolen with as little as a single, small-sized, query image using simple distillation. We study this phenomenon on a wide variety of model architectures, datasets, and tasks, including denoising, deblurring, deraining, super-resolution, and biological image-to-image translation. Remarkably, we find that the vulnerability to stealing attacks is shared by CNNs and by models with attention mechanisms, and that stealing is commonly possible even without knowing the architecture of the target model.
Authors: Yang Cao, Yihan Zeng, Hang Xu, Dan Xu
Abstract: Open-vocabulary 3D Object Detection (OV-3DDet) addresses the detection of objects from an arbitrary list of novel categories in 3D scenes, which remains a very challenging problem. In this work, we propose CoDAv2, a unified framework designed to innovatively tackle both the localization and classification of novel 3D objects, under the condition of limited base categories. For localization, the proposed 3D Novel Object Discovery (3D-NOD) strategy utilizes 3D geometries and 2D open-vocabulary semantic priors to discover pseudo labels for novel objects during training. 3D-NOD is further extended with an Enrichment strategy that significantly enriches the novel object distribution in the training scenes, and then enhances the model's ability to localize more novel objects. The 3D-NOD with Enrichment is termed 3D-NODE. For classification, the Discovery-driven Cross-modal Alignment (DCMA) module aligns features from 3D point clouds and 2D/textual modalities, employing both class-agnostic and class-specific alignments that are iteratively refined to handle the expanding vocabulary of objects. Besides, 2D box guidance boosts the classification accuracy against complex background noises, which is coined as Box-DCMA. Extensive evaluation demonstrates the superiority of CoDAv2. CoDAv2 outperforms the best-performing method by a large margin (AP_Novel of 9.17 vs. 3.61 on SUN-RGBD and 9.12 vs. 3.74 on ScanNetv2). Source code and pre-trained models are available at the GitHub project page.
Authors: Abdelilah Nossair, Hamza El Housni
Abstract: The Smart Dietary Assistant utilizes Machine Learning to provide personalized dietary advice, focusing on users with conditions like diabetes. This app leverages the Grounding DINO model, which combines a text encoder and image backbone to enhance food item detection without requiring a labeled dataset. With an AP score of 52.5 on the COCO dataset, the model demonstrates high accuracy in real-world scenarios, utilizing attention mechanisms to precisely recognize objects based on user-provided labels and images. Developed using React Native and TypeScript, the app operates seamlessly across multiple platforms and integrates a self-hosted PostgreSQL database, ensuring data integrity and enhancing user privacy. Key functionalities include personalized nutrition profiles, real-time food scanning, and health insights, facilitating informed dietary choices for health management and lifestyle optimization. Future developments aim to integrate wearable technologies for more tailored health recommendations. Keywords: Food Image Recognition, Machine Learning in Nutrition, Zero-Shot Object Detection
Authors: Yewon Lim, Changyeon Lee, Aerin Kim, Oren Etzioni
Abstract: A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward category, the computational load is significant when employing the "reconstruction then compare" technique. This approach, known as DIRE (Diffusion Reconstruction Error), not only identifies diffusion-generated images but also detects those produced by GANs, highlighting the technique's broad applicability. To address the computational challenges and improve efficiency, we propose distilling the knowledge embedded in diffusion models to develop rapid deepfake detection models. Our approach, aimed at creating a small, fast, cheap, and lightweight diffusion synthesized deepfake detector, maintains robust performance while significantly reducing operational demands. Maintaining performance, our experimental results indicate an inference speed 3.2 times faster than the existing DIRE framework. This advance not only enhances the practicality of deploying these systems in real-world settings but also paves the way for future research endeavors that seek to leverage diffusion model knowledge.
Authors: Timothy Ossowski, Junjie Hu
Abstract: Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms of modeling, existing VLMs implicitly align text tokens with image patch tokens, which is ineffective for embedding alignment at the same granularity and inevitably introduces noisy spurious background features. Additionally, these models struggle when generalizing to unseen visual concepts and may not be reliable for domain-specific tasks without further fine-tuning. To address these limitations, we propose a novel method to prompt large language models with in-context visual object vectors, thereby enabling controllable object-level reasoning. This eliminates the necessity of fusing a lengthy array of image patch features and significantly speeds up training. Furthermore, we propose region-level retrieval using our object representations, facilitating rapid adaptation to new objects without additional training. Our experiments reveal that our method achieves competitive referring object classification and captioning performance, while also offering zero-shot generalization and robustness to visually challenging contexts.
Authors: Ivan Moskalenko, Anastasiia Kornilova, Gonzalo Ferrer
Abstract: Aerial imagery and its direct application to visual localization is an essential problem for many Robotics and Computer Vision tasks. While Global Navigation Satellite Systems (GNSS) are the standard default solution for solving the aerial localization problem, it is subject to a number of limitations, such as, signal instability or solution unreliability that make this option not so desirable. Consequently, visual geolocalization is emerging as a viable alternative. However, adapting Visual Place Recognition (VPR) task to aerial imagery presents significant challenges, including weather variations and repetitive patterns. Current VPR reviews largely neglect the specific context of aerial data. This paper introduces a methodology tailored for evaluating VPR techniques specifically in the domain of aerial imagery, providing a comprehensive assessment of various methods and their performance. However, we not only compare various VPR methods, but also demonstrate the importance of selecting appropriate zoom and overlap levels when constructing map tiles to achieve maximum efficiency of VPR algorithms in the case of aerial imagery. The code is available on our GitHub repository -- https://github.com/prime-slam/aero-vloc.
Authors: Xin-Yi Tong, Runmin Dong, Xiao Xiang Zhu
Abstract: Land cover information is indispensable for advancing the United Nations' sustainable development goals, and land cover mapping under a more detailed category system would significantly contribute to economic livelihood tracking and environmental degradation measurement. However, the substantial difficulty in acquiring fine-grained training data makes the implementation of this task particularly challenging. Here, we propose to combine fully labeled source domain and weakly labeled target domain for weakly supervised domain adaptation (WSDA). This is beneficial as the utilization of sparse and coarse weak labels can considerably alleviate the labor required for precise and detailed land cover annotation. Specifically, we introduce the Prototype-based pseudo-label Rectification and Expansion (PRE) approach, which leverages the prototypes (i.e., the class-wise feature centroids) as the bridge to connect sparse labels and global feature distributions. According to the feature distances to the prototypes, the confidence of pseudo-labels predicted in the unlabeled regions of the target domain is assessed. This confidence is then utilized to guide the dynamic expansion and rectification of pseudo-labels. Based on PRE, we carry out high categorical resolution land cover mapping for 10 cities in different regions around the world, severally using PlanetScope, Gaofen-1, and Sentinel-2 satellite images. In the study areas, we achieve cross-sensor, cross-category, and cross-continent WSDA, with the overall accuracy exceeding 80%. The promising results indicate that PRE is capable of reducing the dependency of land cover classification on high-quality annotations, thereby improving label efficiency. We expect our work to enable global fine-grained land cover mapping, which in turn promote Earth observation to provide more precise and thorough information for environmental monitoring.
Authors: Yuning Zhou, Henry Badgery, Matthew Read, James Bailey, Catherine E. Davey
Abstract: Self-supervised learning (SSL) has potential for effective representation learning in medical imaging, but the choice of data augmentation is critical and domain-specific. It remains uncertain if general augmentation policies suit surgical applications. In this work, we automate the search for suitable augmentation policies through a new method called Dimensionality Driven Augmentation Search (DDA). DDA leverages the local dimensionality of deep representations as a proxy target, and differentiably searches for suitable data augmentation policies in contrastive learning. We demonstrate the effectiveness and efficiency of DDA in navigating a large search space and successfully identifying an appropriate data augmentation policy for laparoscopic surgery. We systematically evaluate DDA across three laparoscopic image classification and segmentation tasks, where it significantly improves over existing baselines. Furthermore, DDA's optimised set of augmentations provides insight into domain-specific dependencies when applying contrastive learning in medical applications. For example, while hue is an effective augmentation for natural images, it is not advantageous for laparoscopic images.
Authors: Shaoshu Yang, Yong Zhang, Xiaodong Cun, Ying Shan, Ran He
Abstract: Video generation has made remarkable progress in recent years, especially since the advent of the video diffusion models. Many video generation models can produce plausible synthetic videos, e.g., Stable Video Diffusion (SVD). However, most video models can only generate low frame rate videos due to the limited GPU memory as well as the difficulty of modeling a large set of frames. The training videos are always uniformly sampled at a specified interval for temporal compression. Previous methods promote the frame rate by either training a video interpolation model in pixel space as a postprocessing stage or training an interpolation model in latent space for a specific base video model. In this paper, we propose a training-free video interpolation method for generative video diffusion models, which is generalizable to different models in a plug-and-play manner. We investigate the non-linearity in the feature space of video diffusion models and transform a video model into a self-cascaded video diffusion model with incorporating the designed hidden state correction modules. The self-cascaded architecture and the correction module are proposed to retain the temporal consistency between key frames and the interpolated frames. Extensive evaluations are preformed on multiple popular video models to demonstrate the effectiveness of the propose method, especially that our training-free method is even comparable to trained interpolation models supported by huge compute resources and large-scale datasets.
Authors: Kunpeng Wang, Danying Lin, Chenglong Li, Zhengzheng Tu, Bin Luo
Abstract: RGB and Thermal (RGBT) Salient Object Detection (SOD) aims to achieve high-quality saliency prediction by exploiting the complementary information of visible and thermal image pairs, which are initially captured in an unaligned manner. However, existing methods are tailored for manually aligned image pairs, which are labor-intensive, and directly applying these methods to original unaligned image pairs could significantly degrade their performance. In this paper, we make the first attempt to address RGBT SOD for initially captured RGB and thermal image pairs without manual alignment. Specifically, we propose a Semantics-guided Asymmetric Correlation Network (SACNet) that consists of two novel components: 1) an asymmetric correlation module utilizing semantics-guided attention to model cross-modal correlations specific to unaligned salient regions; 2) an associated feature sampling module to sample relevant thermal features according to the corresponding RGB features for multi-modal feature integration. In addition, we construct a unified benchmark dataset called UVT2000, containing 2000 RGB and thermal image pairs directly captured from various real-world scenes without any alignment, to facilitate research on alignment-free RGBT SOD. Extensive experiments on both aligned and unaligned datasets demonstrate the effectiveness and superior performance of our method. The dataset and code are available at https://github.com/Angknpng/SACNet.
Authors: Jinxing Zhou, Dan Guo, Yiran Zhong, Meng Wang
Abstract: The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised manner, where only video event labels are provided, \ie, the modalities and the timestamps of the labels are unknown. Due to the lack of densely annotated labels, recent work attempts to leverage pseudo labels to enrich the supervision. A commonly used strategy is to generate pseudo labels by categorizing the known video event labels for each modality. However, the labels are still confined to the video level, and the temporal boundaries of events remain unlabeled. In this paper, we propose a new pseudo label generation strategy that can explicitly assign labels to each video segment by utilizing prior knowledge learned from the open world. Specifically, we exploit the large-scale pretrained models, namely CLIP and CLAP, to estimate the events in each video segment and generate segment-level visual and audio pseudo labels, respectively. We then propose a new loss function to exploit these pseudo labels by taking into account their category-richness and segment-richness. A label denoising strategy is also adopted to further improve the visual pseudo labels by flipping them whenever abnormally large forward losses occur. We perform extensive experiments on the LLP dataset and demonstrate the effectiveness of each proposed design and we achieve state-of-the-art video parsing performance on all types of event parsing, \ie, audio event, visual event, and audio-visual event. We also examine the proposed pseudo label generation strategy on a relevant weakly-supervised audio-visual event localization task and the experimental results again verify the benefits and generalization of our method.
Authors: Takayuki Kanai, Igor Vasiljevic, Vitor Guizilini, Kazuhiro Shintani
Abstract: Monocular visual odometry is a key technology in a wide variety of autonomous systems. Relative to traditional feature-based methods, that suffer from failures due to poor lighting, insufficient texture, large motions, etc., recent learning-based SLAM methods exploit iterative dense bundle adjustment to address such failure cases and achieve robust accurate localization in a wide variety of real environments, without depending on domain-specific training data. However, despite its potential, learning-based SLAM still struggles with scenarios involving large motion and object dynamics. In this paper, we diagnose key weaknesses in a popular learning-based SLAM model (DROID-SLAM) by analyzing major failure cases on outdoor benchmarks and exposing various shortcomings of its optimization process. We then propose the use of self-supervised priors leveraging a frozen large-scale pre-trained monocular depth estimation to initialize the dense bundle adjustment process, leading to robust visual odometry without the need to fine-tune the SLAM backbone. Despite its simplicity, our proposed method demonstrates significant improvements on KITTI odometry, as well as the challenging DDAD benchmark. Code and pre-trained models will be released upon publication.
Authors: Tianyuan Zhang, Lu Wang, Hainan Li, Yisong Xiao, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao
Abstract: Lane detection (LD) is an essential component of autonomous driving systems, providing fundamental functionalities like adaptive cruise control and automated lane centering. Existing LD benchmarks primarily focus on evaluating common cases, neglecting the robustness of LD models against environmental illusions such as shadows and tire marks on the road. This research gap poses significant safety challenges since these illusions exist naturally in real-world traffic situations. For the first time, this paper studies the potential threats caused by these environmental illusions to LD and establishes the first comprehensive benchmark LanEvil for evaluating the robustness of LD against this natural corruption. We systematically design 14 prevalent yet critical types of environmental illusions (e.g., shadow, reflection) that cover a wide spectrum of real-world influencing factors in LD tasks. Based on real-world environments, we create 94 realistic and customizable 3D cases using the widely used CARLA simulator, resulting in a dataset comprising 90,292 sampled images. Through extensive experiments, we benchmark the robustness of popular LD methods using LanEvil, revealing substantial performance degradation (-5.37% Accuracy and -10.70% F1-Score on average), with shadow effects posing the greatest risk (-7.39% Accuracy). Additionally, we assess the performance of commercial auto-driving systems OpenPilot and Apollo through collaborative simulations, demonstrating that proposed environmental illusions can lead to incorrect decisions and potential traffic accidents. To defend against environmental illusions, we propose the Attention Area Mixing (AAM) approach using hard examples, which witness significant robustness improvement (+3.76%) under illumination effects. We hope our paper can contribute to advancing more robust auto-driving systems in the future. Website: https://lanevil.github.io/.
Authors: Fei Gao, Siwen Wang, Churan Wang, Fandong Zhang, Hong-Yu Zhou, Yizhou Wang, Gang Yu, Yizhou Yu
Abstract: Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods.
Authors: Sumit Sarin, Utkarsh Mall, Purva Tendulkar, Carl Vondrick
Abstract: Do our facial expressions change when we speak over video calls? Given two unpaired sets of videos of people, we seek to automatically find spatio-temporal patterns that are distinctive of each set. Existing methods use discriminative approaches and perform post-hoc explainability analysis. Such methods are insufficient as they are unable to provide insights beyond obvious dataset biases, and the explanations are useful only if humans themselves are good at the task. Instead, we tackle the problem through the lens of generative domain translation: our method generates a detailed report of learned, input-dependent spatio-temporal features and the extent to which they vary between the domains. We demonstrate that our method can discover behavioral differences between conversing face-to-face (F2F) and on video-calls (VCs). We also show the applicability of our method on discovering differences in presidential communication styles. Additionally, we are able to predict temporal change-points in videos that decouple expressions in an unsupervised way, and increase the interpretability and usefulness of our model. Finally, our method, being generative, can be used to transform a video call to appear as if it were recorded in a F2F setting. Experiments and visualizations show our approach is able to discover a range of behaviors, taking a step towards deeper understanding of human behaviors.
Authors: Tianyu Huang, Tao Zhou, Weidi Xie, Shuo Wang, Qi Dou, Yizhe Zhang
Abstract: The current variants of the Segment Anything Model (SAM), which include the original SAM and Medical SAM, still lack the capability to produce sufficiently accurate segmentation for medical images. In medical imaging contexts, it is not uncommon for human experts to rectify segmentations of specific test samples after SAM generates its segmentation predictions. These rectifications typically entail manual or semi-manual corrections employing state-of-the-art annotation tools. Motivated by this process, we introduce a novel approach that leverages the advantages of online machine learning to enhance Segment Anything (SA) during test time. We employ rectified annotations to perform online learning, with the aim of improving the segmentation quality of SA on medical images. To improve the effectiveness and efficiency of online learning when integrated with large-scale vision models like SAM, we propose a new method called Auxiliary Online Learning (AuxOL). AuxOL creates and applies a small auxiliary model (specialist) in conjunction with SAM (generalist), entails adaptive online-batch and adaptive segmentation fusion. Experiments conducted on eight datasets covering four medical imaging modalities validate the effectiveness of the proposed method. Our work proposes and validates a new, practical, and effective approach for enhancing SA on downstream segmentation tasks (e.g., medical image segmentation).
Authors: Vahid Azizi, Fatemeh Koochaki
Abstract: Vision-Language Models (VLMs) have recently seen significant advancements through integrating with Large Language Models (LLMs). The VLMs, which process image and text modalities simultaneously, have demonstrated the ability to learn and understand the interaction between images and texts across various multi-modal tasks. Reverse designing, which could be defined as a complex vision-language task, aims to predict the edits and their parameters, given a source image, an edited version, and an optional high-level textual edit description. This task requires VLMs to comprehend the interplay between the source image, the edited version, and the optional textual context simultaneously, going beyond traditional vision-language tasks. In this paper, we extend and fine-tune MiniGPT-4 for the reverse designing task. Our experiments demonstrate the extensibility of off-the-shelf VLMs, specifically MiniGPT-4, for more complex tasks such as reverse designing. Code is available at this \href{https://github.com/VahidAz/MiniGPT-Reverse-Designing}
Authors: Kezhen Chen, Rahul Thapa, Rahul Chalamala, Ben Athiwaratkun, Shuaiwen Leon Song, James Zou
Abstract: Recent advances in large multimodal models (LMMs) suggest that higher image resolution enhances the fine-grained understanding of image details, crucial for tasks such as visual commonsense reasoning and analyzing biomedical images. However, increasing input resolution poses two main challenges: 1) It extends the context length required by the language model, leading to inefficiencies and hitting the model's context limit; 2) It increases the complexity of visual features, necessitating more training data or more complex architecture. We introduce Dragonfly, a new LMM architecture that enhances fine-grained visual understanding and reasoning about image regions to address these challenges. Dragonfly employs two key strategies: multi-resolution visual encoding and zoom-in patch selection. These strategies allow the model to process high-resolution images efficiently while maintaining reasonable context length. Our experiments on eight popular benchmarks demonstrate that Dragonfly achieves competitive or better performance compared to other architectures, highlighting the effectiveness of our design. Additionally, we finetuned Dragonfly on biomedical instructions, achieving state-of-the-art results on multiple biomedical tasks requiring fine-grained visual understanding, including 92.3% accuracy on the Path-VQA dataset (compared to 83.3% for Med-Gemini) and the highest reported results on biomedical image captioning. To support model training, we curated a visual instruction-tuning dataset with 5.5 million image-instruction samples in the general domain and 1.4 million samples in the biomedical domain. We also conducted ablation studies to characterize the impact of various architectural designs and image resolutions, providing insights for future research on visual instruction alignment. The codebase and model are available at https://github.com/togethercomputer/Dragonfly.
Authors: Mingzhen Huang, Jialing Cai, Shan Jia, Vishnu Suresh Lokhande, Siwei Lyu
Abstract: Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in computer graphics, faces unique challenges. A major challenge is making simultaneous edits across multiple objects or attributes. Applying these methods sequentially for multi-aspect edits increases computational demands and efficiency losses. In this paper, we address these challenges with significant contributions. Our main contribution is the development of MultiEdits, a method that seamlessly manages simultaneous edits across multiple attributes. In contrast to previous approaches, MultiEdits not only preserves the quality of single attribute edits but also significantly improves the performance of multitasking edits. This is achieved through an innovative attention distribution mechanism and a multi-branch design that operates across several processing heads. Additionally, we introduce the PIE-Bench++ dataset, an expansion of the original PIE-Bench dataset, to better support evaluating image-editing tasks involving multiple objects and attributes simultaneously. This dataset is a benchmark for evaluating text-driven image editing methods in multifaceted scenarios. Dataset and code are available at https://mingzhenhuang.com/projects/MultiEdits.html.
Authors: Lingen Li, Mingde Yao, Xingyu Meng, Muquan Yu, Tianfan Xue, Jinwei Gu
Abstract: Modern end-to-end image signal processors (ISPs) can learn complex mappings from RAW/XYZ data to sRGB (or inverse), opening new possibilities in image processing. However, as the diversity of camera models continues to expand, developing and maintaining individual ISPs is not sustainable in the long term, which inherently lacks versatility, hindering the adaptability to multiple camera models. In this paper, we propose a novel pipeline, Uni-ISP, which unifies the learning of ISPs from multiple cameras, offering an accurate and versatile processor to multiple camera models. The core of Uni-ISP is leveraging device-aware embeddings through learning inverse/forward ISPs and its special training scheme. By doing so, Uni-ISP not only improves the performance of inverse/forward ISPs but also unlocks a variety of new applications inaccessible to existing learned ISPs. Moreover, since there is no dataset synchronously captured by multiple cameras for training, we construct a real-world 4K dataset, FiveCam, comprising more than 2,400 pairs of sRGB-RAW images synchronously captured by five smartphones. We conducted extensive experiments demonstrating Uni-ISP's accuracy in inverse/forward ISPs (with improvements of +1.5dB/2.4dB PSNR), its versatility in enabling new applications, and its adaptability to new camera models.
Authors: Daekyu Kwon, Dongyoung Kim, Sehwan Ki, Younghyun Jo, Hyong-Euk Lee, Seon Joo Kim
Abstract: In no-reference image quality assessment (NR-IQA), the challenge of limited dataset sizes hampers the development of robust and generalizable models. Conventional methods address this issue by utilizing large datasets to extract rich representations for IQA. Also, some approaches propose vision language models (VLM) based IQA, but the domain gap between generic VLM and IQA constrains their scalability. In this work, we propose a novel pretraining framework that constructs a generalizable representation for IQA by selectively extracting quality-related knowledge from VLM and leveraging the scalability of large datasets. Specifically, we carefully select optimal text prompts for five representative image quality attributes and use VLM to generate pseudo-labels. Numerous attribute-aware pseudo-labels can be generated with large image datasets, allowing our IQA model to learn rich representations about image quality. Our approach achieves state-of-the-art performance on multiple IQA datasets and exhibits remarkable generalization capabilities. Leveraging these strengths, we propose several applications, such as evaluating image generation models and training image enhancement models, demonstrating our model's real-world applicability. We will make the code available for access.
Authors: Pourya Jafarzadeh, Padideh Choobdar, Vahid Mohammadi Safarzadeh
Abstract: Handwriting analysis is still an important application in machine learning. A basic requirement for any handwriting recognition application is the availability of comprehensive datasets. Standard labelled datasets play a significant role in training and evaluating learning algorithms. In this paper, we present the Khayyam dataset as another large unconstrained handwriting dataset for elements (words, sentences, letters, digits) of the Persian language. We intentionally concentrated on collecting Persian word samples which are rare in the currently available datasets. Khayyam's dataset contains 44000 words, 60000 letters, and 6000 digits. Moreover, the forms were filled out by 400 native Persian writers. To show the applicability of the dataset, machine learning algorithms are trained on the digits, letters, and word data and results are reported. This dataset is available for research and academic use.
Authors: Xuanqi Zhang, Haijin Zeng, Jinwang Pan, Qiangqiang Shen, Yongyong Chen
Abstract: Transformer-based low-light enhancement methods have yielded promising performance by effectively capturing long-range dependencies in a global context. However, their elevated computational demand limits the scalability of multiple iterations in deep unfolding networks, and hence they have difficulty in flexibly balancing interpretability and distortion. To address this issue, we propose a novel Low-Light Enhancement method via relighting-guided Mamba with a deep unfolding network (LLEMamba), whose theoretical interpretability and fidelity are guaranteed by Retinex optimization and Mamba deep priors, respectively. Specifically, our LLEMamba first constructs a Retinex model with deep priors, embedding the iterative optimization process based on the Alternating Direction Method of Multipliers (ADMM) within a deep unfolding network. Unlike Transformer, to assist the deep unfolding framework with multiple iterations, the proposed LLEMamba introduces a novel Mamba architecture with lower computational complexity, which not only achieves light-dependent global visual context for dark images during reflectance relight but also optimizes to obtain more stable closed-form solutions. Experiments on the benchmarks show that LLEMamba achieves superior quantitative evaluations and lower distortion visual results compared to existing state-of-the-art methods.
Authors: Trong-Thuan Nguyen, Pha Nguyen, Xin Li, Jackson Cothren, Alper Yilmaz, Khoa Luu
Abstract: Video scene graph generation (VidSGG) has emerged as a transformative approach to capturing and interpreting the intricate relationships among objects and their temporal dynamics in video sequences. In this paper, we introduce the new AeroEye dataset that focuses on multi-object relationship modeling in aerial videos. Our AeroEye dataset features various drone scenes and includes a visually comprehensive and precise collection of predicates that capture the intricate relationships and spatial arrangements among objects. To this end, we propose the novel Cyclic Graph Transformer (CYCLO) approach that allows the model to capture both direct and long-range temporal dependencies by continuously updating the history of interactions in a circular manner. The proposed approach also allows one to handle sequences with inherent cyclical patterns and process object relationships in the correct sequential order. Therefore, it can effectively capture periodic and overlapping relationships while minimizing information loss. The extensive experiments on the AeroEye dataset demonstrate the effectiveness of the proposed CYCLO model, demonstrating its potential to perform scene understanding on drone videos. Finally, the CYCLO method consistently achieves State-of-the-Art (SOTA) results on two in-the-wild scene graph generation benchmarks, i.e., PVSG and ASPIRe.
Authors: Yung-Hui Lin, Yu-Wen Chang, Huang-Chia Shih, Takahiro Ogawa
Abstract: Jersey number recognition (JNR) has always been an important task in sports analytics. Improving recognition accuracy remains an ongoing challenge because images are subject to blurring, occlusion, deformity, and low resolution. Recent research has addressed these problems using number localization and optical character recognition. Some approaches apply player identification schemes to image sequences, ignoring the impact of human body rotation angles on jersey digit identification. Accurately predicting the number of jersey digits by using a multi-task scheme to recognize each individual digit enables more robust results. Based on the above considerations, this paper proposes a multi-task learning method called the angle-digit refine scheme (ADRS), which combines human body orientation angles and digit number clues to recognize athletic jersey numbers. Based on our experimental results, our approach increases inference information, significantly improving prediction accuracy. Compared to state-of-the-art methods, which can only handle a single type of sport, the proposed method produces a more diverse and practical JNR application. The incorporation of diverse types of team sports such as soccer, football, basketball, volleyball, and baseball into our dataset contributes greatly to generalized JNR in sports analytics. Our accuracy achieves 64.07% on Top-1 and 89.97% on Top-2, with corresponding F1 scores of 67.46% and 90.64%, respectively.
Authors: Shahar Zuler, Dan Raviv
Abstract: Accurate analysis of 3D myocardium deformation using high-resolution computerized tomography (CT) datasets with ground truth (GT) annotations is crucial for advancing cardiovascular imaging research. However, the scarcity of such datasets poses a significant challenge for developing robust myocardium deformation analysis models. To address this, we propose a novel approach to synthetic data generation for enriching cardiovascular imaging datasets. We introduce a synthetic data generation method, enriched with crucial GT 3D optical flow annotations. We outline the data preparation from a cardiac four-dimensional (4D) CT scan, selection of parameters, and the subsequent creation of synthetic data from the same or other sources of 3D cardiac CT data for training. Our work contributes to overcoming the limitations imposed by the scarcity of high-resolution CT datasets with precise annotations, thereby facilitating the development of accurate and reliable myocardium deformation analysis algorithms for clinical applications and diagnostics. Our code is available at: http://www.github.com/shaharzuler/cardio_volume_skewer
URLs: http://www.github.com/shaharzuler/cardio_volume_skewer
Authors: Fang Li, Hao Zhang, Narendra Ahuja
Abstract: Gaussian Splatting (GS) has significantly elevated scene reconstruction efficiency and novel view synthesis (NVS) accuracy compared to Neural Radiance Fields (NeRF), particularly for dynamic scenes. However, current 4D NVS methods, whether based on GS or NeRF, primarily rely on camera parameters provided by COLMAP and even utilize sparse point clouds generated by COLMAP for initialization, which lack accuracy as well are time-consuming. This sometimes results in poor dynamic scene representation, especially in scenes with large object movements, or extreme camera conditions e.g. small translations combined with large rotations. Some studies simultaneously optimize the estimation of camera parameters and scenes, supervised by additional information like depth, optical flow, etc. obtained from off-the-shelf models. Using this unverified information as ground truth can reduce robustness and accuracy, which does frequently occur for long monocular videos (with e.g. > hundreds of frames). We propose a novel approach that learns a high-fidelity 4D GS scene representation with self-calibration of camera parameters. It includes the extraction of 2D point features that robustly represent 3D structure, and their use for subsequent joint optimization of camera parameters and 3D structure towards overall 4D scene optimization. We demonstrate the accuracy and time efficiency of our method through extensive quantitative and qualitative experimental results on several standard benchmarks. The results show significant improvements over state-of-the-art methods for 4D novel view synthesis. The source code will be released soon at https://github.com/fangli333/SC-4DGS.
Authors: Sai Mandava
Abstract: We introduce SABR-CLIMB, a novel video model simulating human movement in rock climbing environments using a virtual avatar. Our diffusion transformer predicts the sample instead of noise in each diffusion step and ingests entire videos to output complete motion sequences. By leveraging a large proprietary dataset, NAV-22M, and substantial computational resources, we showcase a proof of concept for a system to train general-purpose virtual avatars for complex tasks in robotics, sports, and healthcare.
Authors: Jinze Yang, Haoran Wang, Zining Zhu, Chenglong Liu, Meng Wymond Wu, Zeke Xie, Zhong Ji, Jungong Han, Mingming Sun
Abstract: In this paper, we focus on resolving the problem of image outpainting, which aims to extrapolate the surrounding parts given the center contents of an image. Although recent works have achieved promising performance, the lack of versatility and customization hinders their practical applications in broader scenarios. Therefore, this work presents a novel image outpainting framework that is capable of customizing the results according to the requirement of users. First of all, we take advantage of a Multimodal Large Language Model (MLLM) that automatically extracts and organizes the corresponding textual descriptions of the masked and unmasked part of a given image. Accordingly, the obtained text prompts are introduced to endow our model with the capacity to customize the outpainting results. In addition, a special Cross-Attention module, namely Center-Total-Surrounding (CTS), is elaborately designed to enhance further the the interaction between specific space regions of the image and corresponding parts of the text prompts. Note that unlike most existing methods, our approach is very resource-efficient since it is just slightly fine-tuned on the off-the-shelf stable diffusion (SD) model rather than being trained from scratch. Finally, the experimental results on three commonly used datasets, i.e. Scenery, Building, and WikiArt, demonstrate our model significantly surpasses the SoTA methods. Moreover, versatile outpainting results are listed to show its customized ability.
Authors: Qilong Zhangli, Jindong Jiang, Di Liu, Licheng Yu, Xiaoliang Dai, Ankit Ramchandani, Guan Pang, Dimitris N. Metaxas, Praveen Krishnan
Abstract: While diffusion models have significantly advanced the quality of image generation, their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene text generation are typically limited by their reliance on an intermediate layout output. This dependency often results in a constrained diversity of text styles and fonts, an inherent limitation stemming from the deterministic nature of the layout generation phase. To address these challenges, this paper introduces SceneTextGen, a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. By doing so, SceneTextGen facilitates a more natural and varied representation of text. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties, coupled with a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies. We validate the performance of our method by demonstrating improved character recognition rates on generated images across different public visual text datasets in comparison to both standard diffusion based methods and text specific methods.
Authors: Hansong Zhang, Shikun Li, Fanzhao Lin, Weiping Wang, Zhenxing Qian, Shiming Ge
Abstract: Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by optimization-oriented methods, but their inefficiency hinders their application to realistic datasets. On the other hand, the Distribution-Matching (DM) methods show remarkable efficiency but sub-optimal results compared to optimization-oriented methods. In this paper, we reveal the limitations of current DM-based methods from the inner-class and inter-class views, i.e., Persistent Training and Distribution Shift. To address these problems, we propose a new DM-based method named Dual-view distribution AligNment for dataset CondEnsation (DANCE), which exploits a few pre-trained models to improve DM from both inner-class and inter-class views. Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing. Experiments demonstrate the proposed method achieves a SOTA performance while maintaining comparable efficiency with the original DM across various scenarios. Source codes are available at https://github.com/Hansong-Zhang/DANCE.
Authors: Hantao Zhou, Longxiang Tang, Rui Yang, Guanyi Qin, Yan Zhang, Runze Hu, Xiu Li
Abstract: Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) aim to simulate human subjective perception of image visual quality and aesthetic appeal. Existing methods typically address these tasks independently due to distinct learning objectives. However, they neglect the underlying interconnectedness of both tasks, which hinders the learning of task-agnostic shared representations for human subjective perception. To confront this challenge, we propose Unified vision-language pre-training of Quality and Aesthetics (UniQA), to learn general perceptions of two tasks, thereby benefiting them simultaneously. Addressing the absence of text in the IQA datasets and the presence of textual noise in the IAA datasets, (1) we utilize multimodal large language models (MLLMs) to generate high-quality text descriptions; (2) the generated text for IAA serves as metadata to purify noisy IAA data. To effectively adapt the pre-trained UniQA to downstream tasks, we further propose a lightweight adapter that utilizes versatile cues to fully exploit the extensive knowledge of the pre-trained model. Extensive experiments demonstrate that our approach attains a new state-of-the-art performance on both IQA and IAA tasks, while concurrently showcasing exceptional zero-shot and few-label image assessment capabilities. The source code will be available at https://github.com/zht8506/UniQA.
Authors: Jan Lippemeier, Stefanie Hittmeyer, Oliver Nieh\"orster, Markus Lange-Hegermann
Abstract: Recent advancements in machine learning, particularly in deep learning and object detection, have significantly improved performance in various tasks, including image classification and synthesis. However, challenges persist, particularly in acquiring labeled data that accurately represents specific use cases. In this work, we propose an automatic pipeline for generating synthetic image datasets using Stable Diffusion, an image synthesis model capable of producing highly realistic images. We leverage YOLOv8 for automatic bounding box detection and quality assessment of synthesized images. Our contributions include demonstrating the feasibility of training image classifiers solely on synthetic data, automating the image generation pipeline, and describing the computational requirements for our approach. We evaluate the usability of different modes of Stable Diffusion and achieve a classification accuracy of 75%.
Authors: Georgia Markham, Mehala Balamurali, Andrew J. Hill
Abstract: Few-shot action recognition (FSAR) aims to learn a model capable of identifying novel actions in videos using only a few examples. In assuming the base dataset seen during meta-training and novel dataset used for evaluation can come from different domains, cross-domain few-shot learning alleviates data collection and annotation costs required by methods with greater supervision and conventional (single-domain) few-shot methods. While this form of learning has been extensively studied for image classification, studies in cross-domain FSAR (CD-FSAR) are limited to proposing a model, rather than first understanding the cross-domain capabilities of existing models. To this end, we systematically evaluate existing state-of-the-art single-domain, transfer-based, and cross-domain FSAR methods on new cross-domain tasks with increasing difficulty, measured based on the domain shift between the base and novel set. Our empirical meta-analysis reveals a correlation between domain difference and downstream few-shot performance, and uncovers several important insights into which model aspects are effective for CD-FSAR and which need further development. Namely, we find that as the domain difference increases, the simple transfer-learning approach outperforms other methods by over 12 percentage points, and under these more challenging cross-domain settings, the specialised cross-domain model achieves the lowest performance. We also witness state-of-the-art single-domain FSAR models which use temporal alignment achieving similar or worse performance than earlier methods which do not, suggesting existing temporal alignment techniques fail to generalise on unseen domains. To the best of our knowledge, we are the first to systematically study the CD-FSAR problem in-depth. We hope the insights and challenges revealed in our study inspires and informs future work in these directions.
Authors: Jan Pauls, Max Zimmer, Una M. Kelly, Martin Schwartz, Sassan Saatchi, Philippe Ciais, Sebastian Pokutta, Martin Brandt, Fabian Gieseke
Abstract: We propose a framework for global-scale canopy height estimation based on satellite data. Our model leverages advanced data preprocessing techniques, resorts to a novel loss function designed to counter geolocation inaccuracies inherent in the ground-truth height measurements, and employs data from the Shuttle Radar Topography Mission to effectively filter out erroneous labels in mountainous regions, enhancing the reliability of our predictions in those areas. A comparison between predictions and ground-truth labels yields an MAE / RMSE of 2.43 / 4.73 (meters) overall and 4.45 / 6.72 (meters) for trees taller than five meters, which depicts a substantial improvement compared to existing global-scale maps. The resulting height map as well as the underlying framework will facilitate and enhance ecological analyses at a global scale, including, but not limited to, large-scale forest and biomass monitoring.
Authors: Han Sun, Yunkang Cao, Olga Fink
Abstract: Visual anomaly detection (AD) inherently faces significant challenges due to the scarcity of anomalous data. Although numerous works have been proposed to synthesize anomalous samples, the generated samples often lack authenticity or can only reflect the distribution of the available training data samples. In this work, we propose CUT: a Controllable, Universal and Training-free visual anomaly generation framework, which leverages the capability of Stable Diffusion (SD) in image generation to generate diverse and realistic anomalies. With CUT, we achieve controllable and realistic anomaly generation universally across both unseen data and novel anomaly types, using a single model without acquiring additional training effort. To demonstrate the effectiveness of our approach, we propose a Vision-Language-based Anomaly Detection framework (VLAD). By training the VLAD model with our generated anomalous samples, we achieve state-of-the-art performance on several benchmark anomaly detection tasks, highlighting the significant improvements enabled by our synthetic data.
Authors: Joungbin An, Yunsu Park, Hyolim Kang, Seon Joo Kim
Abstract: Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in augmented reality and assisted living. Despite these advancements, current Online Action Detection methods, which efficiently detect actions in streaming videos, are predominantly designed for exocentric views and thus fail to capitalize on the unique perspectives inherent to egocentric videos. To address this gap, we introduce an Object-Aware Module that integrates egocentric-specific priors into existing OAD frameworks, enhancing first-person footage interpretation. Utilizing object-specific details and temporal dynamics, our module improves scene understanding in detecting actions. Validated extensively on the Epic-Kitchens 100 dataset, our work can be seamlessly integrated into existing models with minimal overhead and bring consistent performance enhancements, marking an important step forward in adapting action detection systems to egocentric video analysis.
Authors: Zheng Zhou, Hongbo Zhao, Guangliang Cheng, Xiangtai Li, Shuchang Lyu, Wenquan Feng, Qi Zhao
Abstract: Dataset Distillation (DD) aims to distill knowledge from extensive datasets into more compact ones while preserving performance on the test set, thereby reducing storage costs and training expenses. However, existing methods often suffer from computational intensity, particularly exhibiting suboptimal performance with large dataset sizes due to the lack of a robust theoretical framework for analyzing the DD problem. To address these challenges, we propose the BAyesian optimal CONdensation framework (BACON), which is the first work to introduce the Bayesian theoretical framework to the literature of DD. This framework provides theoretical support for enhancing the performance of DD. Furthermore, BACON formulates the DD problem as the minimization of the expected risk function in joint probability distributions using the Bayesian framework. Additionally, by analyzing the expected risk function for optimal condensation, we derive a numerically feasible lower bound based on specific assumptions, providing an approximate solution for BACON. We validate BACON across several datasets, demonstrating its superior performance compared to existing state-of-the-art methods. For instance, under the IPC-10 setting, BACON achieves a 3.46% accuracy gain over the IDM method on the CIFAR-10 dataset and a 3.10% gain on the TinyImageNet dataset. Our extensive experiments confirm the effectiveness of BACON and its seamless integration with existing methods, thereby enhancing their performance for the DD task. Code and distilled datasets are available at BACON.
Authors: Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, Tao Chen
Abstract: Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful results achieved by diffusion transformers (DiT), there is still a lack of exploration regarding the impact of DiT structure on generation, as well as the absence of an acceleration framework tailored to the DiT architecture. To tackle these challenges, we conduct an investigation into the correlation between DiT blocks and image generation. Our findings reveal that the front blocks of DiT are associated with the outline of the generated images, while the rear blocks are linked to the details. Based on this insight, we propose an overall training-free inference acceleration framework $\Delta$-DiT: using a designed cache mechanism to accelerate the rear DiT blocks in the early sampling stages and the front DiT blocks in the later stages. Specifically, a DiT-specific cache mechanism called $\Delta$-Cache is proposed, which considers the inputs of the previous sampling image and reduces the bias in the inference. Extensive experiments on PIXART-$\alpha$ and DiT-XL demonstrate that the $\Delta$-DiT can achieve a $1.6\times$ speedup on the 20-step generation and even improves performance in most cases. In the scenario of 4-step consistent model generation and the more challenging $1.12\times$ acceleration, our method significantly outperforms existing methods. Our code will be publicly available.
Authors: Kunpeng Wang, Zhengzheng Tu, Chenglong Li, Cheng Zhang, Bin Luo
Abstract: Multi-modal salient object detection (MSOD) aims to boost saliency detection performance by integrating visible sources with depth or thermal infrared ones. Existing methods generally design different fusion schemes to handle certain issues or challenges. Although these fusion schemes are effective at addressing specific issues or challenges, they may struggle to handle multiple complex challenges simultaneously. To solve this problem, we propose a novel adaptive fusion bank that makes full use of the complementary benefits from a set of basic fusion schemes to handle different challenges simultaneously for robust MSOD. We focus on handling five major challenges in MSOD, namely center bias, scale variation, image clutter, low illumination, and thermal crossover or depth ambiguity. The fusion bank proposed consists of five representative fusion schemes, which are specifically designed based on the characteristics of each challenge, respectively. The bank is scalable, and more fusion schemes could be incorporated into the bank for more challenges. To adaptively select the appropriate fusion scheme for multi-modal input, we introduce an adaptive ensemble module that forms the adaptive fusion bank, which is embedded into hierarchical layers for sufficient fusion of different source data. Moreover, we design an indirect interactive guidance module to accurately detect salient hollow objects via the skip integration of high-level semantic information and low-level spatial details. Extensive experiments on three RGBT datasets and seven RGBD datasets demonstrate that the proposed method achieves the outstanding performance compared to the state-of-the-art methods. The code and results are available at https://github.com/Angknpng/LAFB.
Authors: Konstantinos Roditakis, Spyridon Thermos, Nikolaos Zioulis
Abstract: Despite the recent advances in the so-called "cold start" generation from text prompts, their needs in data and computing resources, as well as the ambiguities around intellectual property and privacy concerns pose certain counterarguments for their utility. An interesting and relatively unexplored alternative has been the introduction of unconditional synthesis from a single sample, which has led to interesting generative applications. In this paper we focus on single-shot motion generation and more specifically on accelerating the training time of a Generative Adversarial Network (GAN). In particular, we tackle the challenge of GAN's equilibrium collapse when using mini-batch training by carefully annealing the weights of the loss functions that prevent mode collapse. Additionally, we perform statistical analysis in the generator and discriminator models to identify correlations between training stages and enable transfer learning. Our improved GAN achieves competitive quality and diversity on the Mixamo benchmark when compared to the original GAN architecture and a single-shot diffusion model, while being up to x6.8 faster in training time from the former and x1.75 from the latter. Finally, we demonstrate the ability of our improved GAN to mix and compose motion with a single forward pass.
Authors: Zehui Lin, Zhuoneng Zhang, Xindi Hu, Zhifan Gao, Xin Yang, Yue Sun, Dong Ni, Tao Tan
Abstract: Ultrasound is a widely used imaging modality in clinical practice due to its low cost, portability, and safety. Current research in general AI for healthcare focuses on large language models and general segmentation models, with insufficient attention to solutions addressing both disease prediction and tissue segmentation. In this study, we propose a novel universal framework for ultrasound, namely DeepUniUSTransformer, which is a promptable model accommodating multiple clinical task. The universality of this model is derived from its versatility across various aspects. It proficiently manages any ultrasound nature, any anatomical position, any input type and excelling not only in segmentation tasks but also in computer-aided diagnosis tasks. We introduce a novel module that incorporates this information as a prompt and seamlessly embedding it within the model's learning process. To train and validate our proposed model, we curated a comprehensive ultrasound dataset from publicly accessible sources, encompassing up to 7 distinct anatomical positions with over 9.7K annotations. Experimental results demonstrate that our model surpasses both a model trained on a single dataset and an ablated version of the network lacking prompt guidance. We will continuously expand the dataset and optimize the task specific prompting mechanism towards the universality in medical ultrasound. Model weights, datasets, and code will be open source to the public.
Authors: Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Youqiang Zhang, Junshi Huang
Abstract: This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Specifically, Dimba sequentially stacked blocks alternate between Transformer and Mamba layers, and integrate conditional information through the cross-attention layer, thus capitalizing on the advantages of both architectural paradigms. We investigate several optimization strategies, including quality tuning, resolution adaption, and identify critical configurations necessary for large-scale image generation. The model's flexible design supports scenarios that cater to specific resource constraints and objectives. When scaled appropriately, Dimba offers substantial throughput and a reduced memory footprint relative to conventional pure Transformers-based benchmarks. Extensive experiments indicate that Dimba achieves comparable performance compared with benchmarks in terms of image quality, artistic rendering, and semantic control. We also report several intriguing properties of architecture discovered during evaluation and release checkpoints in experiments. Our findings emphasize the promise of large-scale hybrid Transformer-Mamba architectures in the foundational stage of diffusion models, suggesting a bright future for text-to-image generation.
Authors: Choubo Ding, Guansong Pang
Abstract: As vision-language models like CLIP are widely applied to zero-shot tasks and gain remarkable performance on in-distribution (ID) data, detecting and rejecting out-of-distribution (OOD) inputs in the zero-shot setting have become crucial for ensuring the safety of using such models on the fly. Most existing zero-shot OOD detectors rely on ID class label-based prompts to guide CLIP in classifying ID images and rejecting OOD images. In this work we instead propose to leverage a large set of diverse auxiliary outlier class labels as pseudo OOD class text prompts to CLIP for enhancing zero-shot OOD detection, an approach we called Outlier Label Exposure (OLE). The key intuition is that ID images are expected to have lower similarity to these outlier class prompts than OOD images. One issue is that raw class labels often include noise labels, e.g., synonyms of ID labels, rendering raw OLE-based detection ineffective. To address this issue, we introduce an outlier prototype learning module that utilizes the prompt embeddings of the outlier labels to learn a small set of pivotal outlier prototypes for an embedding similarity-based OOD scoring. Additionally, the outlier classes and their prototypes can be loosely coupled with the ID classes, leading to an inseparable decision region between them. Thus, we also introduce an outlier label generation module that synthesizes our outlier prototypes and ID class embeddings to generate in-between outlier prototypes to further calibrate the detection in OLE. Despite its simplicity, extensive experiments show that OLE substantially improves detection performance and achieves new state-of-the-art performance in large-scale OOD and hard OOD detection benchmarks.
Authors: Xiang Wang, Shiwei Zhang, Changxin Gao, Jiayu Wang, Xiaoqiang Zhou, Yingya Zhang, Luxin Yan, Nong Sang
Abstract: Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still two limitations: i) an extra reference model is required to align the identity image with the main video branch, which significantly increases the optimization burden and model parameters; ii) the generated video is usually short in time (e.g., 24 frames), hampering practical applications. To address these shortcomings, we present a UniAnimate framework to enable efficient and long-term human video generation. First, to reduce the optimization difficulty and ensure temporal coherence, we map the reference image along with the posture guidance and noise video into a common feature space by incorporating a unified video diffusion model. Second, we propose a unified noise input that supports random noised input as well as first frame conditioned input, which enhances the ability to generate long-term video. Finally, to further efficiently handle long sequences, we explore an alternative temporal modeling architecture based on state space model to replace the original computation-consuming temporal Transformer. Extensive experimental results indicate that UniAnimate achieves superior synthesis results over existing state-of-the-art counterparts in both quantitative and qualitative evaluations. Notably, UniAnimate can even generate highly consistent one-minute videos by iteratively employing the first frame conditioning strategy. Code and models will be publicly available. Project page: https://unianimate.github.io/.
Authors: Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Josechu Guerrero, Giovanni Maria Farinella, Antonino Furnari
Abstract: Short-Term object-interaction Anticipation consists of detecting the location of the next-active objects, the noun and verb categories of the interaction, and the time to contact from the observation of egocentric video. This ability is fundamental for wearable assistants or human robot interaction to understand the user goals, but there is still room for improvement to perform STA in a precise and reliable way. In this work, we improve the performance of STA predictions with two contributions: 1. We propose STAformer, a novel attention-based architecture integrating frame guided temporal pooling, dual image-video attention, and multiscale feature fusion to support STA predictions from an image-input video pair. 2. We introduce two novel modules to ground STA predictions on human behavior by modeling affordances.First, we integrate an environment affordance model which acts as a persistent memory of interactions that can take place in a given physical scene. Second, we predict interaction hotspots from the observation of hands and object trajectories, increasing confidence in STA predictions localized around the hotspot. Our results show significant relative Overall Top-5 mAP improvements of up to +45% on Ego4D and +42% on a novel set of curated EPIC-Kitchens STA labels. We will release the code, annotations, and pre extracted affordances on Ego4D and EPIC- Kitchens to encourage future research in this area.
Authors: Sihan Wen, Xiantan Zhu, Zhiming Tan
Abstract: In recent years, a plethora of diverse methods have been proposed for 3D pose estimation. Among these, self-attention mechanisms and graph convolutions have both been proven to be effective and practical methods. Recognizing the strengths of those two techniques, we have developed a novel Semantic Graph Attention Network which can benefit from the ability of self-attention to capture global context, while also utilizing the graph convolutions to handle the local connectivity and structural constraints of the skeleton. We also design a Body Part Decoder that assists in extracting and refining the information related to specific segments of the body. Furthermore, our approach incorporates Distance Information, enhancing our model's capability to comprehend and accurately predict spatial relationships. Finally, we introduce a Geometry Loss who makes a critical constraint on the structural skeleton of the body, ensuring that the model's predictions adhere to the natural limits of human posture. The experimental results validate the effectiveness of our approach, demonstrating that every element within the system is essential for improving pose estimation outcomes. With comparison to state-of-the-art, the proposed work not only meets but exceeds the existing benchmarks.
Authors: Nikolas Adaloglou, Felix Michels, Kaspar Senft, Diana Petrusheva, Markus Kollmann
Abstract: Deep image clustering methods are typically evaluated on small-scale balanced classification datasets while feature-based $k$-means has been applied on proprietary billion-scale datasets. In this work, we explore the performance of feature-based deep clustering approaches on large-scale benchmarks whilst disentangling the impact of the following data-related factors: i) class imbalance, ii) class granularity, iii) easy-to-recognize classes, and iv) the ability to capture multiple classes. Consequently, we develop multiple new benchmarks based on ImageNet21K. Our experimental analysis reveals that feature-based $k$-means is often unfairly evaluated on balanced datasets. However, deep clustering methods outperform $k$-means across most large-scale benchmarks. Interestingly, $k$-means underperforms on easy-to-classify benchmarks by large margins. The performance gap, however, diminishes on the highest data regimes such as ImageNet21K. Finally, we find that non-primary cluster predictions capture meaningful classes (i.e. coarser classes).
Authors: Ding Jia, Jianyuan Guo, Kai Han, Han Wu, Chao Zhang, Chang Xu, Xinghao Chen
Abstract: Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange methods which replace less informative tokens with inter-modal features, and demonstrate exchange based methods underperform cross-attention mechanisms, while the computational demand of the latter inevitably restricts its use with longer sequences. To surmount the computational challenges, we propose GeminiFusion, a pixel-wise fusion approach that capitalizes on aligned cross-modal representations. GeminiFusion elegantly combines intra-modal and inter-modal attentions, dynamically integrating complementary information across modalities. We employ a layer-adaptive noise to adaptively control their interplay on a per-layer basis, thereby achieving a harmonized fusion process. Notably, GeminiFusion maintains linear complexity with respect to the number of input tokens, ensuring this multimodal framework operates with efficiency comparable to unimodal networks. Comprehensive evaluations across multimodal image-to-image translation, 3D object detection and arbitrary-modal semantic segmentation tasks, including RGB, depth, LiDAR, event data, etc. demonstrate the superior performance of our GeminiFusion against leading-edge techniques. The PyTorch code is available at https://github.com/JiaDingCN/GeminiFusion
Authors: Bahram Mohammadi, Yicong Hong, Yuankai Qi, Qi Wu, Shirui Pan, Javen Qinfeng Shi
Abstract: The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object features to represent navigable viewpoints. However, these representations are insufficient for proper action prediction, especially for the REVERIE task, which uses concise high-level instructions, such as ''Bring me the blue cushion in the master bedroom''. To address enhancing representation, we propose an augmented commonsense knowledge model (ACK) to leverage commonsense information as a spatio-temporal knowledge graph for improving agent navigation. Specifically, the proposed approach involves constructing a knowledge base by retrieving commonsense information from ConceptNet, followed by a refinement module to remove noisy and irrelevant knowledge. We further present ACK which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information. Moreover, we add a new pipeline for the commonsense-based decision-making process which leads to more accurate local action prediction. Experimental results demonstrate our proposed model noticeably outperforms the baseline and archives the state-of-the-art on the REVERIE benchmark.
Authors: Linshan Wu, Jiaxin Zhuang, Xuefeng Ni, Hao Chen
Abstract: AI-driven tumor analysis has garnered increasing attention in healthcare. However, its progress is significantly hindered by the lack of annotated tumor cases, which requires radiologists to invest a lot of effort in collecting and annotation. In this paper, we introduce a highly practical solution for robust tumor synthesis and segmentation, termed FreeTumor, which refers to annotation-free synthetic tumors and our desire to free patients that suffering from tumors. Instead of pursuing sophisticated technical synthesis modules, we aim to design a simple yet effective tumor synthesis paradigm to unleash the power of large-scale data. Specifically, FreeTumor advances existing methods mainly from three aspects: (1) Existing methods only leverage small-scale labeled data for synthesis training, which limits their ability to generalize well on unseen data from different sources. To this end, we introduce the adversarial training strategy to leverage large-scale and diversified unlabeled data in synthesis training, significantly improving tumor synthesis. (2) Existing methods largely ignored the negative impact of low-quality synthetic tumors in segmentation training. Thus, we employ an adversarial-based discriminator to automatically filter out the low-quality synthetic tumors, which effectively alleviates their negative impact. (3) Existing methods only used hundreds of cases in tumor segmentation. In FreeTumor, we investigate the data scaling law in tumor segmentation by scaling up the dataset to 11k cases. Extensive experiments demonstrate the superiority of FreeTumor, e.g., on three tumor segmentation benchmarks, average $+8.9\%$ DSC over the baseline that only using real tumors and $+6.6\%$ DSC over the state-of-the-art tumor synthesis method. Code will be available.
Authors: Tillmann Ohm, Andres Karjus, Mikhail Tamm, Maximilian Schich
Abstract: The notion of visual similarity is essential for computer vision, and in applications and studies revolving around vector embeddings of images. However, the scarcity of benchmark datasets poses a significant hurdle in exploring how these models perceive similarity. Here we introduce Style Aligned Artwork Datasets (SALADs), and an example of fruit-SALAD with 10,000 images of fruit depictions. This combined semantic category and style benchmark comprises 100 instances each of 10 easy-to-recognize fruit categories, across 10 easy distinguishable styles. Leveraging a systematic pipeline of generative image synthesis, this visually diverse yet balanced benchmark demonstrates salient differences in semantic category and style similarity weights across various computational models, including machine learning models, feature extraction algorithms, and complexity measures, as well as conceptual models for reference. This meticulously designed dataset offers a controlled and balanced platform for the comparative analysis of similarity perception. The SALAD framework allows the comparison of how these models perform semantic category and style recognition task to go beyond the level of anecdotal knowledge, making it robustly quantifiable and qualitatively interpretable.
Authors: Rita Pucci, Niki Martinel
Abstract: Underwater image analysis is crucial for marine monitoring. However, it presents two major challenges (i) the visual quality of the images is often degraded due to wavelength-dependent light attenuation, scattering, and water types; (ii) capturing and storing high-resolution images is limited by hardware, which hinders long-term environmental analyses. Recently, deep neural networks have been introduced for underwater enhancement yet neglecting the challenge posed by the limitations of autonomous underwater image acquisition systems. We introduce a novel architecture that jointly tackles both issues by drawing inspiration from the discrete features quantization approach of Vector Quantized Variational Autoencoder (\myVQVAE). Our model combines an encoding network, that compresses the input into a latent representation, with two independent decoding networks, that enhance/reconstruct images using only the latent representation. One decoder focuses on the spatial information while the other captures information about the entities in the image by leveraging the concept of capsules. With the usage of capsule layers, we also overcome the differentiabilty issues of \myVQVAE making our solution trainable in an end-to-end fashion without the need for particular optimization tricks. Capsules perform feature quantization in a fully differentiable manner. We conducted thorough quantitative and qualitative evaluations on 6 benchmark datasets to assess the effectiveness of our contributions. Results demonstrate that we perform better than existing methods (eg, about $+1.4dB$ gain on the challenging LSUI Test-L400 dataset), while significantly reducing the amount of space needed for data storage (ie, $3\times$ more efficient).
Authors: Elad Richardson, Yuval Alaluf, Ali Mahdavi-Amiri, Daniel Cohen-Or
Abstract: Text-guided image generation enables the creation of visual content from textual descriptions. However, certain visual concepts cannot be effectively conveyed through language alone. This has sparked a renewed interest in utilizing the CLIP image embedding space for more visually-oriented tasks through methods such as IP-Adapter. Interestingly, the CLIP image embedding space has been shown to be semantically meaningful, where linear operations within this space yield semantically meaningful results. Yet, the specific meaning of these operations can vary unpredictably across different images. To harness this potential, we introduce pOps, a framework that trains specific semantic operators directly on CLIP image embeddings. Each pOps operator is built upon a pretrained Diffusion Prior model. While the Diffusion Prior model was originally trained to map between text embeddings and image embeddings, we demonstrate that it can be tuned to accommodate new input conditions, resulting in a diffusion operator. Working directly over image embeddings not only improves our ability to learn semantic operations but also allows us to directly use a textual CLIP loss as an additional supervision when needed. We show that pOps can be used to learn a variety of photo-inspired operators with distinct semantic meanings, highlighting the semantic diversity and potential of our proposed approach.
Authors: Zhusi Zhong, Helen Zhang, Fayez H. Fayad, Andrew C. Lancaster, John Sollee, Shreyas Kulkarni, Cheng Ting Lin, Jie Li, Xinbo Gao, Scott Collinsa, Sun H. Ahn, Harrison X. Bai, Zhicheng Jiao, Michael K. Atalay
Abstract: Purpose: Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using Computed Tomography Pulmonary Angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE mortality. Materials and Methods: 918 patients (median age 64 years, range 13-99 years, 52% female) with 3,978 CTPAs were identified via retrospective review across three institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and/or clinical variables were then incorporated into DL models to predict survival outcomes. Four models were developed as follows: (1) using CTPA imaging features only; (2) using clinical variables only; (3) multimodal, integrating both CTPA and clinical variables; and (4) multimodal fused with calculated PESI score. Performance and contribution from each modality were evaluated using concordance index (c-index) and Net Reclassification Improvement, respectively. Performance was compared to PESI predictions using the Wilcoxon signed-rank test. Kaplan-Meier analysis was performed to stratify patients into high- and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction. Results: For both data sets, the PESI-fused and multimodal models achieved higher c-indices than PESI alone. Following stratification of patients into high- and low-risk groups by multimodal and PESI-fused models, mortality outcomes differed significantly (both p<0.001). A strong correlation was found between high-risk grouping and RV dysfunction. Conclusions: Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.
Authors: Firas Khader, Omar S. M. El Nahhas, Tianyu Han, Gustav M\"uller-Franzes, Sven Nebelung, Jakob Nikolas Kather, Daniel Truhn
Abstract: The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision. However, a critical limitation of this model is its quadratic computational and memory complexity relative to the sequence length, which constrains its application to longer sequences. This is especially crucial in medical imaging where high-resolution images can reach gigapixel scale. Efforts to address this issue have predominantely focused on complex techniques, such as decomposing the softmax operation integral to the Transformer's architecture. This paper addresses this quadratic computational complexity of Transformer models and introduces a remarkably simple and effective method that circumvents this issue by eliminating the softmax function from the attention mechanism and adopting a sequence normalization technique for the key, query, and value tokens. Coupled with a reordering of matrix multiplications this approach reduces the memory- and compute complexity to a linear scale. We evaluate this approach across various medical imaging datasets comprising fundoscopic, dermascopic, radiologic and histologic imaging data. Our findings highlight that these models exhibit a comparable performance to traditional transformer models, while efficiently handling longer sequences.
Authors: Giovanni Barbarani, Francesco Vaccarino, Gabriele Trivigno, Marco Guerra, Gabriele Berton, Carlo Masone
Abstract: In computer vision, keypoint detection is a fundamental task, with applications spanning from robotics to image retrieval; however, existing learning-based methods suffer from scale dependency and lack flexibility. This paper introduces a novel approach that leverages Morse theory and persistent homology, powerful tools rooted in algebraic topology. We propose a novel loss function based on the recent introduction of a notion of subgradient in persistent homology, paving the way toward topological learning. Our detector, MorseDet, is the first topology-based learning model for feature detection, which achieves competitive performance in keypoint repeatability and introduces a principled and theoretically robust approach to the problem.
Authors: Vitor Fortes Rey, Lala Shakti Swarup Ray, Xia Qingxin, Kaishun Wu, Paul Lukowicz
Abstract: Due to the scarcity of labeled sensor data in HAR, prior research has turned to video data to synthesize Inertial Measurement Units (IMU) data, capitalizing on its rich activity annotations. However, generating IMU data from videos presents challenges for HAR in real-world settings, attributed to the poor quality of synthetic IMU data and its limited efficacy in subtle, fine-grained motions. In this paper, we propose Multi$^3$Net, our novel multi-modal, multitask, and contrastive-based framework approach to address the issue of limited data. Our pretraining procedure uses videos from online repositories, aiming to learn joint representations of text, pose, and IMU simultaneously. By employing video data and contrastive learning, our method seeks to enhance wearable HAR performance, especially in recognizing subtle activities.Our experimental findings validate the effectiveness of our approach in improving HAR performance with IMU data. We demonstrate that models trained with synthetic IMU data generated from videos using our method surpass existing approaches in recognizing fine-grained activities.
Authors: Weichao Zhao, Hao Feng, Qi Liu, Jingqun Tang, Shu Wei, Binghong Wu, Lei Liao, Yongjie Ye, Hao Liu, Houqiang Li, Can Huang
Abstract: Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-specific architectures and objectives for individual tasks, resulting in modal isolation and intricate workflows. In this paper, we present a novel large vision-language model, TabPedia, equipped with a concept synergy mechanism. In this mechanism, all the involved diverse visual table understanding (VTU) tasks and multi-source visual embeddings are abstracted as concepts. This unified framework allows TabPedia to seamlessly integrate VTU tasks, such as table detection, table structure recognition, table querying, and table question answering, by leveraging the capabilities of large language models (LLMs). Moreover, the concept synergy mechanism enables table perception-related and comprehension-related tasks to work in harmony, as they can effectively leverage the needed clues from the corresponding source perception embeddings. Furthermore, to better evaluate the VTU task in real-world scenarios, we establish a new and comprehensive table VQA benchmark, ComTQA, featuring approximately 9,000 QA pairs. Extensive quantitative and qualitative experiments on both table perception and comprehension tasks, conducted across various public benchmarks, validate the effectiveness of our TabPedia. The superior performance further confirms the feasibility of using LLMs for understanding visual tables when all concepts work in synergy. The benchmark ComTQA has been open-sourced at https://huggingface.co/datasets/ByteDance/ComTQA. The source code and model will be released later.
Authors: Mengcheng Li, Hongwen Zhang, Yuxiang Zhang, Ruizhi Shao, Tao Yu, Yebin Liu
Abstract: Recent years have witnessed a trend of the deep integration of the generation and reconstruction paradigms. In this paper, we extend the ability of controllable generative models for a more comprehensive hand mesh recovery task: direct hand mesh generation, inpainting, reconstruction, and fitting in a single framework, which we name as Holistic Hand Mesh Recovery (HHMR). Our key observation is that different kinds of hand mesh recovery tasks can be achieved by a single generative model with strong multimodal controllability, and in such a framework, realizing different tasks only requires giving different signals as conditions. To achieve this goal, we propose an all-in-one diffusion framework based on graph convolution and attention mechanisms for holistic hand mesh recovery. In order to achieve strong control generation capability while ensuring the decoupling of multimodal control signals, we map different modalities to a shared feature space and apply cross-scale random masking in both modality and feature levels. In this way, the correlation between different modalities can be fully exploited during the learning of hand priors. Furthermore, we propose Condition-aligned Gradient Guidance to enhance the alignment of the generated model with the control signals, which significantly improves the accuracy of the hand mesh reconstruction and fitting. Experiments show that our novel framework can realize multiple hand mesh recovery tasks simultaneously and outperform the existing methods in different tasks, which provides more possibilities for subsequent downstream applications including gesture recognition, pose generation, mesh editing, and so on.
Authors: Ka Lung Cheung, Chi Chung Lee
Abstract: Precise segmentation of architectural structures provides detailed information about various building components, enhancing our understanding and interaction with our built environment. Nevertheless, existing outdoor 3D point cloud datasets have limited and detailed annotations on architectural exteriors due to privacy concerns and the expensive costs of data acquisition and annotation. To overcome this shortfall, this paper introduces a semantically-enriched, photo-realistic 3D architectural models dataset and benchmark for semantic segmentation. It features 4 different building purposes of real-world buildings as well as an open architectural landscape in Hong Kong. Each point cloud is annotated into one of 14 semantic classes.
Authors: Enhui Ma, Lijun Zhou, Tao Tang, Zhan Zhang, Dong Han, Junpeng Jiang, Kun Zhan, Peng Jia, Xianpeng Lang, Haiyang Sun, Di Lin, Kaicheng Yu
Abstract: Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve the performance of planning of end-to-end autonomous driving models as the generated videos are usually less than 8 frames and the spatial and temporal inconsistencies are not negligible. To this end, we propose Delphi, a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spatial consistency, and a feature-aligned module to achieves both precise controllability and temporal consistency. Our method can generate up to 40 frames of video without loss of consistency which is about 5 times longer compared with state-of-the-art methods. Instead of randomly generating new data, we further design a sampling policy to let Delphi generate new data that are similar to those failure cases to improve the sample efficiency. This is achieved by building a failure-case driven framework with the help of pre-trained visual language models. Our extensive experiment demonstrates that our Delphi generates a higher quality of long videos surpassing previous state-of-the-art methods. Consequentially, with only generating 4% of the training dataset size, our framework is able to go beyond perception and prediction tasks, for the first time to the best of our knowledge, boost the planning performance of the end-to-end autonomous driving model by a margin of 25%.
Authors: Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen, Chia-Mu Yu, Xuebin Ren, Francois Buet-Golfouse
Abstract: The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential privacy offers a rigorous framework for safeguarding individual data points during model training, with Differential Privacy Stochastic Gradient Descent (DP-SGD) being a prominent implementation. Diffusion method decomposes image generation into iterative steps, theoretically aligning well with DP's incremental noise addition. Despite the natural fit, the unique architecture of DMs necessitates tailored approaches to effectively balance privacy-utility trade-off. Recent developments in this field have highlighted the potential for generating high-quality synthetic data by pre-training on public data (i.e., ImageNet) and fine-tuning on private data, however, there is a pronounced gap in research on optimizing the trade-offs involved in DP settings, particularly concerning parameter efficiency and model scalability. Our work addresses this by proposing a parameter-efficient fine-tuning strategy optimized for private diffusion models, which minimizes the number of trainable parameters to enhance the privacy-utility trade-off. We empirically demonstrate that our method achieves state-of-the-art performance in DP synthesis, significantly surpassing previous benchmarks on widely studied datasets (e.g., with only 0.47M trainable parameters, achieving a more than 35% improvement over the previous state-of-the-art with a small privacy budget on the CelebA-64 dataset). Anonymous codes available at https://anonymous.4open.science/r/DP-LORA-F02F.
Authors: Ke-Lei Wang, Pin-Hsuan Chou, Young-Ching Chou, Chia-Jen Liu, Cheng-Kuan Lin, Yu-Chee Tseng
Abstract: While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free design and a single-stage framework that conducts detection and segmentation at one time, PolarMask is proved to be able to balance efficiency and accuracy. Hence, it can be easily connected with other downstream real-time applications. In this work, we observe that there are two deficiencies associated with PolarMask: (i) inability of representing concave objects and (ii) inefficiency in using ray regression. We propose MP-PolarMask (Multi-Point PolarMask) by taking advantage of multiple Polar systems. The main idea is to extend from one main Polar system to four auxiliary Polar systems, thus capable of representing more complicated convex-and-concave-mixed shapes. We validate MP-PolarMask on both general objects and food objects of the COCO dataset, and the results demonstrate significant improvement of 13.69% in AP_L and 7.23% in AP over PolarMask with 36 rays.
Authors: Geraldin Nanfack, Michael Eickenberg, Eugene Belilovsky
Abstract: Understanding the inner working functionality of large-scale deep neural networks is challenging yet crucial in several high-stakes applications. Mechanistic inter- pretability is an emergent field that tackles this challenge, often by identifying human-understandable subgraphs in deep neural networks known as circuits. In vision-pretrained models, these subgraphs are usually interpreted by visualizing their node features through a popular technique called feature visualization. Recent works have analyzed the stability of different feature visualization types under the adversarial model manipulation framework. This paper starts by addressing limitations in existing works by proposing a novel attack called ProxPulse that simultaneously manipulates the two types of feature visualizations. Surprisingly, when analyzing these attacks under the umbrella of visual circuits, we find that visual circuits show some robustness to ProxPulse. We, therefore, introduce a new attack based on ProxPulse that unveils the manipulability of visual circuits, shedding light on their lack of robustness. The effectiveness of these attacks is validated using pre-trained AlexNet and ResNet-50 models on ImageNet.
Authors: Shiqi Liu, Wenhan Cao, Chang Liu, Tianyi Zhang, Shengbo Eben Li
Abstract: Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking methods are based on filtering algorithms that overlook these outliers, leading to reduced tracking accuracy or even loss of the objects trajectory. To handle this challenge, we adopt a probabilistic perspective, regarding the generation of outliers as misspecification between the actual distribution of measurement data and the nominal measurement model used for filtering. We further demonstrate that, by designing a convolutional operation, we can mitigate this misspecification. Incorporating this operation into the widely used unscented Kalman filter (UKF) in commonly adopted tracking algorithms, we derive a variant of the UKF that is robust to outliers, called the convolutional UKF (ConvUKF). We show that ConvUKF maintains the Gaussian conjugate property, thus allowing for real-time tracking. We also prove that ConvUKF has a bounded tracking error in the presence of outliers, which implies robust stability. The experimental results on the KITTI and nuScenes datasets show improved accuracy compared to representative baseline algorithms for MOT tasks.
Authors: Junhao Cheng, Xi Lu, Hanhui Li, Khun Loun Zai, Baiqiao Yin, Yuhao Cheng, Yiqiang Yan, Xiaodan Liang
Abstract: As cutting-edge Text-to-Image (T2I) generation models already excel at producing remarkable single images, an even more challenging task, i.e., multi-turn interactive image generation begins to attract the attention of related research communities. This task requires models to interact with users over multiple turns to generate a coherent sequence of images. However, since users may switch subjects frequently, current efforts struggle to maintain subject consistency while generating diverse images. To address this issue, we introduce a training-free multi-agent framework called AutoStudio. AutoStudio employs three agents based on large language models (LLMs) to handle interactions, along with a stable diffusion (SD) based agent for generating high-quality images. Specifically, AutoStudio consists of (i) a subject manager to interpret interaction dialogues and manage the context of each subject, (ii) a layout generator to generate fine-grained bounding boxes to control subject locations, (iii) a supervisor to provide suggestions for layout refinements, and (iv) a drawer to complete image generation. Furthermore, we introduce a Parallel-UNet to replace the original UNet in the drawer, which employs two parallel cross-attention modules for exploiting subject-aware features. We also introduce a subject-initialized generation method to better preserve small subjects. Our AutoStudio hereby can generate a sequence of multi-subject images interactively and consistently. Extensive experiments on the public CMIGBench benchmark and human evaluations show that AutoStudio maintains multi-subject consistency across multiple turns well, and it also raises the state-of-the-art performance by 13.65% in average Frechet Inception Distance and 2.83% in average character-character similarity.
Authors: Antonio Santo, Juan J. Cabrera, David Valiente, Carlos Viegas, Arturo Gil
Abstract: This paper presents TE-NeXt, a novel and efficient architecture for Traversability Estimation (TE) from sparse LiDAR point clouds based on a residual convolution block. TE-NeXt block fuses notions of current trends such as attention mechanisms and 3D sparse convolutions. TE-NeXt aims to demonstrate high capacity for generalisation in a variety of urban and natural environments, using well-known and accessible datasets such as SemanticKITTI, Rellis-3D and SemanticUSL. Thus, the designed architecture ouperforms state-of-the-art methods in the problem of semantic segmentation, demonstrating better results in unstructured environments and maintaining high reliability and robustness in urbans environments, which leads to better abstraction. Implementation is available in a open repository to the scientific community with the aim of ensuring the reproducibility of results.
Authors: Tao Li, Linjun Shou, Xuejun Liu
Abstract: Zero-shot visual question answering (VQA) is a challenging task that requires reasoning across modalities. While some existing methods rely on a single rationale within the Chain of Thoughts (CoT) framework, they may fall short of capturing the complexity of the VQA problem. On the other hand, some other methods that use multiple rationales may still suffer from low diversity, poor modality alignment, and inefficient retrieval and fusion. In response to these challenges, we propose \emph{Mixture of Rationales (MoR)}, a novel multi-modal reasoning method that mixes multiple rationales for VQA. MoR uses a single frozen Vision-and-Language Pre-trained Models (VLPM) model to {dynamically generate, retrieve and fuse multi-modal thoughts}. We evaluate MoR on two challenging VQA datasets, i.e. NLVR2 and OKVQA, with two representative backbones OFA and VL-T5. MoR achieves a 12.43\% accuracy improvement on NLVR2, and a 2.45\% accuracy improvement on OKVQA-S( the science and technology category of OKVQA).
Authors: Laura Zheng, Wenjie Wei, Tony Wu, Jacob Clements, Shreelekha Revankar, Andre Harrison, Yu Shen, Ming C. Lin
Abstract: Segmentation is an integral module in many visual computing applications such as virtual try-on, medical imaging, autonomous driving, and agricultural automation. These applications often involve either widespread consumer use or highly variable environments, both of which can degrade the quality of visual sensor data, whether from a common mobile phone or an expensive satellite imaging camera. In addition to external noises like user difference or weather conditions, internal noises such as variations in camera quality or lens distortion can affect the performance of segmentation models during both development and deployment. In this work, we present an efficient, adaptable, and gradient-free method to enhance the robustness of learning-based segmentation models across training. First, we introduce a novel adaptive sensitivity analysis (ASA) using Kernel Inception Distance (KID) on basis perturbations to benchmark perturbation sensitivity of pre-trained segmentation models. Then, we model the sensitivity curve using the adaptive SA and sample perturbation hyperparameter values accordingly. Finally, we conduct adversarial training with the selected perturbation values and dynamically re-evaluate robustness during online training. Our method, implemented end-to-end with minimal fine-tuning required, consistently outperforms state-of-the-art data augmentation techniques for segmentation. It shows significant improvement in both clean data evaluation and real-world adverse scenario evaluation across various segmentation datasets used in visual computing and computer graphics applications.
Authors: Thanh-Dat Truong, Utsav Prabhu, Dongyi Wang, Bhiksha Raj, Susan Gauch, Jeyamkondan Subbiah, Khoa Luu
Abstract: Unsupervised Domain Adaptation has been an efficient approach to transferring the semantic segmentation model across data distributions. Meanwhile, the recent Open-vocabulary Semantic Scene understanding based on large-scale vision language models is effective in open-set settings because it can learn diverse concepts and categories. However, these prior methods fail to generalize across different camera views due to the lack of cross-view geometric modeling. At present, there are limited studies analyzing cross-view learning. To address this problem, we introduce a novel Unsupervised Cross-view Adaptation Learning approach to modeling the geometric structural change across views in Semantic Scene Understanding. First, we introduce a novel Cross-view Geometric Constraint on Unpaired Data to model structural changes in images and segmentation masks across cameras. Second, we present a new Geodesic Flow-based Correlation Metric to efficiently measure the geometric structural changes across camera views. Third, we introduce a novel view-condition prompting mechanism to enhance the view-information modeling of the open-vocabulary segmentation network in cross-view adaptation learning. The experiments on different cross-view adaptation benchmarks have shown the effectiveness of our approach in cross-view modeling, demonstrating that we achieve State-of-the-Art (SOTA) performance compared to prior unsupervised domain adaptation and open-vocabulary semantic segmentation methods.
Authors: Thanh-Dat Truong, Xin Li, Bhiksha Raj, Jackson Cothren, Khoa Luu
Abstract: The Vision-Language Foundation Model has recently shown outstanding performance in various perception learning tasks. The outstanding performance of the vision-language model mainly relies on large-scale pre-training datasets and different data augmentation techniques. However, the domain generalization problem of the vision-language foundation model needs to be addressed. This problem has limited the generalizability of the vision-language foundation model to unknown data distributions. In this paper, we introduce a new simple but efficient Diffusion Sampling approach to Domain Generalization (ED-SAM) to improve the generalizability of the vision-language foundation model. Our theoretical analysis in this work reveals the critical role and relation of the diffusion model to domain generalization in the vision-language foundation model. Then, based on the insightful analysis, we introduce a new simple yet effective Transport Transformation to diffusion sampling method. It can effectively generate adversarial samples to improve the generalizability of the foundation model against unknown data distributions. The experimental results on different scales of vision-language pre-training datasets, including CC3M, CC12M, and LAION400M, have consistently shown State-of-the-Art performance and scalability of the proposed ED-SAM approach compared to the other recent methods.
Authors: Maan Qraitem, Piotr Teterwak, Kate Saenko, Bryan A. Plummer
Abstract: Online content is filled with logos, from ads and social media posts to website branding and product placements. Consequently, these logos are prevalent in the extensive web-scraped datasets used to pretrain Vision-Language Models, which are used for a wide array of tasks (content moderation, object classification). While these models have been shown to learn harmful correlations in various tasks, whether these correlations include logos remains understudied. Understanding this is especially important due to logos often being used by public-facing entities like brands and government agencies. To that end, we develop SLANT: A Spurious Logo ANalysis Toolkit. Our key finding is that some logos indeed lead to spurious incorrect predictions, for example, adding the Adidas logo to a photo of a person causes a model classify the person as greedy. SLANT contains a semi-automatic mechanism for mining such "spurious" logos. The mechanism consists of a comprehensive logo bank, CC12M-LogoBank, and an algorithm that searches the bank for logos that VLMs spuriously correlate with a user-provided downstream recognition target. We uncover various seemingly harmless logos that VL models correlate 1) with negative human adjectives 2) with the concept of `harmlessness'; causing models to misclassify harmful online content as harmless, and 3) with user-provided object concepts; causing lower recognition accuracy on ImageNet zero-shot classification. Furthermore, SLANT's logos can be seen as effective attacks against foundational models; an attacker could place a spurious logo on harmful content, causing the model to misclassify it as harmless. This threat is alarming considering the simplicity of logo attacks, increasing the attack surface of VL models. As a defense, we include in our Toolkit two effective mitigation strategies that seamlessly integrate with zero-shot inference of foundation models.
Authors: Danni Yang, Jiayi Ji, Yiwei Ma, Tianyu Guo, Haowei Wang, Xiaoshuai Sun, Rongrong Ji
Abstract: In this paper, we introduce SemiRES, a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle in applying semi-supervised techniques to RES is the prevalence of noisy pseudo-labels, particularly at the boundaries of objects. SemiRES incorporates the Segment Anything Model (SAM), renowned for its precise boundary demarcation, to improve the accuracy of these pseudo-labels. Within SemiRES, we offer two alternative matching strategies: IoU-based Optimal Matching (IOM) and Composite Parts Integration (CPI). These strategies are designed to extract the most accurate masks from SAM's output, thus guiding the training of the student model with enhanced precision. In instances where a precise mask cannot be matched from the available candidates, we develop the Pixel-Wise Adjustment (PWA) strategy, guiding the student model's training directly by the pseudo-labels. Extensive experiments on three RES benchmarks--RefCOCO, RefCOCO+, and G-Ref reveal its superior performance compared to fully supervised methods. Remarkably, with only 1% labeled data, our SemiRES outperforms the supervised baseline by a large margin, e.g. +18.64% gains on RefCOCO val set. The project code is available at \url{https://github.com/nini0919/SemiRES}.
Authors: Alfreds Lapkovskis, Natalia Nefedova, Ali Beikmohammadi
Abstract: Plant classification is vital for ecological conservation and agricultural productivity, enhancing our understanding of plant growth dynamics and aiding species preservation. The advent of deep learning (DL) techniques has revolutionized this field by enabling autonomous feature extraction, significantly reducing the dependence on manual expertise. However, conventional DL models often rely solely on single data sources, failing to capture the full biological diversity of plant species comprehensively. Recent research has turned to multimodal learning to overcome this limitation by integrating multiple data types, which enriches the representation of plant characteristics. This shift introduces the challenge of determining the optimal point for modality fusion. In this paper, we introduce a pioneering multimodal DL-based approach for plant classification with automatic modality fusion. Utilizing the multimodal fusion architecture search, our method integrates images from multiple plant organs-flowers, leaves, fruits, and stems-into a cohesive model. Our method achieves 83.48% accuracy on 956 classes of the PlantCLEF2015 dataset, surpassing state-of-the-art methods. It outperforms late fusion by 11.07% and is more robust to missing modalities. We validate our model against established benchmarks using standard performance metrics and McNemar's test, further underscoring its superiority.
Authors: Yu Zhang, Qi Zhang, Zixuan Gong, Yiwei Shi, Yepeng Liu, Duoqian Miao, Yang Liu, Ke Liu, Kun Yi, Wei Fan, Liang Hu, Changwei Wang
Abstract: Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single contrastive supervision for each image-text pair during representation learning, disregarding a substantial amount of valuable information that could offer richer supervision. Additionally, the retention of non-informative tokens leads to increased computational demands and time costs, particularly in CLIP's ViT image encoder. To address these issues, we propose Multi-Perspective Language-Image Pretraining (MLIP). In MLIP, we leverage the frequency transform's sensitivity to both high and low-frequency variations, which complements the spatial domain's sensitivity limited to low-frequency variations only. By incorporating frequency transforms and token-level alignment, we expand CILP's single supervision into multi-domain and multi-level supervision, enabling a more thorough exploration of informative image features. Additionally, we introduce a token merging method guided by comprehensive semantics from the frequency and spatial domains. This allows us to merge tokens to multi-granularity tokens with a controllable compression rate to accelerate CLIP. Extensive experiments validate the effectiveness of our design.
Authors: Tianyu Huang, Yihan Zeng, Hui Li, Wangmeng Zuo, Rynson W. H. Lau
Abstract: Dynamic 3D interaction has witnessed great interest in recent works, while creating such 4D content remains challenging. One solution is to animate 3D scenes with physics-based simulation, and the other is to learn the deformation of static 3D objects with the distillation of video generative models. The former one requires assigning precise physical properties to the target object, otherwise the simulated results would become unnatural. The latter tends to formulate the video with minor motions and discontinuous frames, due to the absence of physical constraints in deformation learning. We think that video generative models are trained with real-world captured data, capable of judging physical phenomenon in simulation environments. To this end, we propose DreamPhysics in this work, which estimates physical properties of 3D Gaussian Splatting with video diffusion priors. DreamPhysics supports both image- and text-conditioned guidance, optimizing physical parameters via score distillation sampling with frame interpolation and log gradient. Based on a material point method simulator with proper physical parameters, our method can generate 4D content with realistic motions. Experimental results demonstrate that, by distilling the prior knowledge of video diffusion models, inaccurate physical properties can be gradually refined for high-quality simulation. Codes are released at: https://github.com/tyhuang0428/DreamPhysics.
Authors: Ka Lung Cheung, Chi Chung Lee
Abstract: The adoption of Building Information Modeling (BIM) is beneficial in construction projects. However, it faces challenges due to the lack of a unified and scalable framework for converting 3D model details into BIM. This paper introduces SRBIM, a unified semantic reconstruction architecture for BIM generation. Our approach's effectiveness is demonstrated through extensive qualitative and quantitative evaluations, establishing a new paradigm for automated BIM modeling.
Authors: Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari
Abstract: Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-understandable representation of procedural activities, encoding a partial ordering over the key-steps. While previous works generally relied on hand-crafted procedures to extract task graphs from videos, in this paper, we propose an approach based on direct maximum likelihood optimization of edges' weights, which allows gradient-based learning of task graphs and can be naturally plugged into neural network architectures. Experiments on the CaptainCook4D dataset demonstrate the ability of our approach to predict accurate task graphs from the observation of action sequences, with an improvement of +16.7% over previous approaches. Owing to the differentiability of the proposed framework, we also introduce a feature-based approach, aiming to predict task graphs from key-step textual or video embeddings, for which we observe emerging video understanding abilities. Task graphs learned with our approach are also shown to significantly enhance online mistake detection in procedural egocentric videos, achieving notable gains of +19.8% and +7.5% on the Assembly101 and EPIC-Tent datasets. Code for replicating experiments is available at https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.
URLs: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.
Authors: Yang Liu, Xiaofei Li, Jun Zhang, Shengze Hu, Jun Lei
Abstract: The increasing difficulty in accurately detecting forged images generated by AIGC(Artificial Intelligence Generative Content) poses many risks, necessitating the development of effective methods to identify and further locate forged areas. In this paper, to facilitate research efforts, we construct a DA-HFNet forged image dataset guided by text or image-assisted GAN and Diffusion model. Our goal is to utilize a hierarchical progressive network to capture forged artifacts at different scales for detection and localization. Specifically, it relies on a dual-attention mechanism to adaptively fuse multi-modal image features in depth, followed by a multi-branch interaction network to thoroughly interact image features at different scales and improve detector performance by leveraging dependencies between layers. Additionally, we extract more sensitive noise fingerprints to obtain more prominent forged artifact features in the forged areas. Extensive experiments validate the effectiveness of our approach, demonstrating significant performance improvements compared to state-of-the-art methods for forged image detection and localization.The code and dataset will be released in the future.
Authors: Jiahao Shao, Yuanbo Yang, Hongyu Zhou, Youmin Zhang, Yujun Shen, Matteo Poggi, Yiyi Liao
Abstract: This work addresses the challenge of video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. Instead of directly developing a depth estimator from scratch, we reformulate the prediction task into a conditional generation problem. This allows us to leverage the prior knowledge embedded in existing video generation models, thereby reducing learn- ing difficulty and enhancing generalizability. Concretely, we study how to tame the public Stable Video Diffusion (SVD) to predict reliable depth from input videos using a mixture of image depth and video depth datasets. We empirically confirm that a procedural training strategy - first optimizing the spatial layers of SVD and then optimizing the temporal layers while keeping the spatial layers frozen - yields the best results in terms of both spatial accuracy and temporal consistency. We further examine the sliding window strategy for inference on arbitrarily long videos. Our observations indicate a trade-off between efficiency and performance, with a one-frame overlap already producing favorable results. Extensive experimental results demonstrate the superiority of our approach, termed ChronoDepth, over existing alternatives, particularly in terms of the temporal consistency of the estimated depth. Additionally, we highlight the benefits of more consistent video depth in two practical applications: depth-conditioned video generation and novel view synthesis. Our project page is available at $\href{https://jhaoshao.github.io/ChronoDepth/}{this\ http\ URL}$.
Authors: Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer, Maurizio Filippone
Abstract: Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach coupling data augmentation, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation. The method is simple to implement, introduces negligible overheads, and can be combined with existing augmentations. We demonstrate improved robustness and uncertainty quantification on the corrupted image benchmarks of the CIFAR and TinyImageNet datasets.
Authors: Maryam Hosseini, Marco Cipriano, Sedigheh Eslami, Daniel Hodczak, Liu Liu, Andres Sevtsuk, Gerard de Melo
Abstract: Why do some streets attract more social activities than others? Is it due to street design, or do land use patterns in neighborhoods create opportunities for businesses where people gather? These questions have intrigued urban sociologists, designers, and planners for decades. Yet, most research in this area has remained limited in scale, lacking a comprehensive perspective on the various factors influencing social interactions in urban settings. Exploring these issues requires fine-level data on the frequency and variety of social interactions on urban street. Recent advances in computer vision and the emergence of the open-vocabulary detection models offer a unique opportunity to address this long-standing issue on a scale that was previously impossible using traditional observational methods. In this paper, we propose a new benchmark dataset for Evaluating Localization of Social Activities (ELSA) in urban street images. ELSA draws on theoretical frameworks in urban sociology and design. While majority of action recognition datasets are collected in controlled settings, we use in-the-wild street-level imagery, where the size of social groups and the types of activities can vary significantly. ELSA includes 937 manually annotated images with more than 4,300 multi-labeled bounding boxes for individual and group activities, categorized into three primary groups: Condition, State, and Action. Each category contains various sub-categories, e.g., alone or group under Condition category, standing or walking, which fall under the State category, and talking or dining with regards to the Action category. ELSA is publicly available for the research community.
Authors: Xiao Chen, Xudong Jiang, Yunkang Tao, Zhen Lei, Qing Li, Chenyang Lei, Zhaoxiang Zhang
Abstract: Single image reflection removal is inherently ambiguous, as both the reflection and transmission components requiring separation may follow natural image statistics. Existing methods attempt to address the issue by using various types of low-level and physics-based cues as sources of reflection signals. However, these cues are not universally applicable, since they are only observable in specific capture scenarios. This leads to a significant performance drop when test images do not align with their assumptions. In this paper, we aim to explore a novel flexible interactive reflection removal approach that leverages various forms of sparse human guidance, such as points and bounding boxes, as auxiliary high-level prior to achieve robust reflection removal. However, incorporating the raw user guidance naively into the existing reflection removal network does not result in performance gains. To this end, we innovatively transform raw user input into a unified form -- reflection masks using an Interactive Segmentation Foundation Model. Such a design absorbs the quintessence of the foundational segmentation model and flexible human guidance, thereby mitigating the challenges of reflection separations. Furthermore, to fully utilize user guidance and reduce user annotation costs, we design a mask-guided reflection removal network, comprising our proposed self-adaptive prompt block. This block adaptively incorporates user guidance as anchors and refines transmission features via cross-attention mechanisms. Extensive results on real-world images validate that our method demonstrates state-of-the-art performance on various datasets with the help of flexible and sparse user guidance. Our code and dataset will be publicly available here https://github.com/ShawnChenn/FlexibleReflectionRemoval.
URLs: https://github.com/ShawnChenn/FlexibleReflectionRemoval.
Authors: Cheng Han, Yawen Lu, Guohao Sun, James C. Liang, Zhiwen Cao, Qifan Wang, Qiang Guan, Sohail A. Dianat, Raghuveer M. Rao, Tong Geng, Zhiqiang Tao, Dongfang Liu
Abstract: In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoFormer seamlessly integrates prototype learning with Transformer by thoughtfully considering motion dynamics, introducing two innovative designs. First, Cross-Attention Prototyping discovers prototypes based on signature motion patterns, providing transparency in understanding motion scenes. Second, Latent Synchronization guides feature representation learning via prototypes, effectively mitigating the problem of motion uncertainty. Empirical results demonstrate that our approach achieves competitive performance on popular motion tasks such as optical flow and scene depth. Furthermore, it exhibits generality across various downstream tasks, including object tracking and video stabilization.
Authors: Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang
Abstract: Diffusion-based text-to-image generation models trained on extensive text-image pairs have shown the capacity to generate photorealistic images consistent with textual descriptions. However, a significant limitation of these models is their slow sample generation, which requires iterative refinement through the same network. In this paper, we enhance Score identity Distillation (SiD) by developing long and short classifier-free guidance (LSG) to efficiently distill pretrained Stable Diffusion models without using real training data. SiD aims to optimize a model-based explicit score matching loss, utilizing a score-identity-based approximation alongside the proposed LSG for practical computation. By training exclusively with fake images synthesized with its one-step generator, SiD equipped with LSG rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Specifically, its data-free distillation of Stable Diffusion 1.5 achieves a record low FID of 8.15 on the COCO-2014 validation set, with a CLIP score of 0.304 at an LSG scale of 1.5, and a FID of 9.56 with a CLIP score of 0.313 at an LSG scale of 2. We will make our PyTorch implementation and distilled Stable Diffusion one-step generators available at https://github.com/mingyuanzhou/SiD-LSG
Authors: Chun Gu, Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang
Abstract: 3D representation is essential to the significant advance of 3D generation with 2D diffusion priors. As a flexible representation, NeRF has been first adopted for 3D representation. With density-based volumetric rendering, it however suffers both intensive computational overhead and inaccurate mesh extraction. Using a signed distance field and Marching Tetrahedra, DMTet allows for precise mesh extraction and real-time rendering but is limited in handling large topological changes in meshes, leading to optimization challenges. Alternatively, 3D Gaussian Splatting (3DGS) is favored in both training and rendering efficiency while falling short in mesh extraction. In this work, we introduce a novel 3D representation, Tetrahedron Splatting (TeT-Splatting), that supports easy convergence during optimization, precise mesh extraction, and real-time rendering simultaneously. This is achieved by integrating surface-based volumetric rendering within a structured tetrahedral grid while preserving the desired ability of precise mesh extraction, and a tile-based differentiable tetrahedron rasterizer. Furthermore, we incorporate eikonal and normal consistency regularization terms for the signed distance field to improve generation quality and stability. Critically, our representation can be trained without mesh extraction, making the optimization process easier to converge. Our TeT-Splatting can be readily integrated in existing 3D generation pipelines, along with polygonal mesh for texture optimization. Extensive experiments show that our TeT-Splatting strikes a superior tradeoff among convergence speed, render efficiency, and mesh quality as compared to previous alternatives under varying 3D generation settings.
Authors: Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi
Abstract: Recent works have explored how individual components of the CLIP-ViT model contribute to the final representation by leveraging the shared image-text representation space of CLIP. These components, such as attention heads and MLPs, have been shown to capture distinct image features like shape, color or texture. However, understanding the role of these components in arbitrary vision transformers (ViTs) is challenging. To this end, we introduce a general framework which can identify the roles of various components in ViTs beyond CLIP. Specifically, we (a) automate the decomposition of the final representation into contributions from different model components, and (b) linearly map these contributions to CLIP space to interpret them via text. Additionally, we introduce a novel scoring function to rank components by their importance with respect to specific features. Applying our framework to various ViT variants (e.g. DeiT, DINO, DINOv2, Swin, MaxViT), we gain insights into the roles of different components concerning particular image features.These insights facilitate applications such as image retrieval using text descriptions or reference images, visualizing token importance heatmaps, and mitigating spurious correlations.
Authors: An-Chieh Cheng, Hongxu Yin, Yang Fu, Qiushan Guo, Ruihan Yang, Jan Kautz, Xiaolong Wang, Sifei Liu
Abstract: Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT) to enhance VLMs' spatial perception and reasoning capabilities. SpatialRGPT advances VLMs' spatial understanding through two key innovations: (1) a data curation pipeline that enables effective learning of regional representation from 3D scene graphs, and (2) a flexible plugin module for integrating depth information into the visual encoder of existing VLMs. During inference, when provided with user-specified region proposals, SpatialRGPT can accurately perceive their relative directions and distances. Additionally, we propose SpatialRGBT-Bench, a benchmark with ground-truth 3D annotations encompassing indoor, outdoor, and simulated environments, for evaluating 3D spatial cognition in VLMs. Our results demonstrate that SpatialRGPT significantly enhances performance in spatial reasoning tasks, both with and without local region prompts. The model also exhibits strong generalization capabilities, effectively reasoning about complex spatial relations and functioning as a region-aware dense reward annotator for robotic tasks. Code, dataset, and benchmark will be released at https://www.anjiecheng.me/SpatialRGPT
Authors: Chun-Hung Wu, Shih-Hong Chen, Chih-Yao Hu, Hsin-Yu Wu, Kai-Hsin Chen, Yu-You Chen, Chih-Hai Su, Chih-Kuo Lee, Yu-Lun Liu
Abstract: This paper presents Deformable Neural Vessel Representations (DeNVeR), an unsupervised approach for vessel segmentation in X-ray videos without annotated ground truth. DeNVeR uses optical flow and layer separation, enhancing segmentation accuracy and adaptability through test-time training. A key component of our research is the introduction of the XACV dataset, the first X-ray angiography coronary video dataset with high-quality, manually labeled segmentation ground truth. Our evaluation demonstrates that DeNVeR outperforms current state-of-the-art methods in vessel segmentation. This paper marks an advance in medical imaging, providing a robust, data-efficient tool for disease diagnosis and treatment planning and setting a new standard for future research in video vessel segmentation. See our project page for video results at https://kirito878.github.io/DeNVeR/.
Authors: Yun-Chun Chen, Selena Ling, Zhiqin Chen, Vladimir G. Kim, Matheus Gadelha, Alec Jacobson
Abstract: We propose a novel technique for adding geometric details to an input coarse 3D mesh guided by a text prompt. Our method is composed of three stages. First, we generate a single-view RGB image conditioned on the input coarse geometry and the input text prompt. This single-view image generation step allows the user to pre-visualize the result and offers stronger conditioning for subsequent multi-view generation. Second, we use our novel multi-view normal generation architecture to jointly generate six different views of the normal images. The joint view generation reduces inconsistencies and leads to sharper details. Third, we optimize our mesh with respect to all views and generate a fine, detailed geometry as output. The resulting method produces an output within seconds and offers explicit user control over the coarse structure, pose, and desired details of the resulting 3D mesh. Project page: https://text-mesh-refinement.github.io.
Authors: Shaojie Ma, Yawei Luo, Yi Yang
Abstract: 3D reconstruction and simulation, while interrelated, have distinct objectives: reconstruction demands a flexible 3D representation adaptable to diverse scenes, whereas simulation requires a structured representation to model motion principles effectively. This paper introduces the Mesh-adsorbed Gaussian Splatting (MaGS) method to resolve such a dilemma. MaGS constrains 3D Gaussians to hover on the mesh surface, creating a mutual-adsorbed mesh-Gaussian 3D representation that combines the rendering flexibility of 3D Gaussians with the spatial coherence of meshes. Leveraging this representation, we introduce a learnable Relative Deformation Field (RDF) to model the relative displacement between the mesh and 3D Gaussians, extending traditional mesh-driven deformation paradigms that only rely on ARAP prior, thus capturing the motion of each 3D Gaussian more precisely. By joint optimizing meshes, 3D Gaussians, and RDF, MaGS achieves both high rendering accuracy and realistic deformation. Extensive experiments on the D-NeRF and NeRF-DS datasets demonstrate that MaGS can generate competitive results in both reconstruction and simulation.
Authors: Omri Avrahami, Rinon Gal, Gal Chechik, Ohad Fried, Dani Lischinski, Arash Vahdat, Weili Nie
Abstract: Text-to-image diffusion models have proven effective for solving many image editing tasks. However, the seemingly straightforward task of seamlessly relocating objects within a scene remains surprisingly challenging. Existing methods addressing this problem often struggle to function reliably in real-world scenarios due to lacking spatial reasoning. In this work, we propose a training-free method, dubbed DiffUHaul, that harnesses the spatial understanding of a localized text-to-image model, for the object dragging task. Blindly manipulating layout inputs of the localized model tends to cause low editing performance due to the intrinsic entanglement of object representation in the model. To this end, we first apply attention masking in each denoising step to make the generation more disentangled across different objects and adopt the self-attention sharing mechanism to preserve the high-level object appearance. Furthermore, we propose a new diffusion anchoring technique: in the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance; in the later denoising steps, we pass the localized features from the source images to the interpolated images to retain fine-grained object details. To adapt DiffUHaul to real-image editing, we apply a DDPM self-attention bucketing that can better reconstruct real images with the localized model. Finally, we introduce an automated evaluation pipeline for this task and showcase the efficacy of our method. Our results are reinforced through a user preference study.
Authors: Zeren Jiang, Chen Guo, Manuel Kaufmann, Tianjian Jiang, Julien Valentin, Otmar Hilliges, Jie Song
Abstract: We present MultiPly, a novel framework to reconstruct multiple people in 3D from monocular in-the-wild videos. Reconstructing multiple individuals moving and interacting naturally from monocular in-the-wild videos poses a challenging task. Addressing it necessitates precise pixel-level disentanglement of individuals without any prior knowledge about the subjects. Moreover, it requires recovering intricate and complete 3D human shapes from short video sequences, intensifying the level of difficulty. To tackle these challenges, we first define a layered neural representation for the entire scene, composited by individual human and background models. We learn the layered neural representation from videos via our layer-wise differentiable volume rendering. This learning process is further enhanced by our hybrid instance segmentation approach which combines the self-supervised 3D segmentation and the promptable 2D segmentation module, yielding reliable instance segmentation supervision even under close human interaction. A confidence-guided optimization formulation is introduced to optimize the human poses and shape/appearance alternately. We incorporate effective objectives to refine human poses via photometric information and impose physically plausible constraints on human dynamics, leading to temporally consistent 3D reconstructions with high fidelity. The evaluation of our method shows the superiority over prior art on publicly available datasets and in-the-wild videos.
Authors: Jens Decke, Olaf W\"unsch, Bernhard Sick, Christian Gruhl
Abstract: This article investigates the application of computer vision and graph-based models in solving mesh-based partial differential equations within high-performance computing environments. Focusing on structured, graded structured, and unstructured meshes, the study compares the performance and computational efficiency of three computer vision-based models against three graph-based models across three data\-sets. The research aims to identify the most suitable models for different mesh topographies, particularly highlighting the exploration of graded meshes, a less studied area. Results demonstrate that computer vision-based models, notably U-Net, outperform the graph models in prediction performance and efficiency in two (structured and graded) out of three mesh topographies. The study also reveals the unexpected effectiveness of computer vision-based models in handling unstructured meshes, suggesting a potential shift in methodological approaches for data-driven partial differential equation learning. The article underscores deep learning as a viable and potentially sustainable way to enhance traditional high-performance computing methods, advocating for informed model selection based on the topography of the mesh.
Authors: Mingyuan Meng, Dagan Feng, Lei Bi, Jinman Kim
Abstract: Deformable image registration is a fundamental step for medical image analysis. Recently, transformers have been used for registration and outperformed Convolutional Neural Networks (CNNs). Transformers can capture long-range dependence among image features, which have been shown beneficial for registration. However, due to the high computation/memory loads of self-attention, transformers are typically used at downsampled feature resolutions and cannot capture fine-grained long-range dependence at the full image resolution. This limits deformable registration as it necessitates precise dense correspondence between each image pixel. Multi-layer Perceptrons (MLPs) without self-attention are efficient in computation/memory usage, enabling the feasibility of capturing fine-grained long-range dependence at full resolution. Nevertheless, MLPs have not been extensively explored for image registration and are lacking the consideration of inductive bias crucial for medical registration tasks. In this study, we propose the first correlation-aware MLP-based registration network (CorrMLP) for deformable medical image registration. Our CorrMLP introduces a correlation-aware multi-window MLP block in a novel coarse-to-fine registration architecture, which captures fine-grained multi-range dependence to perform correlation-aware coarse-to-fine registration. Extensive experiments with seven public medical datasets show that our CorrMLP outperforms state-of-the-art deformable registration methods.
Authors: Robert Graf, Paul-S\"oren Platzek, Evamaria Olga Riedel, Constanze Ramsch\"utz, Sophie Starck, Hendrik Kristian M\"oller, Matan Atad, Henry V\"olzke, Robin B\"ulow, Carsten Oliver Schmidt, Julia R\"udebusch, Matthias Jung, Marco Reisert, Jakob Weiss, Maximilian L\"offler, Fabian Bamberg, Bene Wiestler, Johannes C. Paetzold, Daniel Rueckert, Jan Stefan Kirschke
Abstract: Objectives: To present a publicly available torso segmentation network for large epidemiology datasets on volumetric interpolated breath-hold examination (VIBE) images. Materials & Methods: We extracted preliminary segmentations from TotalSegmentator, spine, and body composition networks for VIBE images, then improved them iteratively and retrained a nnUNet network. Using subsets of NAKO (85 subjects) and UK Biobank (16 subjects), we evaluated with Dice-score on a holdout set (12 subjects) and existing organ segmentation approach (1000 subjects), generating 71 semantic segmentation types for VIBE images. We provide an additional network for the vertebra segments 22 individual vertebra types. Results: We achieved an average Dice score of 0.89 +- 0.07 overall 71 segmentation labels. We scored > 0.90 Dice-score on the abdominal organs except for the pancreas with a Dice of 0.70. Conclusion: Our work offers a detailed and refined publicly available full torso segmentation on VIBE images.
Authors: Yundi Zhang, Nil Stolt-Ans\'o, Jiazhen Pan, Wenqi Huang, Kerstin Hammernik, Daniel Rueckert
Abstract: The prevailing deep learning-based methods of predicting cardiac segmentation involve reconstructed magnetic resonance (MR) images. The heavy dependency of segmentation approaches on image quality significantly limits the acceleration rate in fast MR reconstruction. Moreover, the practice of treating reconstruction and segmentation as separate sequential processes leads to artifact generation and information loss in the intermediate stage. These issues pose a great risk to achieving high-quality outcomes. To leverage the redundant k-space information overlooked in this dual-step pipeline, we introduce a novel approach to directly deriving segmentations from sparse k-space samples using a transformer (DiSK). DiSK operates by globally extracting latent features from 2D+time k-space data with attention blocks and subsequently predicting the segmentation label of query points. We evaluate our model under various acceleration factors (ranging from 4 to 64) and compare against two image-based segmentation baselines. Our model consistently outperforms the baselines in Dice and Hausdorff distances across foreground classes for all presented sampling rates.
Authors: Chen Feng, Duolikun Danier, Fan Zhang, David Bull
Abstract: Visual artifacts are often introduced into streamed video content, due to prevailing conditions during content production and/or delivery. Since these can degrade the quality of the user's experience, it is important to automatically and accurately detect them in order to enable effective quality measurement and enhancement. Existing detection methods often focus on a single type of artifact and/or determine the presence of an artifact through thresholding objective quality indices. Such approaches have been reported to offer inconsistent prediction performance and are also impractical for real-world applications where multiple artifacts co-exist and interact. In this paper, we propose a Multiple Visual Artifact Detector, MVAD, for video streaming which, for the first time, is able to detect multiple artifacts using a single framework that is not reliant on video quality assessment models. Our approach employs a new Artifact-aware Dynamic Feature Extractor (ADFE) to obtain artifact-relevant spatial features within each frame for multiple artifact types. The extracted features are further processed by a Recurrent Memory Vision Transformer (RMViT) module, which captures both short-term and long-term temporal information within the input video. The proposed network architecture is optimized in an end-to-end manner based on a new, large and diverse training database that is generated by simulating the video streaming pipeline and based on Adversarial Data Augmentation. This model has been evaluated on two video artifact databases, Maxwell and BVI-Artifact, and achieves consistent and improved prediction results for ten target visual artifacts when compared to seven existing single and multiple artifact detectors. The source code and training database will be available at https://chenfeng-bristol.github.io/MVAD/.
Authors: Ananya Jain, Aviral Bhardwaj, Kaushik Murali, Isha Surani
Abstract: Large language models, notably utilizing Transformer architectures, have emerged as powerful tools due to their scalability and ability to process large amounts of data. Dosovitskiy et al. expanded this architecture to introduce Vision Transformers (ViT), extending its applicability to image processing tasks. Motivated by this advancement, we fine-tuned two variants of ViT models, one pre-trained on ImageNet and another trained from scratch, using the NIH Chest X-ray dataset containing over 100,000 frontal-view X-ray images. Our study evaluates the performance of these models in the multi-label classification of 14 distinct diseases, while using Convolutional Neural Networks (CNNs) and ResNet architectures as baseline models for comparison. Through rigorous assessment based on accuracy metrics, we identify that the pre-trained ViT model surpasses CNNs and ResNet in this multilabel classification task, highlighting its potential for accurate diagnosis of various lung conditions from chest X-ray images.
Authors: Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Weijie J. Su, Camillo J. Taylor, Tanwi Mallick
Abstract: Rationality is the quality of being guided by reason, characterized by logical thinking and decision-making that align with evidence and logical rules. This quality is essential for effective problem-solving, as it ensures that solutions are well-founded and systematically derived. Despite the advancements of large language models (LLMs) in generating human-like text with remarkable accuracy, they present biases inherited from the training data, inconsistency across different contexts, and difficulty understanding complex scenarios involving multiple layers of context. Therefore, recent research attempts to leverage the strength of multiple agents working collaboratively with various types of data and tools for enhanced consistency and reliability. To that end, this paper aims to understand whether multi-modal and multi-agent systems are advancing toward rationality by surveying the state-of-the-art works, identifying advancements over single-agent and single-modal systems in terms of rationality, and discussing open problems and future directions. We maintain an open repository at https://github.com/bowen-upenn/MMMA_Rationality.
Authors: Zezhao Guo, Zhanfang Zhao
Abstract: Optical coherence tomography (OCT) is a non-invasive, high-resolution imaging technology that provides cross-sectional images of tissues. Dense acquisition of A-scans along the fast axis is required to obtain high digital resolution images. However, the dense acquisition will increase the acquisition time, causing the discomfort of patients. In addition, the longer acquisition time may lead to motion artifacts, thereby reducing imaging quality. In this work, we proposed a hybrid attention structure preserving network (HASPN) to achieve super-resolution of under-sampled OCT images to speed up the acquisition. It utilized adaptive dilated convolution-based channel attention (ADCCA) and enhanced spatial attention (ESA) to better capture the channel and spatial information of the feature. Moreover, convolutional neural networks (CNNs) exhibit a higher sensitivity of low-frequency than high-frequency information, which may lead to a limited performance on reconstructing fine structures. To address this problem, we introduced an additional branch, i.e., textures & details branch, using high-frequency decomposition images to better super-resolve retinal structures. The superiority of our method was demonstrated by qualitative and quantitative comparisons with mainstream methods. HASPN was applied to the diabetic macular edema retinal dataset, validating its good generalization ability.
Authors: Nikolaos Spanos, Anastasios Arsenos, Paraskevi-Antonia Theofilou, Paraskevi Tzouveli, Athanasios Voulodimos, Stefanos Kollias
Abstract: The absence of well-structured large datasets in medical computer vision results in decreased performance of automated systems and, especially, of deep learning models. Domain generalization techniques aim to approach unknown domains from a single data source. In this paper we introduce a novel framework, named CompStyle, which leverages style transfer and adversarial training, along with high-level input complexity augmentation to effectively expand the domain space and address unknown distributions. State-of-the-art style transfer methods depend on the existence of subdomains within the source dataset. However, this can lead to an inherent dataset bias in the image creation. Input-level augmentation can provide a solution to this problem by widening the domain space in the source dataset and boost performance on out-of-domain distributions. We provide results from experiments on semantic segmentation on prostate data and corruption robustness on cardiac data which demonstrate the effectiveness of our approach. Our method increases performance in both tasks, without added cost to training time or resources.
Authors: Victor A. Kich, Muhammad A. Muttaqien, Junya Toyama, Ryutaro Miyoshi, Yosuke Ida, Akihisa Ohya, Hisashi Date
Abstract: Recent advancements in real-time object detection frameworks have spurred extensive research into their application in robotic systems. This study provides a comparative analysis of YOLOv5 and YOLOv8 models, challenging the prevailing assumption of the latter's superiority in performance metrics. Contrary to initial expectations, YOLOv5 models demonstrated comparable, and in some cases superior, precision in object detection tasks. Our analysis delves into the underlying factors contributing to these findings, examining aspects such as model architecture complexity, training dataset variances, and real-world applicability. Through rigorous testing and an ablation study, we present a nuanced understanding of each model's capabilities, offering insights into the selection and optimization of object detection frameworks for robotic applications. Implications of this research extend to the design of more efficient and contextually adaptive systems, emphasizing the necessity for a holistic approach to evaluating model performance.
Authors: Yongqi Wang, Wenxiang Guo, Rongjie Huang, Jiawei Huang, Zehan Wang, Fuming You, Ruiqi Li, Zhou Zhao
Abstract: Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transformer and channel-level cross-modal feature fusion with strong temporal alignment, our model generates audio that is highly synchronized with the input video. Furthermore, through reflow and one-step distillation with guided vector field, our model can generate decent audio in a few, or even only one sampling step. Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment on VGGSound, with alignment accuracy reaching 97.22%, and 6.2% improvement in inception score over the strong diffusion-based baseline. Audio samples are available at http://frieren-v2a.github.io .
Authors: Yundi Zhang, Chen Chen, Suprosanna Shit, Sophie Starck, Daniel Rueckert, Jiazhen Pan
Abstract: Cardiac Magnetic Resonance (CMR) imaging serves as the gold-standard for evaluating cardiac morphology and function. Typically, a multi-view CMR stack, covering short-axis (SA) and 2/3/4-chamber long-axis (LA) views, is acquired for a thorough cardiac assessment. However, efficiently streamlining the complex, high-dimensional 3D+T CMR data and distilling compact, coherent representation remains a challenge. In this work, we introduce a whole-heart self-supervised learning framework that utilizes masked imaging modeling to automatically uncover the correlations between spatial and temporal patches throughout the cardiac stacks. This process facilitates the generation of meaningful and well-clustered heart representations without relying on the traditionally required, and often costly, labeled data. The learned heart representation can be directly used for various downstream tasks. Furthermore, our method demonstrates remarkable robustness, ensuring consistent representations even when certain CMR planes are missing/flawed. We train our model on 14,000 unlabeled CMR data from UK BioBank and evaluate it on 1,000 annotated data. The proposed method demonstrates superior performance to baselines in tasks that demand comprehensive 3D+T cardiac information, e.g. cardiac phenotype (ejection fraction and ventricle volume) prediction and multi-plane/multi-frame CMR segmentation, highlighting its effectiveness in extracting comprehensive cardiac features that are both anatomically and pathologically relevant.
Authors: Qihang Xie, Mengguo Guo, Lei Mou, Dan Zhang, Da Chen, Caifeng Shan, Yitian Zhao, Ruisheng Su, Jiong Zhang
Abstract: Cerebrovascular diseases (CVDs) remain a leading cause of global disability and mortality. Digital Subtraction Angiography (DSA) sequences, recognized as the golden standard for diagnosing CVDs, can clearly visualize the dynamic flow and reveal pathological conditions within the cerebrovasculature. Therefore, precise segmentation of cerebral arteries (CAs) and classification between their main trunks and branches are crucial for physicians to accurately quantify diseases. However, achieving accurate CA segmentation in DSA sequences remains a challenging task due to small vessels with low contrast, and ambiguity between vessels and residual skull structures. Moreover, the lack of publicly available datasets limits exploration in the field. In this paper, we introduce a DSA Sequence-based Cerebral Artery segmentation dataset (DSCA), the first publicly accessible dataset designed specifically for pixel-level semantic segmentation of CAs. Additionally, we propose DSANet, a spatio-temporal network for CA segmentation in DSA sequences. Unlike existing DSA segmentation methods that focus only on a single frame, the proposed DSANet introduces a separate temporal encoding branch to capture dynamic vessel details across multiple frames. To enhance small vessel segmentation and improve vessel connectivity, we design a novel TemporalFormer module to capture global context and correlations among sequential frames. Furthermore, we develop a Spatio-Temporal Fusion (STF) module to effectively integrate spatial and temporal features from the encoder. Extensive experiments demonstrate that DSANet outperforms other state-of-the-art methods in CA segmentation, achieving a Dice of 0.9033.
Authors: Lemuel Puglisi, Alessia Rondinella, Linda De Meo, Francesco Guarnera, Sebastiano Battiato, Daniele Rav\`i
Abstract: Brain age is a critical measure that reflects the biological ageing process of the brain. The gap between brain age and chronological age, referred to as brain PAD (Predicted Age Difference), has been utilized to investigate neurodegenerative conditions. Brain age can be predicted using MRIs and machine learning techniques. However, existing methods are often sensitive to acquisition-related variabilities, such as differences in acquisition protocols, scanners, MRI sequences, and resolutions, significantly limiting their application in highly heterogeneous clinical settings. In this study, we introduce Synthetic Brain Age (SynthBA), a robust deep-learning model designed for predicting brain age. SynthBA utilizes an advanced domain randomization technique, ensuring effective operation across a wide array of acquisition-related variabilities. To assess the effectiveness and robustness of SynthBA, we evaluate its predictive capabilities on internal and external datasets, encompassing various MRI sequences and resolutions, and compare it with state-of-the-art techniques. Additionally, we calculate the brain PAD in a large cohort of subjects with Alzheimer's Disease (AD), demonstrating a significant correlation with AD-related measures of cognitive dysfunction. SynthBA holds the potential to facilitate the broader adoption of brain age prediction in clinical settings, where re-training or fine-tuning is often unfeasible. The SynthBA source code and pre-trained models are publicly available at https://github.com/LemuelPuglisi/SynthBA.
Authors: Jia Zeng, Qingwen Bu, Bangjun Wang, Wenke Xia, Li Chen, Hao Dong, Haoming Song, Dong Wang, Di Hu, Ping Luo, Heming Cui, Bin Zhao, Xuelong Li, Yu Qiao, Hongyang Li
Abstract: Representation learning approaches for robotic manipulation have boomed in recent years. Due to the scarcity of in-domain robot data, prevailing methodologies tend to leverage large-scale human video datasets to extract generalizable features for visuomotor policy learning. Despite the progress achieved, prior endeavors disregard the interactive dynamics that capture behavior patterns and physical interaction during the manipulation process, resulting in an inadequate understanding of the relationship between objects and the environment. To this end, we propose a general pre-training pipeline that learns Manipulation by Predicting the Interaction (MPI) and enhances the visual representation.Given a pair of keyframes representing the initial and final states, along with language instructions, our algorithm predicts the transition frame and detects the interaction object, respectively. These two learning objectives achieve superior comprehension towards "how-to-interact" and "where-to-interact". We conduct a comprehensive evaluation of several challenging robotic tasks.The experimental results demonstrate that MPI exhibits remarkable improvement by 10% to 64% compared with previous state-of-the-art in real-world robot platforms as well as simulation environments. Code and checkpoints are publicly shared at https://github.com/OpenDriveLab/MPI.
Authors: Jiahua Dong, Hui Yin, Hongliu Li, Wenbo Li, Yulun Zhang, Salman Khan, Fahad Shahbaz Khan
Abstract: Deep unfolding methods have made impressive progress in restoring 3D hyperspectral images (HSIs) from 2D measurements through convolution neural networks or Transformers in spectral compressive imaging. However, they cannot efficiently capture long-range dependencies using global receptive fields, which significantly limits their performance in HSI reconstruction. Moreover, these methods may suffer from local context neglect if we directly utilize Mamba to unfold a 2D feature map as a 1D sequence for modeling global long-range dependencies. To address these challenges, we propose a novel Dual Hyperspectral Mamba (DHM) to explore both global long-range dependencies and local contexts for efficient HSI reconstruction. After learning informative parameters to estimate degradation patterns of the CASSI system, we use them to scale the linear projection and offer noise level for the denoiser (i.e., our proposed DHM). Specifically, our DHM consists of multiple dual hyperspectral S4 blocks (DHSBs) to restore original HSIs. Particularly, each DHSB contains a global hyperspectral S4 block (GHSB) to model long-range dependencies across the entire high-resolution HSIs using global receptive fields, and a local hyperspectral S4 block (LHSB) to address local context neglect by establishing structured state-space sequence (S4) models within local windows. Experiments verify the benefits of our DHM for HSI reconstruction. The source codes and models will be available at https://github.com/JiahuaDong/DHM.
Authors: Jiandong Wang, Alessandro Perelli
Abstract: Dual energy X-ray Computed Tomography (DECT) enables to automatically decompose materials in clinical images without the manual segmentation using the dependency of the X-ray linear attenuation with energy. In this work we propose a deep learning procedure called End-to-End Material Decomposition (E2E-DEcomp) for quantitative material decomposition which directly convert the CT projection data into material images. The algorithm is based on incorporating the knowledge of the spectral model DECT system into the deep learning training loss and combining a data-learned prior in the material image domain. Furthermore, the training does not require any energy-based images in the dataset but rather only sinogram and material images. We show the effectiveness of the proposed direct E2E-DEcomp method on the AAPM spectral CT dataset (Sidky and Pan, 2023) compared with state of the art supervised deep learning networks.
Authors: Xueying Zeng, Baixiang Huang, Yu Luo, Guangyu Wei, Songyan He, Yushuang Shao
Abstract: Coronary artery disease (CAD) is one of the most prevalent diseases in the cardiovascular field and one of the major contributors to death worldwide. Computed Tomography Angiography (CTA) images are regarded as the authoritative standard for the diagnosis of coronary artery disease, and by performing vessel segmentation and stenosis detection on CTA images, physicians are able to diagnose coronary artery disease more accurately. In order to combine the advantages of both the base model and the domain-specific model, and to achieve high-precision and fully-automatic segmentation and detection with a limited number of training samples, we propose a novel architecture, SAM-VMNet, which combines the powerful feature extraction capability of MedSAM with the advantage of the linear complexity of the visual state-space model of VM-UNet, giving it faster inferences than Vision Transformer with faster inference speed and stronger data processing capability, achieving higher segmentation accuracy and stability for CTA images. Experimental results show that the SAM-VMNet architecture performs excellently in the CTA image segmentation task, with a segmentation accuracy of up to 98.32% and a sensitivity of up to 99.33%, which is significantly better than other existing models and has stronger domain adaptability. Comprehensive evaluation of the CTA image segmentation task shows that SAM-VMNet accurately extracts the vascular trunks and capillaries, demonstrating its great potential and wide range of application scenarios for the vascular segmentation task, and also laying a solid foundation for further stenosis detection.
Authors: Davide Berghi, Philip J. B. Jackson
Abstract: Object-based audio production requires the positional metadata to be defined for each point-source object, including the key elements in the foreground of the sound scene. In many media production use cases, both cameras and microphones are employed to make recordings, and the human voice is often a key element. In this research, we detect and locate the active speaker in the video, facilitating the automatic extraction of the positional metadata of the talker relative to the camera's reference frame. With the integration of the visual modality, this study expands upon our previous investigation focused solely on audio-based active speaker detection and localization. Our experiments compare conventional audio-visual approaches for active speaker detection that leverage monaural audio, our previous audio-only method that leverages multichannel recordings from a microphone array, and a novel audio-visual approach integrating vision and multichannel audio. We found the role of the two modalities to complement each other. Multichannel audio, overcoming the problem of visual occlusions, provides a double-digit reduction in detection error compared to audio-visual methods with single-channel audio. The combination of multichannel audio and vision further enhances spatial accuracy, leading to a four-percentage point increase in F1 score on the Tragic Talkers dataset. Future investigations will assess the robustness of the model in noisy and highly reverberant environments, as well as tackle the problem of off-screen speakers.
Authors: Vivek Narayanaswamy, Kowshik Thopalli, Rushil Anirudh, Yamen Mubarka, Wesam Sakla, Jayaraman J. Thiagarajan
Abstract: Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically explore anchoring as a general protocol for training vision models, providing fundamental insights into its training and inference processes and their implications for generalization and safety. Despite its promise, we identify a critical problem in anchored training that can lead to an increased risk of learning undesirable shortcuts, thereby limiting its generalization capabilities. To address this, we introduce a new anchored training protocol that employs a simple regularizer to mitigate this issue and significantly enhances generalization. We empirically evaluate our proposed approach across datasets and architectures of varying scales and complexities, demonstrating substantial performance gains in generalization and safety metrics compared to the standard training protocol.
Authors: Haowen Zhou (Siyu), Steven (Siyu), Lin, Mark Watson, Cory T. Bernadt, Oumeng Zhang, Ramaswamy Govindan, Richard J. Cote, Changhuei Yang
Abstract: Deep learning assisted digital pathology has the potential to impact clinical practice in significant ways. In recent studies, deep neural network (DNN) enabled analysis outperforms human pathologists. Increasing sizes and complexity of the DNN architecture generally improves performance at the cost of DNN's explainability. For pathology, this lack of DNN explainability is particularly problematic as it hinders the broader clinical interpretation of the pathology features that may provide physiological disease insights. To better assess the features that DNN uses in developing predictive algorithms to interpret digital microscopic images, we sought to understand the role of resolution and tissue scale and here describe a novel method for studying the predictive feature length-scale that underpins a DNN's predictive power. We applied the method to study a DNN's predictive capability in the case example of brain metastasis prediction from early-stage non-small-cell lung cancer biopsy slides. The study highlights the DNN attention in the brain metastasis prediction targeting both cellular scale (resolution) and tissue scale features on H&E-stained histological whole slide images. At the cellular scale, we see that DNN's predictive power is progressively increased at higher resolution (i.e., lower resolvable feature length) and is largely lost when the resolvable feature length is longer than 5 microns. In addition, DNN uses more macro-scale features (maximal feature length) associated with tissue organization/architecture and is optimized when assessing visual fields larger than 41 microns. This study for the first time demonstrates the length-scale requirements necessary for optimal DNN learning on digital whole slide images.
Authors: Mohit Prabhushankar, Ghassan AlRegib
Abstract: In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under perturbations to the input. Visual post hoc explainability techniques highlight features within an image to justify a network's prediction. We theoretically show that existing evaluation strategies of visual explanatory techniques partially reduce the predictive uncertainty of neural networks. This analysis allows us to construct a plug in approach to visualize and quantify the remaining predictive uncertainty of any gradient-based explanatory technique. We show that every image, network, prediction, and explanatory technique has a unique uncertainty. The proposed uncertainty visualization and quantification yields two key observations. Firstly, oftentimes under incorrect predictions, explanatory techniques are uncertain about the same features that they are attributing the predictions to, thereby reducing the trustworthiness of the explanation. Secondly, objective metrics of an explanation's uncertainty, empirically behave similarly to epistemic uncertainty. We support these observations on two datasets, four explanatory techniques, and six neural network architectures. The code is available at https://github.com/olivesgatech/VOICE-Uncertainty.
Authors: Dinghuai Zhang, Yizhe Zhang, Jiatao Gu, Ruixiang Zhang, Josh Susskind, Navdeep Jaitly, Shuangfei Zhai
Abstract: Diffusion models have become the \textit{de-facto} approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as alignment to a text description, which can be specified with a black-box reward function. Prior works fine-tune pretrained diffusion models to achieve this goal through reinforcement learning-based algorithms. Nonetheless, they suffer from issues including slow credit assignment as well as low quality in their generated samples. In this work, we explore techniques that do not directly maximize the reward but rather generate high-reward images with relatively high probability -- a natural scenario for the framework of generative flow networks (GFlowNets). To this end, we propose the \textbf{D}iffusion \textbf{A}lignment with \textbf{G}FlowNet (DAG) algorithm to post-train diffusion models with black-box property functions. Extensive experiments on Stable Diffusion and various reward specifications corroborate that our method could effectively align large-scale text-to-image diffusion models with given reward information.
Authors: Yuwei Fu, Haichao Zhang, Di Wu, Wei Xu, Benoit Boulet
Abstract: In this work, we investigate how to leverage pre-trained visual-language models (VLM) for online Reinforcement Learning (RL). In particular, we focus on sparse reward tasks with pre-defined textual task descriptions. We first identify the problem of reward misalignment when applying VLM as a reward in RL tasks. To address this issue, we introduce a lightweight fine-tuning method, named Fuzzy VLM reward-aided RL (FuRL), based on reward alignment and relay RL. Specifically, we enhance the performance of SAC/DrQ baseline agents on sparse reward tasks by fine-tuning VLM representations and using relay RL to avoid local minima. Extensive experiments on the Meta-world benchmark tasks demonstrate the efficacy of the proposed method. Code is available at: {\footnotesize\url{https://github.com/fuyw/FuRL}}.
Authors: Sulaiman Khan, Md. Rafiul Biswas, Alina Murad, Hazrat Ali, Zubair Shah
Abstract: Recent developments in multimodal large language models (MLLMs) have spurred significant interest in their potential applications across various medical imaging domains. On the one hand, there is a temptation to use these generative models to synthesize realistic-looking medical image data, while on the other hand, the ability to identify synthetic image data in a pool of data is also significantly important. In this study, we explore the potential of the Gemini (\textit{gemini-1.0-pro-vision-latest}) and GPT-4V (gpt-4-vision-preview) models for medical image analysis using two modalities of medical image data. Utilizing synthetic and real imaging data, both Gemini AI and GPT-4V are first used to classify real versus synthetic images, followed by an interpretation and analysis of the input images. Experimental results demonstrate that both Gemini and GPT-4 could perform some interpretation of the input images. In this specific experiment, Gemini was able to perform slightly better than the GPT-4V on the classification task. In contrast, responses associated with GPT-4V were mostly generic in nature. Our early investigation presented in this work provides insights into the potential of MLLMs to assist with the classification and interpretation of retinal fundoscopy and lung X-ray images. We also identify key limitations associated with the early investigation study on MLLMs for specialized tasks in medical image analysis.
Authors: Muge Yan, Lizhi Wang, Lin Zhu, Hua Huang
Abstract: Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. While most methods emphasize space-domain learning using image space priors like non-local similarity, frequency-domain learning using image frequency priors remains neglected, limiting the reconstruction capability of networks. In this paper, we first propose a Hyperspectral Frequency Correlation (HFC) prior rooted in in-depth statistical frequency analyses of existent HSI datasets. Leveraging the HFC prior, we subsequently establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF) targeting low-frequency and high-frequency components, respectively. The outputs of SAF and SIF are adaptively merged by a learnable gating filter, thus achieving a thorough exploitation of image frequency priors. Integrating the frequency domain learning and the existing space domain learning, we finally develop the Correlation-driven Mixing Domains Transformer (CMDT) for HSI reconstruction. Extensive experiments highlight that our method surpasses various state-of-the-art (SOTA) methods in reconstruction quality and computational efficiency.
Authors: Anqi Li, Yuxi Liu, Huihui Bai, Feng Li, Runmin Cong, Meng Wang, Yao Zhao
Abstract: Although recent generative image compression methods have demonstrated impressive potential in optimizing the rate-distortion-perception trade-off, they still face the critical challenge of flexible rate adaption to diverse compression necessities and scenarios. To overcome this challenge, this paper proposes a Controllable Generative Image Compression framework, Control-GIC, the first capable of fine-grained bitrate adaption across a broad spectrum while ensuring high-fidelity and generality compression. We base Control-GIC on a VQGAN framework representing an image as a sequence of variable-length codes (i.e. VQ-indices), which can be losslessly compressed and exhibits a direct positive correlation with the bitrates. Therefore, drawing inspiration from the classical coding principle, we naturally correlate the information density of local image patches with their granular representations, to achieve dynamic adjustment of the code quantity following different granularity decisions. This implies we can flexibly determine a proper allocation of granularity for the patches to acquire desirable compression rates. We further develop a probabilistic conditional decoder that can trace back to historic encoded multi-granularity representations according to transmitted codes, and then reconstruct hierarchical granular features in the formalization of conditional probability, enabling more informative aggregation to improve reconstruction realism. Our experiments show that Control-GIC allows highly flexible and controllable bitrate adaption and even once compression on an entire dataset to fulfill constrained bitrate conditions. Experimental results demonstrate its superior performance over recent state-of-the-art methods.
Authors: Jincheng Zhong, Xingzhuo Guo, Jiaxiang Dong, Mingsheng Long
Abstract: Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downstream generation tasks. Current fine-tuning methods focus on parameter-efficient transfer learning but overlook the fundamental transfer characteristics of diffusion models. In this paper, we investigate the transferability of diffusion models and observe a monotonous chain of forgetting trend of transferability along the reverse process. Based on this observation and novel theoretical insights, we present Diff-Tuning, a frustratingly simple transfer approach that leverages the chain of forgetting tendency. Diff-Tuning encourages the fine-tuned model to retain the pre-trained knowledge at the end of the denoising chain close to the generated data while discarding the other noise side. We conduct comprehensive experiments to evaluate Diff-Tuning, including the transfer of pre-trained Diffusion Transformer models to eight downstream generations and the adaptation of Stable Diffusion to five control conditions with ControlNet. Diff-Tuning achieves a 26% improvement over standard fine-tuning and enhances the convergence speed of ControlNet by 24%. Notably, parameter-efficient transfer learning techniques for diffusion models can also benefit from Diff-Tuning.
Authors: Md Taimur Ahad
Abstract: Despite the observable benefit of Natural Language Processing (NLP) in processing a large amount of textual medical data within a limited time for information retrieval, a handful of research efforts have been devoted to uncovering novel data-cleaning methods. Data cleaning in NLP is at the centre point for extracting validated information. Another observed limitation in the NLP domain is having limited medical corpora that provide answers to a given medical question. Realising the limitations and challenges from two perspectives, this research aims to clean a medical dataset using ensemble techniques and to develop a corpus. The corpora expect that it will answer the question based on the semantic relationship of corpus sequences. However, the data cleaning method in this research suggests that the ensemble technique provides the highest accuracy (94%) compared to the single process, which includes vectorisation, exploratory data analysis, and feeding the vectorised data. The second aim of having an adequate corpus was realised by extracting answers from the dataset. This research is significant in machine learning, specifically data cleaning and the medical sector, but it also underscores the importance of NLP in the medical field, where accurate and timely information extraction can be a matter of life and death. It establishes text data processing using NLP as a powerful tool for extracting valuable information like image data.
Authors: Sen Li, Junchi Ma, Minhao Cheng
Abstract: In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated with diffusion models, largely attributed to their susceptibility to malicious exploitation. Notably, recent research has brought to light the vulnerability of diffusion models to backdoor attacks, enabling the generation of specific target images through corresponding triggers. However, prevailing backdoor attack methods rely on manually crafted trigger generation functions, often manifesting as discernible patterns incorporated into input noise, thus rendering them susceptible to human detection. In this paper, we present an innovative and versatile optimization framework designed to acquire invisible triggers, enhancing the stealthiness and resilience of inserted backdoors. Our proposed framework is applicable to both unconditional and conditional diffusion models, and notably, we are the pioneers in demonstrating the backdooring of diffusion models within the context of text-guided image editing and inpainting pipelines. Moreover, we also show that the backdoors in the conditional generation can be directly applied to model watermarking for model ownership verification, which further boosts the significance of the proposed framework. Extensive experiments on various commonly used samplers and datasets verify the efficacy and stealthiness of the proposed framework. Our code is publicly available at https://github.com/invisibleTriggerDiffusion/invisible_triggers_for_diffusion.
URLs: https://github.com/invisibleTriggerDiffusion/invisible_triggers_for_diffusion.
Authors: Xinge Yang, Matheus Souza, Kunyi Wang, Praneeth Chakravarthula, Qiang Fu, Wolfgang Heidrich
Abstract: Hybrid refractive-diffractive lenses combine the light efficiency of refractive lenses with the information encoding power of diffractive optical elements (DOE), showing great potential as the next generation of imaging systems. However, accurately simulating such hybrid designs is generally difficult, and in particular, there are no existing differentiable image formation models for hybrid lenses with sufficient accuracy. In this work, we propose a new hybrid ray-tracing and wave-propagation (ray-wave) model for accurate simulation of both optical aberrations and diffractive phase modulation, where the DOE is placed between the last refractive surface and the image sensor, i.e. away from the Fourier plane that is often used as a DOE position. The proposed ray-wave model is fully differentiable, enabling gradient back-propagation for end-to-end co-design of refractive-diffractive lens optimization and the image reconstruction network. We validate the accuracy of the proposed model by comparing the simulated point spread functions (PSFs) with theoretical results, as well as simulation experiments that show our model to be more accurate than solutions implemented in commercial software packages like Zemax. We demonstrate the effectiveness of the proposed model through real-world experiments and show significant improvements in both aberration correction and extended depth-of-field (EDoF) imaging. We believe the proposed model will motivate further investigation into a wide range of applications in computational imaging, computational photography, and advanced optical design. Code will be released upon publication.
Authors: Tianyi Zhang, Matthew Dutson, Vivek Boominathan, Mohit Gupta, Ashok Veeraraghavan
Abstract: Recently quanta image sensors (QIS) -- ultra-fast, zero-read-noise binary image sensors -- have demonstrated remarkable imaging capabilities in many challenging scenarios. Despite their potential, the adoption of these sensors is severely hampered by (a) high data rates and (b) the need for new computational pipelines to handle the unconventional raw data. We introduce a simple, low-bandwidth computational pipeline to address these challenges. Our approach is based on a novel streaming representation with a small memory footprint, efficiently capturing intensity information at multiple temporal scales. Updating the representation requires only 16 floating-point operations/pixel, which can be efficiently computed online at the native frame rate of the binary frames. We use a neural network operating on this representation to reconstruct videos in real-time (10-30 fps). We illustrate why such representation is well-suited for these emerging sensors, and how it offers low latency and high frame rate while retaining flexibility for downstream computer vision. Our approach results in significant data bandwidth reductions ~100X and real-time image reconstruction and computer vision -- $10^4$-$10^5$ reduction in computation than existing state-of-the-art approach while maintaining comparable quality. To the best of our knowledge, our approach is the first to achieve online, real-time image reconstruction on QIS.
Authors: Jueqing Lu, Lan Du, Wray Buntine, Myong Chol Jung, Joanna Dipnall, Belinda Gabbe
Abstract: Resolving conflicts is essential to make the decisions of multi-view classification more reliable. Much research has been conducted on learning consistent informative representations among different views, assuming that all views are identically important and strictly aligned. However, real-world multi-view data may not always conform to these assumptions, as some views may express distinct information. To address this issue, we develop a computational trust-based discounting method to enhance the existing trustworthy framework in scenarios where conflicts between different views may arise. Its belief fusion process considers the trustworthiness of predictions made by individual views via an instance-wise probability-sensitive trust discounting mechanism. We evaluate our method on six real-world datasets, using Top-1 Accuracy, AUC-ROC for Uncertainty-Aware Prediction, Fleiss' Kappa, and a new metric called Multi-View Agreement with Ground Truth that takes into consideration the ground truth labels. The experimental results show that computational trust can effectively resolve conflicts, paving the way for more reliable multi-view classification models in real-world applications.
Authors: Julian Martin Eisenschlos, Hern\'an Maina, Guido Ivetta, Luciana Benotti
Abstract: Recently, large multi-modal models (LMMs) have emerged with the capacity to perform vision tasks such as captioning and visual question answering (VQA) with unprecedented accuracy. Applications such as helping the blind or visually impaired have a critical need for precise answers. It is specially important for models to be well calibrated and be able to quantify their uncertainty in order to selectively decide when to answer and when to abstain or ask for clarifications. We perform the first in-depth analysis of calibration methods and metrics for VQA with in-context learning LMMs. Studying VQA on two answerability benchmarks, we show that the likelihood score of visually grounded models is better calibrated than in their text-only counterparts for in-context learning, where sampling based methods are generally superior, but no clear winner arises. We propose Avg BLEU, a calibration score combining the benefits of both sampling and likelihood methods across modalities.
Authors: Patrick Palmer, Martin Kr\"uger, Richard Altendorfer, Torsten Bertram
Abstract: Effective tracking of surrounding traffic participants allows for an accurate state estimation as a necessary ingredient for prediction of future behavior and therefore adequate planning of the ego vehicle trajectory. One approach for detecting and tracking surrounding traffic participants is the combination of a learning based object detector with a classical tracking algorithm. Learning based object detectors have been shown to work adequately on lidar and camera data, while learning based object detectors using standard radar data input have proven to be inferior. Recently, with the improvements to radar sensor technology in the form of imaging radars, the object detection performance on radar was greatly improved but is still limited compared to lidar sensors due to the sparsity of the radar point cloud. This presents a unique challenge for the task of multi-object tracking. The tracking algorithm must overcome the limited detection quality while generating consistent tracks. To this end, a comparison between different multi-object tracking methods on imaging radar data is required to investigate its potential for downstream tasks. The work at hand compares multiple approaches and analyzes their limitations when applied to imaging radar data. Furthermore, enhancements to the presented approaches in the form of probabilistic association algorithms are considered for this task.
Authors: Junyang Wang, Haiyang Xu, Haitao Jia, Xi Zhang, Ming Yan, Weizhou Shen, Ji Zhang, Fei Huang, Jitao Sang
Abstract: Mobile device operation tasks are increasingly becoming a popular multi-modal AI application scenario. Current Multi-modal Large Language Models (MLLMs), constrained by their training data, lack the capability to function effectively as operation assistants. Instead, MLLM-based agents, which enhance capabilities through tool invocation, are gradually being applied to this scenario. However, the two major navigation challenges in mobile device operation tasks, task progress navigation and focus content navigation, are significantly complicated under the single-agent architecture of existing work. This is due to the overly long token sequences and the interleaved text-image data format, which limit performance. To address these navigation challenges effectively, we propose Mobile-Agent-v2, a multi-agent architecture for mobile device operation assistance. The architecture comprises three agents: planning agent, decision agent, and reflection agent. The planning agent generates task progress, making the navigation of history operations more efficient. To retain focus content, we design a memory unit that updates with task progress. Additionally, to correct erroneous operations, the reflection agent observes the outcomes of each operation and handles any mistakes accordingly. Experimental results indicate that Mobile-Agent-v2 achieves over a 30% improvement in task completion compared to the single-agent architecture of Mobile-Agent. The code is open-sourced at https://github.com/X-PLUG/MobileAgent.
Authors: Tanvi Verma, Lukas Schwemer, Mingrui Tan, Fei Gao, Yong Liu, Huazhu Fu
Abstract: Deep learning models are widely recognized for their effectiveness in identifying medical image findings in disease classification. However, their limitations become apparent in the dynamic and ever-changing clinical environment, characterized by the continuous influx of newly annotated medical data from diverse sources. In this context, the need for continual learning becomes particularly paramount, not only to adapt to evolving medical scenarios but also to ensure the privacy of healthcare data. In our research, we emphasize the utilization of a network comprising expert classifiers, where a new expert classifier is added each time a new task is introduced. We present CTP, a task-id predictor that utilizes confidence scores, leveraging the probability distribution (logits) of the classifier to accurately determine the task-id at inference time. Logits are adjusted to ensure that classifiers yield a high-entropy distribution for data associated with tasks other than their own. By defining a noise region in the distribution and computing confidence scores, CTP achieves superior performance when compared to other relevant continual learning methods. Additionally, the performance of CTP can be further improved by providing it with a continuum of data at the time of inference.
Authors: Noga Bar, Raja Giryes
Abstract: Having large amounts of annotated data significantly impacts the effectiveness of deep neural networks. However, the annotation task can be very expensive in some domains, such as medical data. Thus, it is important to select the data to be annotated wisely, which is known as the subset selection problem. We investigate the relationship between subset selection and neural network pruning, which is more widely studied, and establish a correspondence between them. Leveraging insights from network pruning, we propose utilizing the norm criterion of neural network features to improve subset selection methods. We empirically validate our proposed strategy on various networks and datasets, demonstrating enhanced accuracy. This shows the potential of employing pruning tools for subset selection.
Authors: Eros Fan\`i, Raffaello Camoriano, Barbara Caputo, Marco Ciccone
Abstract: Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, particularly pronounced in the final classification layer, negatively impacting convergence speed and accuracy. To address this issue, we introduce Federated Recursive Ridge Regression (Fed3R). Our method fits a Ridge Regression classifier computed in closed form leveraging pre-trained features. Fed3R is immune to statistical heterogeneity and is invariant to the sampling order of the clients. Therefore, it proves particularly effective in cross-device scenarios. Furthermore, it is fast and efficient in terms of communication and computation costs, requiring up to two orders of magnitude fewer resources than the competitors. Finally, we propose to leverage the Fed3R parameters as an initialization for a softmax classifier and subsequently fine-tune the model using any FL algorithm (Fed3R with Fine-Tuning, Fed3R+FT). Our findings also indicate that maintaining a fixed classifier aids in stabilizing the training and learning more discriminative features in cross-device settings. Official website: https://fed-3r.github.io/.
Authors: Marek Wodzinski, Henning M\"uller
Abstract: Automatic prediction of fluorescently labeled organelles from label-free transmitted light input images is an important, yet difficult task. The traditional way to obtain fluorescence images is related to performing biochemical labeling which is time-consuming and costly. Therefore, an automatic algorithm to perform the task based on the label-free transmitted light microscopy could be strongly beneficial. The importance of the task motivated researchers from the France-BioImaging to organize the LightMyCells challenge where the goal is to propose an algorithm that automatically predicts the fluorescently labeled nucleus, mitochondria, tubulin, and actin, based on the input consisting of bright field, phase contrast, or differential interference contrast microscopic images. In this work, we present the contribution of the AGHSSO team based on a carefully prepared and trained encoder-decoder deep neural network that achieves a considerable score in the challenge, being placed among the best-performing teams.
Authors: Yuhan Song, Nak Young Chong
Abstract: Ultrasound imaging is pivotal in various medical diagnoses due to its non-invasive nature and safety. In clinical practice, the accuracy and precision of ultrasound image analysis are critical. Recent advancements in deep learning are showing great capacity of processing medical images. However, the data hungry nature of deep learning and the shortage of high-quality ultrasound image training data suppress the development of deep learning based ultrasound analysis methods. To address these challenges, we introduce an advanced deep learning model, dubbed S-CycleGAN, which generates high-quality synthetic ultrasound images from computed tomography (CT) data. This model incorporates semantic discriminators within a CycleGAN framework to ensure that critical anatomical details are preserved during the style transfer process. The synthetic images produced are used to augment training datasets for semantic segmentation models and robot-assisted ultrasound scanning system development, enhancing their ability to accurately parse real ultrasound imagery.
Authors: Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat, Prayag Tiwari, Stefan Byttner
Abstract: Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla gradients, which are inherently susceptible to the saturation phenomena. Despite recent enhancements have incorporated counterfactual gradient strategies as a mitigating measure, these local explanation techniques still exhibit a lack of sensitivity to their baseline parameter. Our work proposes a gradient-weighted CAM augmentation that tackles both the saturation and sensitivity problem by reshaping the gradient computation, incorporating two well-established and provably approaches: Expected Gradients and kernel smoothing. By revisiting the original formulation as the smoothed expectation of the perturbed integrated gradients, one can concurrently construct more faithful, localized and robust explanations which minimize infidelity. Through fine modulation of the perturbation distribution it is possible to regulate the complexity characteristic of the explanation, selectively discriminating stable features. Our technique, Expected Grad-CAM, differently from recent works, exclusively optimizes the gradient computation, purposefully designed as an enhanced substitute of the foundational Grad-CAM algorithm and any method built therefrom. Quantitative and qualitative evaluations have been conducted to assess the effectiveness of our method.
Authors: Pablo Arratia, Matthias Ehrhardt, Lisa Kreusser
Abstract: Image reconstruction for dynamic inverse problems with highly undersampled data poses a major challenge: not accounting for the dynamics of the process leads to a non-realistic motion with no time regularity. Variational approaches that penalize time derivatives or introduce motion model regularizers have been proposed to relate subsequent frames and improve image quality using grid-based discretization. Neural fields offer an alternative parametrization of the desired spatiotemporal quantity with a deep neural network, a lightweight, continuous, and biased towards smoothness representation. The inductive bias has been exploited to enforce time regularity for dynamic inverse problems resulting in neural fields optimized by minimizing a data-fidelity term only. In this paper we investigate and show the benefits of introducing explicit PDE-based motion regularizers, namely, the optical flow equation, in 2D+time computed tomography for the optimization of neural fields. We also compare neural fields against a grid-based solver and show that the former outperforms the latter.
Authors: Roberto Basla, Loris Giulivi, Luca Magri, Giacomo Boracchi
Abstract: Deep Learning (DL) models have been successfully applied to many applications including biomedical cell segmentation and classification in histological images. These models require large amounts of annotated data which might not always be available, especially in the medical field where annotations are scarce and expensive. To overcome this limitation, we propose a novel pipeline for generating synthetic datasets for cell segmentation. Given only a handful of annotated images, our method generates a large dataset of images which can be used to effectively train DL instance segmentation models. Our solution is designed to generate cells of realistic shapes and placement by allowing experts to incorporate domain knowledge during the generation of the dataset.
Authors: Lifeng Shen, Jincheng Yu, Hansi Yang, James T. Kwok
Abstract: Mixup and its variants form a popular class of data augmentation techniques.Using a random sample pair, it generates a new sample by linear interpolation of the inputs and labels. However, generating only one single interpolation may limit its augmentation ability. In this paper, we propose a simple yet effective extension called multi-mix, which generates multiple interpolations from a sample pair. With an ordered sequence of generated samples, multi-mix can better guide the training process than standard mixup. Moreover, theoretically, this can also reduce the stochastic gradient variance. Extensive experiments on a number of synthetic and large-scale data sets demonstrate that multi-mix outperforms various mixup variants and non-mixup-based baselines in terms of generalization, robustness, and calibration.
Authors: Martin J. Hetz, Nicolas Carl, Sarah Haggenm\"uller, Christoph Wies, Maurice Stephan Michel, Frederik Wessels, Titus J. Brinker
Abstract: Large Language Models (LLMs) are revolutionizing medical Question-Answering (medQA) through extensive use of medical literature. However, their performance is often hampered by outdated training data and a lack of explainability, which limits clinical applicability. This study aimed to create and assess UroBot, a urology-specialized chatbot, by comparing it with state-of-the-art models and the performance of urologists on urological board questions, ensuring full clinician-verifiability. UroBot was developed using OpenAI's GPT-3.5, GPT-4, and GPT-4o models, employing retrieval-augmented generation (RAG) and the latest 2023 guidelines from the European Association of Urology (EAU). The evaluation included ten runs of 200 European Board of Urology (EBU) In-Service Assessment (ISA) questions, with performance assessed by the mean Rate of Correct Answers (RoCA). UroBot-4o achieved an average RoCA of 88.4%, surpassing GPT-4o by 10.8%, with a score of 77.6%. It was also clinician-verifiable and exhibited the highest run agreement as indicated by Fleiss' Kappa (k = 0.979). By comparison, the average performance of urologists on board questions, as reported in the literature, is 68.7%. UroBot's clinician-verifiable nature and superior accuracy compared to both existing models and urologists on board questions highlight its potential for clinical integration. The study also provides the necessary code and instructions for further development of UroBot.
Authors: Baowen Zhang, Chuan Fang, Rakesh Shrestha, Yixun Liang, Xiaoxiao Long, Ping Tan
Abstract: Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods often suffer from limited shape accuracy due to the discrete and unstructured nature of Gaussian splats, which complicates the shape extraction. While recent techniques like 2D GS have attempted to improve shape reconstruction, they often reformulate the Gaussian primitives in ways that reduce both rendering quality and computational efficiency. To address these problems, our work introduces a rasterized approach to render the depth maps and surface normal maps of general 3D Gaussian splats. Our method not only significantly enhances shape reconstruction accuracy but also maintains the computational efficiency intrinsic to Gaussian Splatting. Our approach achieves a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and similar training and rendering time as traditional Gaussian Splatting on the Tanks & Temples dataset. Our method is a significant advancement in Gaussian Splatting and can be directly integrated into existing Gaussian Splatting-based methods.
Authors: Mohammad Majid al-Rifaie, Tim Blackwell
Abstract: The use of ray projections to reconstruct images is a common technique in medical imaging. Dealing with incomplete data is particularly important when a patient is vulnerable to potentially damaging radiation or is unable to cope with the long scanning time. This paper utilises the reformulation of the problem into an optimisation tasks, followed by using a swarm-based reconstruction from highly undersampled data where particles move in image space in an attempt to minimise the reconstruction error. The process is prone to noise and, in addition to the recently introduced search space expansion technique, a further smoothing process, total variation regularisation, is adapted and investigated. The proposed method is shown to produce lower reproduction errors compared to standard tomographic reconstruction toolbox algorithms as well as one of the leading high-dimensional optimisers on the clinically important Shepp-Logan phantom.
Authors: Xuelun Shen, Qian Hu, Xin Li, Cheng Wang
Abstract: This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing little computational cost during the inference stage. Another design that makes this framework different from many existing learning based pipelines that require re-training when a different keypoint detector is adopted, our network can directly work with different keypoint detectors without such a time-consuming re-training process. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods.
Authors: Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu
Abstract: Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie, the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduce a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as \textit{relation} metric, which is thus utilized to match the feature embeddings of different augmentations. To boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. The designed asymmetric predictor head and an InfoNCE warm-up strategy enhance the robustness to hyper-parameters and benefit the resulting performance. Experimental results show that our proposed ReSSL substantially outperforms the state-of-the-art methods across different network architectures, including various lightweight networks (\eg, EfficientNet and MobileNet).
Authors: Zhaowen Li, Yousong Zhu, Zhiyang Chen, Wei Li, Chaoyang Zhao, Rui Zhao, Ming Tang, Jinqiao Wang
Abstract: Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio of MIM results in two serious problems: 1) the inadequate data utilization of images within each iteration brings prolonged pre-training, and 2) the high inconsistency of predictions results in unreliable generations, $i.e.$, the prediction of the identical patch may be inconsistent in different mask rounds, leading to divergent semantics in the ultimately generated outcomes. To tackle these problems, we propose the efficient masked autoencoders with self-consistency (EMAE) to improve the pre-training efficiency and increase the consistency of MIM. In particular, we present a parallel mask strategy that divides the image into K non-overlapping parts, each of which is generated by a random mask with the same mask ratio. Then the MIM task is conducted parallelly on all parts in an iteration and the model minimizes the loss between the predictions and the masked patches. Besides, we design the self-consistency learning to further maintain the consistency of predictions of overlapping masked patches among parts. Overall, our method is able to exploit the data more efficiently and obtains reliable representations. Experiments on ImageNet show that EMAE achieves the best performance on ViT-Large with only 13% of MAE pre-training time using NVIDIA A100 GPUs. After pre-training on diverse datasets, EMAE consistently obtains state-of-the-art transfer ability on a variety of downstream tasks, such as image classification, object detection, and semantic segmentation.
Authors: Vitaliy Kinakh, Mariia Drozdova, Slava Voloshynovskiy
Abstract: We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of dependence between learnable embeddings from augmented and non-augmented views, jointly with the maximization of dependence between learnable embeddings from augmented view and multiple non-learnable representations from non-augmented view. We show that the proposed method can be used for efficient self-supervised classification and model-agnostic knowledge distillation. Unlike other self-supervised techniques, our approach does not use any contrastive learning, clustering, or stop gradients. MV-MR is a generic framework allowing the incorporation of constraints on the learnable embeddings via the usage of image multi-representations as regularizers. Along this line, knowledge distillation is considered a particular case of such a regularization. MV-MR provides the state-of-the-art performance on the STL10 and ImageNet-1K datasets among non-contrastive and clustering-free methods. We show that a lower complexity ResNet50 model pretrained using proposed knowledge distillation based on the CLIP ViT model achieves state-of-the-art performance on STL10 linear evaluation. The code is available at: https://github.com/vkinakh/mv-mr
Authors: Nobuhiko Wakai, Satoshi Sato, Yasunori Ishii, Takayoshi Yamashita
Abstract: A Manhattan world lying along cuboid buildings is useful for camera angle estimation. However, accurate and robust angle estimation from fisheye images in the Manhattan world has remained an open challenge because general scene images tend to lack constraints such as lines, arcs, and vanishing points. To achieve higher accuracy and robustness, we propose a learning-based calibration method that uses heatmap regression, which is similar to pose estimation using keypoints, to detect the directions of labeled image coordinates. Simultaneously, our two estimators recover the rotation and remove fisheye distortion by remapping from a general scene image. Without considering vanishing-point constraints, we find that additional points for learning-based methods can be defined. To compensate for the lack of vanishing points in images, we introduce auxiliary diagonal points that have the optimal 3D arrangement of spatial uniformity. Extensive experiments demonstrated that our method outperforms conventional methods on large-scale datasets and with off-the-shelf cameras.
Authors: Yunshan Zhong, Yuyao Zhou, Fei Chao, Rongrong Ji
Abstract: Arbitrary bit-width network quantization has received significant attention due to its high adaptability to various bit-width requirements during runtime. However, in this paper, we investigate existing methods and observe a significant accumulation of quantization errors caused by switching weight and activations bit-widths, leading to limited performance. To address this issue, we propose MBQuant, a novel method that utilizes a multi-branch topology for arbitrary bit-width quantization. MBQuant duplicates the network body into multiple independent branches, where the weights of each branch are quantized to a fixed 2-bit and the activations remain in the input bit-width. The computation of a desired bit-width is completed by selecting an appropriate number of branches that satisfy the original computational constraint. By fixing the weight bit-width, this approach substantially reduces quantization errors caused by switching weight bit-widths. Additionally, we introduce an amortization branch selection strategy to distribute quantization errors caused by switching activation bit-widths among branches to improve performance. Finally, we adopt an in-place distillation strategy that facilitates guidance between branches to further enhance MBQuant's performance. Extensive experiments demonstrate that MBQuant achieves significant performance gains compared to existing arbitrary bit-width quantization methods. Code is at https://github.com/zysxmu/MultiQuant.
Authors: Linli Yao, Yuanmeng Zhang, Ziheng Wang, Xinglin Hou, Tiezheng Ge, Yuning Jiang, Xu Sun, Qin Jin
Abstract: Automatically narrating videos in natural language complying with user requests, i.e. Controllable Video Captioning task, can help people manage massive videos with desired intentions. However, existing works suffer from two shortcomings: 1) the control signal is single-grained which can not satisfy diverse user intentions; 2) the video description is generated in a single round which can not be further edited to meet dynamic needs. In this paper, we propose a novel \textbf{V}ideo \textbf{C}aption \textbf{E}diting \textbf{(VCE)} task to automatically revise an existing video description guided by multi-grained user requests. Inspired by human writing-revision habits, we design the user command as a pivotal triplet \{\textit{operation, position, attribute}\} to cover diverse user needs from coarse-grained to fine-grained. To facilitate the VCE task, we \textit{automatically} construct an open-domain benchmark dataset named VATEX-EDIT and \textit{manually} collect an e-commerce dataset called EMMAD-EDIT. We further propose a specialized small-scale model (i.e., OPA) compared with two generalist Large Multi-modal Models to perform an exhaustive analysis of the novel task. For evaluation, we adopt comprehensive metrics considering caption fluency, command-caption consistency, and video-caption alignment. Experiments reveal the task challenges of fine-grained multi-modal semantics understanding and processing. Our datasets, codes, and evaluation tools are ready to be open-sourced.
Authors: Qiankun Zuo, Hao Tian, Chi-Man Pun, Hongfei Wang, Yudong Zhang, Jin Hong
Abstract: Effective connectivity can describe the causal patterns among brain regions. These patterns have the potential to reveal the pathological mechanism and promote early diagnosis and effective drug development for cognitive disease. However, the current methods utilize software toolkits to extract empirical features from brain imaging to estimate effective connectivity. These methods heavily rely on manual parameter settings and may result in large errors during effective connectivity estimation. In this paper, a novel brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment (MCI) analysis. To be specific, the proposed BIGG framework is based on the diffusion denoising probabilistic models (DDPM), where each denoising step is modeled as a generative adversarial network (GAN) to progressively translate the noise and conditional fMRI to effective connectivity. The hierarchical transformers in the generator are designed to estimate the noise at multiple scales. Each scale concentrates on both spatial and temporal information between brain regions, enabling good quality in noise removal and better inference of causal relations. Meanwhile, the transformer-based discriminator constrains the generator to further capture global and local patterns for improving high-quality and diversity generation. By introducing the diffusive factor, the denoising inference with a large sampling step size is more efficient and can maintain high-quality results for effective connectivity generation. Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model. The proposed model not only achieves superior prediction performance compared with other competing methods but also predicts MCI-related causal connections that are consistent with clinical studies.
Authors: Jingyi Zhou, Jiamu Sheng, Jiayuan Fan, Peng Ye, Tong He, Bin Wang, Tao Chen
Abstract: The effectiveness of spectral-spatial feature learning is crucial for the hyperspectral image (HSI) classification task. Diffusion models, as a new class of groundbreaking generative models, have the ability to learn both contextual semantics and textual details from the distinct timestep dimension, enabling the modeling of complex spectral-spatial relations in HSIs. However, existing diffusion-based HSI classification methods only utilize manually selected single-timestep single-stage features, limiting the full exploration and exploitation of rich contextual semantics and textual information hidden in the diffusion model. To address this issue, we propose a novel diffusion-based feature learning framework that explores Multi-Timestep Multi-Stage Diffusion features for HSI classification for the first time, called MTMSD. Specifically, the diffusion model is first pretrained with unlabeled HSI patches to mine the connotation of unlabeled data, and then is used to extract the multi-timestep multi-stage diffusion features. To effectively and efficiently leverage multi-timestep multi-stage features,two strategies are further developed. One strategy is class & timestep-oriented multi-stage feature purification module with the inter-class and inter-timestep prior for reducing the redundancy of multi-stage features and alleviating memory constraints. The other one is selective timestep feature fusion module with the guidance of global features to adaptively select different timestep features for integrating texture and semantics. Both strategies facilitate the generality and adaptability of the MTMSD framework for diverse patterns of different HSI data. Extensive experiments are conducted on four public HSI datasets, and the results demonstrate that our method outperforms state-of-the-art methods for HSI classification, especially on the challenging Houston 2018 dataset.
Authors: Weiliang Chen, Qianqian Ren, Jinbao Li
Abstract: Representing urban regions accurately and comprehensively is essential for various urban planning and analysis tasks. Recently, with the expansion of the city, modeling long-range spatial dependencies with multiple data sources plays an important role in urban region representation. In this paper, we propose the Attentive Graph Enhanced Region Representation Learning (ATGRL) model, which aims to capture comprehensive dependencies from multiple graphs and learn rich semantic representations of urban regions. Specifically, we propose a graph-enhanced learning module to construct regional graphs by incorporating mobility flow patterns, point of interests (POIs) functions, and check-in semantics with noise filtering. Then, we present a multi-graph aggregation module to capture both local and global spatial dependencies between regions by integrating information from multiple graphs. In addition, we design a dual-stage fusion module to facilitate information sharing between different views and efficiently fuse multi-view representations for urban region embedding using an improved linear attention mechanism. Finally, extensive experiments on real-world datasets for three downstream tasks demonstrate the superior performance of our model compared to state-of-the-art methods.
Authors: Shilong Zhang, Peize Sun, Shoufa Chen, Min Xiao, Wenqi Shao, Wenwei Zhang, Yu Liu, Kai Chen, Ping Luo
Abstract: Visual instruction tuning large language model(LLM) on image-text pairs has achieved general-purpose vision-language abilities. However, the lack of region-text pairs limits their advancements to fine-grained multimodal understanding. In this paper, we propose spatial instruction tuning, which introduces the reference to the region-of-interest(RoI) in the instruction. Before sending to LLM, the reference is replaced by RoI features and interleaved with language embeddings as a sequence. Our model GPT4RoI, trained on 7 region-text pair datasets, brings an unprecedented interactive and conversational experience compared to previous image-level models. (1) Interaction beyond language: Users can interact with our model by both language and drawing bounding boxes to flexibly adjust the referring granularity. (2) Versatile multimodal abilities: A variety of attribute information within each RoI can be mined by GPT4RoI, e.g., color, shape, material, action, etc. Furthermore, it can reason about multiple RoIs based on common sense. On the Visual Commonsense Reasoning(VCR) dataset, GPT4RoI achieves a remarkable accuracy of 81.6%, surpassing all existing models by a significant margin (the second place is 75.6%) and almost reaching human-level performance of 85.0%. The code, dataset, and demo can be found at https://github.com/jshilong/GPT4RoI.
Authors: Jiang-Xin Shi, Tong Wei, Zhi Zhou, Jie-Jing Shao, Xin-Yan Han, Yu-Feng Li
Abstract: The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified. In this paper, we disclose that heavy fine-tuning may even lead to non-negligible performance deterioration on tail classes, and lightweight fine-tuning is more effective. The reason is attributed to inconsistent class conditions caused by heavy fine-tuning. With the observation above, we develop a low-complexity and accurate long-tail learning algorithms LIFT with the goal of facilitating fast prediction and compact models by adaptive lightweight fine-tuning. Experiments clearly verify that both the training time and the learned parameters are significantly reduced with more accurate predictive performance compared with state-of-the-art approaches. The implementation code is available at https://github.com/shijxcs/LIFT.
Authors: Avinash Paliwal, Brandon Nguyen, Andrii Tsarov, Nima Khademi Kalantari
Abstract: In recent years, novel view synthesis from a single image has seen significant progress thanks to the rapid advancements in 3D scene representation and image inpainting techniques. While the current approaches are able to synthesize geometrically consistent novel views, they often do not handle the view-dependent effects properly. Specifically, the highlights in their synthesized images usually appear to be glued to the surfaces, making the novel views unrealistic. To address this major problem, we make a key observation that the process of synthesizing novel views requires changing the shading of the pixels based on the novel camera, and moving them to appropriate locations. Therefore, we propose to split the view synthesis process into two independent tasks of pixel reshading and relocation. During the reshading process, we take the single image as the input and adjust its shading based on the novel camera. This reshaded image is then used as the input to an existing view synthesis method to relocate the pixels and produce the final novel view image. We propose to use a neural network to perform reshading and generate a large set of synthetic input-reshaded pairs to train our network. We demonstrate that our approach produces plausible novel view images with realistic moving highlights on a variety of real world scenes.
Authors: Masoud Taghikhah, Nishant Kumar, Sini\v{s}a \v{S}egvi\'c, Abouzar Eslami, Stefan Gumhold
Abstract: Discriminative learning effectively predicts true object class for image classification. However, it often results in false positives for outliers, posing critical concerns in applications like autonomous driving and video surveillance systems. Previous attempts to address this challenge involved training image classifiers through contrastive learning using actual outlier data or synthesizing outliers for self-supervised learning. Furthermore, unsupervised generative modeling of inliers in pixel space has shown limited success for outlier detection. In this work, we introduce a quantile-based maximum likelihood objective for learning the inlier distribution to improve the outlier separation during inference. Our approach fits a normalizing flow to pre-trained discriminative features and detects the outliers according to the evaluated log-likelihood. The experimental evaluation demonstrates the effectiveness of our method as it surpasses the performance of the state-of-the-art unsupervised methods for outlier detection. The results are also competitive compared with a recent self-supervised approach for outlier detection. Our work allows to reduce dependency on well-sampled negative training data, which is especially important for domains like medical diagnostics or remote sensing.
Authors: Zhaohui Zheng, Yuming Chen, Qibin Hou, Xiang Li, Ping Wang, Ming-Ming Cheng
Abstract: A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders. For a long time, there has been a lack of effective ways to measure and identify spatial bias, and little is known about where it comes from and what degree it is. To this end, we present a new zone evaluation protocol, extending from the traditional evaluation to a more generalized one, which measures the detection performance over zones, yielding a series of Zone Precisions (ZPs). For the first time, we provide numerical results, showing that the object detectors perform quite unevenly across the zones. Surprisingly, the detector's performance in the 96% border zone of the image does not reach the AP value (Average Precision, commonly regarded as the average detection performance in the entire image zone). To better understand spatial bias, a series of heuristic experiments are conducted. Our investigation excludes two intuitive conjectures about spatial bias that the object scale and the absolute positions of objects barely influence the spatial bias. We find that the key lies in the human-imperceptible divergence in data patterns between objects in different zones, thus eventually forming a visible performance gap between the zones. With these findings, we finally discuss a future direction for object detection, namely, spatial disequilibrium problem, aiming at pursuing a balanced detection ability over the entire image zone. By broadly evaluating 10 popular object detectors and 5 detection datasets, we shed light on the spatial bias of object detectors. We hope this work could raise a focus on detection robustness. The source codes, evaluation protocols, and tutorials are publicly available at https://github.com/Zzh-tju/ZoneEval.
Authors: Chau Pham, Truong Vu, Khoi Nguyen
Abstract: This paper addresses the challenging problem of open-vocabulary object detection (OVOD) where an object detector must identify both seen and unseen classes in test images without labeled examples of the unseen classes in training. A typical approach for OVOD is to use joint text-image embeddings of CLIP to assign box proposals to their closest text label. However, this method has a critical issue: many low-quality boxes, such as over- and under-covered-object boxes, have the same similarity score as high-quality boxes since CLIP is not trained on exact object location information. To address this issue, we propose a novel method, LP-OVOD, that discards low-quality boxes by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text. Experimental results on COCO affirm the superior performance of our approach over the state of the art, achieving $\textbf{40.5}$ in $\text{AP}_{novel}$ using ResNet50 as the backbone and without external datasets or knowing novel classes during training. Our code will be available at https://github.com/VinAIResearch/LP-OVOD.
Authors: Dongkyun Kim, Mingi Kwon, Youngjung Uh
Abstract: When the training dataset comprises a 1:1 proportion of dogs to cats, a generative model that produces 1:1 dogs and cats better resembles the training species distribution than another model with 3:1 dogs and cats. Can we capture this phenomenon using existing metrics? Unfortunately, we cannot, because these metrics do not provide any interpretability beyond "diversity". In this context, we propose a new evaluation protocol that measures the divergence of a set of generated images from the training set regarding the distribution of attribute strengths as follows. Single-attribute Divergence (SaD) measures the divergence regarding PDFs of a single attribute. Paired-attribute Divergence (PaD) measures the divergence regarding joint PDFs of a pair of attributes. They provide which attributes the models struggle. For measuring the attribute strengths of an image, we propose Heterogeneous CLIPScore (HCS) which measures the cosine similarity between image and text vectors with heterogeneous initial points. With SaD and PaD, we reveal the following about existing generative models. ProjectedGAN generates implausible attribute relationships such as a baby with a beard even though it has competitive scores of existing metrics. Diffusion models struggle to capture diverse colors in the datasets. The larger sampling timesteps of latent diffusion model generate the more minor objects including earrings and necklaces. Stable Diffusion v1.5 better captures the attributes than v2.1. Our metrics lay a foundation for explainable evaluations of generative models.
Authors: Ali Javidani, Mohammad Amin Sadeghi, Babak Nadjar Araabi
Abstract: Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This integration allows for the simultaneous analysis of local and global visual features, thereby enriching the quality of the learned representations. Initially, the original images undergo spatial augmentation. Subsequently, we employ a distinctive photometric patch-level augmentation, where each patch is individually augmented, independent from other patches within the same view. This approach generates a diverse training dataset with distinct color variations in each segment. The augmented images are then processed through a self-distillation learning framework, utilizing the Vision Transformer (ViT) as its backbone. The proposed method minimizes the representation distances across both image and patch levels to capture details from macro to micro perspectives. To this end, we present a simple yet effective patch-matching algorithm to find the corresponding patches across the augmented views. Thanks to the efficient structure of the patch-matching algorithm, our method reduces computational complexity compared to similar approaches. Consequently, we achieve an advanced understanding of the model without adding significant computational requirements. We have extensively pretrained our method on datasets of varied scales, such as Cifar10, ImageNet-100, and ImageNet-1K. It demonstrates superior performance over state-of-the-art self-supervised representation learning methods in image classification and downstream tasks, such as copy detection and image retrieval. The implementation of our method is accessible on GitHub.
Authors: Hanoona Rasheed, Muhammad Maaz, Sahal Shaji Mullappilly, Abdelrahman Shaker, Salman Khan, Hisham Cholakkal, Rao M. Anwer, Erix Xing, Ming-Hsuan Yang, Fahad S. Khan
Abstract: Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object category at a time, require users to specify the regions, or cannot offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM not only grounds objects appearing in the conversations but is flexible enough to accept both textual and optional visual prompts (region of interest) as input. This empowers users to interact with the model at various levels of granularity, both in textual and visual domains. Due to the lack of standard benchmarks for the novel setting of visually Grounded Conversation Generation (GCG), we introduce a comprehensive evaluation protocol with our curated grounded conversations. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale. To this end, we propose a densely annotated Grounding-anything Dataset (GranD) using our proposed automated annotation pipeline that encompasses 7.5M unique concepts grounded in a total of 810M regions available with segmentation masks. Besides GCG, GLaMM also performs effectively on several downstream tasks, e.g., referring expression segmentation, image and region-level captioning and vision-language conversations.
Authors: Chong Zhong, Yang Li, Danjuan Yang, Meiyan Li, Xingyao Zhou, Bo Fu, Catherine C. Liu, A. H. Welsh
Abstract: Ultra-widefield (UWF) fundus images are replacing traditional fundus images in screening, detection, prediction, and treatment of complications related to myopia because their much broader visual range is advantageous for highly myopic eyes. Spherical equivalent (SE) is extensively used as the main myopia outcome measure, and axial length (AL) has drawn increasing interest as an important ocular component for assessing myopia. Cutting-edge studies show that SE and AL are strongly correlated. Using the joint information from SE and AL is potentially better than using either separately. In the deep learning community, though there is research on multiple-response tasks with a 3D image biomarker, dependence among responses is only sporadically taken into consideration. Inspired by the spirit that information extracted from the data by statistical methods can improve the prediction accuracy of deep learning models, we formulate a class of multivariate response regression models with a higher-order tensor biomarker, for the bivariate tasks of regression-classification and regression-regression. Specifically, we propose a copula-enhanced convolutional neural network (CeCNN) framework that incorporates the dependence between responses through a Gaussian copula (with parameters estimated from a warm-up CNN) and uses the induced copula-likelihood loss with the backbone CNNs. We establish the statistical framework and algorithms for the aforementioned two bivariate tasks. We show that the CeCNN has better prediction accuracy after adding the dependency information to the backbone models. The modeling and the proposed CeCNN algorithm are applicable beyond the UWF scenario and can be effective with other backbones beyond ResNet and LeNet.
Authors: Ayush Kumar Shah, Bryan Manrique Amador, Abhisek Dey, Ming Creekmore, Blake Ocampo, Scott Denmark, Richard Zanibbi
Abstract: Most molecular diagram parsers recover chemical structure from raster images (e.g., PNGs). However, many PDFs include commands giving explicit locations and shapes for characters, lines, and polygons. We present a new parser that uses these born-digital PDF primitives as input. The parsing model is fast and accurate, and does not require GPUs, Optical Character Recognition (OCR), or vectorization. We use the parser to annotate raster images and then train a new multi-task neural network for recognizing molecules in raster images. We evaluate our parsers using SMILES and standard benchmarks, along with a novel evaluation protocol comparing molecular graphs directly that supports automatic error compilation and reveals errors missed by SMILES-based evaluation. On the synthetic USPTO benchmark, our born-digital parser obtains a recognition rate of 98.4% (1% higher than previous models) and our relatively simple neural parser for raster images obtains a rate of 85% using less training data than existing neural approaches (thousands vs. millions of molecules).
Authors: Nicolas Bourriez, Ihab Bendidi, Ethan Cohen, Gabriel Watkinson, Maxime Sanchez, Guillaume Bollot, Auguste Genovesio
Abstract: Unlike color photography images, which are consistently encoded into RGB channels, biological images encompass various modalities, where the type of microscopy and the meaning of each channel varies with each experiment. Importantly, the number of channels can range from one to a dozen and their correlation is often comparatively much lower than RGB, as each of them brings specific information content. This aspect is largely overlooked by methods designed out of the bioimage field, and current solutions mostly focus on intra-channel spatial attention, often ignoring the relationship between channels, yet crucial in most biological applications. Importantly, the variable channel type and count prevent the projection of several experiments to a unified representation for large scale pre-training. In this study, we propose ChAda-ViT, a novel Channel Adaptive Vision Transformer architecture employing an Inter-Channel Attention mechanism on images with an arbitrary number, order and type of channels. We also introduce IDRCell100k, a bioimage dataset with a rich set of 79 experiments covering 7 microscope modalities, with a multitude of channel types, and counts varying from 1 to 10 per experiment. Our architecture, trained in a self-supervised manner, outperforms existing approaches in several biologically relevant downstream tasks. Additionally, it can be used to bridge the gap for the first time between assays with different microscopes, channel numbers or types by embedding various image and experimental modalities into a unified biological image representation. The latter should facilitate interdisciplinary studies and pave the way for better adoption of deep learning in biological image-based analyses. Code and Data available at https://github.com/nicoboou/chadavit.
Authors: Daeun Lee, Minhyeok Heo, Jiwon Kim
Abstract: Lane detection is a vital task for vehicles to navigate and localize their position on the road. To ensure reliable driving, lane detection models must have robust generalization performance in various road environments. However, despite the advanced performance in the trained domain, their generalization performance still falls short of expectations due to the domain discrepancy. To bridge this gap, we propose a novel generative framework using HD Maps for Single-Source Domain Generalization (SSDG) in lane detection. We first generate numerous front-view images from lane markings of HD Maps. Next, we strategically select a core subset among the generated images using (i) lane structure and (ii) road surrounding criteria to maximize their diversity. In the end, utilizing this core set, we train lane detection models to boost their generalization performance. We validate that our generative framework from HD Maps outperforms the Domain Adaptation model MLDA with +3.01%p accuracy improvement, even though we do not access the target domain images.
Authors: Zhihe Lu, Jiawang Bai, Xin Li, Zeyu Xiao, Xinchao Wang
Abstract: Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performance advancements are limited when relying solely on intricate algorithmic designs for a single model, even one exhibiting strong performance, e.g., CLIP-ViT-B/16. This paper, for the first time, explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model. The affirmative findings motivate us to address the generalization problem from a novel perspective, i.e., ensemble of pre-trained VLMs. We introduce three customized ensemble strategies, each tailored to one specific scenario. Firstly, we introduce the zero-shot ensemble, automatically adjusting the logits of different models based on their confidence when only pre-trained VLMs are available. Furthermore, for scenarios with extra few-shot samples, we propose the training-free and tuning ensemble, offering flexibility based on the availability of computing resources. The proposed ensemble strategies are evaluated on zero-shot, base-to-new, and cross-dataset generalization, achieving new state-of-the-art performance. Notably, this work represents an initial stride toward enhancing the generalization performance of VLMs via ensemble. The code is available at https://github.com/zhiheLu/Ensemble_VLM.git.
Authors: Jinsong Zhang, Minjie Zhu, Yuxiang Zhang, Yebin Liu, Kun Li
Abstract: This paper addresses the problem of generating whole-body motion from speech. Despite great successes, prior methods still struggle to produce reasonable and diverse whole-body motions from speech. This is due to their reliance on suboptimal representations and a lack of strategies for generating diverse results. To address these challenges, we present a novel hybrid point representation to achieve accurate and continuous motion generation, e.g., avoiding foot skating, and this representation can be transformed into an easy-to-use representation, i.e., SMPL-X body mesh, for many applications. To generate whole-body motion from speech, for facial motion, closely tied to the audio signal, we introduce an encoder-decoder architecture to achieve deterministic outcomes. However, for the body and hands, which have weaker connections to the audio signal, we aim to generate diverse yet reasonable motions. To boost diversity in motion generation, we propose a contrastive motion learning method to encourage the model to produce more distinctive representations. Specifically, we design a robust VQ-VAE to learn a quantized motion codebook using our hybrid representation. Then, we regress the motion representation from the audio signal by a translation model employing our contrastive motion learning method. Experimental results validate the superior performance and the correctness of our model. The project page is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.
URLs: http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.
Authors: Maximilian Augustin, Yannic Neuhaus, Matthias Hein
Abstract: While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for safety-critical tasks the black-box nature of their decisions is problematic, and explanations or at least methods which make decisions plausible are needed urgently. In this paper, we address these problems by generating images that optimize a classifier-derived objective using a framework for guided image generation. We analyze the decisions of image classifiers by visual counterfactual explanations (VCEs), detection of systematic mistakes by analyzing images where classifiers maximally disagree, and visualization of neurons and spurious features. In this way, we validate existing observations, e.g. the shape bias of adversarially robust models, as well as novel failure modes, e.g. systematic errors of zero-shot CLIP classifiers. Moreover, our VCEs outperform previous work while being more versatile.
Authors: Wolfgang Hoegele
Abstract: Background: Pose estimation of rigid objects is a practical challenge in optical metrology and computer vision. This paper presents a novel stochastic-geometrical modeling framework for object pose estimation based on observing multiple feature points. Methods: This framework utilizes mixture models for feature point densities in object space and for interpreting real measurements. Advantages are the avoidance to resolve individual feature correspondences and to incorporate correct stochastic dependencies in multi-view applications. First, the general modeling framework is presented, second, a general algorithm for pose estimation is derived, and third, two example models (camera and lateration setup) are presented. Results: Numerical experiments show the effectiveness of this modeling and general algorithm by presenting four simulation scenarios for three observation systems, including the dependence on measurement resolution, object deformations and measurement noise. Probabilistic modeling utilizing mixture models shows the potential for accurate and robust pose estimations while avoiding the correspondence problem.
Authors: Yu Deng, Duomin Wang, Xiaohang Ren, Xingyu Chen, Baoyuan Wang
Abstract: Existing one-shot 4D head synthesis methods usually learn from monocular videos with the aid of 3DMM reconstruction, yet the latter is evenly challenging which restricts them from reasonable 4D head synthesis. We present a method to learn one-shot 4D head synthesis via large-scale synthetic data. The key is to first learn a part-wise 4D generative model from monocular images via adversarial learning, to synthesize multi-view images of diverse identities and full motions as training data; then leverage a transformer-based animatable triplane reconstructor to learn 4D head reconstruction using the synthetic data. A novel learning strategy is enforced to enhance the generalizability to real images by disentangling the learning process of 3D reconstruction and reenactment. Experiments demonstrate our superiority over the prior art.
Authors: Chinmay Savadikar, Xi Song, Tianfu Wu
Abstract: We present Generative Interpretable Fine-Tuning (GIFT) for parameter-efficient fine-tuning of pretrained Transformer backbones, which can be formulated as a simple factorized matrix multiplication in the parameter space or equivalently in the activation space, and thus embraces built-in interpretability. For a pretrained layer with weights $\omega\in \mathbb{R}^{d_{out}\times d_{in}}$, our proposed GIFT learns the fine-tuned weights $\hat{\omega}$ directly from $\omega$ as $\hat{\omega}=\omega \cdot (\mathbb{I}+\phi_{d_{in}\times r}\cdot \psi_{r\times d_{in}})$ where $\mathbb{I}$ is an identity matrix. $\Theta=(\phi, \psi)$ are the learnable parameters of the two linear layers of GIFT with $r$ being a hyper-parameter. $\Theta$ is shared by all the layers selected for fine-tuning, resulting in significantly fewer trainable parameters compared to Low-Rank Adaptation (LoRA). We perform comprehensive evaluations on natural language tasks (commonsense reasoning and sequence classification) and computer vision tasks (visual fine-grained classification). We obtain the best accuracy and parameter efficiency among baselines both on the Commonsense170k reasoning benchmark using LLaMA-1 (7B) and Llama-2 (7B)/-3 (8B) and on the FGVC and VTAB visual recognition benchmarks using ImageNet-21k pretrained Vision Transformer (ViT-B/16). Notably, we obtain 5.9% absolute increase in average accuracy with 53.8 times reduction of parameters on Commonsense170k using Llama-3 (8B) compared to LoRA. We obtain performance comparable to LoRA on the GLUE benchmark but with significantly fewer parameters using RoBERTa-Base/Large. We show the output of the first linear layer (i.e., $\omega\cdot \phi$) is surprisingly interpretable, which can play the role of a token-clustering head as a by-product to localize meaningful objects/parts in images for computer vision tasks. Our code is publicly available.
Authors: Zhiqi Li, Zhiding Yu, Shiyi Lan, Jiahan Li, Jan Kautz, Tong Lu, Jose M. Alvarez
Abstract: End-to-end autonomous driving recently emerged as a promising research direction to target autonomy from a full-stack perspective. Along this line, many of the latest works follow an open-loop evaluation setting on nuScenes to study the planning behavior. In this paper, we delve deeper into the problem by conducting thorough analyses and demystifying more devils in the details. We initially observed that the nuScenes dataset, characterized by relatively simple driving scenarios, leads to an under-utilization of perception information in end-to-end models incorporating ego status, such as the ego vehicle's velocity. These models tend to rely predominantly on the ego vehicle's status for future path planning. Beyond the limitations of the dataset, we also note that current metrics do not comprehensively assess the planning quality, leading to potentially biased conclusions drawn from existing benchmarks. To address this issue, we introduce a new metric to evaluate whether the predicted trajectories adhere to the road. We further propose a simple baseline able to achieve competitive results without relying on perception annotations. Given the current limitations on the benchmark and metrics, we suggest the community reassess relevant prevailing research and be cautious whether the continued pursuit of state-of-the-art would yield convincing and universal conclusions. Code and models are available at \url{https://github.com/NVlabs/BEV-Planner}
Authors: Xinshun Wang, Zhongbin Fang, Xia Li, Xiangtai Li, Mengyuan Liu
Abstract: In-context learning provides a new perspective for multi-task modeling for vision and NLP. Under this setting, the model can perceive tasks from prompts and accomplish them without any extra task-specific head predictions or model fine-tuning. However, Skeleton sequence modeling via in-context learning remains unexplored. Directly applying existing in-context models from other areas onto skeleton sequences fails due to the inter-frame and cross-task pose similarity that makes it outstandingly hard to perceive the task correctly from a subtle context. To address this challenge, we propose Skeleton-in-Context (SiC), an effective framework for in-context skeleton sequence modeling. Our SiC is able to handle multiple skeleton-based tasks simultaneously after a single training process and accomplish each task from context according to the given prompt. It can further generalize to new, unseen tasks according to customized prompts. To facilitate context perception, we additionally propose a task-unified prompt, which adaptively learns tasks of different natures, such as partial joint-level generation, sequence-level prediction, or 2D-to-3D motion prediction. We conduct extensive experiments to evaluate the effectiveness of our SiC on multiple tasks, including motion prediction, pose estimation, joint completion, and future pose estimation. We also evaluate its generalization capability on unseen tasks such as motion-in-between. These experiments show that our model achieves state-of-the-art multi-task performance and even outperforms single-task methods on certain tasks.
Authors: Zuyao Chen, Jinlin Wu, Zhen Lei, Zhaoxiang Zhang, Changwen Chen
Abstract: Training Scene Graph Generation (SGG) models with natural language captions has become increasingly popular due to the abundant, cost-effective, and open-world generalization supervision signals that natural language offers. However, such unstructured caption data and its processing pose significant challenges in learning accurate and comprehensive scene graphs. The challenges can be summarized as three aspects: 1) traditional scene graph parsers based on linguistic representation often fail to extract meaningful relationship triplets from caption data. 2) grounding unlocalized objects of parsed triplets will meet ambiguity issues in visual-language alignment. 3) caption data typically are sparse and exhibit bias to partial observations of image content. Aiming to address these problems, we propose a divide-and-conquer strategy with a novel framework named \textit{GPT4SGG}, to obtain more accurate and comprehensive scene graph signals. This framework decomposes a complex scene into a bunch of simple regions, resulting in a set of region-specific narratives. With these region-specific narratives (partial observations) and a holistic narrative (global observation) for an image, a large language model (LLM) performs the relationship reasoning to synthesize an accurate and comprehensive scene graph. Experimental results demonstrate \textit{GPT4SGG} significantly improves the performance of SGG models trained on image-caption data, in which the ambiguity issue and long-tail bias have been well-handled with more accurate and comprehensive scene graphs.
Authors: Shoufa Chen, Mengmeng Xu, Jiawei Ren, Yuren Cong, Sen He, Yanping Xie, Animesh Sinha, Ping Luo, Tao Xiang, Juan-Manuel Perez-Rua
Abstract: In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain primarily utilizes CNN-based U-Net architectures, particularly in diffusion-based models. We introduce GenTron, a family of Generative models employing Transformer-based diffusion, to address this gap. Our initial step was to adapt Diffusion Transformers (DiTs) from class to text conditioning, a process involving thorough empirical exploration of the conditioning mechanism. We then scale GenTron from approximately 900M to over 3B parameters, observing significant improvements in visual quality. Furthermore, we extend GenTron to text-to-video generation, incorporating novel motion-free guidance to enhance video quality. In human evaluations against SDXL, GenTron achieves a 51.1% win rate in visual quality (with a 19.8% draw rate), and a 42.3% win rate in text alignment (with a 42.9% draw rate). GenTron also excels in the T2I-CompBench, underscoring its strengths in compositional generation. We believe this work will provide meaningful insights and serve as a valuable reference for future research.
Authors: Quoc-Huy Trinh, Nhat-Tan Bui, Dinh-Hieu Hoang, Phuoc-Thao Vo Thi, Hai-Dang Nguyen, Debesh Jha, Ulas Bagci, Ngan Le, Minh-Triet Tran
Abstract: Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining clothing data consistency and handling clothing change data, they still rely excessively on clothing information, which can limit performance due to the dynamic nature of human appearances. To mitigate this challenge, we propose the Pose-Guidance Deep Supervision (PGDS), an effective framework for learning pose guidance within the Re-ID task. It consists of three modules: a human encoder, a pose encoder, and a Pose-to-Human Projection module (PHP). Our framework guides the human encoder, i.e., the main re-identification model, with pose information from the pose encoder through multiple layers via the knowledge transfer mechanism from the PHP module, helping the human encoder learn body parts information without increasing computation resources in the inference stage. Through extensive experiments, our method surpasses the performance of current state-of-the-art methods, demonstrating its robustness and effectiveness for real-world applications. Our code is available at https://github.com/huyquoctrinh/PGDS.
Authors: Abdelrahman Eldesokey, Peter Wonka
Abstract: We propose a zero-shot approach for generating consistent videos of animated characters based on Text-to-Image (T2I) diffusion models. Existing Text-to-Video (T2V) methods are expensive to train and require large-scale video datasets to produce diverse characters and motions. At the same time, their zero-shot alternatives fail to produce temporally consistent videos with continuous motion. We strive to bridge this gap, and we introduce LatentMan, which leverages existing text-based motion diffusion models to generate diverse continuous motions to guide the T2I model. To boost the temporal consistency, we introduce the Spatial Latent Alignment module that exploits cross-frame dense correspondences that we compute to align the latents of the video frames. Furthermore, we propose Pixel-Wise Guidance to steer the diffusion process in a direction that minimizes visual discrepancies between frames. Our proposed approach outperforms existing zero-shot T2V approaches in generating videos of animated characters in terms of pixel-wise consistency and user preference. Project page https://abdo-eldesokey.github.io/latentman/.
Authors: Candi Zheng, Yuan Lan
Abstract: Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.
Authors: Haeyong Kang, Jaehong Yoon, Sung Ju Hwang, Chang D. Yoo
Abstract: Inspired by the Lottery Ticket Hypothesis (LTH), which highlights the existence of efficient subnetworks within larger, dense networks, a high-performing Winning Subnetwork (WSN) in terms of task performance under appropriate sparsity conditions is considered for various continual learning tasks. It leverages pre-existing weights from dense networks to achieve efficient learning in Task Incremental Learning (TIL) and Task-agnostic Incremental Learning (TaIL) scenarios. In Few-Shot Class Incremental Learning (FSCIL), a variation of WSN referred to as the Soft subnetwork (SoftNet) is designed to prevent overfitting when the data samples are scarce. Furthermore, the sparse reuse of WSN weights is considered for Video Incremental Learning (VIL). The use of Fourier Subneural Operator (FSO) within WSN is considered. It enables compact encoding of videos and identifies reusable subnetworks across varying bandwidths. We have integrated FSO into different architectural frameworks for continual learning, including VIL, TIL, and FSCIL. Our comprehensive experiments demonstrate FSO's effectiveness, significantly improving task performance at various convolutional representational levels. Specifically, FSO enhances higher-layer performance in TIL and FSCIL and lower-layer performance in VIL.
Authors: Wenhao Xu, Rongtao Xu, Changwei Wang, Shibiao Xu, Li Guo, Man Zhang, Xiaopeng Zhang
Abstract: Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes. Code is available at:https://github.com/clearxu/SPT.
Authors: Max Ku, Dongfu Jiang, Cong Wei, Xiang Yue, Wenhu Chen
Abstract: In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIEScore, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIEScore leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIEScore on seven prominent tasks in conditional image tasks and found: (1) VIEScore (GPT4-o) achieves a high Spearman correlation of 0.4 with human evaluations, while the human-to-human correlation is 0.45. (2) VIEScore (with open-source MLLM) is significantly weaker than GPT-4o and GPT-4v in evaluating synthetic images. (3) VIEScore achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIEScore shows its great potential to replace human judges in evaluating image synthesis tasks.
Authors: Zheng Ding, Xuaner Zhang, Zhuowen Tu, Zhihao Xia
Abstract: The inherent generative power of denoising diffusion models makes them well-suited for image restoration tasks where the objective is to find the optimal high-quality image within the generative space that closely resembles the input image. We propose a method to adapt a pretrained diffusion model for image restoration by simply adding noise to the input image to be restored and then denoise. Our method is based on the observation that the space of a generative model needs to be constrained. We impose this constraint by finetuning the generative model with a set of anchor images that capture the characteristics of the input image. With the constrained space, we can then leverage the sampling strategy used for generation to do image restoration. We evaluate against previous methods and show superior performances on multiple real-world restoration datasets in preserving identity and image quality. We also demonstrate an important and practical application on personalized restoration, where we use a personal album as the anchor images to constrain the generative space. This approach allows us to produce results that accurately preserve high-frequency details, which previous works are unable to do. Project webpage: https://gen2res.github.io.
Authors: Parham Zilouchian Moghaddam, Mehdi Modarressi, Mohammad Amin Sadeghi
Abstract: Video content has experienced a surge in popularity, asserting its dominance over internet traffic and Internet of Things (IoT) networks. Video compression has long been regarded as the primary means of efficiently managing the substantial multimedia traffic generated by video-capturing devices. Nevertheless, video compression algorithms entail significant computational demands in order to achieve substantial compression ratios. This complexity presents a formidable challenge when implementing efficient video coding standards in resource-constrained embedded systems, such as IoT edge node cameras. To tackle this challenge, this paper introduces NU-Class Net, an innovative deep-learning model designed to mitigate compression artifacts stemming from lossy compression codecs. This enhancement significantly elevates the perceptible quality of low-bit-rate videos. By employing the NU-Class Net, the video encoder within the video-capturing node can reduce output quality, thereby generating low-bit-rate videos and effectively curtailing both computation and bandwidth requirements at the edge. On the decoder side, which is typically less encumbered by resource limitations, NU-Class Net is applied after the video decoder to compensate for artifacts and approximate the quality of the original video. Experimental results affirm the efficacy of the proposed model in enhancing the perceptible quality of videos, especially those streamed at low bit rates.
Authors: Erik Isai Valle Salgado, Chen Li, Yaqi Han, Linchao Shi, Xinghui Li
Abstract: Ensemble methods exploit the availability of a given number of classifiers or detectors trained in single or multiple source domains and tasks to address machine learning problems such as domain adaptation or multi-source transfer learning. Existing research measures the domain distance between the sources and the target dataset, trains multiple networks on the same data with different samples per class, or combines predictions from models trained under varied hyperparameters and settings. Their solutions enhanced the performance on small or tail categories but hurt the rest. To this end, we propose a modified consensus focus for semi-supervised and long-tailed object detection. We introduce a voting system based on source confidence that spots the contribution of each model in a consensus, lets the user choose the relevance of each class in the target label space so that it relaxes minority bounding boxes suppression, and combines multiple models' results without discarding the poisonous networks. Our tests on synthetic driving datasets retrieved higher confidence and more accurate bounding boxes than the NMS, soft-NMS, and WBF. The code used to generate the results is available in our GitHub repository: http://github.com/ErikValle/Consensus-focus-for-object-detection.
URLs: http://github.com/ErikValle/Consensus-focus-for-object-detection.
Authors: Yifan Gong, Zheng Zhan, Qing Jin, Yanyu Li, Yerlan Idelbayev, Xian Liu, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, Jian Ren
Abstract: One highly promising direction for enabling flexible real-time on-device image editing is utilizing data distillation by leveraging large-scale text-to-image diffusion models to generate paired datasets used for training generative adversarial networks (GANs). This approach notably alleviates the stringent requirements typically imposed by high-end commercial GPUs for performing image editing with diffusion models. However, unlike text-to-image diffusion models, each distilled GAN is specialized for a specific image editing task, necessitating costly training efforts to obtain models for various concepts. In this work, we introduce and address a novel research direction: can the process of distilling GANs from diffusion models be made significantly more efficient? To achieve this goal, we propose a series of innovative techniques. First, we construct a base GAN model with generalized features, adaptable to different concepts through fine-tuning, eliminating the need for training from scratch. Second, we identify crucial layers within the base GAN model and employ Low-Rank Adaptation (LoRA) with a simple yet effective rank search process, rather than fine-tuning the entire base model. Third, we investigate the minimal amount of data necessary for fine-tuning, further reducing the overall training time. Extensive experiments show that we can efficiently empower GANs with the ability to perform real-time high-quality image editing on mobile devices with remarkably reduced training and storage costs for each concept.
Authors: Yuhao Wang, Yusheng Liao, Heyang Liu, Hongcheng Liu, Yu Wang, Yanfeng Wang
Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in visual perception and understanding. However, these models also suffer from hallucinations, which limit their reliability as AI systems. We believe that these hallucinations are partially due to the models' struggle with understanding what they can and cannot perceive from images, a capability we refer to as self-awareness in perception. Despite its importance, this aspect of MLLMs has been overlooked in prior studies. In this paper, we aim to define and evaluate the self-awareness of MLLMs in perception. To do this, we first introduce the knowledge quadrant in perception, which helps define what MLLMs know and do not know about images. Using this framework, we propose a novel benchmark, the Self-Awareness in Perception for MLLMs (MM-SAP), specifically designed to assess this capability. We apply MM-SAP to a variety of popular MLLMs, offering a comprehensive analysis of their self-awareness and providing detailed insights. The experiment results reveal that current MLLMs possess limited self-awareness capabilities, pointing to a crucial area for future advancement in the development of trustworthy MLLMs. Code and data are available at https://github.com/YHWmz/MM-SAP.
Authors: Trung X. Pham, Zhang Kang, Chang D. Yoo
Abstract: We present X-MDPT ($\underline{Cross}$-view $\underline{M}$asked $\underline{D}$iffusion $\underline{P}$rediction $\underline{T}$ransformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction module that enhances representation learning with semantic information from the reference image. X-MDPT demonstrates scalability, improving FID, SSIM, and LPIPS with larger models. Despite its simple design, our model outperforms state-of-the-art approaches on the DeepFashion dataset while exhibiting efficiency in terms of training parameters, training time, and inference speed. Our compact 33MB model achieves an FID of 7.42, surpassing a prior Unet latent diffusion approach (FID 8.07) using only $11\times$ fewer parameters. Our best model surpasses the pixel-based diffusion with $\frac{2}{3}$ of the parameters and achieves $5.43 \times$ faster inference. The code is available at https://github.com/trungpx/xmdpt.
Authors: Long Ma, Jiajia Zhang, Hongping Deng, Ningyu Zhang, Qinglang Guo, Haiyang Yu, Yong Liao, Pengyuan Zhou
Abstract: The escalating quality of video generated by advanced video generation methods results in new security challenges, while there have been few relevant research efforts: 1) There is no open-source dataset for generated video detection, 2) No generated video detection method has been proposed so far. To this end, we propose an open-source dataset and a detection method for generated video for the first time. First, we propose a scalable dataset consisting of 964 prompts, covering various forgery targets, scenes, behaviors, and actions, as well as various generation models with different architectures and generation methods, including the most popular commercial models like OpenAI's Sora and Google's Veo. Second, we found via probing experiments that spatial artifact-based detectors lack generalizability. Hence, we propose a simple yet effective \textbf{de}tection model based on \textbf{f}rame \textbf{co}nsistency (\textbf{DeCoF}), which focuses on temporal artifacts by eliminating the impact of spatial artifacts during feature learning. Extensive experiments demonstrate the efficacy of DeCoF in detecting videos generated by unseen video generation models and confirm its powerful generalizability across several commercially proprietary models. Our code and dataset will be released at \url{https://anonymous.4open.science/r/DeCoF-8394}.
Authors: Xinyu Peng, Ziyang Zheng, Wenrui Dai, Nuoqian Xiao, Chenglin Li, Junni Zou, Hongkai Xiong
Abstract: Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. In this paper, we reveal that recent methods can be uniformly interpreted as employing a Gaussian approximation with hand-crafted isotropic covariance for the intractable denoising posterior to approximate the conditional posterior mean. Inspired by this finding, we propose to improve recent methods by using more principled covariance determined by maximum likelihood estimation. To achieve posterior covariance optimization without retraining, we provide general plug-and-play solutions based on two approaches specifically designed for leveraging pre-trained models with and without reverse covariance. We further propose a scalable method for learning posterior covariance prediction based on representation with orthonormal basis. Experimental results demonstrate that the proposed methods significantly enhance reconstruction performance without requiring hyperparameter tuning.
Authors: Yang Jin, Zhicheng Sun, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang Song, Kun Gai, Yadong Mu
Abstract: In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for effective large-scale pre-training due to the modeling of its spatiotemporal dynamics. In this paper, we address such limitations in video-language pre-training with an efficient video decomposition that represents each video as keyframes and temporal motions. These are then adapted to an LLM using well-designed tokenizers that discretize visual and temporal information as a few tokens, thus enabling unified generative pre-training of videos, images, and text. At inference, the generated tokens from the LLM are carefully recovered to the original continuous pixel space to create various video content. Our proposed framework is both capable of comprehending and generating image and video content, as demonstrated by its competitive performance across 13 multimodal benchmarks in image and video understanding and generation. Our code and models are available at https://video-lavit.github.io.
Authors: Ashish Shenoy, Yichao Lu, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Abhay Harpale, Vikas Bhardwaj, Di Xu, Shicong Zhao, Longfang Zhao, Ankit Ramchandani, Xin Luna Dong, Anuj Kumar
Abstract: We introduce Lumos, the first end-to-end multimodal question-answering system with text understanding capabilities. At the core of Lumos is a Scene Text Recognition (STR) component that extracts text from first person point-of-view images, the output of which is used to augment input to a Multimodal Large Language Model (MM-LLM). While building Lumos, we encountered numerous challenges related to STR quality, overall latency, and model inference. In this paper, we delve into those challenges, and discuss the system architecture, design choices, and modeling techniques employed to overcome these obstacles. We also provide a comprehensive evaluation for each component, showcasing high quality and efficiency.
Authors: Matthieu Vilain, R\'emi Giraud, Hugo Germain, Guillaume Bourmaud
Abstract: Semi-dense detector-free approaches (SDF), such as LoFTR, are currently among the most popular image matching methods. While SDF methods are trained to establish correspondences between two images, their performances are almost exclusively evaluated using relative pose estimation metrics. Thus, the link between their ability to establish correspondences and the quality of the resulting estimated pose has thus far received little attention. This paper is a first attempt to study this link. We start with proposing a novel structured attention-based image matching architecture (SAM). It allows us to show a counter-intuitive result on two datasets (MegaDepth and HPatches): on the one hand SAM either outperforms or is on par with SDF methods in terms of pose/homography estimation metrics, but on the other hand SDF approaches are significantly better than SAM in terms of matching accuracy. We then propose to limit the computation of the matching accuracy to textured regions, and show that in this case SAM often surpasses SDF methods. Our findings highlight a strong correlation between the ability to establish accurate correspondences in textured regions and the accuracy of the resulting estimated pose/homography. Our code will be made available.
Authors: Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter
Abstract: We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers. Accordingly, MIM-Refiner leverages multiple contrastive heads that are connected to different intermediate layers. In each head, a modified nearest neighbor objective constructs semantic clusters that capture semantic information which improves performance on downstream tasks, including off-the-shelf and fine-tuning settings. The refinement process is short and simple - yet highly effective. Within a few epochs, we refine the features of MIM models from subpar to state-of-the-art, off-the-shelf features. Refining a ViT-H, pre-trained with data2vec 2.0 on ImageNet-1K, sets a new state-of-the-art in linear probing (84.7%) and low-shot classification among models that are pre-trained on ImageNet-1K. At ImageNet-1K 1-shot classification, MIM-Refiner advances the state-of-the-art to 64.2%, outperforming larger models that were trained on up to 2000 times more data such as DINOv2-g, OpenCLIP-G and MAWS-6.5B.
Authors: Raktim Kumar Mondol, Ewan K. A. Millar, Arcot Sowmya, Erik Meijering
Abstract: Breast cancer is a significant health concern affecting millions of women worldwide. Accurate survival risk stratification plays a crucial role in guiding personalised treatment decisions and improving patient outcomes. Here we present BioFusionNet, a deep learning framework that fuses image-derived features with genetic and clinical data to obtain a holistic profile and achieve survival risk stratification of ER+ breast cancer patients. We employ multiple self-supervised feature extractors (DINO and MoCoV3) pretrained on histopathological patches to capture detailed image features. These features are then fused by a variational autoencoder and fed to a self-attention network generating patient-level features. A co-dual-cross-attention mechanism combines the histopathological features with genetic data, enabling the model to capture the interplay between them. Additionally, clinical data is incorporated using a feed-forward network, further enhancing predictive performance and achieving comprehensive multimodal feature integration. Furthermore, we introduce a weighted Cox loss function, specifically designed to handle imbalanced survival data, which is a common challenge. Our model achieves a mean concordance index of 0.77 and a time-dependent area under the curve of 0.84, outperforming state-of-the-art methods. It predicts risk (high versus low) with prognostic significance for overall survival in univariate analysis (HR=2.99, 95% CI: 1.88--4.78, p<0.005), and maintains independent significance in multivariate analysis incorporating standard clinicopathological variables (HR=2.91, 95\% CI: 1.80--4.68, p<0.005).
Authors: Junfei Xiao, Zheng Xu, Alan Yuille, Shen Yan, Boyu Wang
Abstract: This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have been extensively studied, the architecture and training strategy of vision-language adapters vary significantly across recent works. Our research undertakes a thorough exploration of the state-of-the-art perceiver resampler architecture and builds a strong baseline. However, we observe that the vision-language alignment with perceiver resampler exhibits slow convergence and limited scalability with a lack of direct supervision. To address this issue, we propose PaLM2-VAdapter, employing a progressively aligned language model as the vision-language adapter. Compared to the strong baseline with perceiver resampler, our method empirically shows faster convergence, higher performance, and stronger scalability. Extensive experiments across various Visual Question Answering (VQA) and captioning tasks on both images and videos demonstrate that our model exhibits state-of-the-art visual understanding and multi-modal reasoning capabilities. Notably, our method achieves these advancements with 30~70% fewer parameters than the state-of-the-art large vision-language models, marking a significant efficiency improvement.
Authors: Jihyung Kil, Farideh Tavazoee, Dongyeop Kang, Joo-Kyung Kim
Abstract: Visual Question Answering (VQA) often involves diverse reasoning scenarios across Vision and Language (V&L). Most prior VQA studies, however, have merely focused on assessing the model's overall accuracy without evaluating it on different reasoning cases. Furthermore, some recent works observe that conventional Chain-of-Thought (CoT) prompting fails to generate effective reasoning for VQA, especially for complex scenarios requiring multi-hop reasoning. In this paper, we propose II-MMR, a novel idea to identify and improve multi-modal multi-hop reasoning in VQA. In specific, II-MMR takes a VQA question with an image and finds a reasoning path to reach its answer using two novel language promptings: (i) answer prediction-guided CoT prompt, or (ii) knowledge triplet-guided prompt. II-MMR then analyzes this path to identify different reasoning cases in current VQA benchmarks by estimating how many hops and what types (i.e., visual or beyond-visual) of reasoning are required to answer the question. On popular benchmarks including GQA and A-OKVQA, II-MMR observes that most of their VQA questions are easy to answer, simply demanding "single-hop" reasoning, whereas only a few questions require "multi-hop" reasoning. Moreover, while the recent V&L model struggles with such complex multi-hop reasoning questions even using the traditional CoT method, II-MMR shows its effectiveness across all reasoning cases in both zero-shot and fine-tuning settings.
Authors: Byung-Kwan Lee, Beomchan Park, Chae Won Kim, Yong Man Ro
Abstract: The remarkable success of Large Language Models (LLMs) and instruction tuning drives the evolution of Vision Language Models (VLMs) towards a versatile general-purpose model. Yet, it remains unexplored whether current VLMs genuinely possess quality object-level image understanding capabilities determined from 'what objects are in the image?' or 'which object corresponds to a specified bounding box?'. Our findings reveal that the image understanding capabilities of current VLMs are strongly correlated with their zero-shot performance on vision language (VL) tasks. This suggests that prioritizing basic image understanding is crucial for VLMs to excel at VL tasks. To enhance object-level image understanding, we propose Crayon Large Language and Vision mOdel (CoLLaVO), which incorporates instruction tuning with Crayon Prompt as a new visual prompt tuning scheme based on panoptic color maps. Furthermore, we present a learning strategy of Dual QLoRA to preserve object-level image understanding without forgetting it during visual instruction tuning, thereby achieving a significant leap in numerous VL benchmarks in a zero-shot setting.
Authors: Long Qian, Juncheng Li, Yu Wu, Yaobo Ye, Hao Fei, Tat-Seng Chua, Yueting Zhuang, Siliang Tang
Abstract: Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing Video-LLMs can only capture the coarse-grained semantics and are unable to effectively handle tasks related to comprehension or localization of specific video segments. In light of these challenges, we propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks. To support the training of Momentor, we design an automatic data generation engine to construct Moment-10M, a large-scale video instruction dataset with segment-level instruction data. We train Momentor on Moment-10M, enabling it to perform segment-level reasoning and localization. Zero-shot evaluations on several tasks demonstrate that Momentor excels in fine-grained temporally grounded comprehension and localization.
Authors: Haofeng Zhong, Yuchen Hong, Shuchen Weng, Jinxiu Liang, Boxin Shi
Abstract: This paper studies the problem of language-guided reflection separation, which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem, which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons.
Authors: Sankarshanaa Sagaram, Krish Didwania, Laven Srivastava, Aditya Kasliwal, Pallavi Kailas, Ujjwal Verma
Abstract: The increasing adoption of solar energy necessitates advanced methodologies for monitoring and maintenance to ensure optimal performance of solar panel installations. A critical component in this context is the accurate segmentation of solar panels from aerial or satellite imagery, which is essential for identifying operational issues and assessing efficiency. This paper addresses the significant challenges in panel segmentation, particularly the scarcity of annotated data and the labour-intensive nature of manual annotation for supervised learning. We explore and apply Self-Supervised Learning (SSL) to solve these challenges. We demonstrate that SSL significantly enhances model generalization under various conditions and reduces dependency on manually annotated data, paving the way for robust and adaptable solar panel segmentation solutions.
Authors: Juyeon Ko, Inho Kong, Dogyun Park, Hyunwoo J. Kim
Abstract: Semantic image synthesis (SIS) is a task to generate realistic images corresponding to semantic maps (labels). However, in real-world applications, SIS often encounters noisy user inputs. To address this, we propose Stochastic Conditional Diffusion Model (SCDM), which is a robust conditional diffusion model that features novel forward and generation processes tailored for SIS with noisy labels. It enhances robustness by stochastically perturbing the semantic label maps through Label Diffusion, which diffuses the labels with discrete diffusion. Through the diffusion of labels, the noisy and clean semantic maps become similar as the timestep increases, eventually becoming identical at $t=T$. This facilitates the generation of an image close to a clean image, enabling robust generation. Furthermore, we propose a class-wise noise schedule to differentially diffuse the labels depending on the class. We demonstrate that the proposed method generates high-quality samples through extensive experiments and analyses on benchmark datasets, including a novel experimental setup simulating human errors during real-world applications. Code is available at https://github.com/mlvlab/SCDM.
Authors: Matthew Danish, SM Labib, Britta Ricker, Marco Helbich
Abstract: Street View Imagery (SVI) is a valuable data source for studies (e.g., environmental assessments, green space identification or land cover classification). While commercial SVI is available, such providers commonly restrict copying or reuse in ways necessary for research. Open SVI datasets are readily available from less restrictive sources, such as Mapillary, but due to the heterogeneity of the images, these require substantial preprocessing, filtering, and careful quality checks. We present an efficient method for automated downloading, processing, cropping, and filtering open SVI, to be used in a survey of human perceptions of the streets portrayed in these images. We demonstrate our open-source reusable SVI preparation and smartphone-friendly perception-survey software with Amsterdam (Netherlands) as the case study. Using a citizen science approach, we collected from 331 people 22,637 ratings about their perceptions for various criteria. We have published our software in a public repository for future re-use and reproducibility.
Authors: Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, Qi Liu
Abstract: Large vision-language models (LVLMs) excel across diverse tasks involving concrete images from natural scenes. However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains limited due to a scarcity of training datasets in scientific domains. To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension. ArXivCap is a figure-caption dataset comprising 6.4M images and 3.9M captions, sourced from 572K ArXiv papers spanning various scientific domains. Drawing from ArXivCap, we introduce ArXivQA, a question-answering dataset generated by prompting GPT-4V based on scientific figures. ArXivQA greatly enhances open-sourced LVLMs' mathematical reasoning capabilities, achieving a 10.4\% absolute accuracy gain on a multimodal mathematical reasoning benchmark. Furthermore, employing ArXivCap, we devise four vision-to-text tasks for benchmarking LVLMs. Evaluation results with state-of-the-art LVLMs underscore their struggle with the nuanced semantics of academic figures, while domain-specific training yields substantial performance gains. Our error analysis uncovers misinterpretations of visual context, recognition errors, and the production of overly simplified captions by current LVLMs, shedding light on future improvements.
Authors: Huan Ma, Yan Zhu, Changqing Zhang, Peilin Zhao, Baoyuan Wu, Long-Kai Huang, Qinghua Hu, Bingzhe Wu
Abstract: Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of ``decision shortcuts'' that hinder their generalization capabilities. In this work, we find that the CLIP model possesses a rich set of features, encompassing both \textit{desired invariant causal features} and \textit{undesired decision shortcuts}. Moreover, the underperformance of CLIP on downstream tasks originates from its inability to effectively utilize pre-trained features in accordance with specific task requirements. To address this challenge, we propose a simple yet effective method, Spurious Feature Eraser (SEraser), to alleviate the decision shortcuts by erasing the spurious features. Specifically, we introduce a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit invariant features while disregarding decision shortcuts during the inference phase. The proposed method effectively alleviates excessive dependence on potentially misleading spurious information. We conduct comparative analysis of the proposed method against various approaches which validates the significant superiority.
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. Our data will be available at https://github.com/llyx97/TempCompass.
Authors: Yuheng Jia, Jianhong Cheng, Hui Liu, Junhui Hou
Abstract: Deep clustering has exhibited remarkable performance; however, the over-confidence problem, i.e., the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy, has been overlooked in prior research. To tackle this critical issue, we pioneer the development of a calibrated deep clustering framework. Specifically, we propose a novel dual-head (calibration head and clustering head) deep clustering model that can effectively calibrate the estimated confidence and the actual accuracy. The calibration head adjusts the overconfident predictions of the clustering head, generating prediction confidence that match the model learning status. Then, the clustering head dynamically select reliable high-confidence samples estimated by the calibration head for pseudo-label self-training. Additionally, we introduce an effective network initialization strategy that enhances both training speed and network robustness. The effectiveness of the proposed calibration approach and initialization strategy are both endorsed with solid theoretical guarantees. Extensive experiments demonstrate the proposed calibrated deep clustering model not only surpasses state-of-the-art deep clustering methods by 10 times in terms of expected calibration error but also significantly outperforms them in terms of clustering accuracy.
Authors: Shanka Subhra Mondal, Jonathan D. Cohen, Taylor W. Webb
Abstract: Abstract visual reasoning is a characteristically human ability, allowing the identification of relational patterns that are abstracted away from object features, and the systematic generalization of those patterns to unseen problems. Recent work has demonstrated strong systematic generalization in visual reasoning tasks involving multi-object inputs, through the integration of slot-based methods used for extracting object-centric representations coupled with strong inductive biases for relational abstraction. However, this approach was limited to problems containing a single rule, and was not scalable to visual reasoning problems containing a large number of objects. Other recent work proposed Abstractors, an extension of Transformers that incorporates strong relational inductive biases, thereby inheriting the Transformer's scalability and multi-head architecture, but it has yet to be demonstrated how this approach might be applied to multi-object visual inputs. Here we combine the strengths of the above approaches and propose Slot Abstractors, an approach to abstract visual reasoning that can be scaled to problems involving a large number of objects and multiple relations among them. The approach displays state-of-the-art performance across four abstract visual reasoning tasks, as well as an abstract reasoning task involving real-world images.
Authors: Lezhong Wang, Jeppe Revall Frisvad, Mark Bo Jensen, Siavash Arjomand Bigdeli
Abstract: The demand for stereo images increases as manufacturers launch more XR devices. To meet this demand, we introduce StereoDiffusion, a method that, unlike traditional inpainting pipelines, is trainning free, remarkably straightforward to use, and it seamlessly integrates into the original Stable Diffusion model. Our method modifies the latent variable to provide an end-to-end, lightweight capability for fast generation of stereo image pairs, without the need for fine-tuning model weights or any post-processing of images. Using the original input to generate a left image and estimate a disparity map for it, we generate the latent vector for the right image through Stereo Pixel Shift operations, complemented by Symmetric Pixel Shift Masking Denoise and Self-Attention Layers Modification methods to align the right-side image with the left-side image. Moreover, our proposed method maintains a high standard of image quality throughout the stereo generation process, achieving state-of-the-art scores in various quantitative evaluations.
Authors: Dan Guo, Kun Li, Bin Hu, Yan Zhang, Meng Wang
Abstract: Micro-action is an imperceptible non-verbal behaviour characterised by low-intensity movement. It offers insights into the feelings and intentions of individuals and is important for human-oriented applications such as emotion recognition and psychological assessment. However, the identification, differentiation, and understanding of micro-actions pose challenges due to the imperceptible and inaccessible nature of these subtle human behaviors in everyday life. In this study, we innovatively collect a new micro-action dataset designated as Micro-action-52 (MA-52), and propose a benchmark named micro-action network (MANet) for micro-action recognition (MAR) task. Uniquely, MA-52 provides the whole-body perspective including gestures, upper- and lower-limb movements, attempting to reveal comprehensive micro-action cues. In detail, MA-52 contains 52 micro-action categories along with seven body part labels, and encompasses a full array of realistic and natural micro-actions, accounting for 205 participants and 22,422 video instances collated from the psychological interviews. Based on the proposed dataset, we assess MANet and other nine prevalent action recognition methods. MANet incorporates squeeze-and excitation (SE) and temporal shift module (TSM) into the ResNet architecture for modeling the spatiotemporal characteristics of micro-actions. Then a joint-embedding loss is designed for semantic matching between video and action labels; the loss is used to better distinguish between visually similar yet distinct micro-action categories. The extended application in emotion recognition has demonstrated one of the important values of our proposed dataset and method. In the future, further exploration of human behaviour, emotion, and psychological assessment will be conducted in depth. The dataset and source code are released at https://github.com/VUT-HFUT/Micro-Action.
Authors: Boshen Xu, Sipeng Zheng, Qin Jin
Abstract: We introduce SPAFormer, an innovative model designed to overcome the combinatorial explosion challenge in the 3D Part Assembly (3D-PA) task. This task requires accurate prediction of each part's pose and shape in sequential steps, and as the number of parts increases, the possible assembly combinations increase exponentially, leading to a combinatorial explosion that severely hinders the efficacy of 3D-PA. SPAFormer addresses this problem by leveraging weak constraints from assembly sequences, effectively reducing the solution space's complexity. Since assembly part sequences convey construction rules similar to sentences being structured through words, our model explores both parallel and autoregressive generation. It further enhances assembly through knowledge enhancement strategies that utilize the attributes of parts and their sequence information, enabling it to capture the inherent assembly pattern and relationships among sequentially ordered parts. We also construct a more challenging benchmark named PartNet-Assembly covering 21 varied categories to more comprehensively validate the effectiveness of SPAFormer. Extensive experiments demonstrate the superior generalization capabilities of SPAFormer, particularly with multi-tasking and in scenarios requiring long-horizon assembly. Codes and model weights will be released at https://github.com/xuboshen/SPAFormer.
Authors: Dingkang Yang, Kun Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Lihua Zhang
Abstract: Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER methods invariably extract ensemble representations from diverse contexts and subject-centred characteristics to perceive the target person's emotional state. Despite advancements, the biggest challenge remains due to context bias interference. The harmful bias forces the models to rely on spurious correlations between background contexts and emotion labels in likelihood estimation, causing severe performance bottlenecks and confounding valuable context priors. In this paper, we propose a counterfactual emotion inference (CLEF) framework to address the above issue. Specifically, we first formulate a generalized causal graph to decouple the causal relationships among the variables in CAER. Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias. During the inference, we eliminate the direct context effect from the total causal effect by comparing factual and counterfactual outcomes, resulting in bias mitigation and robust prediction. As a model-agnostic framework, CLEF can be readily integrated into existing methods, bringing consistent performance gains.
Authors: Jintao Huang, Yiu-Ming Cheung, Chi-Man Vong
Abstract: Partial Label Learning (PLL) tackles model learning from the data with inexact labels under the assumption that training and test objects are in the same distribution, i.e., closed-set scenario. Nevertheless, this assumption does not hold in real-world open-set scenarios where test data may come from Out-Of-Distribution (OOD), resulting in object detection failure and hence significantly compromising the PLL model's security and trustworthiness. This is a previously unexplored problem called Out-Of-Distribution Partial Label Learning (OODPLL) that our newly proposed PLOOD framework can effectively resolve. During the training phase, our framework leverages self-supervised learning strategy to generate positive and negative samples for each object, emulating in and out-of-distributions respectively. Under these distributions, PLL methods can learn discriminative features for OOD objects. In the inference phase, a novel Partial Energy (PE) scoring technique is proposed which leverages the label confidence established during the above training phase to mine the actual labels. In this way, the issue of inexact labeling in PLL can be effectively addressed for significantly better performance in OOD object detection. PLOOD is compared with SOTA PLL models and OOD scores on CIFAR-10 and CIFAR-100 datasets against various OOD datasets. The results demonstrate the effectiveness of our PLOOD framework, significantly outperforming SOTA PLL models and marking a substantial advancement in addressing PLL problems in real-world OOD scenarios.
Authors: Kang Chen, Shiyan Chen, Jiyuan Zhang, Baoyue Zhang, Yajing Zheng, Tiejun Huang, Zhaofei Yu
Abstract: Reconstructing a sequence of sharp images from the blurry input is crucial for enhancing our insights into the captured scene and poses a significant challenge due to the limited temporal features embedded in the image. Spike cameras, sampling at rates up to 40,000 Hz, have proven effective in capturing motion features and beneficial for solving this ill-posed problem. Nonetheless, existing methods fall into the supervised learning paradigm, which suffers from notable performance degradation when applied to real-world scenarios that diverge from the synthetic training data domain. Moreover, the quality of reconstructed images is capped by the generated images based on motion analysis interpolation, which inherently differs from the actual scene, affecting the generalization ability of these methods in real high-speed scenarios. To address these challenges, we propose the first self-supervised framework for the task of spike-guided motion deblurring. Our approach begins with the formulation of a spike-guided deblurring model that explores the theoretical relationships among spike streams, blurry images, and their corresponding sharp sequences. We subsequently develop a self-supervised cascaded framework to alleviate the issues of spike noise and spatial-resolution mismatching encountered in the deblurring model. With knowledge distillation and re-blurring loss, we further design a lightweight deblur network to generate high-quality sequences with brightness and texture consistency with the original input. Quantitative and qualitative experiments conducted on our real-world and synthetic datasets with spikes validate the superior generalization of the proposed framework. Our code, data and trained models will be available at \url{https://github.com/chenkang455/S-SDM}.
Authors: Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Ping Hu, 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: Tongda Xu, Ziran Zhu, Jian Li, Dailan He, Yuanyuan Wang, Ming Sun, Ling Li, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang
Abstract: Diffusion Inverse Solvers (DIS) are designed to sample from the conditional distribution $p_{\theta}(X_0|y)$, with a predefined diffusion model $p_{\theta}(X_0)$, an operator $f(\cdot)$, and a measurement $y=f(x'_0)$ derived from an unknown image $x'_0$. Existing DIS estimate the conditional score function by evaluating $f(\cdot)$ with an approximated posterior sample drawn from $p_{\theta}(X_0|X_t)$. However, most prior approximations rely on the posterior means, which may not lie in the support of the image distribution, thereby potentially diverge from the appearance of genuine images. Such out-of-support samples may significantly degrade the performance of the operator $f(\cdot)$, particularly when it is a neural network. In this paper, we introduces a novel approach for posterior approximation that guarantees to generate valid samples within the support of the image distribution, and also enhances the compatibility with neural network-based operators $f(\cdot)$. We first demonstrate that the solution of the Probability Flow Ordinary Differential Equation (PF-ODE) with an initial value $x_t$ yields an effective posterior sample $p_{\theta}(X_0|X_t=x_t)$. Based on this observation, we adopt the Consistency Model (CM), which is distilled from PF-ODE, for posterior sampling. Furthermore, we design a novel family of DIS using only CM. Through extensive experiments, we show that our proposed method for posterior sample approximation substantially enhance the effectiveness of DIS for neural network operators $f(\cdot)$ (e.g., in semantic segmentation). Additionally, our experiments demonstrate the effectiveness of the new CM-based inversion techniques. The source code is provided in the supplementary material.
Authors: Santosh Sanjeev, Nuren Zhaksylyk, Ibrahim Almakky, Anees Ur Rehman Hashmi, Mohammad Areeb Qazi, Mohammad Yaqub
Abstract: The scarcity of well-annotated medical datasets requires leveraging transfer learning from broader datasets like ImageNet or pre-trained models like CLIP. Model soups averages multiple fine-tuned models aiming to improve performance on In-Domain (ID) tasks and enhance robustness against Out-of-Distribution (OOD) datasets. However, applying these methods to the medical imaging domain faces challenges and results in suboptimal performance. This is primarily due to differences in error surface characteristics that stem from data complexities such as heterogeneity, domain shift, class imbalance, and distributional shifts between training and testing phases. To address this issue, we propose a hierarchical merging approach that involves local and global aggregation of models at various levels based on models' hyperparameter configurations. Furthermore, to alleviate the need for training a large number of models in the hyperparameter search, we introduce a computationally efficient method using a cyclical learning rate scheduler to produce multiple models for aggregation in the weight space. Our method demonstrates significant improvements over the model souping approach across multiple datasets (around 6% gain in HAM10000 and CheXpert datasets) while maintaining low computational costs for model generation and selection. Moreover, we achieve better results on OOD datasets than model soups. The code is available at https://github.com/BioMedIA-MBZUAI/FissionFusion.
Authors: Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai, Qingkun Su, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, Siyu Zhu
Abstract: In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques. The methodology utilizes the SMPL(Skinned Multi-Person Linear) model as the 3D human parametric model to establish a unified representation of body shape and pose. This facilitates the accurate capture of intricate human geometry and motion characteristics from source videos. Specifically, we incorporate rendered depth images, normal maps, and semantic maps obtained from SMPL sequences, alongside skeleton-based motion guidance, to enrich the conditions to the latent diffusion model with comprehensive 3D shape and detailed pose attributes. A multi-layer motion fusion module, integrating self-attention mechanisms, is employed to fuse the shape and motion latent representations in the spatial domain. By representing the 3D human parametric model as the motion guidance, we can perform parametric shape alignment of the human body between the reference image and the source video motion. Experimental evaluations conducted on benchmark datasets demonstrate the methodology's superior ability to generate high-quality human animations that accurately capture both pose and shape variations. Furthermore, our approach also exhibits superior generalization capabilities on the proposed in-the-wild dataset. Project page: https://fudan-generative-vision.github.io/champ.
Authors: Tianfu Wang, Guosheng Hu, Hongguang Wang
Abstract: Estimating the pose of objects from images is a crucial task of 3D scene understanding, and recent approaches have shown promising results on very large benchmarks. However, these methods experience a significant performance drop when dealing with unseen objects. We believe that it results from the limited generalizability of image features. To address this problem, we have an in-depth analysis on the features of diffusion models, e.g. Stable Diffusion, which hold substantial potential for modeling unseen objects. Based on this analysis, we then innovatively introduce these diffusion features for object pose estimation. To achieve this, we propose three distinct architectures that can effectively capture and aggregate diffusion features of different granularity, greatly improving the generalizability of object pose estimation. Our approach outperforms the state-of-the-art methods by a considerable margin on three popular benchmark datasets, LM, O-LM, and T-LESS. In particular, our method achieves higher accuracy than the previous best arts on unseen objects: 98.2% vs. 93.5% on Unseen LM, 85.9% vs. 76.3% on Unseen O-LM, showing the strong generalizability of our method. Our code is released at https://github.com/Tianfu18/diff-feats-pose.
Authors: Marco Cannici, Davide Scaramuzza
Abstract: Neural Radiance Fields (NeRFs) have shown great potential in novel view synthesis. However, they struggle to render sharp images when the data used for training is affected by motion blur. On the other hand, event cameras excel in dynamic scenes as they measure brightness changes with microsecond resolution and are thus only marginally affected by blur. Recent methods attempt to enhance NeRF reconstructions under camera motion by fusing frames and events. However, they face challenges in recovering accurate color content or constrain the NeRF to a set of predefined camera poses, harming reconstruction quality in challenging conditions. This paper proposes a novel formulation addressing these issues by leveraging both model- and learning-based modules. We explicitly model the blur formation process, exploiting the event double integral as an additional model-based prior. Additionally, we model the event-pixel response using an end-to-end learnable response function, allowing our method to adapt to non-idealities in the real event-camera sensor. We show, on synthetic and real data, that the proposed approach outperforms existing deblur NeRFs that use only frames as well as those that combine frames and events by +6.13dB and +2.48dB, respectively.
Authors: Jinbae Im, JeongYeon Nam, Nokyung Park, Hyungmin Lee, Seunghyun Park
Abstract: Scene Graph Generation (SGG) is a challenging task of detecting objects and predicting relationships between objects. After DETR was developed, one-stage SGG models based on a one-stage object detector have been actively studied. However, complex modeling is used to predict the relationship between objects, and the inherent relationship between object queries learned in the multi-head self-attention of the object detector has been neglected. We propose a lightweight one-stage SGG model that extracts the relation graph from the various relationships learned in the multi-head self-attention layers of the DETR decoder. By fully utilizing the self-attention by-products, the relation graph can be extracted effectively with a shallow relation extraction head. Considering the dependency of the relation extraction task on the object detection task, we propose a novel relation smoothing technique that adjusts the relation label adaptively according to the quality of the detected objects. By the relation smoothing, the model is trained according to the continuous curriculum that focuses on object detection task at the beginning of training and performs multi-task learning as the object detection performance gradually improves. Furthermore, we propose a connectivity prediction task that predicts whether a relation exists between object pairs as an auxiliary task of the relation extraction. We demonstrate the effectiveness and efficiency of our method for the Visual Genome and Open Image V6 datasets. Our code is publicly available at https://github.com/naver-ai/egtr.
Authors: Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Yangchao Wu, Stefano Soatto, Byung-Woo Hong, Dong Lao, Alex Wong
Abstract: Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To "select" a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and outdoor (KITTI) scenarios, where we show that language can consistently improve performance in both.
Authors: Dongzhi Jiang, Guanglu Song, Xiaoshi Wu, Renrui Zhang, Dazhong Shen, Zhuofan Zong, Yu Liu, Hongsheng Li
Abstract: Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been extensively investigated. We observe that the misalignment is caused by inadequate token attention activation. We further attribute this phenomenon to the diffusion model's insufficient condition utilization, which is caused by its training paradigm. To address the issue, we propose CoMat, an end-to-end diffusion model fine-tuning strategy with an image-to-text concept matching mechanism. We leverage an image captioning model to measure image-to-text alignment and guide the diffusion model to revisit ignored tokens. A novel attribute concentration module is also proposed to address the attribute binding problem. Without any image or human preference data, we use only 20K text prompts to fine-tune SDXL to obtain CoMat-SDXL. Extensive experiments show that CoMat-SDXL significantly outperforms the baseline model SDXL in two text-to-image alignment benchmarks and achieves start-of-the-art performance.
Authors: Theo Di Piazza, Enric Meinhardt-Llopis, Gabriele Facciolo, Benedicte Bascle, Corentin Abgrall, Jean-Clement Devaux
Abstract: We propose a novel method for geolocalizing Unmanned Aerial Vehicles (UAVs) in environments lacking Global Navigation Satellite Systems (GNSS). Current state-of-the-art techniques employ an offline-trained encoder to generate a vector representation (embedding) of the UAV's current view, which is then compared with pre-computed embeddings of geo-referenced images to determine the UAV's position. Here, we demonstrate that the performance of these methods can be significantly enhanced by preprocessing the images to extract their edges, which exhibit robustness to seasonal and illumination variations. Furthermore, we establish that utilizing edges enhances resilience to orientation and altitude inaccuracies. Additionally, we introduce a confidence criterion for localization. Our findings are substantiated through synthetic experiments.
Authors: Lei Chen, Xinghang Gao, Fei Chao, Chih Min Lin, Xingen Gao, Hongyi Zhang, Juqiang Lin
Abstract: In the field of crowd counting research, many recent deep learning based methods have demonstrated robust capabilities for accurately estimating crowd sizes. However, the enhancement in their performance often arises from an increase in the complexity of the model structure. This paper discusses how to construct high-performance crowd counting models using only simple structures. We proposes the Fuss-Free Network (FFNet) that is characterized by its simple and efficieny structure, consisting of only a backbone network and a multi-scale feature fusion structure. The multi-scale feature fusion structure is a simple structure consisting of three branches, each only equipped with a focus transition module, and combines the features from these branches through the concatenation operation. Our proposed crowd counting model is trained and evaluated on four widely used public datasets, and it achieves accuracy that is comparable to that of existing complex models. Furthermore, we conduct a comprehensive evaluation by replacing the existing backbones of various models such as FFNet and CCTrans with different networks, including MobileNet-v3, ConvNeXt-Tiny, and Swin-Transformer-Small. The experimental results further indicate that excellent crowd counting performance can be achieved with the simplied structure proposed by us.
Authors: Sanghyun Son, Matheus Gadelha, Yang Zhou, Zexiang Xu, Ming C. Lin, Yi Zhou
Abstract: We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates the domain based on Weighted Delaunay Triangulation (WDT), and select triangular faces on the tetrahedra to define the final mesh. We formulate probability of faces to exist on the actual surface in a differentiable manner based on the WDT. This enables DMesh to represent meshes of various topology in a differentiable way, and allows us to reconstruct the mesh under various observations, such as point cloud and multi-view images using gradient-based optimization. The source code and full paper is available at: https://sonsang.github.io/dmesh-project.
Authors: Cai Chen, Runzhong Zhang, Jianjun Gao, Kejun Wu, Kim-Hui Yap, Yi Wang
Abstract: Temporal sentence grounding involves the retrieval of a video moment with a natural language query. Many existing works directly incorporate the given video and temporally localized query for temporal grounding, overlooking the inherent domain gap between different modalities. In this paper, we utilize pseudo-query features containing extensive temporally global textual knowledge sourced from the same video-query pair, to enhance the bridging of domain gaps and attain a heightened level of similarity between multi-modal features. Specifically, we propose a Pseudo-query Intermediary Network (PIN) to achieve an improved alignment of visual and comprehensive pseudo-query features within the feature space through contrastive learning. Subsequently, we utilize learnable prompts to encapsulate the knowledge of pseudo-queries, propagating them into the textual encoder and multi-modal fusion module, further enhancing the feature alignment between visual and language for better temporal grounding. Extensive experiments conducted on the Charades-STA and ActivityNet-Captions datasets demonstrate the effectiveness of our method.
Authors: Tao Hu, Wenhang Ge, Yuyang Zhao, Gim Hee Lee
Abstract: We introduce X-Ray, a novel 3D sequential representation inspired by the penetrability of x-ray scans. X-Ray transforms a 3D object into a series of surface frames at different layers, making it suitable for generating 3D models from images. Our method utilizes ray casting from the camera center to capture geometric and textured details, including depth, normal, and color, across all intersected surfaces. This process efficiently condenses the whole 3D object into a multi-frame video format, motivating the utilize of a network architecture similar to those in video diffusion models. This design ensures an efficient 3D representation by focusing solely on surface information. Also, we propose a two-stage pipeline to generate 3D objects from X-Ray Diffusion Model and Upsampler. We demonstrate the practicality and adaptability of our X-Ray representation by synthesizing the complete visible and hidden surfaces of a 3D object from a single input image. Experimental results reveal the state-of-the-art superiority of our representation in enhancing the accuracy of 3D generation, paving the way for new 3D representation research and practical applications.
Authors: Junfeng Ni, Yixin Chen, Bohan Jing, Nan Jiang, Bin Wang, Bo Dai, Puhao Li, Yixin Zhu, Song-Chun Zhu, Siyuan Huang
Abstract: Neural implicit representations have gained popularity in multi-view 3D reconstruction. However, most previous work struggles to yield physically plausible results, limiting their utility in domains requiring rigorous physical accuracy, such as embodied AI and robotics. This lack of plausibility stems from the absence of physics modeling in existing methods and their inability to recover intricate geometrical structures. In this paper, we introduce PhyRecon, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. PhyRecon features a novel differentiable particle-based physical simulator built on neural implicit representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points via our proposed Surface Points Marching Cubes (SP-MC), enabling differentiable learning with both rendering and physical losses. Additionally, PhyRecon models both rendering and physical uncertainty to identify and compensate for inconsistent and inaccurate monocular geometric priors. This physical uncertainty further facilitates a novel physics-guided pixel sampling to enhance the learning of slender structures. By integrating these techniques, our model supports differentiable joint modeling of appearance, geometry, and physics. Extensive experiments demonstrate that PhyRecon significantly outperforms all state-of-the-art methods. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets, paving the way for future physics-based applications.
Authors: Paulina Tomaszewska, Przemys{\l}aw Biecek
Abstract: Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it's obvious, why don't explanation methods for vision models use contextual information? In this paper, we (1) review the most popular methods of explaining computer vision models by pointing out that they do not take into account context information, (2) show examples of failures of popular XAI methods, (3) provide examples of real-world use cases where spatial context plays a significant role, (4) propose new research directions that may lead to better use of context information in explaining computer vision models, (5) argue that a change in approach to explanations is needed from 'where' to 'how'.
Authors: M\'elodie Boillet, Sol\`ene Tarride, Manon Blanco, Valentin Rigal, Yoann Schneider, Bastien Abadie, Lionel Kesztenbaum, Christopher Kermorvant
Abstract: This paper presents a complete processing workflow for extracting information from French census lists from 1836 to 1936. These lists contain information about individuals living in France and their households. We aim at extracting all the information contained in these tables using automatic handwritten table recognition. At the end of the Socface project, in which our work is taking place, the extracted information will be redistributed to the departmental archives, and the nominative lists will be freely available to the public, allowing anyone to browse hundreds of millions of records. The extracted data will be used by demographers to analyze social change over time, significantly improving our understanding of French economic and social structures. For this project, we developed a complete processing workflow: large-scale data collection from French departmental archives, collaborative annotation of documents, training of handwritten table text and structure recognition models, and mass processing of millions of images. We present the tools we have developed to easily collect and process millions of pages. We also show that it is possible to process such a wide variety of tables with a single table recognition model that uses the image of the entire page to recognize information about individuals, categorize them and automatically group them into households. The entire process has been successfully used to process the documents of a departmental archive, representing more than 450,000 images.
Authors: Minsu Kim, Giseop Kim, Sunwook Choi
Abstract: Recent advancements in Bird's Eye View (BEV) fusion for map construction have demonstrated remarkable mapping of urban environments. However, their deep and bulky architecture incurs substantial amounts of backpropagation memory and computing latency. Consequently, the problem poses an unavoidable bottleneck in constructing high-resolution (HR) BEV maps, as their large-sized features cause significant increases in costs including GPU memory consumption and computing latency, named diverging training costs issue. Affected by the problem, most existing methods adopt low-resolution (LR) BEV and struggle to estimate the precise locations of urban scene components like road lanes, and sidewalks. As the imprecision leads to risky self-driving, the diverging training costs issue has to be resolved. In this paper, we address the issue with our novel Trumpet Neural Network (TNN) mechanism. The framework utilizes LR BEV space and outputs an up-sampled semantic BEV map to create a memory-efficient pipeline. To this end, we introduce Local Restoration of BEV representation. Specifically, the up-sampled BEV representation has severely aliased, blocky signals, and thick semantic labels. Our proposed Local Restoration restores the signals and thins (or narrows down) the width of the labels. Our extensive experiments show that the TNN mechanism provides a plug-and-play memory-efficient pipeline, thereby enabling the effective estimation of real-sized (or precise) semantic labels for BEV map construction.
Authors: Yuchuan Tian, Zhijun Tu, Hanting Chen, Jie Hu, Chao Xu, Yunhe Wang
Abstract: Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good scalability; but meanwhile, the abandonment of U-Net by DiTs and their following improvements is worth rethinking. To this end, we conduct a simple toy experiment by comparing a U-Net architectured DiT with an isotropic one. It turns out that the U-Net architecture only gain a slight advantage amid the U-Net inductive bias, indicating potential redundancies within the U-Net-style DiT. Inspired by the discovery that U-Net backbone features are low-frequency-dominated, we perform token downsampling on the query-key-value tuple for self-attention that bring further improvements despite a considerable amount of reduction in computation. Based on self-attention with downsampled tokens, we propose a series of U-shaped DiTs (U-DiTs) in the paper and conduct extensive experiments to demonstrate the extraordinary performance of U-DiT models. The proposed U-DiT could outperform DiT-XL/2 with only 1/6 of its computation cost. Codes are available at https://github.com/YuchuanTian/U-DiT.
Authors: Boujemaa Guermazi, Naimul Khan
Abstract: Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, their reliance on extensive pixel-level annotations limits scalability. We introduce DynaSeg, an innovative unsupervised image segmentation approach that overcomes the challenge of balancing feature similarity and spatial continuity without relying on extensive hyperparameter tuning. Unlike traditional methods, DynaSeg employs a dynamic weighting scheme that automates parameter tuning, adapts flexibly to image characteristics, and facilitates easy integration with other segmentation networks. By incorporating a Silhouette Score Phase, DynaSeg prevents undersegmentation failures where the number of predicted clusters might converge to one. DynaSeg uses CNN-based and pre-trained ResNet feature extraction, making it computationally efficient and more straightforward than other complex models. Experimental results showcase state-of-the-art performance, achieving a 12.2% and 14.12% mIOU improvement over current unsupervised segmentation approaches on COCO-All and COCO-Stuff datasets, respectively. We provide qualitative and quantitative results on five benchmark datasets, demonstrating the efficacy of the proposed approach.
Authors: Hongwei Ren, Yue Zhou, Jiadong Zhu, Haotian Fu, Yulong Huang, Xiaopeng Lin, Yuetong Fang, Fei Ma, Hao Yu, Bojun Cheng
Abstract: Event cameras, drawing inspiration from biological systems, efficiently detect changes in ambient light with low latency and high dynamic range while consuming minimal power. The most current approach to processing event data often involves converting it into frame-based representations, which is well-established in traditional vision. However, this approach neglects the sparsity of event data, loses fine-grained temporal information during the transformation process, and increases the computational burden, making it ineffective for characterizing event camera properties. In contrast, Point Cloud is a popular representation for 3D processing and is better suited to match the sparse and asynchronous nature of the event camera. Nevertheless, despite the theoretical compatibility of point-based methods with event cameras, the results show a performance gap that is not yet satisfactory compared to frame-based methods. In order to bridge the performance gap, we propose EventMamba, an efficient and effective Point Cloud framework that achieves competitive results even compared to the state-of-the-art (SOTA) frame-based method in both classification and regression tasks. This notable accomplishment is facilitated by our rethinking of the distinction between Event Cloud and Point Cloud, emphasizing effective temporal information extraction through optimized network structures. Specifically, EventMamba leverages temporal aggregation and State Space Model (SSM) based Mamba boasting enhanced temporal information extraction capabilities. Through a hierarchical structure, EventMamba is adept at abstracting local and global spatial features and implicit and explicit temporal features. By adhering to the lightweight design principle, EventMamba delivers impressive results with minimal computational resource utilization, demonstrating its efficiency and effectiveness.
Authors: Tianhe Ren, Qing Jiang, Shilong Liu, Zhaoyang Zeng, Wenlong Liu, Han Gao, Hongjie Huang, Zhengyu Ma, Xiaoke Jiang, Yihao Chen, Yuda Xiong, Hao Zhang, Feng Li, Peijun Tang, Kent Yu, Lei Zhang
Abstract: This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detection. The suite encompasses two models: Grounding DINO 1.5 Pro, a high-performance model designed for stronger generalization capability across a wide range of scenarios, and Grounding DINO 1.5 Edge, an efficient model optimized for faster speed demanded in many applications requiring edge deployment. The Grounding DINO 1.5 Pro model advances its predecessor by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding. The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection capabilities by being trained on the same comprehensive dataset. Empirical results demonstrate the effectiveness of Grounding DINO 1.5, with the Grounding DINO 1.5 Pro model attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for open-set object detection. Furthermore, the Grounding DINO 1.5 Edge model, when optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark, making it more suitable for edge computing scenarios. Model examples and demos with API will be released at https://github.com/IDEA-Research/Grounding-DINO-1.5-API
URLs: https://github.com/IDEA-Research/Grounding-DINO-1.5-API
Authors: Kyle Gao, Dening Lu, Hongjie He, Linlin Xu, Jonathan Li
Abstract: 3D urban scene reconstruction and modelling is a crucial research area in remote sensing with numerous applications in academia, commerce, industry, and administration. Recent advancements in view synthesis models have facilitated photorealistic 3D reconstruction solely from 2D images. Leveraging Google Earth imagery, we construct a 3D Gaussian Splatting model of the Waterloo region centered on the University of Waterloo and are able to achieve view-synthesis results far exceeding previous 3D view-synthesis results based on neural radiance fields which we demonstrate in our benchmark. Additionally, we retrieved the 3D geometry of the scene using the 3D point cloud extracted from the 3D Gaussian Splatting model which we benchmarked against our Multi- View-Stereo dense reconstruction of the scene, thereby reconstructing both the 3D geometry and photorealistic lighting of the large-scale urban scene through 3D Gaussian Splatting
Authors: Jihwan Kim, Junoh Kang, Jinyoung Choi, Bohyung Han
Abstract: We propose a novel inference technique based on a pretrained diffusion model for text-conditional video generation. Our approach, called FIFO-Diffusion, is conceptually capable of generating infinitely long videos without additional training. This is achieved by iteratively performing diagonal denoising, which concurrently processes a series of consecutive frames with increasing noise levels in a queue; our method dequeues a fully denoised frame at the head while enqueuing a new random noise frame at the tail. However, diagonal denoising is a double-edged sword as the frames near the tail can take advantage of cleaner ones by forward reference but such a strategy induces the discrepancy between training and inference. Hence, we introduce latent partitioning to reduce the training-inference gap and lookahead denoising to leverage the benefit of forward referencing. Practically, FIFO-Diffusion consumes a constant amount of memory regardless of the target video length given a baseline model, while well-suited for parallel inference on multiple GPUs. We have demonstrated the promising results and effectiveness of the proposed methods on existing text-to-video generation baselines. Generated video samples and source codes are available at our project page.
Authors: Weizhen Liu, Jiayu Tan, Guangyu Lan, Ao Li, Dongye Li, Le Zhao, Xiaohui Yuan, Nanqing Dong
Abstract: Accurate phenotypic analysis in aquaculture breeding necessitates the quantification of subtle morphological phenotypes. Existing datasets suffer from limitations such as small scale, limited species coverage, and inadequate annotation of keypoints for measuring refined and complex morphological phenotypes of fish body parts. To address this gap, we introduce FishPhenoKey, a comprehensive dataset comprising 23,331 high-resolution images spanning six fish species. Notably, FishPhenoKey includes 22 phenotype-oriented annotations, enabling the capture of intricate morphological phenotypes. Motivated by the nuanced evaluation of these subtle morphologies, we also propose a new evaluation metric, Percentage of Measured Phenotype (PMP). It is designed to assess the accuracy of individual keypoint positions and is highly sensitive to the phenotypes measured using the corresponding keypoints. To enhance keypoint detection accuracy, we further propose a novel loss, Anatomically-Calibrated Regularization (ACR), that can be integrated into keypoint detection models, leveraging biological insights to refine keypoint localization. Our contributions set a new benchmark in fish phenotype analysis, addressing the challenges of precise morphological quantification and opening new avenues for research in sustainable aquaculture and genetic studies. Our dataset and code are available at https://github.com/WeizhenLiuBioinform/Fish-Phenotype-Detect.
URLs: https://github.com/WeizhenLiuBioinform/Fish-Phenotype-Detect.
Authors: Theodore Zhao, Yu Gu, Jianwei Yang, Naoto Usuyama, Ho Hin Lee, Tristan Naumann, Jianfeng Gao, Angela Crabtree, Brian Piening, Carlo Bifulco, Mu Wei, Hoifung Poon, Sheng Wang
Abstract: Biomedical image analysis is fundamental for biomedical discovery in cell biology, pathology, radiology, and many other biomedical domains. Holistic image analysis comprises interdependent subtasks such as segmentation, detection, and recognition of relevant objects. Here, we propose BiomedParse, a biomedical foundation model for imaging parsing that can jointly conduct segmentation, detection, and recognition for 82 object types across 9 imaging modalities. Through joint learning, we can improve accuracy for individual tasks and enable novel applications such as segmenting all relevant objects in an image through a text prompt, rather than requiring users to laboriously specify the bounding box for each object. We leveraged readily available natural-language labels or descriptions accompanying those datasets and use GPT-4 to harmonize the noisy, unstructured text information with established biomedical object ontologies. We created a large dataset comprising over six million triples of image, segmentation mask, and textual description. On image segmentation, we showed that BiomedParse is broadly applicable, outperforming state-of-the-art methods on 102,855 test image-mask-label triples across 9 imaging modalities (everything). On object detection, which aims to locate a specific object of interest, BiomedParse again attained state-of-the-art performance, especially on objects with irregular shapes (everywhere). On object recognition, which aims to identify all objects in a given image along with their semantic types, we showed that BiomedParse can simultaneously segment and label all biomedical objects in an image (all at once). In summary, BiomedParse is an all-in-one tool for biomedical image analysis by jointly solving segmentation, detection, and recognition for all major biomedical image modalities, paving the path for efficient and accurate image-based biomedical discovery.
Authors: Teng Xu, Jiamin Chen, Peng Chen, Youjia Zhang, Junqing Yu, Wei Yang
Abstract: Editing objects within a scene is a critical functionality required across a broad spectrum of applications in computer vision and graphics. As 3D Gaussian Splatting (3DGS) emerges as a frontier in scene representation, the effective modification of 3D Gaussian scenes has become increasingly vital. This process entails accurately retrieve the target objects and subsequently performing modifications based on instructions. Though available in pieces, existing techniques mainly embed sparse semantics into Gaussians for retrieval, and rely on an iterative dataset update paradigm for editing, leading to over-smoothing or inconsistency issues. To this end, this paper proposes a systematic approach, namely TIGER, for coherent text-instructed 3D Gaussian retrieval and editing. In contrast to the top-down language grounding approach for 3D Gaussians, we adopt a bottom-up language aggregation strategy to generate a denser language embedded 3D Gaussians that supports open-vocabulary retrieval. To overcome the over-smoothing and inconsistency issues in editing, we propose a Coherent Score Distillation (CSD) that aggregates a 2D image editing diffusion model and a multi-view diffusion model for score distillation, producing multi-view consistent editing with much finer details. In various experiments, we demonstrate that our TIGER is able to accomplish more consistent and realistic edits than prior work.
Authors: Shuang Wu, Youtian Lin, Feihu Zhang, Yifei Zeng, Jingxi Xu, Philip Torr, Xun Cao, Yao Yao
Abstract: Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a native 3D generative model scalable to in-the-wild input images, without requiring a multiview diffusion model or SDS optimization. Our approach comprises two primary components: a Direct 3D Variational Auto-Encoder (D3D-VAE) and a Direct 3D Diffusion Transformer (D3D-DiT). D3D-VAE efficiently encodes high-resolution 3D shapes into a compact and continuous latent triplane space. Notably, our method directly supervises the decoded geometry using a semi-continuous surface sampling strategy, diverging from previous methods relying on rendered images as supervision signals. D3D-DiT models the distribution of encoded 3D latents and is specifically designed to fuse positional information from the three feature maps of the triplane latent, enabling a native 3D generative model scalable to large-scale 3D datasets. Additionally, we introduce an innovative image-to-3D generation pipeline incorporating semantic and pixel-level image conditions, allowing the model to produce 3D shapes consistent with the provided conditional image input. Extensive experiments demonstrate the superiority of our large-scale pre-trained Direct3D over previous image-to-3D approaches, achieving significantly better generation quality and generalization ability, thus establishing a new state-of-the-art for 3D content creation. Project page: https://nju-3dv.github.io/projects/Direct3D/.
Authors: Prakash Chandra Chhipa, Kanjar De, Meenakshi Subhash Chippa, Rajkumar Saini, Marcus Liwicki
Abstract: The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Open-vocabulary object detection extends the capabilities of traditional object detection frameworks to recognize and classify objects beyond predefined categories. Investigating OOD robustness in open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness evaluation of zero-shot capabilities of three recent open-vocabulary foundation object detection models, namely OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the COCO-O and COCO-C benchmarks encompassing distribution shifts highlight the challenges of the models' robustness. Source code shall be made available to the research community on GitHub.
Authors: Jiaxu Wang, Junhao He, Ziyi Zhang, Mingyuan Sun, Jingkai Sun, Renjing Xu
Abstract: Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is difficult because event data is sparse and does not carry absolute color information. To release its potential in 3D reconstruction, we propose the first event-based generalizable 3D reconstruction framework, called EvGGS, which reconstructs scenes as 3D Gaussians from only event input in a feedforward manner and can generalize to unseen cases without any retraining. This framework includes a depth estimation module, an intensity reconstruction module, and a Gaussian regression module. These submodules connect in a cascading manner, and we collaboratively train them with a designed joint loss to make them mutually promote. To facilitate related studies, we build a novel event-based 3D dataset with various material objects and calibrated labels of grayscale images, depth maps, camera poses, and silhouettes. Experiments show models that have jointly trained significantly outperform those trained individually. Our approach performs better than all baselines in reconstruction quality, and depth/intensity predictions with satisfactory rendering speed.
Authors: Jialong Wu, Shaofeng Yin, Ningya Feng, Xu He, Dong Li, Jianye Hao, Mingsheng Long
Abstract: World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT features a novel compressive tokenization technique that efficiently discretizes high-dimensional visual observations. Leveraging its scalable architecture, we are able to pre-train iVideoGPT on millions of human and robotic manipulation trajectories, establishing a versatile foundation that is adaptable to serve as interactive world models for a wide range of downstream tasks. These include action-conditioned video prediction, visual planning, and model-based reinforcement learning, where iVideoGPT achieves competitive performance compared with state-of-the-art methods. Our work advances the development of interactive general world models, bridging the gap between generative video models and practical model-based reinforcement learning applications.
Authors: Eduard Zamfir, Zongwei Wu, Nancy Mehta, Danda Pani Paudel, Yulun Zhang, Radu Timofte
Abstract: Reconstructing missing details from degraded low-quality inputs poses a significant challenge. Recent progress in image restoration has demonstrated the efficacy of learning large models capable of addressing various degradations simultaneously. Nonetheless, these approaches introduce considerable computational overhead and complex learning paradigms, limiting their practical utility. In response, we propose \textit{DaAIR}, an efficient All-in-One image restorer employing a Degradation-aware Learner (DaLe) in the low-rank regime to collaboratively mine shared aspects and subtle nuances across diverse degradations, generating a degradation-aware embedding. By dynamically allocating model capacity to input degradations, we realize an efficient restorer integrating holistic and specific learning within a unified model. Furthermore, DaAIR introduces a cost-efficient parameter update mechanism that enhances degradation awareness while maintaining computational efficiency. Extensive comparisons across five image degradations demonstrate that our DaAIR outperforms both state-of-the-art All-in-One models and degradation-specific counterparts, affirming our efficacy and practicality. The source will be publicly made available at https://eduardzamfir.github.io/daair/
Authors: Zhaochen Liu, Limeng Qiao, Xiangxiang Chu, Tingting Jiang
Abstract: Aiming to predict the complete shapes of partially occluded objects, amodal segmentation is an important step towards visual intelligence. With crucial significance, practical prior knowledge derives from sufficient training, while limited amodal annotations pose challenges to achieve better performance. To tackle this problem, utilizing the mighty priors accumulated in the foundation model, we propose the first SAM-based amodal segmentation approach, PLUG. Methodologically, a novel framework with hierarchical focus is presented to better adapt the task characteristics and unleash the potential capabilities of SAM. In the region level, due to the association and division in visible and occluded areas, inmodal and amodal regions are assigned as the focuses of distinct branches to avoid mutual disturbance. In the point level, we introduce the concept of uncertainty to explicitly assist the model in identifying and focusing on ambiguous points. Guided by the uncertainty map, a computation-economic point loss is applied to improve the accuracy of predicted boundaries. Experiments are conducted on several prominent datasets, and the results show that our proposed method outperforms existing methods with large margins. Even with fewer total parameters, our method still exhibits remarkable advantages.
Authors: Soumava Paul, Christopher Wewer, Bernt Schiele, Jan Eric Lenssen
Abstract: We aim to tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM). The sparse-view setting is ill-posed and underconstrained, especially for scenes where the camera rotates 360 degrees around a point, as no visual information is available beyond some frontal views focused on the central object(s) of interest. In this work, we show that pretrained 2D diffusion models can strongly improve the reconstruction of a scene with low-cost fine-tuning. Specifically, we present SparseSplat360 (Sp2360), a method that employs a cascade of in-painting and artifact removal models to fill in missing details and clean novel views. Due to superior training and rendering speeds, we use an explicit scene representation in the form of 3D Gaussians over NeRF-based implicit representations. We propose an iterative update strategy to fuse generated pseudo novel views with existing 3D Gaussians fitted to the initial sparse inputs. As a result, we obtain a multi-view consistent scene representation with details coherent with the observed inputs. Our evaluation on the challenging Mip-NeRF360 dataset shows that our proposed 2D to 3D distillation algorithm considerably improves the performance of a regularized version of 3DGS adapted to a sparse-view setting and outperforms existing sparse-view reconstruction methods in 360 scene reconstruction. Qualitatively, our method generates entire 360 scenes from as few as 9 input views, with a high degree of foreground and background detail.
Authors: Yong Liu, Hang Dong, Jinshan Pan, Qingji Dong, Kai Chen, Rongxiang Zhang, Xing Mei, Lean Fu, Fei Wang
Abstract: Diffusion models significantly improve the quality of super-resolved images with their impressive content generation capabilities. However, the huge computational costs limit the applications of these methods.Recent efforts have explored reasonable inference acceleration to reduce the number of sampling steps, but the computational cost remains high as each step is performed on the entire image.This paper introduces PatchScaler, a patch-independent diffusion-based single image super-resolution (SR) method, designed to enhance the efficiency of the inference process.The proposed method is motivated by the observation that not all the image patches within an image need the same sampling steps for reconstructing high-resolution images.Based on this observation, we thus develop a Patch-adaptive Group Sampling (PGS) to divide feature patches into different groups according to the patch-level reconstruction difficulty and dynamically assign an appropriate sampling configuration for each group so that the inference speed can be better accelerated.In addition, to improve the denoising ability at each step of the sampling, we develop a texture prompt to guide the estimations of the diffusion model by retrieving high-quality texture priors from a patch-independent reference texture memory.Experiments show that our PatchScaler achieves favorable performance in both quantitative and qualitative evaluations with fast inference speed.Our code and model are available at \url{https://github.com/yongliuy/PatchScaler}.
Authors: Boshen Xu, Ziheng Wang, Yang Du, Zhinan Song, Sipeng Zheng, Qin Jin
Abstract: Egocentric video-language pretraining is a crucial paradigm to advance the learning of egocentric hand-object interactions (EgoHOI). Despite the great success on existing testbeds, these benchmarks focus more on closed-set visual concepts or limited scenarios. Due to the occurrence of diverse EgoHOIs in the real world, we propose an open-vocabulary benchmark named EgoHOIBench to reveal the diminished performance of current egocentric video-language models (EgoVLM) on fined-grained concepts, indicating that these models still lack a full spectrum of egocentric understanding. We attribute this performance gap to insufficient fine-grained supervision and strong bias towards understanding objects rather than temporal dynamics in current methods. To tackle these issues, we introduce a novel asymmetric contrastive objective for EgoHOI named EgoNCE++. For video-to-text loss, we enhance text supervision through the generation of negative captions by leveraging the in-context learning of large language models to perform HOI-related word substitution. For text-to-video loss, we propose an object-centric positive video sampling strategy that aggregates video representations by the same nouns. Our extensive experiments demonstrate that EgoNCE++ significantly boosts open-vocabulary HOI recognition, multi-instance retrieval, and action recognition tasks across various egocentric models, with improvements of up to +26.55%. Our code is available at https://github.com/xuboshen/EgoNCEpp.
Authors: Maxime Zanella, Ismail Ben Ayed
Abstract: Recent progress in the few-shot adaptation of Vision-Language Models (VLMs) has further pushed their generalization capabilities, at the expense of just a few labeled samples within the target downstream task. However, this promising, already quite abundant few-shot literature has focused principally on prompt learning and, to a lesser extent, on adapters, overlooking the recent advances in Parameter-Efficient Fine-Tuning (PEFT). Furthermore, existing few-shot learning methods for VLMs often rely on heavy training procedures and/or carefully chosen, task-specific hyper-parameters, which might impede their applicability. In response, we introduce Low-Rank Adaptation (LoRA) in few-shot learning for VLMs, and show its potential on 11 datasets, in comparison to current state-of-the-art prompt- and adapter-based approaches. Surprisingly, our simple CLIP-LoRA method exhibits substantial improvements, while reducing the training times and keeping the same hyper-parameters in all the target tasks, i.e., across all the datasets and numbers of shots. Certainly, our surprising results do not dismiss the potential of prompt-learning and adapter-based research. However, we believe that our strong baseline could be used to evaluate progress in these emergent subjects in few-shot VLMs.
Authors: Renyi Qu, Mark Yatskar
Abstract: (Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from large language models (LLMs). This introduces randomness and compromises both transparency and reliability, which are essential for addressing safety issues in AI systems. We introduce \texttt{Hi-CoDe} (Hierarchical Concept Decomposition), a novel framework designed to enhance model interpretability through structured concept analysis. Our approach consists of two main components: (1) We use GPT-4 to decompose an input image into a structured hierarchy of visual concepts, thereby forming a visual concept tree. (2) We then employ an ensemble of simple linear classifiers that operate on concept-specific features derived from CLIP to perform classification. Our approach not only aligns with the performance of state-of-the-art models but also advances transparency by providing clear insights into the decision-making process and highlighting the importance of various concepts. This allows for a detailed analysis of potential failure modes and improves model compactness, therefore setting a new benchmark in interpretability without compromising the accuracy.
Authors: Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen, Marc Pollefeys, Songyou Peng
Abstract: Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes. Existing methods manage controlled environments and low occlusion ratios but fall short in render quality, especially under high occlusion scenarios. In this paper, we introduce NeRF On-the-go, a simple yet effective approach that enables the robust synthesis of novel views in complex, in-the-wild scenes from only casually captured image sequences. Delving into uncertainty, our method not only efficiently eliminates distractors, even when they are predominant in captures, but also achieves a notably faster convergence speed. Through comprehensive experiments on various scenes, our method demonstrates a significant improvement over state-of-the-art techniques. This advancement opens new avenues for NeRF in diverse and dynamic real-world applications.
Authors: Markus J. Buehler
Abstract: We present Cephalo, a series of multimodal vision large language models (V-LLMs) designed for materials science applications, integrating visual and linguistic data for enhanced understanding and interaction within human-AI and multi-agent AI frameworks. A key innovation of Cephalo is its advanced dataset generation method, which employs a sophisticated algorithm to accurately detect and separate images and their corresponding textual descriptions from PDF documents, such as scientific papers. The method includes a careful refinement of image-text pairs through integrated vision and language processing, ensuring high-quality, contextually relevant, and well reasoned training data. Cephalo is trained on integrated image and text data extracted from thousands of scientific papers and science-focused Wikipedia pages demonstrates can interpret complex visual scenes, generate precise language descriptions, and answer queries about images effectively. The combination of a vision encoder with an autoregressive transformer supports complex natural language understanding in an integrated model, which can be coupled with other generative methods to create an image-to-text-to-image or image-to-text-to-3D pipeline. To explore the development of larger models from smaller ones, we report both mixture-of-expert methods and model merging. These hybrid approaches allow us to leverage the domain-specific expertise and general conversational capabilities to harness the strengths of multiple models. We examine the models in diverse use cases that incorporate biological materials, fracture and engineering analysis, protein biophysics, and bio-inspired design based on insect behavior. Generative applications include bio-inspired designs, including pollen-inspired architected materials, as well as the synthesis of bio-inspired material microstructures from a photograph of a solar eclipse.
Authors: Ningli Xu, Rongjun Qin
Abstract: Generating wide-area digital surface models (DSMs) requires registering a large number of individual, and partially overlapped DSMs. This presents a challenging problem for a typical registration algorithm, since when a large number of observations from these multiple DSMs are considered, it may easily cause memory overflow. Sequential registration algorithms, although can significantly reduce the computation, are especially vulnerable for small overlapped pairs, leading to a large error accumulation. In this work, we propose a novel solution that builds the DSM registration task as a motion averaging problem: pair-wise DSMs are registered to build a scene graph, with edges representing relative poses between DSMs. Specifically, based on the grid structure of the large DSM, the pair-wise registration is performed using a novel nearest neighbor search method. We show that the scene graph can be optimized via an extremely fast motion average algorithm with O(N) complexity (N refers to the number of images). Evaluation of high-resolution satellite-derived DSM demonstrates significant improvement in computation and accuracy.
Authors: Honghao Fu, Yufei Wang, Wenhan Yang, Bihan Wen
Abstract: Image quality assessment (IQA) plays a critical role in selecting high-quality images and guiding compression and enhancement methods in a series of applications. The blind IQA, which assesses the quality of in-the-wild images containing complex authentic distortions without reference images, poses greater challenges. Existing methods are limited to modeling a uniform distribution with local patches and are bothered by the gap between low and high-level visions (caused by widely adopted pre-trained classification networks). In this paper, we propose a novel IQA method called diffusion priors-based IQA (DP-IQA), which leverages the prior knowledge from the pre-trained diffusion model with its excellent powers to bridge semantic gaps in the perception of the visual quality of images. Specifically, we use pre-trained stable diffusion as the backbone, extract multi-level features from the denoising U-Net during the upsampling process at a specified timestep, and decode them to estimate the image quality score. The text and image adapters are adopted to mitigate the domain gap for downstream tasks and correct the information loss caused by the variational autoencoder bottleneck. Finally, we distill the knowledge in the above model into a CNN-based student model, significantly reducing the parameter to enhance applicability, with the student model performing similarly or even better than the teacher model surprisingly. Experimental results demonstrate that our DP-IQA achieves state-of-the-art results on various in-the-wild datasets with better generalization capability, which shows the superiority of our method in global modeling and utilizing the hierarchical feature clues of diffusion for evaluating image quality.
Authors: Muyao Niu, Xiaodong Cun, Xintao Wang, Yong Zhang, Ying Shan, Yinqiang Zheng
Abstract: We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even provided video) or their combinations. This is different from previous methods which only can work on a specific motion domain or show weak control abilities with diffusion prior. To achieve our goal, we design several domain-aware motion field adapters (\ie, MOFA-Adapters) to control the generated motions in the video generation pipeline. For MOFA-Adapters, we consider the temporal motion consistency of the video and generate the dense motion flow from the given sparse control conditions first, and then, the multi-scale features of the given image are wrapped as a guided feature for stable video diffusion generation. We naively train two motion adapters for the manual trajectories and the human landmarks individually since they both contain sparse information about the control. After training, the MOFA-Adapters in different domains can also work together for more controllable video generation. Project Page: https://myniuuu.github.io/MOFA_Video/
Authors: Jinrui Yang, Xianhang Li, Druv Pai, Yuyin Zhou, Yi Ma, Yaodong Yu, Cihang Xie
Abstract: CRATE, a white-box transformer architecture designed to learn compressed and sparse representations, offers an intriguing alternative to standard vision transformers (ViTs) due to its inherent mathematical interpretability. Despite extensive investigations into the scaling behaviors of language and vision transformers, the scalability of CRATE remains an open question which this paper aims to address. Specifically, we propose CRATE-$\alpha$, featuring strategic yet minimal modifications to the sparse coding block in the CRATE architecture design, and a light training recipe designed to improve the scalability of CRATE. Through extensive experiments, we demonstrate that CRATE-$\alpha$ can effectively scale with larger model sizes and datasets. For example, our CRATE-$\alpha$-B substantially outperforms the prior best CRATE-B model accuracy on ImageNet classification by 3.7%, achieving an accuracy of 83.2%. Meanwhile, when scaling further, our CRATE-$\alpha$-L obtains an ImageNet classification accuracy of 85.1%. More notably, these model performance improvements are achieved while preserving, and potentially even enhancing the interpretability of learned CRATE models, as we demonstrate through showing that the learned token representations of increasingly larger trained CRATE-$\alpha$ models yield increasingly higher-quality unsupervised object segmentation of images. The project page is https://rayjryang.github.io/CRATE-alpha/.
Authors: Jianghao Shen, Nan Xue, Tianfu Wu
Abstract: Learning 3D scene representation from a single-view image is a long-standing fundamental problem in computer vision, with the inherent ambiguity in predicting contents unseen from the input view. Built on the recently proposed 3D Gaussian Splatting (3DGS), the Splatter Image method has made promising progress on fast single-image novel view synthesis via learning a single 3D Gaussian for each pixel based on the U-Net feature map of an input image. However, it has limited expressive power to represent occluded components that are not observable in the input view. To address this problem, this paper presents a Hierarchical Splatter Image method in which a pixel is worth more than one 3D Gaussians. Specifically, each pixel is represented by a parent 3D Gaussian and a small number of child 3D Gaussians. Parent 3D Gaussians are learned as done in the vanilla Splatter Image. Child 3D Gaussians are learned via a lightweight Multi-Layer Perceptron (MLP) which takes as input the projected image features of a parent 3D Gaussian and the embedding of a target camera view. Both parent and child 3D Gaussians are learned end-to-end in a stage-wise way. The joint condition of input image features from eyes of the parent Gaussians and the target camera position facilitates learning to allocate child Gaussians to ``see the unseen'', recovering the occluded details that are often missed by parent Gaussians. In experiments, the proposed method is tested on the ShapeNet-SRN and CO3D datasets with state-of-the-art performance obtained, especially showing promising capabilities of reconstructing occluded contents in the input view.
Authors: Han Feng, Wenchao Ma, Quankai Gao, Xianwei Zheng, Nan Xue, Huijuan Xu
Abstract: Estimating 3D full-body avatars from AR/VR devices is essential for creating immersive experiences in AR/VR applications. This task is challenging due to the limited input from Head Mounted Devices, which capture only sparse observations from the head and hands. Predicting the full-body avatars, particularly the lower body, from these sparse observations presents significant difficulties. In this paper, we are inspired by the inherent property of the kinematic tree defined in the Skinned Multi-Person Linear (SMPL) model, where the upper body and lower body share only one common ancestor node, bringing the potential of decoupled reconstruction. We propose a stratified approach to decouple the conventional full-body avatar reconstruction pipeline into two stages, with the reconstruction of the upper body first and a subsequent reconstruction of the lower body conditioned on the previous stage. To implement this straightforward idea, we leverage the latent diffusion model as a powerful probabilistic generator, and train it to follow the latent distribution of decoupled motions explored by a VQ-VAE encoder-decoder model. Extensive experiments on AMASS mocap dataset demonstrate our state-of-the-art performance in the reconstruction of full-body motions.
Authors: Haolong Ma, Hui Li, Chunyang Cheng, Gaoang Wang, Xiaoning Song, Xiaojun Wu
Abstract: As one of the tasks in Image Fusion, Infrared and Visible Image Fusion aims to integrate complementary information captured by sensors of different modalities into a single image. The Selective State Space Model (SSSM), known for its ability to capture long-range dependencies, has demonstrated its potential in the field of computer vision. However, in image fusion, current methods underestimate the potential of SSSM in capturing the global spatial information of both modalities. This limitation prevents the simultaneous consideration of the global spatial information from both modalities during interaction, leading to a lack of comprehensive perception of salient targets. Consequently, the fusion results tend to bias towards one modality instead of adaptively preserving salient targets. To address this issue, we propose the Saliency-aware Selective State Space Fusion Model (S4Fusion). In our S4Fusion, the designed Cross-Modal Spatial Awareness Module (CMSA) can simultaneously focus on global spatial information from both modalities while facilitating their interaction, thereby comprehensively capturing complementary information. Additionally, S4Fusion leverages a pre-trained network to perceive uncertainty in the fused images. By minimizing this uncertainty, S4Fusion adaptively highlights salient targets from both images. Extensive experiments demonstrate that our approach produces high-quality images and enhances performance in downstream tasks.
Authors: Pengyuan Lyu, Yulin Li, Hao Zhou, Weihong Ma, Xingyu Wan, Qunyi Xie, Liang Wu, Chengquan Zhang, Kun Yao, Errui Ding, Jingdong Wang
Abstract: Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images play crucial roles in information transmission but are accompanied by diverse challenges. Therefore, the efficient and effective understanding of text-rich images is a crucial litmus test for the capability of Vision-Language Models. We have crafted an efficient vision-language model, StrucTexTv3, tailored to tackle various intelligent tasks for text-rich images. The significant design of StrucTexTv3 is presented in the following aspects: Firstly, we adopt a combination of an effective multi-scale reduced visual transformer and a multi-granularity token sampler (MG-Sampler) as a visual token generator, successfully solving the challenges of high-resolution input and complex representation learning for text-rich images. Secondly, we enhance the perception and comprehension abilities of StrucTexTv3 through instruction learning, seamlessly integrating various text-oriented tasks into a unified framework. Thirdly, we have curated a comprehensive collection of high-quality text-rich images, abbreviated as TIM-30M, encompassing diverse scenarios like incidental scenes, office documents, web pages, and screenshots, thereby improving the robustness of our model. Our method achieved SOTA results in text-rich image perception tasks, and significantly improved performance in comprehension tasks. Among multimodal models with LLM decoder of approximately 1.8B parameters, it stands out as a leader, which also makes the deployment of edge devices feasible. In summary, the StrucTexTv3 model, featuring efficient structural design, outstanding performance, and broad adaptability, offers robust support for diverse intelligent application tasks involving text-rich images, thus exhibiting immense potential for widespread application.
Authors: Micha{\l} Koziarski, Bogus{\l}aw Cyganek, Przemys{\l}aw Niedziela, Bogus{\l}aw Olborski, Zbigniew Antosz, Marcin \.Zydak, Bogdan Kwolek, Pawe{\l} W\k{a}sowicz, Andrzej Buka{\l}a, Jakub Swad\'zba, Piotr Sitkowski
Abstract: Cancer diseases constitute one of the most significant societal challenges. In this paper, we introduce a novel histopathological dataset for prostate cancer detection. The proposed dataset, consisting of over 2.6 million tissue patches extracted from 430 fully annotated scans, 4675 scans with assigned binary diagnoses, and 46 scans with diagnoses independently provided by a group of histopathologists can be found at https://github.com/michalkoziarski/DiagSet. Furthermore, we propose a machine learning framework for detection of cancerous tissue regions and prediction of scan-level diagnosis, utilizing thresholding to abstain from the decision in uncertain cases. The proposed approach, composed of ensembles of deep neural networks operating on the histopathological scans at different scales, achieves 94.6% accuracy in patch-level recognition and is compared in a scan-level diagnosis with 9 human histopathologists showing high statistical agreement.
Authors: Kecheng Chen, Jie Liu, Renjie Wan, Victor Ho-Fun Lee, Varut Vardhanabhuti, Hong Yan, Haoliang Li
Abstract: Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning is widely used in this problem, but the performance of testing data (a.k.a. target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (a.k.a. source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance.
Authors: Bang Yang, Fenglin Liu, Yuexian Zou, Xian Wu, Yaowei Wang, David A. Clifton
Abstract: Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled downstream pairs for training. During training, ZeroNLG (i) projects different domains (across modalities and languages) to corresponding coordinates in a shared common latent space; (ii) bridges different domains by aligning their corresponding coordinates in this space; and (iii) builds an unsupervised multilingual auto-encoder to learn to generate text by reconstructing the input text given its coordinate in shared latent space. Consequently, during inference, based on the data-to-text pipeline, ZeroNLG can generate target sentences across different languages given the coordinate of input data in the common space. Within this unified framework, given visual (imaging or video) data as input, ZeroNLG can perform zero-shot visual captioning; given textual sentences as input, ZeroNLG can perform zero-shot machine translation. We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and believable outputs and significantly outperforms existing zero-shot methods.
Authors: Saikat Roy, Gregor Koehler, Constantin Ulrich, Michael Baumgartner, Jens Petersen, Fabian Isensee, Paul F. Jaeger, Klaus Maier-Hein
Abstract: There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images challenging. Convolutional networks, in contrast, have higher inductive biases and consequently, are easily trainable to high performance. Recently, the ConvNeXt architecture attempted to modernize the standard ConvNet by mirroring Transformer blocks. In this work, we improve upon this to design a modernized and scalable convolutional architecture customized to challenges of data-scarce medical settings. We introduce MedNeXt, a Transformer-inspired large kernel segmentation network which introduces - 1) A fully ConvNeXt 3D Encoder-Decoder Network for medical image segmentation, 2) Residual ConvNeXt up and downsampling blocks to preserve semantic richness across scales, 3) A novel technique to iteratively increase kernel sizes by upsampling small kernel networks, to prevent performance saturation on limited medical data, 4) Compound scaling at multiple levels (depth, width, kernel size) of MedNeXt. This leads to state-of-the-art performance on 4 tasks on CT and MRI modalities and varying dataset sizes, representing a modernized deep architecture for medical image segmentation. Our code is made publicly available at: https://github.com/MIC-DKFZ/MedNeXt.
Authors: Simon Dahan, Logan Z. J. Williams, Daniel Rueckert, Emma C. Robinson
Abstract: Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis. While Transformers have excelled as domain-agnostic architectures for sequence-to-sequence learning, the quadratic cost of the self-attention operation remains an obstacle for many dense prediction tasks. Inspired by some of the latest advances in hierarchical modelling with vision transformers, we introduce the Multiscale Surface Vision Transformer (MS-SiT) as a backbone architecture for surface deep learning. The self-attention mechanism is applied within local-mesh-windows to allow for high-resolution sampling of the underlying data, while a shifted-window strategy improves the sharing of information between windows. Neighbouring patches are successively merged, allowing the MS-SiT to learn hierarchical representations suitable for any prediction task. Results demonstrate that the MS-SiT outperforms existing surface deep learning methods for neonatal phenotyping prediction tasks using the Developing Human Connectome Project (dHCP) dataset. Furthermore, building the MS-SiT backbone into a U-shaped architecture for surface segmentation demonstrates competitive results on cortical parcellation using the UK Biobank (UKB) and manually-annotated MindBoggle datasets. Code and trained models are publicly available at https://github.com/metrics-lab/surface-vision-transformers.
URLs: https://github.com/metrics-lab/surface-vision-transformers.
Authors: Frank Permenter, Chenyang Yuan
Abstract: Denoising is intuitively related to projection. Indeed, under the manifold hypothesis, adding random noise is approximately equivalent to orthogonal perturbation. Hence, learning to denoise is approximately learning to project. In this paper, we use this observation to interpret denoising diffusion models as approximate gradient descent applied to the Euclidean distance function. We then provide straight-forward convergence analysis of the DDIM sampler under simple assumptions on the projection error of the denoiser. Finally, we propose a new gradient-estimation sampler, generalizing DDIM using insights from our theoretical results. In as few as 5-10 function evaluations, our sampler achieves state-of-the-art FID scores on pretrained CIFAR-10 and CelebA models and can generate high quality samples on latent diffusion models.
Authors: Meng Zhou, Amoon Jamzad, Jason Izard, Alexandre Menard, Robert Siemens, Parvin Mousavi
Abstract: Prostate Cancer (PCa) is a prevalent disease among men, and multi-parametric MRIs offer a non-invasive method for its detection. While MRI-based deep learning solutions have shown promise in supporting PCa diagnosis, acquiring sufficient training data, particularly in local clinics remains challenging. One potential solution is to take advantage of publicly available datasets to pre-train deep models and fine-tune them on the local data, but multi-source MRIs can pose challenges due to cross-domain distribution differences. These limitations hinder the adoption of explainable and reliable deep-learning solutions in local clinics for PCa diagnosis. In this work, we present a novel approach for unpaired image-to-image translation of prostate multi-parametric MRIs and an uncertainty-aware training approach for classifying clinically significant PCa, to be applied in data-constrained settings such as local and small clinics. Our approach involves a novel pipeline for translating unpaired 3.0T multi-parametric prostate MRIs to 1.5T, thereby augmenting the available training data. Additionally, we introduce an evidential deep learning approach to estimate model uncertainty and employ dataset filtering techniques during training. Furthermore, we propose a simple, yet efficient Evidential Focal Loss, combining focal loss with evidential uncertainty, to train our model effectively. Our experiments demonstrate that the proposed method significantly improves the Area Under ROC Curve (AUC) by over 20% compared to the previous work. Our code is available at https://github.com/med-i-lab/DT_UE_PCa
Authors: Aaron J. Li, Robin Netzorg, Zhihan Cheng, Zhuoqin Zhang, Bin Yu
Abstract: In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One such of these methods is the Prototypical Part Network (ProtoPNet), which attempts to classify images based on meaningful parts of the input. While this architecture is able to produce visually interpretable classifications, it often learns to classify based on parts of the image that are not semantically meaningful. To address this problem, we propose the Reward Reweighing, Reselecting, and Retraining (R3) post-processing framework, which performs three additional corrective updates to a pretrained ProtoPNet in an offline and efficient manner. The first two steps involve learning a reward model based on collected human feedback and then aligning the prototypes with human preferences. The final step is retraining, which realigns the base features and the classifier layer of the original model with the updated prototypes. We find that our R3 framework consistently improves both the interpretability and the predictive accuracy of ProtoPNet and its variants.
Authors: Jingyao Wang, Wenwen Qiang, Xingzhe Su, Changwen Zheng, Fuchun Sun, Hui Xiong
Abstract: Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of meta-learning models. However, this paper challenges this view through empirical and theoretical analysis. We obtain three conclusions: (i) there is no universal task sampling strategy that can guarantee the optimal performance of meta-learning models; (ii) over-constraining task diversity may incur the risk of under-fitting or over-fitting during training; and (iii) the generalization performance of meta-learning models are affected by task diversity, task entropy, and task difficulty. Based on this insight, we design a novel task sampler, called Adaptive Sampler (ASr). ASr is a plug-and-play module that can be integrated into any meta-learning framework. It dynamically adjusts task weights according to task diversity, task entropy, and task difficulty, thereby obtaining the optimal probability distribution for meta-training tasks. Finally, we conduct experiments on a series of benchmark datasets across various scenarios, and the results demonstrate that ASr has clear advantages.
Authors: Zeyu Tang, Xiaodan Xing, Guang Yang
Abstract: Deep learning-based Generative Models have the potential to convert low-resolution CT images into high-resolution counterparts without long acquisition times and increased radiation exposure in thin-slice CT imaging. However, procuring appropriate training data for these Super-Resolution (SR) models is challenging. Previous SR research has simulated thick-slice CT images from thin-slice CT images to create training pairs. However, these methods either rely on simplistic interpolation techniques that lack realism or sinogram reconstruction, which require the release of raw data and complex reconstruction algorithms. Thus, we introduce a simple yet realistic method to generate thick CT images from thin-slice CT images, facilitating the creation of training pairs for SR algorithms. The training pairs produced by our method closely resemble real data distributions (PSNR=49.74 vs. 40.66, p$<$0.05). A multivariate Cox regression analysis involving thick slice CT images with lung fibrosis revealed that only the radiomics features extracted using our method demonstrated a significant correlation with mortality (HR=1.19 and HR=1.14, p$<$0.005). This paper represents the first to identify and address the challenge of generating appropriate paired training data for Deep Learning-based CT SR models, which enhances the efficacy and applicability of SR models in real-world scenarios.
Authors: Simon Dahan, Logan Z. J. Williams, Yourong Guo, Daniel Rueckert, Emma C. Robinson
Abstract: The development of robust and generalisable models for encoding the spatio-temporal dynamics of human brain activity is crucial for advancing neuroscientific discoveries. However, significant individual variation in the organisation of the human cerebral cortex makes it difficult to identify population-level trends in these signals. Recently, Surface Vision Transformers (SiTs) have emerged as a promising approach for modelling cortical signals, yet they face some limitations in low-data scenarios due to the lack of inductive biases in their architecture. To address these challenges, this paper proposes the surface Masked AutoEncoder (sMAE) and video surface Masked AutoEncoder (vsMAE) - for multivariate and spatio-temporal pre-training of cortical signals over regular icosahedral grids. These models are trained to reconstruct cortical feature maps from masked versions of the input by learning strong latent representations of cortical structure and function. Such representations translate into better modelling of individual phenotypes and enhanced performance in downstream tasks. The proposed approach was evaluated on cortical phenotype regression using data from the young adult Human Connectome Project (HCP) and developing HCP (dHCP). Results show that (v)sMAE pre-trained models improve phenotyping prediction performance on multiple tasks by $\ge 26\%$, and offer faster convergence relative to models trained from scratch. Finally, we show that pre-training vision transformers on large datasets, such as the UK Biobank (UKB), supports transfer learning to low-data regimes. Our code and pre-trained models are publicly available at https://github.com/metrics-lab/surface-masked-autoencoders .
URLs: https://github.com/metrics-lab/surface-masked-autoencoders
Authors: Hejia Geng, Peng Li
Abstract: While spiking neural networks (SNNs) offer a promising neurally-inspired model of computation, they are vulnerable to adversarial attacks. We present the first study that draws inspiration from neural homeostasis to design a threshold-adapting leaky integrate-and-fire (TA-LIF) neuron model and utilize TA-LIF neurons to construct the adversarially robust homeostatic SNNs (HoSNNs) for improved robustness. The TA-LIF model incorporates a self-stabilizing dynamic thresholding mechanism, offering a local feedback control solution to the minimization of each neuron's membrane potential error caused by adversarial disturbance. Theoretical analysis demonstrates favorable dynamic properties of TA-LIF neurons in terms of the bounded-input bounded-output stability and suppressed time growth of membrane potential error, underscoring their superior robustness compared with the standard LIF neurons. When trained with weak FGSM attacks (attack budget = 2/255) and tested with much stronger PGD attacks (attack budget = 8/255), our HoSNNs significantly improve model accuracy on several datasets: from 30.54% to 74.91% on FashionMNIST, from 0.44% to 35.06% on SVHN, from 0.56% to 42.63% on CIFAR10, from 0.04% to 16.66% on CIFAR100, over the conventional LIF-based SNNs.
Authors: Purvi Goel, Kuan-Chieh Wang, C. Karen Liu, Kayvon Fatahalian
Abstract: Text-to-motion diffusion models can generate realistic animations from text prompts, but do not support fine-grained motion editing controls. In this paper, we present a method for using natural language to iteratively specify local edits to existing character animations, a task that is common in most computer animation workflows. Our key idea is to represent a space of motion edits using a set of kinematic motion editing operators (MEOs) whose effects on the source motion is well-aligned with user expectations. We provide an algorithm that leverages pre-existing language models to translate textual descriptions of motion edits into source code for programs that define and execute sequences of MEOs on a source animation. We execute MEOs by first translating them into keyframe constraints, and then use diffusion-based motion models to generate output motions that respect these constraints. Through a user study and quantitative evaluation, we demonstrate that our system can perform motion edits that respect the animator's editing intent, remain faithful to the original animation (it edits the original animation, but does not dramatically change it), and yield realistic character animation results.
Authors: Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
Abstract: With the emergence of pretrained vision-language models (VLMs), considerable efforts have been devoted to fine-tuning them for downstream tasks. Despite the progress made in designing efficient fine-tuning methods, such methods require access to the model's parameters, which can be challenging as model owners often opt to provide their models as a black box to safeguard model ownership. This paper proposes a \textbf{C}ollabo\textbf{ra}tive \textbf{F}ine-\textbf{T}uning (\textbf{CraFT}) approach for fine-tuning black-box VLMs to downstream tasks, where one only has access to the input prompts and the output predictions of the model. CraFT comprises two modules, a prompt generation module for learning text prompts and a prediction refinement module for enhancing output predictions in residual style. Additionally, we introduce an auxiliary prediction-consistent loss to promote consistent optimization across these modules. These modules are optimized by a novel collaborative training algorithm. Extensive experiments on few-shot classification over 15 datasets demonstrate the superiority of CraFT. The results show that CraFT achieves a decent gain of about 12\% with 16-shot datasets and only 8,000 queries. Moreover, CraFT trains faster and uses only about 1/80 of the memory footprint for deployment, while sacrificing only 1.62\% compared to the white-box method. Our code is publicly available at https://github.com/mrflogs/CraFT .
Authors: Jaemoo Choi, Jaewoong Choi, Myungjoo Kang
Abstract: Wasserstein Gradient Flow (WGF) describes the gradient dynamics of probability density within the Wasserstein space. WGF provides a promising approach for conducting optimization over the probability distributions. Numerically approximating the continuous WGF requires the time discretization method. The most well-known method for this is the JKO scheme. In this regard, previous WGF models employ the JKO scheme and parametrize transport map for each JKO step. However, this approach results in quadratic training complexity $O(K^2)$ with the number of JKO step $K$. This severely limits the scalability of WGF models. In this paper, we introduce a scalable WGF-based generative model, called Semi-dual JKO (S-JKO). Our model is based on the semi-dual form of the JKO step, derived from the equivalence between the JKO step and the Unbalanced Optimal Transport. Our approach reduces the training complexity to $O(K)$. We demonstrate that our model significantly outperforms existing WGF-based generative models, achieving FID scores of 2.62 on CIFAR-10 and 5.46 on CelebA-HQ-256, which are comparable to state-of-the-art image generative models.
Authors: Xiangming Gu, Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Ye Wang, Jing Jiang, Min Lin
Abstract: A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can jailbreak an MLLM and cause unaligned behaviors. In this work, we report an even more severe safety issue in multi-agent environments, referred to as infectious jailbreak. It entails the adversary simply jailbreaking a single agent, and without any further intervention from the adversary, (almost) all agents will become infected exponentially fast and exhibit harmful behaviors. To validate the feasibility of infectious jailbreak, we simulate multi-agent environments containing up to one million LLaVA-1.5 agents, and employ randomized pair-wise chat as a proof-of-concept instantiation for multi-agent interaction. Our results show that feeding an (infectious) adversarial image into the memory of any randomly chosen agent is sufficient to achieve infectious jailbreak. Finally, we derive a simple principle for determining whether a defense mechanism can provably restrain the spread of infectious jailbreak, but how to design a practical defense that meets this principle remains an open question to investigate. Our project page is available at https://sail-sg.github.io/Agent-Smith/.
Authors: Daeun Lee, Jaehong Yoon, Sung Ju Hwang
Abstract: Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which helps to selectively capture the domain adaptive knowledge with multiple domain routers, and (ii) Domain-Expert Synergy Loss to maximize the dependency between each domain and expert. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring ~98% fewer trainable parameters. We also provide analyses of our method, including the construction of experts, the effect of domain-adaptive experts, and visualizations.
Authors: Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen
Abstract: Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA). DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning, specifically employing LoRA for directional updates to efficiently minimize the number of trainable parameters. By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead. \ours~consistently outperforms LoRA on fine-tuning LLaMA, LLaVA, and VL-BART on various downstream tasks, such as commonsense reasoning, visual instruction tuning, and image/video-text understanding. Code is available at https://github.com/NVlabs/DoRA.
Authors: Chaoqun Du, Yizeng Han, Gao Huang
Abstract: Recent advancements in semi-supervised learning have focused on a more realistic yet challenging task: addressing imbalances in labeled data while the class distribution of unlabeled data remains both unknown and potentially mismatched. Current approaches in this sphere often presuppose rigid assumptions regarding the class distribution of unlabeled data, thereby limiting the adaptability of models to only certain distribution ranges. In this study, we propose a novel approach, introducing a highly adaptable framework, designated as SimPro, which does not rely on any predefined assumptions about the distribution of unlabeled data. Our framework, grounded in a probabilistic model, innovatively refines the expectation-maximization (EM) algorithm by explicitly decoupling the modeling of conditional and marginal class distributions. This separation facilitates a closed-form solution for class distribution estimation during the maximization phase, leading to the formulation of a Bayes classifier. The Bayes classifier, in turn, enhances the quality of pseudo-labels in the expectation phase. Remarkably, the SimPro framework not only comes with theoretical guarantees but also is straightforward to implement. Moreover, we introduce two novel class distributions broadening the scope of the evaluation. Our method showcases consistent state-of-the-art performance across diverse benchmarks and data distribution scenarios. Our code is available at https://github.com/LeapLabTHU/SimPro.
Authors: Wenbo Shao, Jiahui Xu, Wenhao Yu, Jun Li, Hong Wang
Abstract: In the rapidly evolving field of autonomous driving, reliable prediction is pivotal for vehicular safety. However, trajectory predictions often deviate from actual paths, particularly in complex and challenging environments, leading to significant errors. To address this issue, our study introduces a novel method for Dynamic Occupancy Set (DOS) prediction, it effectively combines advanced trajectory prediction networks with a DOS prediction module, overcoming the shortcomings of existing models. It provides a comprehensive and adaptable framework for predicting the potential occupancy sets of traffic participants. The innovative contributions of this study include the development of a novel DOS prediction model specifically tailored for navigating complex scenarios, the introduction of precise DOS mathematical representations, and the formulation of optimized loss functions that collectively advance the safety and efficiency of autonomous systems. Through rigorous validation, our method demonstrates marked improvements over traditional models, establishing a new benchmark for safety and operational efficiency in intelligent transportation systems.
Authors: Jonathan Heek, Emiel Hoogeboom, Tim Salimans
Abstract: Diffusion models are relatively easy to train but require many steps to generate samples. Consistency models are far more difficult to train, but generate samples in a single step. In this paper we propose Multistep Consistency Models: A unification between Consistency Models (Song et al., 2023) and TRACT (Berthelot et al., 2023) that can interpolate between a consistency model and a diffusion model: a trade-off between sampling speed and sampling quality. Specifically, a 1-step consistency model is a conventional consistency model whereas a $\infty$-step consistency model is a diffusion model. Multistep Consistency Models work really well in practice. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples, while retaining much of the sampling speed benefits. Notable results are 1.4 FID on Imagenet 64 in 8 step and 2.1 FID on Imagenet128 in 8 steps with consistency distillation, using simple losses without adversarial training. We also show that our method scales to a text-to-image diffusion model, generating samples that are close to the quality of the original model.
Authors: Albert J. Miao, Shan Lin, Jingpei Lu, Florian Richter, Benjamin Ostrander, Emily K. Funk, Ryan K. Orosco, Michael C. Yip
Abstract: Hemorrhaging occurs in surgeries of all types, forcing surgeons to quickly adapt to the visual interference that results from blood rapidly filling the surgical field. Introducing automation into the crucial surgical task of hemostasis management would offload mental and physical tasks from the surgeon and surgical assistants while simultaneously increasing the efficiency and safety of the operation. The first step in automation of hemostasis management is detection of blood in the surgical field. To propel the development of blood detection algorithms in surgeries, we present HemoSet, the first blood segmentation dataset based on bleeding during a live animal robotic surgery. Our dataset features vessel hemorrhage scenarios where turbulent flow leads to abnormal pooling geometries in surgical fields. These pools are formed in conditions endemic to surgical procedures -- uneven heterogeneous tissue, under glossy lighting conditions and rapid tool movement. We benchmark several state-of-the-art segmentation models and provide insight into the difficulties specific to blood detection. We intend for HemoSet to spur development of autonomous blood suction tools by providing a platform for training and refining blood segmentation models, addressing the precision needed for such robotics.
Authors: Abdelrhman Werby, Chenguang Huang, Martin B\"uchner, Abhinav Valada, Wolfram Burgard
Abstract: Recent open-vocabulary robot mapping methods enrich dense geometric maps with pre-trained visual-language features. While these maps allow for the prediction of point-wise saliency maps when queried for a certain language concept, large-scale environments and abstract queries beyond the object level still pose a considerable hurdle, ultimately limiting language-grounded robotic navigation. In this work, we present HOV-SG, a hierarchical open-vocabulary 3D scene graph mapping approach for language-grounded robot navigation. Leveraging open-vocabulary vision foundation models, we first obtain state-of-the-art open-vocabulary segment-level maps in 3D and subsequently construct a 3D scene graph hierarchy consisting of floor, room, and object concepts, each enriched with open-vocabulary features. Our approach is able to represent multi-story buildings and allows robotic traversal of those using a cross-floor Voronoi graph. HOV-SG is evaluated on three distinct datasets and surpasses previous baselines in open-vocabulary semantic accuracy on the object, room, and floor level while producing a 75% reduction in representation size compared to dense open-vocabulary maps. In order to prove the efficacy and generalization capabilities of HOV-SG, we showcase successful long-horizon language-conditioned robot navigation within real-world multi-storage environments. We provide code and trial video data at http://hovsg.github.io/.
URLs: http://hovsg.github.io/.
Authors: Yao Ni, Piotr Koniusz
Abstract: Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs often struggle with discriminator overfitting and unstable training. Batch Normalization (BN), despite being known for enhancing generalization and training stability, has rarely been used in the discriminator of Data-Efficient GANs. Our work addresses this gap by identifying a critical flaw in BN: the tendency for gradient explosion during the centering and scaling steps. To tackle this issue, we present CHAIN (lipsCHitz continuity constrAIned Normalization), which replaces the conventional centering step with zero-mean regularization and integrates a Lipschitz continuity constraint in the scaling step. CHAIN further enhances GAN training by adaptively interpolating the normalized and unnormalized features, effectively avoiding discriminator overfitting. Our theoretical analyses firmly establishes CHAIN's effectiveness in reducing gradients in latent features and weights, improving stability and generalization in GAN training. Empirical evidence supports our theory. CHAIN achieves state-of-the-art results in data-limited scenarios on CIFAR-10/100, ImageNet, five low-shot and seven high-resolution few-shot image datasets. Code: https://github.com/MaxwellYaoNi/CHAIN
Authors: Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth
Abstract: Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse process' task in learning generative trajectories, and results in costly inference for diffusion models. To address these limitations, we introduce Neural Flow Diffusion Models (NFDM), a novel framework that enhances diffusion models by supporting a broader range of forward processes beyond the standard Gaussian. We also propose a novel parameterization technique for learning the forward process. Our framework provides an end-to-end, simulation-free optimization objective, effectively minimizing a variational upper bound on the negative log-likelihood. Experimental results demonstrate NFDM's strong performance, evidenced by state-of-the-art likelihood estimation. Furthermore, we investigate NFDM's capacity for learning generative dynamics with specific characteristics, such as deterministic straight lines trajectories, and demonstrate how the framework may be adopted for learning bridges between two distributions. The results underscores NFDM's versatility and its potential for a wide range of applications.
Authors: Marek Wodzinski, Daria Hemmerling, Mateusz Daniol
Abstract: Thousands of people suffer from cranial injuries every year. They require personalized implants that need to be designed and manufactured before the reconstruction surgery. The manual design is expensive and time-consuming leading to searching for algorithms whose goal is to automatize the process. The problem can be formulated as volumetric shape completion and solved by deep neural networks dedicated to supervised image segmentation. However, such an approach requires annotating the ground-truth defects which is costly and time-consuming. Usually, the process is replaced with synthetic defect generation. However, even the synthetic ground-truth generation is time-consuming and limits the data heterogeneity, thus the deep models' generalizability. In our work, we propose an alternative and simple approach to use a self-supervised masked autoencoder to solve the problem. This approach by design increases the heterogeneity of the training set and can be seen as a form of data augmentation. We compare the proposed method with several state-of-the-art deep neural networks and show both the quantitative and qualitative improvement on the SkullBreak and SkullFix datasets. The proposed method can be used to efficiently reconstruct the cranial defects in real time.
Authors: Anthony Bilic, Chen Chen
Abstract: Binary breast cancer tumor segmentation with Magnetic Resonance Imaging (MRI) data is typically trained and evaluated on private medical data, which makes comparing deep learning approaches difficult. We propose a benchmark (BC-MRI-SEG) for binary breast cancer tumor segmentation based on publicly available MRI datasets. The benchmark consists of four datasets in total, where two datasets are used for supervised training and evaluation, and two are used for zero-shot evaluation. Additionally we compare state-of-the-art (SOTA) approaches on our benchmark and provide an exhaustive list of available public breast cancer MRI datasets. The source code has been made available at https://irulenot.github.io/BC_MRI_SEG_Benchmark.
Authors: Xiaoling Zhou, Wei Ye, Zhemg Lee, Rui Xie, Shikun Zhang
Abstract: Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To address this, we propose to augment the deep features of samples by incorporating their adversarial and anti-adversarial perturbation distributions, enabling adaptive adjustment in the learning difficulty tailored to each sample's specific characteristics. We then theoretically reveal that our augmentation process approximates the optimization of a surrogate loss function as the number of augmented copies increases indefinitely. This insight leads us to develop a meta-learning-based framework for optimizing classifiers with this novel loss, introducing the effects of augmentation while bypassing the explicit augmentation process. We conduct extensive experiments across four common biased learning scenarios: long-tail learning, generalized long-tail learning, noisy label learning, and subpopulation shift learning. The empirical results demonstrate that our method consistently achieves state-of-the-art performance, highlighting its broad adaptability.
Authors: Jiayi Wang, Yi-An Mao, Xiaoyu Ma, Sicen Guo, Yuting Shao, Xiao Lv, Wenting Han, Mark Christopher, Linda M. Zangwill, Yanlong Bi, Rui Fan
Abstract: Optic nerve head (ONH) detection has been a crucial area of study in ophthalmology for years. However, the significant discrepancy between fundus image datasets, each generated using a single type of fundus camera, poses challenges to the generalizability of ONH detection approaches developed based on semantic segmentation networks. Despite the numerous recent advancements in general-purpose semantic segmentation methods using convolutional neural networks (CNNs) and Transformers, there is currently a lack of benchmarks for these state-of-the-art (SoTA) networks specifically trained for ONH detection. Therefore, in this article, we make contributions from three key aspects: network design, the publication of a dataset, and the establishment of a comprehensive benchmark. Our newly developed ONH detection network, referred to as ODFormer, is based upon the Swin Transformer architecture and incorporates two novel components: a multi-scale context aggregator and a lightweight bidirectional feature recalibrator. Our published large-scale dataset, known as TongjiU-DROD, provides multi-resolution fundus images for each participant, captured using two distinct types of cameras. Our established benchmark involves three datasets: DRIONS-DB, DRISHTI-GS1, and TongjiU-DROD, created by researchers from different countries and containing fundus images captured from participants of diverse races and ages. Extensive experimental results demonstrate that our proposed ODFormer outperforms other state-of-the-art (SoTA) networks in terms of performance and generalizability. Our dataset and source code are publicly available at mias.group/ODFormer.
Authors: Lavsen Dahal, Mobina Ghojoghnejad, Dhrubajyoti Ghosh, Yubraj Bhandari, David Kim, Fong Chi Ho, Fakrul Islam Tushar, Sheng Luoa, Kyle J. Lafata, Ehsan Abadi, Ehsan Samei, Joseph Y. Lo, W. Paul Segars
Abstract: Virtual Imaging Trials (VIT) offer a cost-effective and scalable approach for evaluating medical imaging technologies. Computational phantoms, which mimic real patient anatomy and physiology, play a central role in VIT. However, the current libraries of computational phantoms face limitations, particularly in terms of sample size and diversity. Insufficient representation of the population hampers accurate assessment of imaging technologies across different patient groups. Traditionally, phantoms were created by manual segmentation, which is a laborious and time-consuming task, impeding the expansion of phantom libraries. This study presents a framework for realistic computational phantom modeling using a suite of four deep learning segmentation models, followed by three forms of automated organ segmentation quality control. Over 2500 computational phantoms with up to 140 structures illustrating a sophisticated approach to detailed anatomical modeling are released. Phantoms are available in both voxelized and surface mesh formats. The framework is aggregated with an in-house CT scanner simulator to produce realistic CT images. The framework can potentially advance virtual imaging trials, facilitating comprehensive and reliable evaluations of medical imaging technologies. Phantoms may be requested at https://cvit.duke.edu/resources/, code, model weights, and sample CT images are available at https://xcat-3.github.io.
URLs: https://cvit.duke.edu/resources/,, https://xcat-3.github.io.
Authors: Md. Toukir Ahmed, Arthur Villordon, Mohammed Kamruzzaman
Abstract: Hyperspectral imaging (HSI) has become a key technology for non-invasive quality evaluation in various fields, offering detailed insights through spatial and spectral data. Despite its efficacy, the complexity and high cost of HSI systems have hindered their widespread adoption. This study addressed these challenges by exploring deep learning-based hyperspectral image reconstruction from RGB (Red, Green, Blue) images, particularly for agricultural products. Specifically, different hyperspectral reconstruction algorithms, such as Hyperspectral Convolutional Neural Network - Dense (HSCNN-D), High-Resolution Network (HRNET), and Multi-Scale Transformer Plus Plus (MST++), were compared to assess the dry matter content of sweet potatoes. Among the tested reconstruction methods, HRNET demonstrated superior performance, achieving the lowest mean relative absolute error (MRAE) of 0.07, root mean square error (RMSE) of 0.03, and the highest peak signal-to-noise ratio (PSNR) of 32.28 decibels (dB). Some key features were selected using the genetic algorithm (GA), and their importance was interpreted using explainable artificial intelligence (XAI). Partial least squares regression (PLSR) models were developed using the RGB, reconstructed, and ground truth (GT) data. The visual and spectra quality of these reconstructed methods was compared with GT data, and predicted maps were generated. The results revealed the prospect of deep learning-based hyperspectral image reconstruction as a cost-effective and efficient quality assessment tool for agricultural and biological applications.
Authors: Brendan Park, Madeline Janecek, Naser Ezzati-Jivan, Yifeng Li, Ali Emami
Abstract: Large Language Models (LLMs) have demonstrated remarkable success in tasks like the Winograd Schema Challenge (WSC), showcasing advanced textual common-sense reasoning. However, applying this reasoning to multimodal domains, where understanding text and images together is essential, remains a substantial challenge. To address this, we introduce WinoVis, a novel dataset specifically designed to probe text-to-image models on pronoun disambiguation within multimodal contexts. Utilizing GPT-4 for prompt generation and Diffusion Attentive Attribution Maps (DAAM) for heatmap analysis, we propose a novel evaluation framework that isolates the models' ability in pronoun disambiguation from other visual processing challenges. Evaluation of successive model versions reveals that, despite incremental advancements, Stable Diffusion 2.0 achieves a precision of 56.7% on WinoVis, only marginally surpassing random guessing. Further error analysis identifies important areas for future research aimed at advancing text-to-image models in their ability to interpret and interact with the complex visual world.
Authors: Duhun Hwang, Suhyun Kang, Moonjung Eo, Jimyeong Kim, Wonjong Rhee
Abstract: The objective of Domain Generalization (DG) is to devise algorithms and models capable of achieving high performance on previously unseen test distributions. In the pursuit of this objective, average measure has been employed as the prevalent measure for evaluating models and comparing algorithms in the existing DG studies. Despite its significance, a comprehensive exploration of the average measure has been lacking and its suitability in approximating the true domain generalization performance has been questionable. In this study, we carefully investigate the limitations inherent in the average measure and propose worst+gap measure as a robust alternative. We establish theoretical grounds of the proposed measure by deriving two theorems starting from two different assumptions. We conduct extensive experimental investigations to compare the proposed worst+gap measure with the conventional average measure. Given the indispensable need to access the true DG performance for studying measures, we modify five existing datasets to come up with SR-CMNIST, C-Cats&Dogs, L-CIFAR10, PACS-corrupted, and VLCS-corrupted datasets. The experiment results unveil an inferior performance of the average measure in approximating the true DG performance and confirm the robustness of the theoretically supported worst+gap measure.