Authors: Alifu Xiafukaiti, Devanshu Garg, Aruto Hosaka, Koichi Yanagisawa, Yuichiro Minato, Tsuyoshi Yoshida
Abstract: Convolutional neural networks (CNNs) have gained widespread usage across various fields such as weather forecasting, computer vision, autonomous driving, and medical image analysis due to its exceptional ability to extract spatial information, share parameters, and learn local features. However, the practical implementation and commercialization of CNNs in these domains are hindered by challenges related to model sizes, overfitting, and computational time. To address these limitations, our study proposes a groundbreaking approach that involves tensorizing the dense layers in the CNN to reduce model size and computational time. Additionally, we incorporate attention layers into the CNN and train it using Contrastive self-supervised learning to effectively classify cloud information, which is crucial for accurate weather forecasting. We elucidate the key characteristics of tensorized neural network (TNN), including the data compression rate, accuracy, and computational speed. The results indicate how TNN change their properties under the batch size setting.
Authors: Tuan Nguyen, Max Mehltretter, Franz Rottensteiner
Abstract: Panoptic segmentation unifies semantic and instance segmentation and thus delivers a semantic class label and, for so-called thing classes, also an instance label per pixel. The differentiation of distinct objects of the same class with a similar appearance is particularly challenging and frequently causes such objects to be incorrectly assigned to a single instance. In the present work, we demonstrate that information on the 3D geometry of the observed scene can be used to mitigate this issue: We present a novel CNN-based method for panoptic segmentation which processes RGB images and depth maps given as input in separate network branches and fuses the resulting feature maps in a late fusion manner. Moreover, we propose a new depth-aware dice loss term which penalises the assignment of pixels to the same thing instance based on the difference between their associated distances to the camera. Experiments carried out on the Cityscapes dataset show that the proposed method reduces the number of objects that are erroneously merged into one thing instance and outperforms the method used as basis by 2.2% in terms of panoptic quality.
Authors: Guankun Wang, Long Bai, Wan Jun Nah, Jie Wang, Zhaoxi Zhang, Zhen Chen, Jinlin Wu, Mobarakol Islam, Hongbin Liu, Hongliang Ren
Abstract: Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simple structured answers and struggle with complex scenarios due to their limited capability in recognizing long-range dependencies and aligning multimodal information. In this paper, we introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios. Leveraging the pre-trained large vision-language model and specialized Visual Perception LoRA (VP-LoRA) blocks, our model excels in understanding complex visual-language tasks within surgical contexts. In addressing the visual grounding task, we propose the Token-Interaction (TIT) module, which strengthens the interaction between the grounding module and the language responses of the Large Visual Language Model (LVLM) after projecting them into the latent space. We demonstrate the effectiveness of Surgical-LVLM on several benchmarks, including EndoVis-17-VQLA, EndoVis-18-VQLA, and a newly introduced EndoVis Conversations dataset, which sets new performance standards. Our work contributes to advancing the field of automated surgical mentorship by providing a context-aware solution.
Authors: Siddharth Agrawal
Abstract: In the pursuit of advancing the state-of-the-art (SOTA) in road safety, traffic monitoring, surveillance, and logistics automation, we introduce the Global License Plate Dataset (GLPD). The dataset consists of over 5 million images, including diverse samples captured from 74 countries with meticulous annotations, including license plate characters, license plate segmentation masks, license plate corner vertices, as well as vehicle make, colour, and model. We also include annotated data on more classes, such as pedestrians, vehicles, roads, etc. We include a statistical analysis of the dataset, and provide baseline efficient and accurate models. The GLPD aims to be the primary benchmark dataset for model development and finetuning for license plate recognition.
Authors: Sreetama Sarkar, Souvik Kundu, Kai Zheng, Peter A. Beerel
Abstract: The ubiquity of vision transformers (ViTs) for various edge applications, including personalized learning, has created the demand for on-device fine-tuning. However, training with the limited memory and computation power of edge devices remains a significant challenge. In particular, the memory required for training is much higher than that needed for inference, primarily due to the need to store activations across all layers in order to compute the gradients needed for weight updates. Previous works have explored reducing this memory requirement via frozen-weight training as well storing the activations in a compressed format. However, these methods are deemed inefficient due to their inability to provide training or inference speedup. In this paper, we first investigate the limitations of existing on-device training methods aimed at reducing memory and compute requirements. We then present block selective reprogramming (BSR) in which we fine-tune only a fraction of total blocks of a pre-trained model and selectively drop tokens based on self-attention scores of the frozen layers. To show the efficacy of BSR, we present extensive evaluations on ViT-B and DeiT-S with five different datasets. Compared to the existing alternatives, our approach simultaneously reduces training memory by up to 1.4x and compute cost by up to 2x while maintaining similar accuracy. We also showcase results for Mixture-of-Expert (MoE) models, demonstrating the effectiveness of our approach in multitask learning scenarios.
Authors: Gabriel Moreira, Manuel Marques, Jo\~ao Paulo Costeira, Alexander Hauptmann
Abstract: The precise estimation of camera poses within large camera networks is a foundational problem in computer vision and robotics, with broad applications spanning autonomous navigation, surveillance, and augmented reality. In this paper, we introduce a novel methodology that extends state-of-the-art Pose Graph Optimization (PGO) techniques. Departing from the conventional PGO paradigm, which primarily relies on camera-camera edges, our approach centers on the introduction of a dynamic element - any rigid object free to move in the scene - whose pose can be reliably inferred from a single image. Specifically, we consider the bipartite graph encompassing cameras, object poses evolving dynamically, and camera-object relative transformations at each time step. This shift not only offers a solution to the challenges encountered in directly estimating relative poses between cameras, particularly in adverse environments, but also leverages the inclusion of numerous object poses to ameliorate and integrate errors, resulting in accurate camera pose estimates. Though our framework retains compatibility with traditional PGO solvers, its efficacy benefits from a custom-tailored optimization scheme. To this end, we introduce an iterative primal-dual algorithm, capable of handling large graphs. Empirical benchmarks, conducted on a new dataset of simulated indoor environments, substantiate the efficacy and efficiency of our approach.
Authors: Constance Ferragu, Philomene Chagniot, Vincent Coyette
Abstract: In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup, excluding the use of external data. Given the recent advancements in large language and vision models, a question naturally arises: can these models directly perform well on meta-few-shot learning benchmarks? Multimodal foundation models like CLIP, which learn a joint (image, text) embedding, are of particular interest. Indeed, multimodal training has proven to enhance model robustness, especially regarding ambiguities, a limitation frequently observed in the few-shot setup. This study demonstrates that combining modalities from CLIP's text and image encoders outperforms state-of-the-art meta-few-shot learners on widely adopted benchmarks, all without additional training. Our results confirm the potential and robustness of multimodal foundation models like CLIP and serve as a baseline for existing and future approaches leveraging such models.
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: Nisha L. Raichur, Lucas Heublein, Tobias Feigl, Alexander R\"ugamer, Christopher Mutschler, Felix Ott
Abstract: The primary objective of methods in continual learning is to learn tasks in a sequential manner over time from a stream of data, while mitigating the detrimental phenomenon of catastrophic forgetting. In this paper, we focus on learning an optimal representation between previous class prototypes and newly encountered ones. We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL) tailored specifically for class-incremental learning scenarios. Therefore, we introduce a contrastive loss that incorporates new classes into the latent representation by reducing the intra-class distance and increasing the inter-class distance. Our approach dynamically adapts the balance between the cross-entropy and contrastive loss functions with a Bayesian learning technique. Empirical evaluations conducted on both the CIFAR-10 dataset for image classification and images of a GNSS-based dataset for interference classification validate the efficacy of our method, showcasing its superiority over existing state-of-the-art approaches.
Authors: J. Buitenhuis
Abstract: We explore the field of wildlife re-identification by implementing an MLP from scratch using NumPy, A DCNN using Keras, and a binary classifier with LightGBM for the purpose of learning for an assignment. Analyzing the performance of multiple models on multiple datasets. We attempt to replicate prior research in metric learning for wildlife re-identification. Firstly, we find that the usage of MLPs trained for classification, then removing the output layer and using the second last layer as an embedding was not a successful strategy for similar learning; it seems like losses designed for embeddings such as triplet loss are required. The DCNNS performed well on some datasets but poorly on others, which did not align with findings in previous literature. The LightGBM classifier overfitted too heavily and was not significantly better than a constant model when trained and evaluated on all pairs using accuracy as a metric. The technical implementations used seem to match standards according to comparisons with documentation examples and good results on certain datasets. However, there is still more to explore in regards to being able to fully recreate past literature.
Authors: Setareh Cohan, Guy Tevet, Daniele Reda, Xue Bin Peng, Michiel van de Panne
Abstract: Motion in-betweening, a fundamental task in character animation, consists of generating motion sequences that plausibly interpolate user-provided keyframe constraints. It has long been recognized as a labor-intensive and challenging process. We investigate the potential of diffusion models in generating diverse human motions guided by keyframes. Unlike previous inbetweening methods, we propose a simple unified model capable of generating precise and diverse motions that conform to a flexible range of user-specified spatial constraints, as well as text conditioning. To this end, we propose Conditional Motion Diffusion In-betweening (CondMDI) which allows for arbitrary dense-or-sparse keyframe placement and partial keyframe constraints while generating high-quality motions that are diverse and coherent with the given keyframes. We evaluate the performance of CondMDI on the text-conditioned HumanML3D dataset and demonstrate the versatility and efficacy of diffusion models for keyframe in-betweening. We further explore the use of guidance and imputation-based approaches for inference-time keyframing and compare CondMDI against these methods.
Authors: Xinli Guo, Peng Han, Weidong Zhang, Hongtian Chen
Abstract: With their high-fidelity scene representation capability, the attention of SLAM field is deeply attracted by the Neural Radiation Field (NeRF) and 3D Gaussian Splatting (3DGS). Recently, there has been a Surge in NeRF-based SLAM, while 3DGS-based SLAM is sparse. A novel 3DGS-based SLAM approach with a fusion of deep visual feature, dual keyframe selection and 3DGS is presented in this paper. Compared with the existing methods, the proposed selectively tracking is achieved by feature extraction and motion filter on each frame. The joint optimization of pose and 3D Gaussian runs through the entire mapping process. Additionally, the coarse-to-fine pose estimation and compact Gaussian scene representation are implemented by dual keyfeature selection and novel loss functions. Experimental results demonstrate that the proposed algorithm not only outperforms the existing methods in tracking and mapping, but also has less memory usage.
Authors: Junzhang Liu, Zhecan Wang, Hammad Ayyubi, Haoxuan You, Chris Thomas, Rui Sun, Shih-Fu Chang, Kai-Wei Chang
Abstract: Despite the widespread adoption of Vision-Language Understanding (VLU) benchmarks such as VQA v2, OKVQA, A-OKVQA, GQA, VCR, SWAG, and VisualCOMET, our analysis reveals a pervasive issue affecting their integrity: these benchmarks contain samples where answers rely on assumptions unsupported by the provided context. Training models on such data foster biased learning and hallucinations as models tend to make similar unwarranted assumptions. To address this issue, we collect contextual data for each sample whenever available and train a context selection module to facilitate evidence-based model predictions. Strong improvements across multiple benchmarks demonstrate the effectiveness of our approach. Further, we develop a general-purpose Context-AwaRe Abstention (CARA) detector to identify samples lacking sufficient context and enhance model accuracy by abstaining from responding if the required context is absent. CARA exhibits generalization to new benchmarks it wasn't trained on, underscoring its utility for future VLU benchmarks in detecting or cleaning samples with inadequate context. Finally, we curate a Context Ambiguity and Sufficiency Evaluation (CASE) set to benchmark the performance of insufficient context detectors. Overall, our work represents a significant advancement in ensuring that vision-language models generate trustworthy and evidence-based outputs in complex real-world scenarios.
Authors: Xiaolu Kang, Zhuoqi Ma, Kang Liu, Yunan Li, Qiguang Miao
Abstract: Polyp segmentation for colonoscopy images is of vital importance in clinical practice. It can provide valuable information for colorectal cancer diagnosis and surgery. While existing methods have achieved relatively good performance, polyp segmentation still faces the following challenges: (1) Varying lighting conditions in colonoscopy and differences in polyp locations, sizes, and morphologies. (2) The indistinct boundary between polyps and surrounding tissue. To address these challenges, we propose a Multi-scale information sharing and selection network (MISNet) for polyp segmentation task. We design a Selectively Shared Fusion Module (SSFM) to enforce information sharing and active selection between low-level and high-level features, thereby enhancing model's ability to capture comprehensive information. We then design a Parallel Attention Module (PAM) to enhance model's attention to boundaries, and a Balancing Weight Module (BWM) to facilitate the continuous refinement of boundary segmentation in the bottom-up process. Experiments on five polyp segmentation datasets demonstrate that MISNet successfully improved the accuracy and clarity of segmentation result, outperforming state-of-the-art methods.
Authors: Fan Yang, Mingxuan Xia, Sangzhou Xia, Chicheng Ma, Hui Hui
Abstract: Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms generally adopt prompt learning strategies for adversarial fine-tuning to improve the adversarial robustness of the pre-trained model while keeping the efficiency of adapting to downstream tasks. Such a setup leads to the problem of over-fitting which impedes further improvement of the model's generalization capacity on both clean and adversarial examples. In this work, we propose an adaptive Consistency-guided Adversarial Prompt Tuning (i.e., CAPT) framework that utilizes multi-modal prompt learning to enhance the alignment of image and text features for adversarial examples and leverage the strong generalization of pre-trained CLIP to guide the model-enhancing its robust generalization on adversarial examples while maintaining its accuracy on clean ones. We also design a novel adaptive consistency objective function to balance the consistency of adversarial inputs and clean inputs between the fine-tuning model and the pre-trained model. We conduct extensive experiments across 14 datasets and 4 data sparsity schemes (from 1-shot to full training data settings) to show the superiority of CAPT over other state-of-the-art adaption methods. CAPT demonstrated excellent performance in terms of the in-distribution performance and the generalization under input distribution shift and across datasets.
Authors: Madhu Vankadari, Samuel Hodgson, Sangyun Shin, Kaichen Zhou Andrew Markham, Niki Trigoni
Abstract: Self-supervised depth estimation algorithms rely heavily on frame-warping relationships, exhibiting substantial performance degradation when applied in challenging circumstances, such as low-visibility and nighttime scenarios with varying illumination conditions. Addressing this challenge, we introduce an algorithm designed to achieve accurate self-supervised stereo depth estimation focusing on nighttime conditions. Specifically, we use pretrained visual foundation models to extract generalised features across challenging scenes and present an efficient method for matching and integrating these features from stereo frames. Moreover, to prevent pixels violating photometric consistency assumption from negatively affecting the depth predictions, we propose a novel masking approach designed to filter out such pixels. Lastly, addressing weaknesses in the evaluation of current depth estimation algorithms, we present novel evaluation metrics. Our experiments, conducted on challenging datasets including Oxford RobotCar and Multi-Spectral Stereo, demonstrate the robust improvements realized by our approach. Code is available at: https://github.com/madhubabuv/dtd
Authors: Mengxi Zhang, Kang Rong
Abstract: Current multimodal Large Language Models (MLLMs) suffer from ``hallucination'', occasionally generating responses that are not grounded in the input images. To tackle this challenge, one promising path is to utilize reinforcement learning from human feedback (RLHF), which steers MLLMs towards learning superior responses while avoiding inferior ones. We rethink the common practice of using binary preferences (\emph{i.e.}, superior, inferior), and find that adopting multi-level preferences (\emph{e.g.}, superior, medium, inferior) is better for two benefits: 1) It narrows the gap between adjacent levels, thereby encouraging MLLMs to discern subtle differences. 2) It further integrates cross-level comparisons (beyond adjacent-level comparisons), thus providing a broader range of comparisons with hallucination examples. To verify our viewpoint, we present the Automated Multi-level Preference (\textbf{AMP}) framework for MLLMs. To facilitate this framework, we first develop an automated dataset generation pipeline that provides high-quality multi-level preference datasets without any human annotators. Furthermore, we design the Multi-level Direct Preference Optimization (MDPO) algorithm to robustly conduct complex multi-level preference learning. Additionally, we propose a new hallucination benchmark, MRHal-Bench. Extensive experiments across public hallucination and general benchmarks, as well as our MRHal-Bench, demonstrate the effectiveness of our proposed method.
Authors: Mallika Garg, Debashis Ghosh, Pyari Mohan Pradhan
Abstract: Transformer model have achieved state-of-the-art results in many applications like NLP, classification, etc. But their exploration in gesture recognition task is still limited. So, we propose a novel GestFormer architecture for dynamic hand gesture recognition. The motivation behind this design is to propose a resource efficient transformer model, since transformers are computationally expensive and very complex. So, we propose to use a pooling based token mixer named PoolFormer, since it uses only pooling layer which is a non-parametric layer instead of quadratic attention. The proposed model also leverages the space-invariant features of the wavelet transform and also the multiscale features are selected using multi-scale pooling. Further, a gated mechanism helps to focus on fine details of the gesture with the contextual information. This enhances the performance of the proposed model compared to the traditional transformer with fewer parameters, when evaluated on dynamic hand gesture datasets, NVidia Dynamic Hand Gesture and Briareo datasets. To prove the efficacy of the proposed model, we have experimented on single as well multimodal inputs such as infrared, normals, depth, optical flow and color images. We have also compared the proposed GestFormer in terms of resource efficiency and number of operations. The source code is available at https://github.com/mallikagarg/GestFormer.
Authors: Ying Jin, Pengyang Ling, Xiaoyi Dong, Pan Zhang, Jiaqi Wang, Dahua Lin
Abstract: Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images. Current approaches typically comprehend explicit and specific instructions. However, they often exhibit a deficiency in executing active reasoning capacities required to comprehend instructions that are implicit or insufficiently defined. To enhance active reasoning capabilities and impart intelligence to the editing model, we introduce ReasonPix2Pix, a comprehensive reasoning-attentive instruction editing dataset. The dataset is characterized by 1) reasoning instruction, 2) more realistic images from fine-grained categories, and 3) increased variances between input and edited images. When fine-tuned with our dataset under supervised conditions, the model demonstrates superior performance in instructional editing tasks, independent of whether the tasks require reasoning or not. The code, model, and dataset will be publicly available.
Authors: Yichen Yan, Xingjian He, Sihan Chen, Shichen Lu, Jing Liu
Abstract: Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous methods typically rely on single-modality features, such as vision or language features, to guide the multi-modal fusion process. However, this approach limits the interaction between vision and language, leading to a lack of fine-grained correlation between the language description and pixel-level details during the decoding process. In this paper, we introduce FCNet, a framework that employs a bi-directional guided fusion approach where both vision and language play guiding roles. Specifically, we use a vision-guided approach to conduct initial multi-modal fusion, obtaining multi-modal features that focus on key vision information. We then propose a language-guided calibration module to further calibrate these multi-modal features, ensuring they understand the context of the input sentence. This bi-directional vision-language guided approach produces higher-quality multi-modal features sent to the decoder, facilitating adaptive propagation of fine-grained semantic information from textual features to visual features. Experiments on RefCOCO, RefCOCO+, and G-Ref datasets with various backbones consistently show our approach outperforming state-of-the-art methods.
Authors: Chengcheng Feng, Mu He, Qiuyu Tian, Haojie Yin, Xiaofang Zhao, Hongwei Tang, Xingqiang Wei
Abstract: As deep learning technology continues to advance, image generation models, especially models like Stable Diffusion, are finding increasingly widespread application in visual arts creation. However, these models often face challenges such as overfitting, lack of stability in generated results, and difficulties in accurately capturing the features desired by creators during the fine-tuning process. In response to these challenges, we propose an innovative method that integrates Singular Value Decomposition (SVD) into the Low-Rank Adaptation (LoRA) parameter update strategy, aimed at enhancing the fine-tuning efficiency and output quality of image generation models. By incorporating SVD within the LoRA framework, our method not only effectively reduces the risk of overfitting but also enhances the stability of model outputs, and captures subtle, creator-desired feature adjustments more accurately. We evaluated our method on multiple datasets, and the results show that, compared to traditional fine-tuning methods, our approach significantly improves the model's generalization ability and creative flexibility while maintaining the quality of generation. Moreover, this method maintains LoRA's excellent performance under resource-constrained conditions, allowing for significant improvements in image generation quality without sacrificing the original efficiency and resource advantages.
Authors: Christian Rathgeb, Mathias Ibsen, Denise Hartmann, Simon Hradetzky, Berglind \'Olafsd\'ottir
Abstract: The fairness of biometric systems, in particular facial recognition, is often analysed for larger demographic groups, e.g. female vs. male or black vs. white. In contrast to this, minority groups are commonly ignored. This paper investigates the performance of facial recognition algorithms on individuals with Down syndrome, a common chromosomal abnormality that affects approximately one in 1,000 births per year. To do so, a database of 98 individuals with Down syndrome, each represented by at least five facial images, is semi-automatically collected from YouTube. Subsequently, two facial image quality assessment algorithms and five recognition algorithms are evaluated on the newly collected database and on the public facial image databases CelebA and FRGCv2. The results show that the quality scores of facial images for individuals with Down syndrome are comparable to those of individuals without Down syndrome captured under similar conditions. Furthermore, it is observed that face recognition performance decreases significantly for individuals with Down syndrome, which is largely attributed to the increased likelihood of false matches.
Authors: Xingyu Miao, Haoran Duan, Varun Ojha, Jun Song, Tejal Shah, Yang Long, Rajiv Ranjan
Abstract: In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversion process of DDIM to generate two paths from the same starting point for calculation. Since both paths start from the same starting point, TSM can reduce the accumulated error compared to ISM, thus alleviating the problem of pseudo ground truth inconsistency. TSM enhances the stability and consistency of the model's generated paths during the distillation process. We demonstrate this experimentally and further show that ISM is a special case of TSM. Furthermore, to optimize the current multi-stage optimization process from high-resolution text to 3D generation, we adopt Stable Diffusion XL for guidance. In response to the issues of abnormal replication and splitting caused by unstable gradients during the 3D Gaussian splatting process when using Stable Diffusion XL, we propose a pixel-by-pixel gradient clipping method. Extensive experiments show that our model significantly surpasses the state-of-the-art models in terms of visual quality and performance. Code: \url{https://github.com/xingy038/Dreamer-XL}.
Authors: Qifeng Chen, Rengan Xie, Kai Huang, Qi Wang, Wenting Zheng, Rong Li, Yuchi Huo
Abstract: Recently, implicit neural representation has been widely used to generate animatable human avatars. However, the materials and geometry of those representations are coupled in the neural network and hard to edit, which hinders their application in traditional graphics engines. We present a framework for acquiring human avatars that are attached with high-resolution physically-based material textures and triangular mesh from monocular video. Our method introduces a novel information fusion strategy to combine the information from the monocular video and synthesize virtual multi-view images to tackle the sparsity of the input view. We reconstruct humans as deformable neural implicit surfaces and extract triangle mesh in a well-behaved pose as the initial mesh of the next stage. In addition, we introduce an approach to correct the bias for the boundary and size of the coarse mesh extracted. Finally, we adapt prior knowledge of the latent diffusion model at super-resolution in multi-view to distill the decomposed texture. Experiments show that our approach outperforms previous representations in terms of high fidelity, and this explicit result supports deployment on common renderers.
Authors: Bing Cao, Haiyu Yao, Pengfei Zhu, Qinghua Hu
Abstract: Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features of tiny objects. Existing methods usually perform generation-based feature enhancement, which is seriously affected by spurious textures and artifacts, making it difficult to make the tiny-object-specific features visible and clear for detection. To address this issue, we propose a self-reconstructed tiny object detection (SR-TOD) framework. We for the first time introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. This inspires us to enhance the weak representations of tiny objects under the guidance of the difference maps. Thus, improving the visibility of tiny objects for the detectors. Building on this, we further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear. In addition, we further propose a new multi-instance anti-UAV dataset, which is called DroneSwarms dataset and contains a large number of tiny drones with the smallest average size to date. Extensive experiments on the DroneSwarms dataset and other datasets demonstrate the effectiveness of the proposed method. The code and dataset will be publicly available.
Authors: Zeyu Zhang, Yiran Wang, Biao Wu, Shuo Chen, Zhiyuan Zhang, Shiya Huang, Wenbo Zhang, Meng Fang, Ling Chen, Yang Zhao
Abstract: In recent years, there has been significant interest in creating 3D avatars and motions, driven by their diverse applications in areas like film-making, video games, AR/VR, and human-robot interaction. However, current efforts primarily concentrate on either generating the 3D avatar mesh alone or producing motion sequences, with integrating these two aspects proving to be a persistent challenge. Additionally, while avatar and motion generation predominantly target humans, extending these techniques to animals remains a significant challenge due to inadequate training data and methods. To bridge these gaps, our paper presents three key contributions. Firstly, we proposed a novel agent-based approach named Motion Avatar, which allows for the automatic generation of high-quality customizable human and animal avatars with motions through text queries. The method significantly advanced the progress in dynamic 3D character generation. Secondly, we introduced a LLM planner that coordinates both motion and avatar generation, which transforms a discriminative planning into a customizable Q&A fashion. Lastly, we presented an animal motion dataset named Zoo-300K, comprising approximately 300,000 text-motion pairs across 65 animal categories and its building pipeline ZooGen, which serves as a valuable resource for the community. See project website https://steve-zeyu-zhang.github.io/MotionAvatar/
Authors: Wuzhou Li, Jiawei Zhou, Xiang Li, Yi Cao, Guang Jin, Xuemin Zhang
Abstract: Recently, the field of few-shot detection within remote sensing imagery has witnessed significant advancements. Despite these progresses, the capacity for continuous conceptual learning still poses a significant challenge to existing methodologies. In this paper, we explore the intricate task of incremental few-shot object detection in remote sensing images. We introduce a pioneering fine-tuningbased technique, termed InfRS, designed to facilitate the incremental learning of novel classes using a restricted set of examples, while concurrently preserving the performance on established base classes without the need to revisit previous datasets. Specifically, we pretrain the model using abundant data from base classes and then generate a set of class-wise prototypes that represent the intrinsic characteristics of the data. In the incremental learning stage, we introduce a Hybrid Prototypical Contrastive (HPC) encoding module for learning discriminative representations. Furthermore, we develop a prototypical calibration strategy based on the Wasserstein distance to mitigate the catastrophic forgetting problem. Comprehensive evaluations on the NWPU VHR-10 and DIOR datasets demonstrate that our model can effectively solve the iFSOD problem in remote sensing images. Code will be released.
Authors: Ximiao Zhang, Min Xu, Dehui Qiu, Ruixin Yan, Ning Lang, Xiuzhuang Zhou
Abstract: In the field of medical decision-making, precise anomaly detection in medical imaging plays a pivotal role in aiding clinicians. However, previous work is reliant on large-scale datasets for training anomaly detection models, which increases the development cost. This paper first focuses on the task of medical image anomaly detection in the few-shot setting, which is critically significant for the medical field where data collection and annotation are both very expensive. We propose an innovative approach, MediCLIP, which adapts the CLIP model to few-shot medical image anomaly detection through self-supervised fine-tuning. Although CLIP, as a vision-language model, demonstrates outstanding zero-/fewshot performance on various downstream tasks, it still falls short in the anomaly detection of medical images. To address this, we design a series of medical image anomaly synthesis tasks to simulate common disease patterns in medical imaging, transferring the powerful generalization capabilities of CLIP to the task of medical image anomaly detection. When only few-shot normal medical images are provided, MediCLIP achieves state-of-the-art performance in anomaly detection and location compared to other methods. Extensive experiments on three distinct medical anomaly detection tasks have demonstrated the superiority of our approach. The code is available at https://github.com/cnulab/MediCLIP.
Authors: Duo Peng, Qiuhong Ke, Jun Liu
Abstract: Text-to-Image (T2I) models have raised security concerns due to their potential to generate inappropriate or harmful images. In this paper, we propose UPAM, a novel framework that investigates the robustness of T2I models from the attack perspective. Unlike most existing attack methods that focus on deceiving textual defenses, UPAM aims to deceive both textual and visual defenses in T2I models. UPAM enables gradient-based optimization, offering greater effectiveness and efficiency than previous methods. Given that T2I models might not return results due to defense mechanisms, we introduce a Sphere-Probing Learning (SPL) scheme to support gradient optimization even when no results are returned. Additionally, we devise a Semantic-Enhancing Learning (SEL) scheme to finetune UPAM for generating target-aligned images. Our framework also ensures attack stealthiness. Extensive experiments demonstrate UPAM's effectiveness and efficiency.
Authors: Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan G\"unnemann
Abstract: When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled data. In this context, robust out-of-distribution (OOD) detection mechanisms are essential for handling data outside the target distribution of the application. However, current works investigate both problems separately. In this work, we introduce SISOM as the first unified solution for both AL and OOD detection. By leveraging feature space distance metrics SISOM combines the strengths of the currently independent tasks to solve both effectively. We conduct extensive experiments showing the problems arising when migrating between both tasks. In these evaluations SISOM underlined its effectiveness by achieving first place in two of the widely used OpenOOD benchmarks and second place in the remaining one. In AL, SISOM outperforms others and delivers top-1 performance in three benchmarks
Authors: Danli Shi, Weiyi Zhang, Xiaolan Chen, Yexin Liu, Jianchen Yang, Siyu Huang, Yih Chung Tham, Yingfeng Zheng, Mingguang He
Abstract: Artificial intelligence (AI) is vital in ophthalmology, tackling tasks like diagnosis, classification, and visual question answering (VQA). However, existing AI models in this domain often require extensive annotation and are task-specific, limiting their clinical utility. While recent developments have brought about foundation models for ophthalmology, they are limited by the need to train separate weights for each imaging modality, preventing a comprehensive representation of multi-modal features. This highlights the need for versatile foundation models capable of handling various tasks and modalities in ophthalmology. To address this gap, we present EyeFound, a multimodal foundation model for ophthalmic images. Unlike existing models, EyeFound learns generalizable representations from unlabeled multimodal retinal images, enabling efficient model adaptation across multiple applications. Trained on 2.78 million images from 227 hospitals across 11 ophthalmic modalities, EyeFound facilitates generalist representations and diverse multimodal downstream tasks, even for detecting challenging rare diseases. It outperforms previous work RETFound in diagnosing eye diseases, predicting systemic disease incidents, and zero-shot multimodal VQA. EyeFound provides a generalizable solution to improve model performance and lessen the annotation burden on experts, facilitating widespread clinical AI applications from retinal imaging.
Authors: Yuqiang Lin, Sam Lockyer, Adrian Evans, Markus Zarbock, Nic Zhang
Abstract: Multi-Target Multi-Camera Tracking (MTMCT) has broad applications and forms the basis for numerous future city-wide systems (e.g. traffic management, crash detection, etc.). However, the challenge of matching vehicle trajectories across different cameras based solely on feature extraction poses significant difficulties. This article introduces an innovative multi-camera vehicle tracking system that utilizes a self-supervised camera link model. In contrast to related works that rely on manual spatial-temporal annotations, our model automatically extracts crucial multi-camera relationships for vehicle matching. The camera link is established through a pre-matching process that evaluates feature similarities, pair numbers, and time variance for high-quality tracks. This process calculates the probability of spatial linkage for all camera combinations, selecting the highest scoring pairs to create camera links. Our approach significantly improves deployment times by eliminating the need for human annotation, offering substantial improvements in efficiency and cost-effectiveness when it comes to real-world application. This pairing process supports cross camera matching by setting spatial-temporal constraints, reducing the searching space for potential vehicle matches. According to our experimental results, the proposed method achieves a new state-of-the-art among automatic camera-link based methods in CityFlow V2 benchmarks with 61.07% IDF1 Score.
Authors: Yuanzhe Liu, Yixiang Mao, Yao Wang
Abstract: This work applies an encoder-decoder-based machine learning network to detect and track the motion and growth of the flowering stem apex of Arabidopsis Thaliana. Based on the CenterTrack, a machine learning back-end network, we trained a model based on ten time-lapsed labeled videos and tested against three videos.
Authors: Fadila Wendigoundi Douamba, Jianjun Song, Ling Fu, Yuliang Liu, Xiang Bai
Abstract: Scene text recognition is essential in many applications, including automated translation, information retrieval, driving assistance, and enhancing accessibility for individuals with visual impairments. Much research has been done to improve the accuracy and performance of scene text detection and recognition models. However, most of this research has been conducted in the most common languages, English and Chinese. There is a significant gap in low-resource languages, especially the Swahili Language. Swahili is widely spoken in East African countries but is still an under-explored language in scene text recognition. No studies have been focused explicitly on Swahili natural scene text detection and recognition, and no dataset for Swahili language scene text detection and recognition is publicly available. We propose a comprehensive dataset of Swahili scene text images and evaluate the dataset on different scene text detection and recognition models. The dataset contains 976 images collected in different places and under various circumstances. Each image has its annotation at the word level. The proposed dataset can also serve as a benchmark dataset specific to the Swahili language for evaluating and comparing different approaches and fostering future research endeavors. The dataset is available on GitHub via this link: https://github.com/FadilaW/Swahili-STR-Dataset
Authors: Ziyu Zhu, Zhuofan Zhang, Xiaojian Ma, Xuesong Niu, Yixin Chen, Baoxiong Jia, Zhidong Deng, Siyuan Huang, Qing Li
Abstract: A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene. However, a considerable gap exists between existing methods and such a unified model, due to the independent application of representation and insufficient exploration of 3D multi-task training. In this paper, we introduce PQ3D, a unified model capable of using Promptable Queries to tackle a wide range of 3D-VL tasks, from low-level instance segmentation to high-level reasoning and planning. This is achieved through three key innovations: (1) unifying various 3D scene representations (i.e., voxels, point clouds, multi-view images) into a shared 3D coordinate space by segment-level grouping, (2) an attention-based query decoder for task-specific information retrieval guided by prompts, and (3) universal output heads for different tasks to support multi-task training. Tested across ten diverse 3D-VL datasets, PQ3D demonstrates impressive performance on these tasks, setting new records on most benchmarks. Particularly, PQ3D improves the state-of-the-art on ScanNet200 by 1.8% (AP), ScanRefer by 5.4% (acc@0.5), Multi3DRefer by 11.7% (F1@0.5), and Scan2Cap by 13.4% (CIDEr@0.5). Moreover, PQ3D supports flexible inference with individual or combined forms of available 3D representations, e.g., solely voxel input.
Authors: Zejun Gu, Zhong-Qiu Zhao, Henghui Ding, Hao Shen, Zhao Zhang, De-Shuang Huang
Abstract: In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution models by distilling knowledge from a high-resolution model. However, we face the challenge of feature size mismatch and class number mismatch when applying knowledge distillation to networks with different input resolutions. To address this issue, we propose a novel cross-domain knowledge distillation (CDKD) framework. In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions. It adopts a projector ensemble to map low-resolution features into multiple common spaces and adaptively merges them based on multi-scale information to match high-resolution features. Additionally, we construct a cross-class alignment (CCA) module to solve the problem of the mismatch of class numbers. By combining an easy-to-hard training (ETHT) strategy, the CCA module further enhances the distillation performance. The effectiveness and efficiency of our approach are demonstrated by extensive experiments on two common benchmark datasets: MPII and COCO. The code is made available in supplementary material.
Authors: Suorong Yang, Peijia Li, Xin Xiong, Furao Shen, Jian Zhao
Abstract: Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods use augmentation operations with random magnitudes throughout training. While this fosters diversity, it can also inevitably introduce uncontrolled variability in augmented data, which may cause misalignment with the evolving training status of the target models. Both theoretical and empirical findings suggest that this misalignment increases the risks of underfitting and overfitting. To address these limitations, we propose AdaAugment, an innovative and tuning-free Adaptive Augmentation method that utilizes reinforcement learning to dynamically adjust augmentation magnitudes for individual training samples based on real-time feedback from the target network. Specifically, AdaAugment features a dual-model architecture consisting of a policy network and a target network, which are jointly optimized to effectively adapt augmentation magnitudes. The policy network optimizes the variability within the augmented data, while the target network utilizes the adaptively augmented samples for training. Extensive experiments across benchmark datasets and deep architectures demonstrate that AdaAugment consistently outperforms other state-of-the-art DA methods in effectiveness while maintaining remarkable efficiency.
Authors: Hu Gao, Bowen Ma, Ying Zhang, Jingfan Yang, Jing Yang, Depeng Dang
Abstract: Image restoration is a challenging ill-posed problem which estimates latent sharp image from its degraded counterpart. Although the existing methods have achieved promising performance by designing novelty architecture of module, they ignore the fact that different regions in a corrupted image undergo varying degrees of degradation. In this paper, we propose an efficient and effective framework to adapt to varying degrees of degradation across different regions for image restoration. Specifically, we design a spatial and frequency attention mechanism (SFAM) to emphasize crucial features for restoration. SFAM consists of two modules: the spatial domain attention module (SDAM) and the frequency domain attention module (FDAM). The SFAM discerns the degradation location through spatial selective attention and channel selective attention in the spatial domain, while the FDAM enhances high-frequency signals to amplify the disparities between sharp and degraded image pairs in the spectral domain. Additionally, to capture global range information, we introduce a multi-scale block (MSBlock) that consists of three scale branches, each containing multiple simplified channel attention blocks (SCABlocks) and a multi-scale feed-forward block (MSFBlock). Finally, we propose our ECFNet, which integrates the aforementioned components into a U-shaped backbone for recovering high-quality images. Extensive experimental results demonstrate the effectiveness of ECFNet, outperforming state-of-the-art (SOTA) methods on both synthetic and real-world datasets.
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 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. We have demonstrated the promising results and effectiveness of the proposed methods on existing text-to-video generation baselines.
Authors: Zhiyu Xu, Qingliang Chen
Abstract: Driven by large data trained segmentation models, such as SAM , research in one-shot segmentation has experienced significant advancements. Recent contributions like PerSAM and MATCHER , presented at ICLR 2024, utilize a similar approach by leveraging SAM with one or a few reference images to generate high quality segmentation masks for target images. Specifically, they utilize raw encoded features to compute cosine similarity between patches within reference and target images along the channel dimension, effectively generating prompt points or boxes for the target images a technique referred to as the matching strategy. However, relying solely on raw features might introduce biases and lack robustness for such a complex task. To address this concern, we delve into the issues of feature interaction and uneven distribution inherent in raw feature based matching. In this paper, we propose a simple and training-free method to enhance the validity and robustness of the matching strategy at no additional computational cost (NubbleDrop). The core concept involves randomly dropping feature channels (setting them to zero) during the matching process, thereby preventing models from being influenced by channels containing deceptive information. This technique mimics discarding pathological nubbles, and it can be seamlessly applied to other similarity computing scenarios. We conduct a comprehensive set of experiments, considering a wide range of factors, to demonstrate the effectiveness and validity of our proposed method. Our results showcase the significant improvements achieved through this simmple and straightforward approach.
Authors: Igor Morawski, Kai He, Shusil Dangi, Winston H. Hsu
Abstract: Currently, low-light conditions present a significant challenge for machine cognition. In this paper, rather than optimizing models by assuming that human and machine cognition are correlated, we use zero-reference low-light enhancement to improve the performance of downstream task models. We propose to improve the zero-reference low-light enhancement method by leveraging the rich visual-linguistic CLIP prior without any need for paired or unpaired normal-light data, which is laborious and difficult to collect. We propose a simple but effective strategy to learn prompts that help guide the enhancement method and experimentally show that the prompts learned without any need for normal-light data improve image contrast, reduce over-enhancement, and reduce noise over-amplification. Next, we propose to reuse the CLIP model for semantic guidance via zero-shot open vocabulary classification to optimize low-light enhancement for task-based performance rather than human visual perception. We conduct extensive experimental results showing that the proposed method leads to consistent improvements across various datasets regarding task-based performance and compare our method against state-of-the-art methods, showing favorable results across various low-light datasets.
Authors: Haowen Luo, Yunze Liu, Li Yi
Abstract: The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers, this paper proposes a novel physically-aware hand motion de-noising method. Specifically, we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy, surpassing current state-of-the-art de-noising methods.
Authors: Haran Raajesh, Naveen Reddy Desanur, Zeeshan Khan, Makarand Tapaswi
Abstract: Characters are an important aspect of any storyline and identifying and including them in descriptions is necessary for story understanding. While previous work has largely ignored identity and generated captions with someone (anonymized names), recent work formulates id-aware captioning as a fill-in-the-blanks (FITB) task, where, given a caption with blanks, the goal is to predict person id labels. However, to predict captions with ids, a two-stage approach is required: first predict captions with someone, then fill in identities. In this work, we present a new single stage approach that can seamlessly switch between id-aware caption generation or FITB when given a caption with blanks. Our model, Movie-Identity Captioner (MICap), uses a shared auto-regressive decoder that benefits from training with FITB and full-caption generation objectives, while the encoder can benefit from or disregard captions with blanks as input. Another challenge with id-aware captioning is the lack of a metric to capture subtle differences between person ids. To this end, we introduce iSPICE, a caption evaluation metric that focuses on identity tuples created through intermediate scene graphs. We evaluate MICap on Large-Scale Movie Description Challenge (LSMDC), where we show a 4.2% improvement in FITB accuracy, and a 1-2% bump in classic captioning metrics.
Authors: Aditya Kumar Singh, Dhruv Srivastava, Makarand Tapaswi
Abstract: We introduce multimodal story summarization by leveraging TV episode recaps - short video sequences interweaving key story moments from previous episodes to bring viewers up to speed. We propose PlotSnap, a dataset featuring two crime thriller TV shows with rich recaps and long episodes of 40 minutes. Story summarization labels are unlocked by matching recap shots to corresponding sub-stories in the episode. We propose a hierarchical model TaleSumm that processes entire episodes by creating compact shot and dialog representations, and predicts importance scores for each video shot and dialog utterance by enabling interactions between local story groups. Unlike traditional summarization, our method extracts multiple plot points from long videos. We present a thorough evaluation on story summarization, including promising cross-series generalization. TaleSumm also shows good results on classic video summarization benchmarks.
Authors: Jun Wang, Benedetta Tondi, Mauro Barni
Abstract: Synthetic image attribution addresses the problem of tracing back the origin of images produced by generative models. Extensive efforts have been made to explore unique representations of generative models and use them to attribute a synthetic image to the model that produced it. Most of the methods classify the models or the architectures among those in a closed set without considering the possibility that the system is fed with samples produced by unknown architectures. With the continuous progress of AI technology, new generative architectures continuously appear, thus driving the attention of researchers towards the development of tools capable of working in open-set scenarios. In this paper, we propose a framework for open set attribution of synthetic images, named BOSC (Backdoor-based Open Set Classification), that relies on the concept of backdoor attacks to design a classifier with rejection option. BOSC works by purposely injecting class-specific triggers inside a portion of the images in the training set to induce the network to establish a matching between class features and trigger features. The behavior of the trained model with respect to triggered samples is then exploited at test time to perform sample rejection using an ad-hoc score. Experiments show that the proposed method has good performance, always surpassing the state-of-the-art. Robustness against image processing is also very good. Although we designed our method for the task of synthetic image attribution, the proposed framework is a general one and can be used for other image forensic applications.
Authors: Hongning Ruan, Yulin Shao, Qianqian Yang, Liang Zhao, Dusit Niyato
Abstract: Point clouds have become increasingly vital across various applications thanks to their ability to realistically depict 3D objects and scenes. Nevertheless, effectively compressing unstructured, high-precision point cloud data remains a significant challenge. In this paper, we present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Unlike traditional approaches and existing learning-based methods, our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. The first network generates the occupancy status of a voxel, while the second network determines the attributes of an occupied voxel. To tackle an immense number of voxels within the volumetric space, we partition the space into smaller cubes and focus solely on voxels within non-empty cubes. By feeding the coordinates of these voxels into the respective networks, we reconstruct the geometry and attribute components of the original point cloud. The neural network parameters are further quantized and compressed. Experimental results underscore the superior performance of our proposed method compared to the octree-based approach employed in the latest G-PCC standards. Moreover, our method exhibits high universality when contrasted with existing learning-based techniques.
Authors: Conor O'Sullivan, Seamus Coveney, Xavier Monteys, Soumyabrata Dev
Abstract: We analyse the effectiveness of edge detection algorithms for the purpose of automatically extracting coastlines from satellite images. Four algorithms - Canny, Sobel, Scharr and Prewitt are compared visually and using metrics. With an average SSIM of 0.8, Canny detected edges that were closest to the reference edges. However, the algorithm had difficulty distinguishing noisy edges, e.g. due to development, from coastline edges. In addition, histogram equalization and Gaussian blur were shown to improve the effectiveness of the edge detection algorithms by up to 1.5 and 1.6 times respectively.
Authors: Fan Zhang, Xian-Sheng Hua, Chong Chen, Xiao Luo
Abstract: Image-text matching has been a long-standing problem, which seeks to connect vision and language through semantic understanding. Due to the capability to manage large-scale raw data, unsupervised hashing-based approaches have gained prominence recently. They typically construct a semantic similarity structure using the natural distance, which subsequently provides guidance to the model optimization process. However, the similarity structure could be biased at the boundaries of semantic distributions, causing error accumulation during sequential optimization. To tackle this, we introduce a novel hashing approach termed Distribution-based Structure Mining with Consistency Learning (DEMO) for efficient image-text matching. From a statistical view, DEMO characterizes each image using multiple augmented views, which are considered as samples drawn from its intrinsic semantic distribution. Then, we employ a non-parametric distribution divergence to ensure a robust and precise similarity structure. In addition, we introduce collaborative consistency learning which not only preserves the similarity structure in the Hamming space but also encourages consistency between retrieval distribution from different directions in a self-supervised manner. Through extensive experiments on three benchmark image-text matching datasets, we demonstrate that DEMO achieves superior performance compared with many state-of-the-art methods.
Authors: Conor O'Sullivan, Seamus Coveney, Xavier Monteys, Soumyabrata Dev
Abstract: We analyse the effectiveness of RMSE, PSNR, SSIM and FOM for evaluating edge detection algorithms used for automated coastline detection. Typically, the accuracy of detected coastlines is assessed visually. This can be impractical on a large scale leading to the need for objective evaluation metrics. Hence, we conduct an experiment to find reliable metrics. We apply Canny edge detection to 95 coastline satellite images across 49 testing locations. We vary the Hysteresis thresholds and compare metric values to a visual analysis of detected edges. We found that FOM was the most reliable metric for selecting the best threshold. It could select a better threshold 92.6% of the time and the best threshold 66.3% of the time. This is compared RMSE, PSNR and SSIM which could select the best threshold 6.3%, 6.3% and 11.6% of the time respectively. We provide a reason for these results by reformulating RMSE, PSNR and SSIM in terms of confusion matrix measures. This suggests these metrics not only fail for this experiment but are not useful for evaluating edge detection in general.
Authors: George Martvel, Greta Abele, Annika Bremhorst, Chiara Canori, Nareed Farhat, Giulia Pedretti, Ilan Shimshoni, Anna Zamansky
Abstract: Affective computing for animals is a rapidly expanding research area that is going deeper than automated movement tracking to address animal internal states, like pain and emotions. Facial expressions can serve to communicate information about these states in mammals. However, unlike human-related studies, there is a significant shortage of datasets that would enable the automated analysis of animal facial expressions. Inspired by the recently introduced Cat Facial Landmarks in the Wild dataset, presenting cat faces annotated with 48 facial anatomy-based landmarks, in this paper, we develop an analogous dataset containing 3,274 annotated images of dogs. Our dataset is based on a scheme of 46 facial anatomy-based landmarks. The DogFLW dataset is available from the corresponding author upon a reasonable request.
Authors: Vishnu S Nair, Sneha Sree, Jayaraj Joseph, Mohanasankar Sivaprakasam
Abstract: This paper addresses the critical need for online action representation, which is essential for various applications like rehabilitation, surveillance, etc. The task can be defined as representation of actions as soon as they happen in a streaming video without access to video frames in the future. Most of the existing methods use predefined window sizes for video segments, which is a restrictive assumption on the dynamics. The proposed method employs a change detection algorithm to automatically segment action sequences, which form meaningful sub-actions and subsequently fit symbolic generative motion programs to the clipped segments. We determine the start time and end time of segments using change detection followed by a piece-wise linear fit algorithm on joint angle and bone length sequences. Domain-specific symbolic primitives are fit to pose keypoint trajectories of those extracted segments in order to obtain a higher level semantic representation. Since this representation is part-based, it is complementary to the compositional nature of human actions, i.e., a complex activity can be broken down into elementary sub-actions. We show the effectiveness of this representation in the downstream task of class agnostic repetition detection. We propose a repetition counting algorithm based on consecutive similarity matching of primitives, which can do online repetition counting. We also compare the results with a similar but offline repetition counting algorithm. The results of the experiments demonstrate that, despite operating online, the proposed method performs better or on par with the existing method.
Authors: Youmin Xu, Xuanyu Zhang, Jiwen Yu, Chong Mou, Xiandong Meng, Jian Zhang
Abstract: This paper introduces Hierarchical Image Steganography, a novel method that enhances the security and capacity of embedding multiple images into a single container using diffusion models. HIS assigns varying levels of robustness to images based on their importance, ensuring enhanced protection against manipulation. It adaptively exploits the robustness of the Diffusion Model alongside the reversibility of the Flow Model. The integration of Embed-Flow and Enhance-Flow improves embedding efficiency and image recovery quality, respectively, setting HIS apart from conventional multi-image steganography techniques. This innovative structure can autonomously generate a container image, thereby securely and efficiently concealing multiple images and text. Rigorous subjective and objective evaluations underscore our advantage in analytical resistance, robustness, and capacity, illustrating its expansive applicability in content safeguarding and privacy fortification.
Authors: Xuan Yu, Zhenyong Fu
Abstract: Visual Place Recognition (VPR) refers to the process of using computer vision to recognize the position of the current query image. Due to the significant changes in appearance caused by season, lighting, and time spans between query images and database images for retrieval, these differences increase the difficulty of place recognition. Previous methods often discarded useless features (such as sky, road, vehicles) while uncontrolled discarding features that help improve recognition accuracy (such as buildings, trees). To preserve these useful features, we propose a new feature aggregation method to address this issue. Specifically, in order to obtain global and local features that contain discriminative place information, we added some registers on top of the original image tokens to assist in model training. After reallocating attention weights, these registers were discarded. The experimental results show that these registers surprisingly separate unstable features from the original image representation and outperform state-of-the-art methods.
Authors: Mohamed Nagy, Naoufel Werghi, Bilal Hassan, Jorge Dias, Majid Khonji
Abstract: This work addresses the inherited limitations in the current state-of-the-art 3D multi-object tracking (MOT) methods that follow the tracking-by-detection paradigm, notably trajectory estimation drift for long-occluded objects in LiDAR point cloud streams acquired by autonomous cars. In addition, the absence of adequate track legitimacy verification results in ghost track accumulation. To tackle these issues, we introduce a two-fold innovation. Firstly, we propose refinement in Kalman filter that enhances trajectory drift noise mitigation, resulting in more robust state estimation for occluded objects. Secondly, we propose a novel online track validity mechanism to distinguish between legitimate and ghost tracks combined with a multi-stage observational gating process for incoming observations. This mechanism substantially reduces ghost tracks by up to 80\% and improves HOTA by 7\%. Accordingly, we propose an online 3D MOT framework, RobMOT, that demonstrates superior performance over the top-performing state-of-the-art methods, including deep learning approaches, across various detectors with up to 3.28\% margin in MOTA and 2.36\% in HOTA. RobMOT excels under challenging conditions, such as prolonged occlusions and the tracking of distant objects, with up to 59\% enhancement in processing latency.
Authors: Yangming Chen
Abstract: Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign samples, it makes wrong predictions for samples containing triggers. However, most existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human inspection. In this paper, we propose a novel backdoor attack, making imperceptible changes. Concretely, our attack first utilizes the pre-trained victim model to extract low-level and high-level semantic features from clean images and generates trigger pattern associated with high-level features based on channel attention. Then, the encoder model generates poisoned images based on the trigger and extracted low-level semantic features without causing noticeable feature loss. We evaluate our attack on three prominent image classification DNN across three standard datasets. The results demonstrate that our attack achieves high attack success rates while maintaining robustness against backdoor defenses. Furthermore, we conduct extensive image similarity experiments to emphasize the stealthiness of our attack strategy.
Authors: Zidong Cao, Lin Wang
Abstract: Monocular 360 depth estimation is challenging due to the inherent distortion of the equirectangular projection (ERP). This distortion causes a problem: spherical adjacent points are separated after being projected to the ERP plane, particularly in the polar regions. To tackle this problem, recent methods calculate the spherical neighbors in the tangent domain. However, as the tangent patch and sphere only have one common point, these methods construct neighboring spherical relationships around the common point. In this paper, we propose spherical fully-connected CRFs (SF-CRFs). We begin by evenly partitioning an ERP image with regular windows, where windows at the equator involve broader spherical neighbors than those at the poles. To improve the spherical relationships, our SF-CRFs enjoy two key components. Firstly, to involve sufficient spherical neighbors, we propose a Spherical Window Transform (SWT) module. This module aims to replicate the equator window's spherical relationships to all other windows, leveraging the rotational invariance of the sphere. Remarkably, the transformation process is highly efficient, completing the transformation of all windows in a 512X1024 ERP with 0.038 seconds on CPU. Secondly, we propose a Planar-Spherical Interaction (PSI) module to facilitate the relationships between regular and transformed windows, which not only preserves the local details but also captures global structures. By building a decoder based on the SF-CRFs blocks, we propose CRF360D, a novel 360 depth estimation framework that achieves state-of-the-art performance across diverse datasets. Our CRF360D is compatible with different perspective image-trained backbones (e.g., EfficientNet), serving as the encoder.
Authors: Manan Shah, Yash Bhalgat
Abstract: This report is a reproducibility study of the paper "CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification" (Abdelfattah et al, ICCV 2023). Our report makes the following contributions: (1) We provide a reproducible, well commented and open-sourced code implementation for the entire method specified in the original paper. (2) We try to verify the effectiveness of the novel aggregation strategy which uses the CLIP model to initialize the pseudo labels for the subsequent unsupervised multi-label image classification task. (3) We try to verify the effectiveness of the gradient-alignment training method specified in the original paper, which is used to update the network parameters and pseudo labels. The code can be found at https://github.com/cs-mshah/CDUL
Authors: Jialong Guo, Xinghao Chen, Yehui Tang, Yunhe Wang
Abstract: Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the computational bottleneck modules of efficient transformer, i.e., normalization layers and attention modules. LayerNorm is commonly used in transformer architectures but is not computational friendly due to statistic calculation during inference. However, replacing LayerNorm with more efficient BatchNorm in transformer often leads to inferior performance and collapse in training. To address this problem, we propose a novel method named PRepBN to progressively replace LayerNorm with re-parameterized BatchNorm in training. Moreover, we propose a simplified linear attention (SLA) module that is simple yet effective to achieve strong performance. Extensive experiments on image classification as well as object detection demonstrate the effectiveness of our proposed method. For example, our SLAB-Swin obtains $83.6\%$ top-1 accuracy on ImageNet-1K with $16.2$ms latency, which is $2.4$ms less than that of Flatten-Swin with $0.1\%$ higher accuracy. We also evaluated our method for language modeling task and obtain comparable performance and lower latency.Codes are publicly available at https://github.com/xinghaochen/SLAB and https://github.com/mindspore-lab/models/tree/master/research/huawei-noah/SLAB.
URLs: https://github.com/xinghaochen/SLAB, https://github.com/mindspore-lab/models/tree/master/research/huawei-noah/SLAB.
Authors: Sangyeop Yeo, Yoojin Jang, Jaejun Yoo
Abstract: In this paper, we address the challenge of compressing generative adversarial networks (GANs) for deployment in resource-constrained environments by proposing two novel methodologies: Distribution Matching for Efficient compression (DiME) and Network Interactive Compression via Knowledge Exchange and Learning (NICKEL). DiME employs foundation models as embedding kernels for efficient distribution matching, leveraging maximum mean discrepancy to facilitate effective knowledge distillation. Simultaneously, NICKEL employs an interactive compression method that enhances the communication between the student generator and discriminator, achieving a balanced and stable compression process. Our comprehensive evaluation on the StyleGAN2 architecture with the FFHQ dataset shows the effectiveness of our approach, with NICKEL & DiME achieving FID scores of 10.45 and 15.93 at compression rates of 95.73% and 98.92%, respectively. Remarkably, our methods sustain generative quality even at an extreme compression rate of 99.69%, surpassing the previous state-of-the-art performance by a large margin. These findings not only demonstrate our methodologies' capacity to significantly lower GANs' computational demands but also pave the way for deploying high-quality GAN models in settings with limited resources. Our code will be released soon.
Authors: Peng Li, Yuan Liu, Xiaoxiao Long, Feihu Zhang, Cheng Lin, Mengfei Li, Xingqun Qi, Shanghang Zhang, Wenhan Luo, Ping Tan, Wenping Wang, Qifeng Liu, Yike Guo
Abstract: In this paper, we introduce Era3D, a novel multiview diffusion method that generates high-resolution multiview images from a single-view image. Despite significant advancements in multiview generation, existing methods still suffer from camera prior mismatch, inefficacy, and low resolution, resulting in poor-quality multiview images. Specifically, these methods assume that the input images should comply with a predefined camera type, e.g. a perspective camera with a fixed focal length, leading to distorted shapes when the assumption fails. Moreover, the full-image or dense multiview attention they employ leads to an exponential explosion of computational complexity as image resolution increases, resulting in prohibitively expensive training costs. To bridge the gap between assumption and reality, Era3D first proposes a diffusion-based camera prediction module to estimate the focal length and elevation of the input image, which allows our method to generate images without shape distortions. Furthermore, a simple but efficient attention layer, named row-wise attention, is used to enforce epipolar priors in the multiview diffusion, facilitating efficient cross-view information fusion. Consequently, compared with state-of-the-art methods, Era3D generates high-quality multiview images with up to a 512*512 resolution while reducing computation complexity by 12x times. Comprehensive experiments demonstrate that Era3D can reconstruct high-quality and detailed 3D meshes from diverse single-view input images, significantly outperforming baseline multiview diffusion methods.
Authors: Guillaume Jaume, Lukas Oldenburg, Anurag Vaidya, Richard J. Chen, Drew F. K. Williamson, Thomas Peeters, Andrew H. Song, Faisal Mahmood
Abstract: Self-supervised learning (SSL) has been successful in building patch embeddings of small histology images (e.g., 224x224 pixels), but scaling these models to learn slide embeddings from the entirety of giga-pixel whole-slide images (WSIs) remains challenging. Here, we leverage complementary information from gene expression profiles to guide slide representation learning using multimodal pre-training. Expression profiles constitute highly detailed molecular descriptions of a tissue that we hypothesize offer a strong task-agnostic training signal for learning slide embeddings. Our slide and expression (S+E) pre-training strategy, called Tangle, employs modality-specific encoders, the outputs of which are aligned via contrastive learning. Tangle was pre-trained on samples from three different organs: liver (n=6,597 S+E pairs), breast (n=1,020), and lung (n=1,012) from two different species (Homo sapiens and Rattus norvegicus). Across three independent test datasets consisting of 1,265 breast WSIs, 1,946 lung WSIs, and 4,584 liver WSIs, Tangle shows significantly better few-shot performance compared to supervised and SSL baselines. When assessed using prototype-based classification and slide retrieval, Tangle also shows a substantial performance improvement over all baselines. Code available at https://github.com/mahmoodlab/TANGLE.
Authors: Shayan Rokhva, Babak Teimourpour, Amir Hossein Soltani
Abstract: In contemporary society, the application of artificial intelligence for automatic food recognition offers substantial potential for nutrition tracking, reducing food waste, and enhancing productivity in food production and consumption scenarios. Modern technologies such as Computer Vision and Deep Learning are highly beneficial, enabling machines to learn automatically, thereby facilitating automatic visual recognition. Despite some research in this field, the challenge of achieving accurate automatic food recognition quickly remains a significant research gap. Some models have been developed and implemented, but maintaining high performance swiftly, with low computational cost and low access to expensive hardware accelerators, still needs further exploration and research. This study employs the pretrained MobileNetV2 model, which is efficient and fast, for food recognition on the public Food11 dataset, comprising 16643 images. It also utilizes various techniques such as dataset understanding, transfer learning, data augmentation, regularization, dynamic learning rate, hyperparameter tuning, and consideration of images in different sizes to enhance performance and robustness. These techniques aid in choosing appropriate metrics, achieving better performance, avoiding overfitting and accuracy fluctuations, speeding up the model, and increasing the generalization of findings, making the study and its results applicable to practical applications. Despite employing a light model with a simpler structure and fewer trainable parameters compared to some deep and dense models in the deep learning area, it achieved commendable accuracy in a short time. This underscores the potential for practical implementation, which is the main intention of this study.
Authors: Shengxiang Sun, Shenzhe Zhu
Abstract: Numerous studies on adversarial attacks targeting self-driving policies fail to incorporate realistic-looking adversarial objects, limiting real-world applicability. Building upon prior research that facilitated the transition of adversarial objects from simulations to practical applications, this paper discusses a modified gradient-based texture optimization method to discover realistic-looking adversarial objects. While retaining the core architecture and techniques of the prior research, the proposed addition involves an entity termed the 'Judge'. This agent assesses the texture of a rendered object, assigning a probability score reflecting its realism. This score is integrated into the loss function to encourage the NeRF object renderer to concurrently learn realistic and adversarial textures. The paper analyzes four strategies for developing a robust 'Judge': 1) Leveraging cutting-edge vision-language models. 2) Fine-tuning open-sourced vision-language models. 3) Pretraining neurosymbolic systems. 4) Utilizing traditional image processing techniques. Our findings indicate that strategies 1) and 4) yield less reliable outcomes, pointing towards strategies 2) or 3) as more promising directions for future research.
Authors: Andrew H. Song, Richard J. Chen, Tong Ding, Drew F. K. Williamson, Guillaume Jaume, Faisal Mahmood
Abstract: Representation learning of pathology whole-slide images (WSIs) has been has primarily relied on weak supervision with Multiple Instance Learning (MIL). However, the slide representations resulting from this approach are highly tailored to specific clinical tasks, which limits their expressivity and generalization, particularly in scenarios with limited data. Instead, we hypothesize that morphological redundancy in tissue can be leveraged to build a task-agnostic slide representation in an unsupervised fashion. To this end, we introduce PANTHER, a prototype-based approach rooted in the Gaussian mixture model that summarizes the set of WSI patches into a much smaller set of morphological prototypes. Specifically, each patch is assumed to have been generated from a mixture distribution, where each mixture component represents a morphological exemplar. Utilizing the estimated mixture parameters, we then construct a compact slide representation that can be readily used for a wide range of downstream tasks. By performing an extensive evaluation of PANTHER on subtyping and survival tasks using 13 datasets, we show that 1) PANTHER outperforms or is on par with supervised MIL baselines and 2) the analysis of morphological prototypes brings new qualitative and quantitative insights into model interpretability.
Authors: Tharun V. Puthanveettil, Fnu Obaid ur Rahman
Abstract: Object tracking is a fundamental task in computer vision with broad practical applications across various domains, including traffic monitoring, robotics, and autonomous vehicle tracking. In this project, we aim to develop a sophisticated aerial vehicle system known as Track Anything Raptor (TAR), designed to detect, segment, and track objects of interest based on user-provided multimodal queries, such as text, images, and clicks. TAR utilizes cutting-edge pre-trained models like DINO, CLIP, and SAM to estimate the relative pose of the queried object. The tracking problem is approached as a Visual Servoing task, enabling the UAV to consistently focus on the object through advanced motion planning and control algorithms. We showcase how the integration of these foundational models with a custom high-level control algorithm results in a highly stable and precise tracking system deployed on a custom-built PX4 Autopilot-enabled Voxl2 M500 drone. To validate the tracking algorithm's performance, we compare it against Vicon-based ground truth. Additionally, we evaluate the reliability of the foundational models in aiding tracking in scenarios involving occlusions. Finally, we test and validate the model's ability to work seamlessly with multiple modalities, such as click, bounding box, and image templates.
Authors: Orfeas Menis-Mastromichalakis, Natasa Sofou, Giorgos Stamou
Abstract: The massive digitization of artworks during the last decades created the need for categorization, analysis, and management of huge amounts of data related to abstract concepts, highlighting a challenging problem in the field of computer science. The rapid progress of artificial intelligence and neural networks has provided tools and technologies that seem worthy of the challenge. Recognition of various art features in artworks has gained attention in the deep learning society. In this paper, we are concerned with the problem of art style recognition using deep networks. We compare the performance of 8 different deep architectures (VGG16, VGG19, ResNet50, ResNet152, Inception-V3, DenseNet121, DenseNet201 and Inception-ResNet-V2), on two different art datasets, including 3 architectures that have never been used on this task before, leading to state-of-the-art performance. We study the effect of data preprocessing prior to applying a deep learning model. We introduce a stacking ensemble method combining the results of first-stage classifiers through a meta-classifier, with the innovation of a versatile approach based on multiple models that extract and recognize different characteristics of the input, creating a more consistent model compared to existing works and achieving state-of-the-art accuracy on the largest art dataset available (WikiArt - 68,55%). We also discuss the impact of the data and art styles themselves on the performance of our models forming a manifold perspective on the problem.
Authors: Christiaan G. A. Viviers, Lena Filatova, Maurice Termeer, Peter H. N. de With, Fons van der Sommen
Abstract: Accurate 6-DoF pose estimation of surgical instruments during minimally invasive surgeries can substantially improve treatment strategies and eventual surgical outcome. Existing deep learning methods have achieved accurate results, but they require custom approaches for each object and laborious setup and training environments often stretching to extensive simulations, whilst lacking real-time computation. We propose a general-purpose approach of data acquisition for 6-DoF pose estimation tasks in X-ray systems, a novel and general purpose YOLOv5-6D pose architecture for accurate and fast object pose estimation and a complete method for surgical screw pose estimation under acquisition geometry consideration from a monocular cone-beam X-ray image. The proposed YOLOv5-6D pose model achieves competitive results on public benchmarks whilst being considerably faster at 42 FPS on GPU. In addition, the method generalizes across varying X-ray acquisition geometry and semantic image complexity to enable accurate pose estimation over different domains. Finally, the proposed approach is tested for bone-screw pose estimation for computer-aided guidance during spine surgeries. The model achieves a 92.41% by the 0.1 ADD-S metric, demonstrating a promising approach for enhancing surgical precision and patient outcomes. The code for YOLOv5-6D is publicly available at https://github.com/cviviers/YOLOv5-6D-Pose
Authors: Ziang Guo, Zakhar Yagudin, Selamawit Asfaw, Artem Lykov, Dzmitry Tsetserukou
Abstract: Camera, LiDAR and radar are common perception sensors for autonomous driving tasks. Robust prediction of 3D object detection is optimally based on the fusion of these sensors. To exploit their abilities wisely remains a challenge because each of these sensors has its own characteristics. In this paper, we propose FADet, a multi-sensor 3D detection network, which specifically studies the characteristics of different sensors based on our local featured attention modules. For camera images, we propose dual-attention-based sub-module. For LiDAR point clouds, triple-attention-based sub-module is utilized while mixed-attention-based sub-module is applied for features of radar points. With local featured attention sub-modules, our FADet has effective detection results in long-tail and complex scenes from camera, LiDAR and radar input. On NuScenes validation dataset, FADet achieves state-of-the-art performance on LiDAR-camera object detection tasks with 71.8% NDS and 69.0% mAP, at the same time, on radar-camera object detection tasks with 51.7% NDS and 40.3% mAP. Code will be released at https://github.com/ZionGo6/FADet.
Authors: Ahnaf Mozib Samin, M. Firoz Ahmed, Md. Mushtaq Shahriyar Rafee
Abstract: With the utilization of Transformer architecture, large Vision and Language (V&L) models have shown promising performance in even zero-shot settings. Several studies, however, indicate a lack of robustness of the models when dealing with complex linguistics and visual attributes. In this work, we introduce a novel V&L benchmark - ColorFoil, by creating color-related foils to assess the models' perception ability to detect colors like red, white, green, etc. We evaluate seven state-of-the-art V&L models including CLIP, ViLT, GroupViT, and BridgeTower, etc. in a zero-shot setting and present intriguing findings from the V&L models. The experimental evaluation indicates that ViLT and BridgeTower demonstrate much better color perception capabilities compared to CLIP and its variants and GroupViT. Moreover, CLIP-based models and GroupViT struggle to distinguish colors that are visually distinct to humans with normal color perception ability.
Authors: Yinghao Huang, Leo Ho, Dafei Qin, Mingyi Shi, Taku Komura
Abstract: We address the problem of accurate capture and expressive modelling of interactive behaviors happening between two persons in daily scenarios. Different from previous works which either only consider one person or focus on conversational gestures, we propose to simultaneously model the activities of two persons, and target objective-driven, dynamic, and coherent interactions which often span long duration. To this end, we capture a new dataset dubbed InterAct, which is composed of 241 motion sequences where two persons perform a realistic scenario over the whole sequence. The audios, body motions, and facial expressions of both persons are all captured in our dataset. We also demonstrate the first diffusion model based approach that directly estimates the interactive motions between two persons from their audios alone. All the data and code will be available for research purposes upon acceptance of the paper.
Authors: Yihao Zhao, Cuiyun Yuan, Ying Liang, Yang Li, Chunxia Li, Man Zhao, Jun Hu, Wei Liu, Chenbin Liu
Abstract: The delineation of tumor target and organs-at-risk is critical in the radiotherapy treatment planning. Automatic segmentation can be used to reduce the physician workload and improve the consistency. However, the quality assurance of the automatic segmentation is still an unmet need in clinical practice. The patient data used in our study was a standardized dataset from AAPM Thoracic Auto-Segmentation Challenge. The OARs included were left and right lungs, heart, esophagus, and spinal cord. Two groups of OARs were generated, the benchmark dataset manually contoured by experienced physicians and the test dataset automatically created using a software AccuContour. A resnet-152 network was performed as feature extractor, and one-class support vector classifier was used to determine the high or low quality. We evaluate the model performance with balanced accuracy, F-score, sensitivity, specificity and the area under the receiving operator characteristic curve. We randomly generated contour errors to assess the generalization of our method, explored the detection limit, and evaluated the correlations between detection limit and various metrics such as volume, Dice similarity coefficient, Hausdorff distance, and mean surface distance. The proposed one-class classifier outperformed in metrics such as balanced accuracy, AUC, and others. The proposed method showed significant improvement over binary classifiers in handling various types of errors. Our proposed model, which introduces residual network and attention mechanism in the one-class classification framework, was able to detect the various types of OAR contour errors with high accuracy. The proposed method can significantly reduce the burden of physician review for contour delineation.
Authors: Runou Yang, Tian Tian, Jinwen Tian
Abstract: Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, has shown significant accuracy improvements. However, existing methods often overlook class differences, treating all classes equally, resulting in suboptimal results. Furthermore, the integration of instance-level alignment with a one-stage detector, essential due to the absence of a Region Proposal Network (RPN), remains unexplored in this framework. In response to these shortcomings, we introduce a novel teacher-student model named Versatile Teacher (VT). VT differs from previous works by considering class-specific detection difficulty and employing a two-step pseudo-label selection mechanism, referred to as Class-aware Pseudo-label Adaptive Selection (CAPS), to generate more reliable pseudo labels. These labels are leveraged as saliency matrices to guide the discriminator for targeted instance-level alignment. Our method demonstrates promising results on three benchmark datasets, and extends the alignment methods for widely-used one-stage detectors, presenting significant potential for practical applications. Code is available at https://github.com/RicardooYoung/VersatileTeacher.
Authors: Jiawei Wang, Kai Hu, Qiang Huo
Abstract: Document layout analysis (DLA) is crucial for understanding the physical layout and logical structure of documents, serving information retrieval, document summarization, knowledge extraction, etc. However, previous studies have typically used separate models to address individual sub-tasks within DLA, including table/figure detection, text region detection, logical role classification, and reading order prediction. In this work, we propose an end-to-end transformer-based approach for document layout analysis, called DLAFormer, which integrates all these sub-tasks into a single model. To achieve this, we treat various DLA sub-tasks (such as text region detection, logical role classification, and reading order prediction) as relation prediction problems and consolidate these relation prediction labels into a unified label space, allowing a unified relation prediction module to handle multiple tasks concurrently. Additionally, we introduce a novel set of type-wise queries to enhance the physical meaning of content queries in DETR. Moreover, we adopt a coarse-to-fine strategy to accurately identify graphical page objects. Experimental results demonstrate that our proposed DLAFormer outperforms previous approaches that employ multi-branch or multi-stage architectures for multiple tasks on two document layout analysis benchmarks, DocLayNet and Comp-HRDoc.
Authors: Jianhong Han, Liang Chen, Yupei Wang
Abstract: Object detectors frequently encounter significant performance degradation when confronted with domain gaps between collected data (source domain) and data from real-world applications (target domain). To address this task, numerous unsupervised domain adaptive detectors have been proposed, leveraging carefully designed feature alignment techniques. However, these techniques primarily align instance-level features in a class-agnostic manner, overlooking the differences between extracted features from different categories, which results in only limited improvement. Furthermore, the scope of current alignment modules is often restricted to a limited batch of images, failing to learn the entire dataset-level cues, thereby severely constraining the detector's generalization ability to the target domain. To this end, we introduce a strong DETR-based detector named Domain Adaptive detection TRansformer (DATR) for unsupervised domain adaptation of object detection. Firstly, we propose the Class-wise Prototypes Alignment (CPA) module, which effectively aligns cross-domain features in a class-aware manner by bridging the gap between object detection task and domain adaptation task. Then, the designed Dataset-level Alignment Scheme (DAS) explicitly guides the detector to achieve global representation and enhance inter-class distinguishability of instance-level features across the entire dataset, which spans both domains, by leveraging contrastive learning. Moreover, DATR incorporates a mean-teacher based self-training framework, utilizing pseudo-labels generated by the teacher model to further mitigate domain bias. Extensive experimental results demonstrate superior performance and generalization capabilities of our proposed DATR in multiple domain adaptation scenarios. Code is released at https://github.com/h751410234/DATR.
Authors: Yuanwu Xu, Feifan Song, Haofeng Zhang
Abstract: Few-shot object counting aims to count the number of objects in a query image that belong to the same class as the given exemplar images. Existing methods compute the similarity between the query image and exemplars in the 2D spatial domain and perform regression to obtain the counting number. However, these methods overlook the rich information about the spatial distribution of similarity on the exemplar images, leading to significant impact on matching accuracy. To address this issue, we propose a network learning Spatial Similarity Distribution (SSD) for few-shot object counting, which preserves the spatial structure of exemplar features and calculates a 4D similarity pyramid point-to-point between the query features and exemplar features, capturing the complete distribution information for each point in the 4D similarity space. We propose a Similarity Learning Module (SLM) which applies the efficient center-pivot 4D convolutions on the similarity pyramid to map different similarity distributions to distinct predicted density values, thereby obtaining accurate count. Furthermore, we also introduce a Feature Cross Enhancement (FCE) module that enhances query and exemplar features mutually to improve the accuracy of feature matching. Our approach outperforms state-of-the-art methods on multiple datasets, including FSC-147 and CARPK. Code is available at https://github.com/CBalance/SSD.
Authors: Ruiqi Wu, Chenran Zhang, Jianle Zhang, Yi Zhou, Tao Zhou, Huazhu Fu
Abstract: Current fundus image analysis models are predominantly built for specific tasks relying on individual datasets. The learning process is usually based on data-driven paradigm without prior knowledge, resulting in poor transferability and generalizability. To address this issue, we propose MM-Retinal, a multi-modal dataset that encompasses high-quality image-text pairs collected from professional fundus diagram books. Moreover, enabled by MM-Retinal, we present a novel Knowledge-enhanced foundational pretraining model which incorporates Fundus Image-Text expertise, called KeepFIT. It is designed with image similarity-guided text revision and mixed training strategy to infuse expert knowledge. Our proposed fundus foundation model achieves state-of-the-art performance across six unseen downstream tasks and holds excellent generalization ability in zero-shot and few-shot scenarios. MM-Retinal and KeepFIT are available at https://github.com/lxirich/MM-Retinal.
Authors: Zixun Fang, Wei Zhai, Aimin Su, Hongliang Song, Kai Zhu, Mao Wang, Yu Chen, Zhiheng Liu, Yang Cao, Zheng-Jun Zha
Abstract: Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.
Authors: Baiyu Pan, Jichao Jiao, Jianxing Pang, Jun Cheng
Abstract: In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the improvements are only modest. In this paper, we propose a novel strategy by incorporating knowledge distillation and model pruning to overcome the inherent trade-off between speed and accuracy. As a result, we obtained a model that maintains real-time performance while delivering high accuracy on edge devices. Our proposed method involves three key steps. Firstly, we review state-of-the-art methods and design our lightweight model by removing redundant modules from those efficient models through a comparison of their contributions. Next, we leverage the efficient model as the teacher to distill knowledge into the lightweight model. Finally, we systematically prune the lightweight model to obtain the final model. Through extensive experiments conducted on two widely-used benchmarks, Sceneflow and KITTI, we perform ablation studies to analyze the effectiveness of each module and present our state-of-the-art results.
Authors: Masato Sakai, Marcus Freitag, Akihisa Sakurai, Conrad M Albrecht, Hendrik F Hamann
Abstract: Preservation of the Nasca geoglyphs at the UNESCO World Heritage Site in Peru is urgent as natural and human impact accelerates. More frequent weather extremes such as flashfloods threaten Nasca artifacts. We demonstrate that runoff models based on (sub-)meter scale, LiDAR-derived digital elevation data can highlight AI-detected geoglyphs that are in danger of erosion. We recommend measures of mitigation to protect the famous "lizard", "tree", and "hand" geoglyphs located close by, or even cut by the Pan-American Highway.
Authors: Sunyuan Qiang, Xuxin Lin, Yanyan Liang, Jun Wan, Du Zhang
Abstract: Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned knowledge. Recent CL models have gradually shifted towards the utilization of pre-trained models (PTMs) with parameter-efficient fine-tuning (PEFT) strategies. However, continual fine-tuning still presents a serious challenge of catastrophic forgetting due to the absence of previous task data. Additionally, the fine-tune-then-frozen mechanism suffers from performance limitations due to feature channels suppression and insufficient training data in the first CL task. To this end, this paper proposes feature transformation tuning (FeTT) model to non-parametrically fine-tune backbone features across all tasks, which not only operates independently of CL training data but also smooths feature channels to prevent excessive suppression. Then, the extended ensemble strategy incorporating different PTMs with FeTT model facilitates further performance improvement. We further elaborate on the discussions of the fine-tune-then-frozen paradigm and the FeTT model from the perspectives of discrepancy in class marginal distributions and feature channels. Extensive experiments on CL benchmarks validate the effectiveness of our proposed method.
Authors: Aryan Garg, Raghav Mallampali, Akshat Joshi, Shrisudhan Govindarajan, Kaushik Mitra
Abstract: Dual pixels contain disparity cues arising from the defocus blur. This disparity information is useful for many vision tasks ranging from autonomous driving to 3D creative realism. However, directly estimating disparity from dual pixels is less accurate. This work hypothesizes that distilling high-precision dark stereo knowledge, implicitly or explicitly, to efficient dual-pixel student networks enables faithful reconstructions. This dark knowledge distillation should also alleviate stereo-synchronization setup and calibration costs while dramatically increasing parameter and inference time efficiency. We collect the first and largest 3-view dual-pixel video dataset, dpMV, to validate our explicit dark knowledge distillation hypothesis. We show that these methods outperform purely monocular solutions, especially in challenging foreground-background separation regions using faithful guidance from dual pixels. Finally, we demonstrate an unconventional use case unlocked by dpMV and implicit dark knowledge distillation from an ensemble of teachers for Light Field (LF) video reconstruction. Our LF video reconstruction method is the fastest and most temporally consistent to date. It remains competitive in reconstruction fidelity while offering many other essential properties like high parameter efficiency, implicit disocclusion handling, zero-shot cross-dataset transfer, geometrically consistent inference on higher spatial-angular resolutions, and adaptive baseline control. All source code is available at the anonymous repository https://github.com/Aryan-Garg.
Authors: Mounes Zaval, Sedat Ozer
Abstract: In the evolving field of Explainable AI (XAI), interpreting the decisions of deep neural networks (DNNs) in computer vision tasks is an important process. While pixel-based XAI methods focus on identifying significant pixels, existing concept-based XAI methods use pre-defined or human-annotated concepts. The recently proposed Segment Anything Model (SAM) achieved a significant step forward to prepare automatic concept sets via comprehensive instance segmentation. Building upon this, the Explain Any Concept (EAC) model emerged as a flexible method for explaining DNN decisions. EAC model is based on using a surrogate model which has one trainable linear layer to simulate the target model. In this paper, by introducing an additional nonlinear layer to the original surrogate model, we show that we can improve the performance of the EAC model. We compare our proposed approach to the original EAC model and report improvements obtained on both ImageNet and MS COCO datasets.
Authors: Mengqi Lei, Xin Wang
Abstract: Accurate segmentation of polyps in colonoscopy images is essential for early-stage diagnosis and management of colorectal cancer. Despite advancements in deep learning for polyp segmentation, enduring limitations persist. The edges of polyps are typically ambiguous, making them difficult to discern from the background, and the model performance is often compromised by the influence of irrelevant or unimportant features. To alleviate these challenges, we propose a novel model named Edge-Prioritized Polyp Segmentation (EPPS). Specifically, we incorporate an Edge Mapping Engine (EME) aimed at accurately extracting the edges of polyps. Subsequently, an Edge Information Injector (EII) is devised to augment the mask prediction by injecting the captured edge information into Decoder blocks. Furthermore, we introduce a component called Selective Feature Decoupler (SFD) to suppress the influence of noise and extraneous features on the model. Extensive experiments on 3 widely used polyp segmentation benchmarks demonstrate the superior performance of our method compared with other state-of-the-art approaches.
Authors: Yuan Liu, Le Tian, Xiao Zhou, Jie Zhou
Abstract: Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact, lead to its degradation. Furthermore, we have established a pipeline to pinpoint the most efficient instruction tuning (SFT) dataset, implying that not all SFT data utilized in existing studies are necessary. The primary objective of this paper is not to introduce a state-of-the-art model, but rather to serve as a roadmap for future research, aiming to optimize data usage during pre-training and fine-tuning processes to enhance the performance of vision-language models.
Authors: Xiyu Wang, Yufei Wang, Satoshi Tsutsui, Weisi Lin, Bihan Wen, Alex C. Kot
Abstract: Diffusion-based models for story visualization have shown promise in generating content-coherent images for storytelling tasks. However, how to effectively integrate new characters into existing narratives while maintaining character consistency remains an open problem, particularly with limited data. Two major limitations hinder the progress: (1) the absence of a suitable benchmark due to potential character leakage and inconsistent text labeling, and (2) the challenge of distinguishing between new and old characters, leading to ambiguous results. To address these challenges, we introduce the NewEpisode benchmark, comprising refined datasets designed to evaluate generative models' adaptability in generating new stories with fresh characters using just a single example story. The refined dataset involves refined text prompts and eliminates character leakage. Additionally, to mitigate the character confusion of generated results, we propose EpicEvo, a method that customizes a diffusion-based visual story generation model with a single story featuring the new characters seamlessly integrating them into established character dynamics. EpicEvo introduces a novel adversarial character alignment module to align the generated images progressively in the diffusive process, with exemplar images of new characters, while applying knowledge distillation to prevent forgetting of characters and background details. Our evaluation quantitatively demonstrates that EpicEvo outperforms existing baselines on the NewEpisode benchmark, and qualitative studies confirm its superior customization of visual story generation in diffusion models. In summary, EpicEvo provides an effective way to incorporate new characters using only one example story, unlocking new possibilities for applications such as serialized cartoons.
Authors: Chunxia Qin, Zhenrong Zhang, Pengfei Hu, Chenyu Liu, Jiefeng Ma, Jun Du
Abstract: Table structure recognition (TSR) aims to parse the inherent structure of a table from its input image. The `"split-and-merge" paradigm is a pivotal approach to parse table structure, where the table separation line detection is crucial. However, challenges such as wireless and deformed tables make it demanding. In this paper, we adhere to the "split-and-merge" paradigm and propose SEMv3 (SEM: Split, Embed and Merge), a method that is both fast and robust for detecting table separation lines. During the split stage, we introduce a Keypoint Offset Regression (KOR) module, which effectively detects table separation lines by directly regressing the offset of each line relative to its keypoint proposals. Moreover, in the merge stage, we define a series of merge actions to efficiently describe the table structure based on table grids. Extensive ablation studies demonstrate that our proposed KOR module can detect table separation lines quickly and accurately. Furthermore, on public datasets (e.g. WTW, ICDAR-2019 cTDaR Historical and iFLYTAB), SEMv3 achieves state-of-the-art (SOTA) performance. The code is available at https://github.com/Chunchunwumu/SEMv3.
Authors: Jin-Hwi Park, Chanhwi Jeong, Junoh Lee, Hae-Gon Jeon
Abstract: Dense depth maps have been used as a key element of visual perception tasks. There have been tremendous efforts to enhance the depth quality, ranging from optimization-based to learning-based methods. Despite the remarkable progress for a long time, their applicability in the real world is limited due to systematic measurement biases such as density, sensing pattern, and scan range. It is well-known that the biases make it difficult for these methods to achieve their generalization. We observe that learning a joint representation for input modalities (e.g., images and depth), which most recent methods adopt, is sensitive to the biases. In this work, we disentangle those modalities to mitigate the biases with prompt engineering. For this, we design a novel depth prompt module to allow the desirable feature representation according to new depth distributions from either sensor types or scene configurations. Our depth prompt can be embedded into foundation models for monocular depth estimation. Through this embedding process, our method helps the pretrained model to be free from restraint of depth scan range and to provide absolute scale depth maps. We demonstrate the effectiveness of our method through extensive evaluations. Source code is publicly available at https://github.com/JinhwiPark/DepthPrompting .
Authors: Takahiro Shindo, Yui Tatsumi, Taiju Watanabe, Hiroshi Watanabe
Abstract: Scalable image coding for both humans and machines is a technique that has gained a lot of attention recently. This technology enables the hierarchical decoding of images for human vision and image recognition models. It is a highly effective method when images need to serve both purposes. However, no research has yet incorporated the post-processing commonly used in popular image compression schemes into scalable image coding method for humans and machines. In this paper, we propose a method to enhance the quality of decoded images for humans by integrating post-processing into scalable coding scheme. Experimental results show that the post-processing improves compression performance. Furthermore, the effectiveness of the proposed method is validated through comparisons with traditional methods.
Authors: Sushmita Sarker, Prithul Sarker, Gunner Stone, Ryan Gorman, Alireza Tavakkoli, George Bebis, Javad Sattarvand
Abstract: Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-- namely, 3D shape classification and semantic segmentation.
Authors: Jaewon Son, Jaehun Park, Kwangsu Kim
Abstract: Video summarization aims to generate a concise representation of a video, capturing its essential content and key moments while reducing its overall length. Although several methods employ attention mechanisms to handle long-term dependencies, they often fail to capture the visual significance inherent in frames. To address this limitation, we propose a CNN-based SpatioTemporal Attention (CSTA) method that stacks each feature of frames from a single video to form image-like frame representations and applies 2D CNN to these frame features. Our methodology relies on CNN to comprehend the inter and intra-frame relations and to find crucial attributes in videos by exploiting its ability to learn absolute positions within images. In contrast to previous work compromising efficiency by designing additional modules to focus on spatial importance, CSTA requires minimal computational overhead as it uses CNN as a sliding window. Extensive experiments on two benchmark datasets (SumMe and TVSum) demonstrate that our proposed approach achieves state-of-the-art performance with fewer MACs compared to previous methods. Codes are available at https://github.com/thswodnjs3/CSTA.
Authors: Sizhe Li, Yiming Qin, Minghang Zheng, Xin Jin, Yang Liu
Abstract: When editing a video, a piece of attractive background music is indispensable. However, video background music generation tasks face several challenges, for example, the lack of suitable training datasets, and the difficulties in flexibly controlling the music generation process and sequentially aligning the video and music. In this work, we first propose a high-quality music-video dataset BGM909 with detailed annotation and shot detection to provide multi-modal information about the video and music. We then present evaluation metrics to assess music quality, including music diversity and alignment between music and video with retrieval precision metrics. Finally, we propose the Diff-BGM framework to automatically generate the background music for a given video, which uses different signals to control different aspects of the music during the generation process, i.e., uses dynamic video features to control music rhythm and semantic features to control the melody and atmosphere. We propose to align the video and music sequentially by introducing a segment-aware cross-attention layer. Experiments verify the effectiveness of our proposed method. The code and models are available at https://github.com/sizhelee/Diff-BGM.
Authors: Yiheng Xiong, Angela Dai
Abstract: Generating 3D shapes from single RGB images is essential in various applications such as robotics. Current approaches typically target images containing clear and complete visual descriptions of the object, without considering common realistic cases where observations of objects that are largely occluded or truncated. We thus propose a transformer-based autoregressive model to generate the probabilistic distribution of 3D shapes conditioned on an RGB image containing potentially highly ambiguous observations of the object. To handle realistic scenarios such as occlusion or field-of-view truncation, we create simulated image-to-shape training pairs that enable improved fine-tuning for real-world scenarios. We then adopt cross-attention to effectively identify the most relevant region of interest from the input image for shape generation. This enables inference of sampled shapes with reasonable diversity and strong alignment with the input image. We train and test our model on our synthetic data then fine-tune and test it on real-world data. Experiments demonstrate that our model outperforms state of the art in both scenarios
Authors: Jiayue Liu, Xiao Tang, Freeman Cheng, Roy Yang, Zhihao Li, Jianzhuang Liu, Yi Huang, Jiaqi Lin, Shiyong Liu, Xiaofei Wu, Songcen Xu, Chun Yuan
Abstract: 3D Gaussian Splatting showcases notable advancements in photo-realistic and real-time novel view synthesis. However, it faces challenges in modeling mirror reflections, which exhibit substantial appearance variations from different viewpoints. To tackle this problem, we present MirrorGaussian, the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting. The key insight is grounded on the mirror symmetry between the real-world space and the virtual mirror space. We introduce an intuitive dual-rendering strategy that enables differentiable rasterization of both the real-world 3D Gaussians and the mirrored counterpart obtained by reflecting the former about the mirror plane. All 3D Gaussians are jointly optimized with the mirror plane in an end-to-end framework. MirrorGaussian achieves high-quality and real-time rendering in scenes with mirrors, empowering scene editing like adding new mirrors and objects. Comprehensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods, achieving state-of-the-art results. Project page: https://mirror-gaussian.github.io/.
Authors: Wenjia Xu, Yaxuan Yao, Jiaqi Cao, Zhiwei Wei, Chunbo Liu, Jiuniu Wang, Mugen Peng
Abstract: The application of unmanned aerial vehicles (UAV) has been widely extended recently. It is crucial to ensure accurate latitude and longitude coordinates for UAVs, especially when the global navigation satellite systems (GNSS) are disrupted and unreliable. Existing visual localization methods achieve autonomous visual localization without error accumulation by matching the ground-down view image of UAV with the ortho satellite maps. However, collecting UAV ground-down view images across diverse locations is costly, leading to a scarcity of large-scale datasets for real-world scenarios. Existing datasets for UAV visual localization are often limited to small geographic areas or are focused only on urban regions with distinct textures. To address this, we define the UAV visual localization task by determining the UAV's real position coordinates on a large-scale satellite map based on the captured ground-down view. In this paper, we present a large-scale dataset, UAV-VisLoc, to facilitate the UAV visual localization task. This dataset comprises images from diverse drones across 11 locations in China, capturing a range of topographical features. The dataset features images from fixed-wing drones and multi-terrain drones, captured at different altitudes and orientations. Our dataset includes 6,742 drone images and 11 satellite maps, with metadata such as latitude, longitude, altitude, and capture date. Our dataset is tailored to support both the training and testing of models by providing a diverse and extensive data.
Authors: Zheng Li, Lijia Si, Caili Guo, Yang Yang, Qiushi Cao
Abstract: Text-based Person Retrieval (TPR) aims to retrieve person images that match the description given a text query. The performance improvement of the TPR model relies on high-quality data for supervised training. However, it is difficult to construct a large-scale, high-quality TPR dataset due to expensive annotation and privacy protection. Recently, Large Language Models (LLMs) have approached or even surpassed human performance on many NLP tasks, creating the possibility to expand high-quality TPR datasets. This paper proposes an LLM-based Data Augmentation (LLM-DA) method for TPR. LLM-DA uses LLMs to rewrite the text in the current TPR dataset, achieving high-quality expansion of the dataset concisely and efficiently. These rewritten texts are able to increase the diversity of vocabulary and sentence structure while retaining the original key concepts and semantic information. In order to alleviate the hallucinations of LLMs, LLM-DA introduces a Text Faithfulness Filter (TFF) to filter out unfaithful rewritten text. To balance the contributions of original text and augmented text, a Balanced Sampling Strategy (BSS) is proposed to control the proportion of original text and augmented text used for training. LLM-DA is a plug-and-play method that can be easily integrated into various TPR models. Comprehensive experiments on three TPR benchmarks show that LLM-DA can improve the retrieval performance of current TPR models.
Authors: Zhichao Sun, Yuliang Gu, Yepeng Liu, Zerui Zhang, Zhou Zhao, Yongchao Xu
Abstract: Anomaly detection in chest X-rays is a critical task. Most methods mainly model the distribution of normal images, and then regard significant deviation from normal distribution as anomaly. Recently, CLIP-based methods, pre-trained on a large number of medical images, have shown impressive performance on zero/few-shot downstream tasks. In this paper, we aim to explore the potential of CLIP-based methods for anomaly detection in chest X-rays. Considering the discrepancy between the CLIP pre-training data and the task-specific data, we propose a position-guided prompt learning method. Specifically, inspired by the fact that experts diagnose chest X-rays by carefully examining distinct lung regions, we propose learnable position-guided text and image prompts to adapt the task data to the frozen pre-trained CLIP-based model. To enhance the model's discriminative capability, we propose a novel structure-preserving anomaly synthesis method within chest x-rays during the training process. Extensive experiments on three datasets demonstrate that our proposed method outperforms some state-of-the-art methods. The code of our implementation is available at https://github.com/sunzc-sunny/PPAD.
Authors: Alexandre Cafaro, Amaury Leroy, Guillaume Beldjoudi, Pauline Maury, Charlotte Robert, Eric Deutsch, Vincent Gr\'egoire, Vincent Lepetit, Nikos Paragios
Abstract: We introduce a novel unsupervised approach to reconstructing a 3D volume from only two planar projections that exploits a previous\-ly-captured 3D volume of the patient. Such volume is readily available in many important medical procedures and previous methods already used such a volume. Earlier methods that work by deforming this volume to match the projections typically fail when the number of projections is very low as the alignment becomes underconstrained. We show how to use a generative model of the volume structures to constrain the deformation and obtain a correct estimate. Moreover, our method is not bounded to a specific sensor calibration and can be applied to new calibrations without retraining. We evaluate our approach on a challenging dataset and show it outperforms state-of-the-art methods. As a result, our method could be used in treatment scenarios such as surgery and radiotherapy while drastically reducing patient radiation exposure.
Authors: Antonio Parziale, Moises Diaz, Miguel A. Ferrer, Angelo Marcelli
Abstract: Building upon findings in computational model of handwriting learning and execution, we introduce the concept of stability to explain the difference between the actual movements performed during multiple execution of the subject's signature, and conjecture that the most stable parts of the signature should play a paramount role in evaluating the similarity between a questioned signature and the reference ones during signature verification. We then introduce the Stability Modulated Dynamic Time Warping algorithm for incorporating the stability regions, i.e. the most similar parts between two signatures, into the distance measure between a pair of signatures computed by the Dynamic Time Warping for signature verification. Experiments were conducted on two datasets largely adopted for performance evaluation. Experimental results show that the proposed algorithm improves the performance of the baseline system and compares favourably with other top performing signature verification systems.
Authors: Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, Chunhui Lin, Wanqing Li, Mohamad Fitri Faiz Bin Mahmood, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang
Abstract: Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding. However, most TEC-VQA benchmarks have focused on high-resource languages like English and Chinese. Despite pioneering works to expand multilingual QA pairs in non-text-centric VQA datasets using translation engines, the translation-based protocol encounters a substantial ``Visual-textual misalignment'' problem when applied to TEC-VQA. Specifically, it prioritizes the text in question-answer pairs while disregarding the visual text present in images. Furthermore, it does not adequately tackle challenges related to nuanced meaning, contextual distortion, language bias, and question-type diversity. In this work, we address the task of multilingual TEC-VQA and provide a benchmark with high-quality human expert annotations in 9 diverse languages, called MTVQA. To our knowledge, MTVQA is the first multilingual TEC-VQA benchmark to provide human expert annotations for text-centric scenarios. Further, by evaluating several state-of-the-art Multimodal Large Language Models (MLLMs), including GPT-4V, on our MTVQA dataset, it is evident that there is still room for performance improvement, underscoring the value of our dataset. We hope this dataset will provide researchers with fresh perspectives and inspiration within the community. The MTVQA dataset will be available at https://huggingface.co/datasets/ByteDance/MTVQA.
Authors: Xinyang Li, Jiaxin Wang, Yixin Xuan, Gongxin Yao, Yu Pan
Abstract: We propose GGAvatar, a novel 3D avatar representation designed to robustly model dynamic head avatars with complex identities and deformations. GGAvatar employs a coarse-to-fine structure, featuring two core modules: Neutral Gaussian Initialization Module and Geometry Morph Adjuster. Neutral Gaussian Initialization Module pairs Gaussian primitives with deformable triangular meshes, employing an adaptive density control strategy to model the geometric structure of the target subject with neutral expressions. Geometry Morph Adjuster introduces deformation bases for each Gaussian in global space, creating fine-grained low-dimensional representations of deformation behaviors to address the Linear Blend Skinning formula's limitations effectively. Extensive experiments show that GGAvatar can produce high-fidelity renderings, outperforming state-of-the-art methods in visual quality and quantitative metrics.
Authors: Weilian Zhou (Cynthia), Sei-Ichiro Kamata (Cynthia), Haipeng Wang (Cynthia), Man-Sing Wong (Cynthia), Huiying (Cynthia), Hou
Abstract: Hyperspectral image (HSI) classification is pivotal in the remote sensing (RS) field, particularly with the advancement of deep learning techniques. Sequential models, adapted from the natural language processing (NLP) field such as Recurrent Neural Networks (RNNs) and Transformers, have been tailored to this task, offering a unique viewpoint. However, several challenges persist 1) RNNs struggle with centric feature aggregation and are sensitive to interfering pixels, 2) Transformers require significant computational resources and often underperform with limited HSI training samples, and 3) Current scanning methods for converting images into sequence-data are simplistic and inefficient. In response, this study introduces the innovative Mamba-in-Mamba (MiM) architecture for HSI classification, the first attempt of deploying State Space Model (SSM) in this task. The MiM model includes 1) A novel centralized Mamba-Cross-Scan (MCS) mechanism for transforming images into sequence-data, 2) A Tokenized Mamba (T-Mamba) encoder that incorporates a Gaussian Decay Mask (GDM), a Semantic Token Learner (STL), and a Semantic Token Fuser (STF) for enhanced feature generation and concentration, and 3) A Weighted MCS Fusion (WMF) module coupled with a Multi-Scale Loss Design to improve decoding efficiency. Experimental results from three public HSI datasets with fixed and disjoint training-testing samples demonstrate that our method outperforms existing baselines and state-of-the-art approaches, highlighting its efficacy and potential in HSI applications.
Authors: Rukun Qiao, Hiroshi Kawasaki, Hongbin Zha
Abstract: We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised differentiable rendering. Unlike passive vision, where joint estimation of radiance and geometry fields is necessary, we capitalize on known radiance fields from projected patterns in structured light systems. This enables isolated optimization of the geometry field, ensuring convergence and network efficacy with fixed device positioning. To enhance geometric fidelity, we incorporate an additional color loss based on object surfaces during training. Real-world experiments demonstrate our method's superiority in geometric performance for few-shot scenarios, while achieving comparable results with increased pattern availability.
Authors: Neena Aloysius, Geetha M, Prema Nedungadi
Abstract: Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The sequence learning module is a crucial part wherein transformers have demonstrated their efficacy in the sequence-to-sequence tasks. Analyzing the research progress in the field of Natural Language Processing and Speech Recognition, a rapid introduction of various transformer variants is observed. However, in the realm of sign language, experimentation in the sequence learning component is limited. In this work, the state-of-the-art Conformer model for Speech Recognition is adapted for CSLR and the proposed model is termed ConSignformer. This marks the first instance of employing Conformer for a vision-based task. ConSignformer has bimodal pipeline of CNN as feature extractor and Conformer for sequence learning. For improved context learning we also introduce Cross-Modal Relative Attention (CMRA). By incorporating CMRA into the model, it becomes more adept at learning and utilizing complex relationships within the data. To further enhance the Conformer model, unsupervised pretraining called Regressional Feature Extraction is conducted on a curated sign language dataset. The pretrained Conformer is then fine-tuned for the downstream recognition task. The experimental results confirm the effectiveness of the adopted pretraining strategy and demonstrate how CMRA contributes to the recognition process. Remarkably, leveraging a Conformer-based backbone, our model achieves state-of-the-art performance on the benchmark datasets: PHOENIX-2014 and PHOENIX-2014T.
Authors: Fotios Logothetis, Ignas Budvytis, Roberto Cipolla
Abstract: In this work we present a novel multi-view photometric stereo (PS) method. Like many works in 3D reconstruction we are leveraging neural shape representations and learnt renderers. However, our work differs from the state-of-the-art multi-view PS methods such as PS-NeRF or SuperNormal we explicity leverage per-pixel intensity renderings rather than relying mainly on estimated normals. We model point light attenuation and explicitly raytrace cast shadows in order to best approximate each points incoming radiance. This is used as input to a fully neural material renderer that uses minimal prior assumptions and it is jointly optimised with the surface. Finally, estimated normal and segmentation maps can also incorporated in order to maximise the surface accuracy. Our method is among the first to outperform the classical approach of DiLiGenT-MV and achieves average 0.2mm Chamfer distance for objects imaged at approx 1.5m distance away with approximate 400x400 resolution. Moreover, we show robustness to poor normals in low light count scenario, achieving 0.27mm Chamfer distance when pixel rendering is used instead of estimated normals.
Authors: Tianhao Wu, Jing Yang, Zhilin Guo, Jingyi Wan, Fangcheng Zhong, Cengiz Oztireli
Abstract: By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity. However, most existing methods only reconstruct a head without the body, substantially limiting their application scenarios. We found that naively applying Gaussians to model the clothed chest and shoulders tends to result in blurry reconstruction and noisy floaters under novel poses. This is because of the fundamental limitation of Gaussians and point clouds -- each Gaussian or point can only have a single directional radiance without spatial variance, therefore an unnecessarily large number of them is required to represent complicated spatially varying texture, even for simple geometry. In contrast, we propose to model the body part with a neural texture that consists of coarse and pose-dependent fine colors. To properly render the body texture for each view and pose without accurate geometry nor UV mapping, we optimize another sparse set of Gaussians as anchors that constrain the neural warping field that maps image plane coordinates to the texture space. We demonstrate that Gaussian Head & Shoulders can fit the high-frequency details on the clothed upper body with high fidelity and potentially improve the accuracy and fidelity of the head region. We evaluate our method with casual phone-captured and internet videos and show our method archives superior reconstruction quality and robustness in both self and cross reenactment tasks. To fully utilize the efficient rendering speed of Gaussian splatting, we additionally propose an accelerated inference method of our trained model without Multi-Layer Perceptron (MLP) queries and reach a stable rendering speed of around 130 FPS for any subjects.
Authors: Calvin Yeung, Kenjiro Ide, Keisuke Fujii
Abstract: Image understanding is a foundational task in computer vision, with recent applications emerging in soccer posture analysis. However, existing publicly available datasets lack comprehensive information, notably in the form of posture sequences and 2D pose annotations. Moreover, current analysis models often rely on interpretable linear models (e.g., PCA and regression), limiting their capacity to capture non-linear spatiotemporal relationships in complex and diverse scenarios. To address these gaps, we introduce the 3D Shot Posture (3DSP) dataset in soccer broadcast videos, which represents the most extensive sports image dataset with 2D pose annotations to our knowledge. Additionally, we present the 3DSP-GRAE (Graph Recurrent AutoEncoder) model, a non-linear approach for embedding pose sequences. Furthermore, we propose AutoSoccerPose, a pipeline aimed at semi-automating 2D and 3D pose estimation and posture analysis. While achieving full automation proved challenging, we provide a foundational baseline, extending its utility beyond the scope of annotated data. We validate AutoSoccerPose on SoccerNet and 3DSP datasets, and present posture analysis results based on 3DSP. The dataset, code, and models are available at: https://github.com/calvinyeungck/3D-Shot-Posture-Dataset.
URLs: https://github.com/calvinyeungck/3D-Shot-Posture-Dataset.
Authors: Antonio R\'ios-Vila, Jorge Calvo-Zaragoza, David Rizo, Thierry Paquet
Abstract: Optical Music Recognition is a field that has progressed significantly, bringing accurate systems that transcribe effectively music scores into digital formats. Despite this, there are still several limitations that hinder OMR from achieving its full potential. Specifically, state of the art OMR still depends on multi-stage pipelines for performing full-page transcription, as well as it has only been demonstrated in monophonic cases, leaving behind very relevant engravings. In this work, we present the Sheet Music Transformer++, an end-to-end model that is able to transcribe full-page polyphonic music scores without the need of a previous Layout Analysis step. This is done thanks to an extensive curriculum learning-based pretraining with synthetic data generation. We conduct several experiments on a full-page extension of a public polyphonic transcription dataset. The experimental outcomes confirm that the model is competent at transcribing full-page pianoform scores, marking a noteworthy milestone in end-to-end OMR transcription.
Authors: Zhenwei Shao, Zhou Yu, Jun Yu, Xuecheng Ouyang, Lihao Zheng, Zhenbiao Gai, Mingyang Wang, Jiajun Ding
Abstract: By harnessing the capabilities of large language models (LLMs), recent large multimodal models (LMMs) have shown remarkable versatility in open-world multimodal understanding. Nevertheless, they are usually parameter-heavy and computation-intensive, thus hindering their applicability in resource-constrained scenarios. To this end, several lightweight LMMs have been proposed successively to maximize the capabilities under constrained scale (e.g., 3B). Despite the encouraging results achieved by these methods, most of them only focus on one or two aspects of the design space, and the key design choices that influence model capability have not yet been thoroughly investigated. In this paper, we conduct a systematic study for lightweight LMMs from the aspects of model architecture, training strategy, and training data. Based on our findings, we obtain Imp -- a family of highly capable LMMs at the 2B-4B scales. Notably, our Imp-3B model steadily outperforms all the existing lightweight LMMs of similar size, and even surpasses the state-of-the-art LMMs at the 13B scale. With low-bit quantization and resolution reduction techniques, our Imp model can be deployed on a Qualcomm Snapdragon 8Gen3 mobile chip with a high inference speed of about 13 tokens/s.
Authors: Jiawei Zhang, Jiahe Li, Xiaohan Yu, Lei Huang, Lin Gu, Jin Zheng, Xiao Bai
Abstract: 3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting the reconstruction quality. This paper introduces a new co-regularization perspective for improving sparse-view 3DGS. When training two 3D Gaussian radiance fields with the same sparse views of a scene, we observe that the two radiance fields exhibit \textit{point disagreement} and \textit{rendering disagreement} that can unsupervisedly predict reconstruction quality, stemming from the sampling implementation in densification. We further quantify the point disagreement and rendering disagreement by evaluating the registration between Gaussians' point representations and calculating differences in their rendered pixels. The empirical study demonstrates the negative correlation between the two disagreements and accurate reconstruction, which allows us to identify inaccurate reconstruction without accessing ground-truth information. Based on the study, we propose CoR-GS, which identifies and suppresses inaccurate reconstruction based on the two disagreements: (\romannumeral1) Co-pruning considers Gaussians that exhibit high point disagreement in inaccurate positions and prunes them. (\romannumeral2) Pseudo-view co-regularization considers pixels that exhibit high rendering disagreement are inaccurately rendered and suppress the disagreement. Results on LLFF, Mip-NeRF360, DTU, and Blender demonstrate that CoR-GS effectively regularizes the scene geometry, reconstructs the compact representations, and achieves state-of-the-art novel view synthesis quality under sparse training views.
Authors: Zhigang Jia, Yuelian Xiang, Meixiang Zhao, Tingting Wu, Michael K. Ng
Abstract: The cross-channel deblurring problem in color image processing is difficult to solve due to the complex coupling and structural blurring of color pixels. Until now, there are few efficient algorithms that can reduce color infection in deblurring process. To solve this challenging problem, we present a novel cross-space total variation (CSTV) regularization model for color image deblurring by introducing a quaternion blur operator and a cross-color space regularization functional. The existence and uniqueness of the solution is proved and a new L-curve method is proposed to find a sweet balance of regularization functionals on different color spaces. The Euler-Lagrange equation is derived to show that CSTV has taken into account the coupling of all color channels and the local smoothing within each color channel. A quaternion operator splitting method is firstly proposed to enhance the ability of color infection reduction of the CSTV regularization model. This strategy also applies to the well-known color deblurring models. Numerical experiments on color image databases illustrate the efficiency and manoeuvrability of the new model and algorithms. The color images restored by them successfully maintain the color and spatial information and are of higher quality in terms of PSNR, SSIM, MSE and CIEde2000 than the restorations of the-state-of-the-art methods.
Authors: Nida Nasir, Muneeb Ahmed, Neda Afreen, Mustafa Sameer
Abstract: Deep learning, a cutting-edge machine learning approach, outperforms traditional machine learning in identifying intricate structures in complex high-dimensional data, particularly in the domain of healthcare. This study focuses on classifying Magnetic Resonance Imaging (MRI) data for Alzheimer's disease (AD) by leveraging deep learning techniques characterized by state-of-the-art CNNs. Brain imaging techniques such as MRI have enabled the measurement of pathophysiological brain changes related to Alzheimer's disease. Alzheimer's disease is the leading cause of dementia in the elderly, and it is an irreversible brain illness that causes gradual cognitive function disorder. In this paper, we train some benchmark deep models individually for the approach of the solution and later use an ensembling approach to combine the effect of multiple CNNs towards the observation of higher recall and accuracy. Here, the model's effectiveness is evaluated using various methods, including stacking, majority voting, and the combination of models with high recall values. The majority voting performs better than the alternative modelling approach as the majority voting approach typically reduces the variance in the predictions. We report a test accuracy of 90% with a precision score of 0.90 and a recall score of 0.89 in our proposed approach. In future, this study can be extended to incorporate other types of medical data, including signals, images, and other data. The same or alternative datasets can be used with additional classifiers, neural networks, and AI techniques to enhance Alzheimer's detection.
Authors: Xuchen Li, Xiaokun Feng, Shiyu Hu, Meiqi Wu, Dailing Zhang, Jing Zhang, Kaiqi Huang
Abstract: Visual Language Tracking (VLT) enhances single object tracking (SOT) by integrating natural language descriptions from a video, for the precise tracking of a specified object. By leveraging high-level semantic information, VLT guides object tracking, alleviating the constraints associated with relying on a visual modality. Nevertheless, most VLT benchmarks are annotated in a single granularity and lack a coherent semantic framework to provide scientific guidance. Moreover, coordinating human annotators for high-quality annotations is laborious and time-consuming. To address these challenges, we introduce DTLLM-VLT, which automatically generates extensive and multi-granularity text to enhance environmental diversity. (1) DTLLM-VLT generates scientific and multi-granularity text descriptions using a cohesive prompt framework. Its succinct and highly adaptable design allows seamless integration into various visual tracking benchmarks. (2) We select three prominent benchmarks to deploy our approach: short-term tracking, long-term tracking, and global instance tracking. We offer four granularity combinations for these benchmarks, considering the extent and density of semantic information, thereby showcasing the practicality and versatility of DTLLM-VLT. (3) We conduct comparative experiments on VLT benchmarks with different text granularities, evaluating and analyzing the impact of diverse text on tracking performance. Conclusionally, this work leverages LLM to provide multi-granularity semantic information for VLT task from efficient and diverse perspectives, enabling fine-grained evaluation of multi-modal trackers. In the future, we believe this work can be extended to more datasets to support vision datasets understanding.
Authors: Bipin Saha, Md. Johirul Islam, Shaikh Khaled Mostaque, Aditya Bhowmik, Tapodhir Karmakar Taton, Md. Nakib Hayat Chowdhury, Mamun Bin Ibne Reaz
Abstract: The success of autonomous navigation relies on robust and precise vehicle recognition, hindered by the scarcity of region-specific vehicle detection datasets, impeding the development of context-aware systems. To advance terrestrial object detection research, this paper proposes a native vehicle detection dataset for the most commonly appeared vehicle classes in Bangladesh. 17 distinct vehicle classes have been taken into account, with fully annotated 81542 instances of 17326 images. Each image width is set to at least 1280px. The dataset's average vehicle bounding box-to-image ratio is 4.7036. This Bangladesh Native Vehicle Dataset (BNVD) has accounted for several geographical, illumination, variety of vehicle sizes, and orientations to be more robust on surprised scenarios. In the context of examining the BNVD dataset, this work provides a thorough assessment with four successive You Only Look Once (YOLO) models, namely YOLO v5, v6, v7, and v8. These dataset's effectiveness is methodically evaluated and contrasted with other vehicle datasets already in use. The BNVD dataset exhibits mean average precision(mAP) at 50% intersection over union (IoU) is 0.848 corresponding precision and recall values of 0.841 and 0.774. The research findings indicate a mAP of 0.643 at an IoU range of 0.5 to 0.95. The experiments show that the BNVD dataset serves as a reliable representation of vehicle distribution and presents considerable complexities.
Authors: Vaibhav Dhore, Achintya Bhat, Viraj Nerlekar, Kashyap Chavhan, Aniket Umare
Abstract: We present a new technique that explains the output of a CNN-based model using a combination of GradCAM and LRP methods. Both of these methods produce visual explanations by highlighting input regions that are important for predictions. In the new method, the explanation produced by GradCAM is first processed to remove noises. The processed output is then multiplied elementwise with the output of LRP. Finally, a Gaussian blur is applied on the product. We compared the proposed method with GradCAM and LRP on the metrics of Faithfulness, Robustness, Complexity, Localisation and Randomisation. It was observed that this method performs better on Complexity than both GradCAM and LRP and is better than atleast one of them in the other metrics.
Authors: Xianpeng Liu, Ce Zheng, Ming Qian, Nan Xue, Chen Chen, Zhebin Zhang, Chen Li, Tianfu Wu
Abstract: We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of query-based MV3D object detection, prior art often suffers from either the lack of exploiting high-resolution 2D features in dense attention-based lifting, due to high computational costs, or from insufficiently dense grounding of 3D queries to multi-scale 2D features in sparse attention-based lifting. Our proposed MvACon hits the two birds with one stone using a representationally dense yet computationally sparse attentive feature contextualization scheme that is agnostic to specific 2D-to-3D feature lifting approaches. In experiments, the proposed MvACon is thoroughly tested on the nuScenes benchmark, using both the BEVFormer and its recent 3D deformable attention (DFA3D) variant, as well as the PETR, showing consistent detection performance improvement, especially in enhancing performance in location, orientation, and velocity prediction. It is also tested on the Waymo-mini benchmark using BEVFormer with similar improvement. We qualitatively and quantitatively show that global cluster-based contexts effectively encode dense scene-level contexts for MV3D object detection. The promising results of our proposed MvACon reinforces the adage in computer vision -- ``(contextualized) feature matters".
Authors: Xihaier Luo, Xiaoning Qian, Byung-Jun Yoon
Abstract: In this work, we present an arbitrary-scale super-resolution (SR) method to enhance the resolution of scientific data, which often involves complex challenges such as continuity, multi-scale physics, and the intricacies of high-frequency signals. Grounded in operator learning, the proposed method is resolution-invariant. The core of our model is a hierarchical neural operator that leverages a Galerkin-type self-attention mechanism, enabling efficient learning of mappings between function spaces. Sinc filters are used to facilitate the information transfer across different levels in the hierarchy, thereby ensuring representation equivalence in the proposed neural operator. Additionally, we introduce a learnable prior structure that is derived from the spectral resizing of the input data. This loss prior is model-agnostic and is designed to dynamically adjust the weighting of pixel contributions, thereby balancing gradients effectively across the model. We conduct extensive experiments on diverse datasets from different domains and demonstrate consistent improvements compared to strong baselines, which consist of various state-of-the-art SR methods.
Authors: Nathaniel Cohen, Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, Tomer Michaeli
Abstract: Text-to-image (T2I) diffusion models achieve state-of-the-art results in image synthesis and editing. However, leveraging such pretrained models for video editing is considered a major challenge. Many existing works attempt to enforce temporal consistency in the edited video through explicit correspondence mechanisms, either in pixel space or between deep features. These methods, however, struggle with strong nonrigid motion. In this paper, we introduce a fundamentally different approach, which is based on the observation that spatiotemporal slices of natural videos exhibit similar characteristics to natural images. Thus, the same T2I diffusion model that is normally used only as a prior on video frames, can also serve as a strong prior for enhancing temporal consistency by applying it on spatiotemporal slices. Based on this observation, we present Slicedit, a method for text-based video editing that utilizes a pretrained T2I diffusion model to process both spatial and spatiotemporal slices. Our method generates videos that retain the structure and motion of the original video while adhering to the target text. Through extensive experiments, we demonstrate Slicedit's ability to edit a wide range of real-world videos, confirming its clear advantages compared to existing competing methods. Webpage: https://matankleiner.github.io/slicedit/
Authors: Guanglin Zhou, Zhongyi Han, Shiming Chen, Biwei Huang, Liming Zhu, Salman Khan, Xin Gao, Lina Yao
Abstract: Recent studies indicate that large multimodal models (LMMs) are highly robust against natural distribution shifts, often surpassing previous baselines. Despite this, domain-specific adaptation is still necessary, particularly in specialized areas like healthcare. Due to the impracticality of fine-tuning LMMs given their vast parameter space, this work investigates in-context learning (ICL) as an effective alternative for enhancing LMMs' adaptability. We find that the success of ICL heavily relies on the choice of demonstration, mirroring challenges seen in large language models but introducing unique complexities for LMMs facing distribution shifts. Our study addresses this by evaluating an unsupervised ICL method, TopKNearestPR, which selects in-context examples through a nearest example search based on feature similarity. We uncover that its effectiveness is limited by the deficiencies of pre-trained vision encoders under distribution shift scenarios. To address these challenges, we propose InvariantSelectPR, a novel method leveraging Class-conditioned Contrastive Invariance (CCI) for more robust demonstration selection. Specifically, CCI enhances pre-trained vision encoders by improving their discriminative capabilities across different classes and ensuring invariance to domain-specific variations. This enhancement allows the encoders to effectively identify and retrieve the most informative examples, which are then used to guide LMMs in adapting to new query samples under varying distributions. Our experiments show that InvariantSelectPR substantially improves the adaptability of LMMs, achieving significant performance gains on benchmark datasets, with a 34.2%$\uparrow$ accuracy increase in 7-shot on Camelyon17 and 16.9%$\uparrow$ increase in 7-shot on HAM10000 compared to the baseline zero-shot performance.
Authors: Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu
Abstract: We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point clouds generated by the generalizable model, serving as the initialization for per-scene optimization. Compared with previous generalizable NeRF-based methods, which typically require minutes of fine-tuning and seconds of rendering per image, MVSGaussian achieves real-time rendering with better synthesis quality for each scene. Compared with the vanilla 3D-GS, MVSGaussian achieves better view synthesis with less training computational cost. Extensive experiments on DTU, Real Forward-facing, NeRF Synthetic, and Tanks and Temples datasets validate that MVSGaussian attains state-of-the-art performance with convincing generalizability, real-time rendering speed, and fast per-scene optimization.
Authors: Ziyang Chen, Daniel Geng, Andrew Owens
Abstract: Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these spectrograms images that sound. Our approach is simple and zero-shot, and it leverages pre-trained text-to-image and text-to-spectrogram diffusion models that operate in a shared latent space. During the reverse process, we denoise noisy latents with both the audio and image diffusion models in parallel, resulting in a sample that is likely under both models. Through quantitative evaluations and perceptual studies, we find that our method successfully generates spectrograms that align with a desired audio prompt while also taking the visual appearance of a desired image prompt. Please see our project page for video results: https://ificl.github.io/images-that-sound/
Authors: B. Borkovits, E. Kontsek, A. Pesti, P. Gordon, S. Gergely, I. Csabai, A. Kiss, P. Pollner
Abstract: In this project, we used formalin-fixed paraffin-embedded (FFPE) tissue samples to measure thousands of spectra per tissue core with Fourier transform mid-infrared spectroscopy using an FT-IR imaging system. These cores varied between normal colon (NC) and colorectal primer carcinoma (CRC) tissues. We created a database to manage all the multivariate data obtained from the measurements. Then, we applied classifier algorithms to identify the tissue based on its yielded spectra. For classification, we used the random forest, a support vector machine, XGBoost, and linear discriminant analysis methods, as well as three deep neural networks. We compared two data manipulation techniques using these models and then applied filtering. In the end, we compared model performances via the sum of ranking differences (SRD).
Authors: Sandeep Singh Sengar, Affan Bin Hasan, Sanjay Kumar, Fiona Carroll
Abstract: In recent years, the study of artificial intelligence (AI) has undergone a paradigm shift. This has been propelled by the groundbreaking capabilities of generative models both in supervised and unsupervised learning scenarios. Generative AI has shown state-of-the-art performance in solving perplexing real-world conundrums in fields such as image translation, medical diagnostics, textual imagery fusion, natural language processing, and beyond. This paper documents the systematic review and analysis of recent advancements and techniques in Generative AI with a detailed discussion of their applications including application-specific models. Indeed, the major impact that generative AI has made to date, has been in language generation with the development of large language models, in the field of image translation and several other interdisciplinary applications of generative AI. Moreover, the primary contribution of this paper lies in its coherent synthesis of the latest advancements in these areas, seamlessly weaving together contemporary breakthroughs in the field. Particularly, how it shares an exploration of the future trajectory for generative AI. In conclusion, the paper ends with a discussion of Responsible AI principles, and the necessary ethical considerations for the sustainability and growth of these generative models.
Authors: Zihao Zou, Shirin Shoushtari, Jiaming Liu, Jialiang Zhang, Patrick Judge, Emilia Santana, Alison Lim, Marcus Foston, Ulugbek S. Kamilov
Abstract: Nuclear Magnetic Resonance (NMR) spectroscopy is a widely-used technique in the fields of bio-medicine, chemistry, and biology for the analysis of chemicals and proteins. The signals from NMR spectroscopy often have low signal-to-noise ratio (SNR) due to acquisition noise, which poses significant challenges for subsequent analysis. Recent work has explored the potential of deep learning (DL) for NMR denoising, showing significant performance gains over traditional methods such as total variation (TV) denoising. This paper shows that the performance of DL denoising for NMR can be further improved by combining data-driven training with traditional TV denoising. The proposed TVCondNet method outperforms both traditional TV and DL methods by including the TV solution as a condition during DL training. Our validation on experimentally collected NMR data shows the superior denoising performance and faster inference speed of TVCondNet compared to existing methods.
Authors: Lavsen Dahal, Mobina Ghojoghnejad, Dhrubajyoti Ghosh, Yubraj Bhandari, David Kim, Fong Chi Ho, Fakrul Islam Tushar, Ehsan Abadi, Ehsan Samei, Joseph Lo, 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-2.github.io.
URLs: https://cvit.duke.edu/resources/,, https://xcat-2.github.io.
Authors: Hyungtae Lim
Abstract: Despite the remarkable advancements in deep learning-based perception technologies and simultaneous localization and mapping~(SLAM), one can face the failure of these approaches when robots encounter scenarios outside their modeled experiences~(here, the term \textit{modeling} encompasses both conventional pattern finding and data-driven approaches). In particular, because learning-based methods are prone to catastrophic failure when operated in untrained scenes, there is still a demand for conventional yet robust approaches that work out of the box in diverse scenarios, such as real-world robotic services and SLAM competitions. In addition, the dynamic nature of real-world environments, characterized by changing surroundings over time and the presence of moving objects, leads to undesirable data points that hinder a robot from localization and path planning. Consequently, methodologies that enable long-term map management, such as multi-session SLAM and static map building, become essential. Therefore, to achieve a robust long-term robotic mapping system that can work out of the box, first, I propose (i)~fast and robust ground segmentation to reject the ground points, which are featureless and thus not helpful for localization and mapping. Then, by employing the concept of graduated non-convexity~(GNC), I propose (ii)~outlier-robust registration with ground segmentation that overcomes the presence of gross outliers within the feature matching results, and (iii)~hierarchical multi-session SLAM that not only uses our proposed GNC-based registration but also employs a GNC solver to be robust against outlier loop candidates. Finally, I propose (iv)~instance-aware static map building that can handle the presence of moving objects in the environment based on the observation that most moving objects in urban environments are inevitably in contact with the ground.
Authors: Yunxin Li, Shenyuan Jiang, Baotian Hu, Longyue Wang, Wanqi Zhong, Wenhan Luo, Lin Ma, Min Zhang
Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE) architecture has been employed to efficiently scale large language and image-text models, these efforts typically involve fewer experts and limited modalities. To address this, our work presents the pioneering attempt to develop a unified MLLM with the MoE architecture, named Uni-MoE that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We also implement a sparse MoE architecture within the LLMs to enable efficient training and inference through modality-level data parallelism and expert-level model parallelism. To enhance the multi-expert collaboration and generalization, we present a progressive training strategy: 1) Cross-modality alignment using various connectors with different cross-modality data, 2) Training modality-specific experts with cross-modality instruction data to activate experts' preferences, and 3) Tuning the Uni-MoE framework utilizing Low-Rank Adaptation (LoRA) on mixed multimodal instruction data. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets. The extensive experimental results demonstrate Uni-MoE's principal advantage of significantly reducing performance bias in handling mixed multimodal datasets, alongside improved multi-expert collaboration and generalization. Our findings highlight the substantial potential of MoE frameworks in advancing MLLMs and the code is available at https://github.com/HITsz-TMG/UMOE-Scaling-Unified-Multimodal-LLMs.
URLs: https://github.com/HITsz-TMG/UMOE-Scaling-Unified-Multimodal-LLMs.
Authors: Ming Hu, Siyuan Yan, Peng Xia, Feilong Tang, Wenxue Li, Peibo Duan, Lin Zhang, Zongyuan Ge
Abstract: Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging equipment variability, brightness changes, and image blur. This will reduce the reliability of model deployment in real-world scenarios. Most existing solutions focus on adapting the source model through retraining on different target domains. Although effective, this retraining process is sensitive to the amount of data and the hyperparameter configuration for optimization. In this paper, we propose a test-time image adaptation method to enhance the accuracy of the model on test data by simultaneously updating and predicting test images. We modify the target test images by projecting them back to the source domain using a diffusion model. Specifically, we design a structure guidance module that adds refinement operations through low-pass filtering during reverse sampling, regularizing the diffusion to preserve structural information. Additionally, we introduce a self-ensembling scheme automatically adjusts the reliance on adapted and unadapted inputs, enhancing adaptation robustness by rejecting inappropriate generative modeling results. To facilitate this study, we constructed the ISIC2019-C and Dermnet-C corruption robustness evaluation benchmarks. Extensive experiments on the proposed benchmarks demonstrate that our method makes the classifier more robust across various corruptions, architectures, and data regimes. Our datasets and code will be available at \url{https://github.com/minghu0830/Skin-TTA_Diffusion}.
Authors: Nand Lal Yadav, Satyendra Singh, Rajesh Kumar, Sudhakar Singh
Abstract: X-ray is one of the prevalent image modalities for the detection and diagnosis of the human body. X-ray provides an actual anatomical structure of an organ present with disease or absence of disease. Segmentation of disease in chest X-ray images is essential for the diagnosis and treatment. In this paper, a framework for the segmentation of X-ray images using artificial intelligence techniques has been discussed. Here data has been pre-processed and cleaned followed by segmentation using SegNet and Residual Net approaches to X-ray images. Finally, segmentation has been evaluated using well known metrics like Loss, Dice Coefficient, Jaccard Coefficient, Precision, Recall, Binary Accuracy, and Validation Accuracy. The experimental results reveal that the proposed approach performs better in all respect of well-known parameters with 16 batch size and 50 epochs. The value of validation accuracy, precision, and recall of SegNet and Residual Unet models are 0.9815, 0.9699, 0.9574, and 0.9901, 0.9864, 0.9750 respectively.
Authors: Jack Vice, Natalie Ruiz-Sanchez, Pamela K. Douglas, Gita Sukthankar
Abstract: In humans, intrinsic motivation is an important mechanism for open-ended cognitive development; in robots, it has been shown to be valuable for exploration. An important aspect of human cognitive development is $\textit{episodic memory}$ which enables both the recollection of events from the past and the projection of subjective future. This paper explores the use of visual episodic memory as a source of intrinsic motivation for robotic exploration problems. Using a convolutional recurrent neural network autoencoder, the agent learns an efficient representation for spatiotemporal features such that accurate sequence prediction can only happen once spatiotemporal features have been learned. Structural similarity between ground truth and autoencoder generated images is used as an intrinsic motivation signal to guide exploration. Our proposed episodic memory model also implicitly accounts for the agent's actions, motivating the robot to seek new interactive experiences rather than just areas that are visually dissimilar. When guiding robotic exploration, our proposed method outperforms the Curiosity-driven Variational Autoencoder (CVAE) at finding dynamic anomalies.
Authors: Canshi Wei
Abstract: Fine-grained image classification, particularly in zero/few-shot scenarios, presents a significant challenge for vision-language models (VLMs), such as CLIP. These models often struggle with the nuanced task of distinguishing between semantically similar classes due to limitations in their pre-trained recipe, which lacks supervision signals for fine-grained categorization. This paper introduces CascadeVLM, an innovative framework that overcomes the constraints of previous CLIP-based methods by effectively leveraging the granular knowledge encapsulated within large vision-language models (LVLMs). Experiments across various fine-grained image datasets demonstrate that CascadeVLM significantly outperforms existing models, specifically on the Stanford Cars dataset, achieving an impressive 85.6% zero-shot accuracy. Performance gain analysis validates that LVLMs produce more accurate predictions for challenging images that CLIPs are uncertain about, bringing the overall accuracy boost. Our framework sheds light on a holistic integration of VLMs and LVLMs for effective and efficient fine-grained image classification.
Authors: Emmanouil Maragkoudakis, Symeon Papadopoulos, Iraklis Varlamis, Christos Diou
Abstract: Synthetically generated images can be used to create media content or to complement datasets for training image analysis models. Several methods have recently been proposed for the synthesis of high-fidelity face images; however, the potential biases introduced by such methods have not been sufficiently addressed. This paper examines the bias introduced by the widely popular StyleGAN2 generative model trained on the Flickr Faces HQ dataset and proposes two sampling strategies to balance the representation of selected attributes in the generated face images. We focus on two protected attributes, gender and age, and reveal that biases arise in the distribution of randomly sampled images against very young and very old age groups, as well as against female faces. These biases are also assessed for different image quality levels based on the GIQA score. To mitigate bias, we propose two alternative methods for sampling on selected lines or spheres of the latent space to increase the number of generated samples from the under-represented classes. The experimental results show a decrease in bias against underrepresented groups and a more uniform distribution of the protected features at different levels of image quality.
Authors: Defang Chen, Zhenyu Zhou, Can Wang, Chunhua Shen, Siwei Lyu
Abstract: Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models. We characterize an implicit denoising trajectory and discuss its vital role in forming the coupled sampling trajectory with a strong shape regularity, regardless of the generated content. We also describe a dynamic programming-based scheme to make the time schedule in sampling better fit the underlying trajectory structure. This simple strategy requires minimal modification to any given ODE-based numerical solvers and incurs negligible computational cost, while delivering superior performance in image generation, especially in $5\sim 10$ function evaluations.
Authors: Qiyue Wang, Wu Xue, Xiaoke Zhang, Fang Jin, James Hahn
Abstract: It is clinically important to detect liver fat content as it is related to cardiac complications and cardiovascular disease mortality. However, existing methods are associated with high cost and/or medical complications (e.g., liver biopsy, medical imaging technology) or only roughly estimate the grades of steatosis. In this paper, we propose a deep neural network to accurately estimate liver fat percentage using only body shapes. The proposed framework is composed of a flexible baseline regression network and a lightweight attention module. The attention module is trained to generate discriminative and diverse features, thus significantly improving performance. To validate our proposed method, we perform extensive tests on medical datasets. The experimental results validate our method and prove the efficacy of designing neural networks to predict liver fat using only body shape. Since body shapes can be acquired using inexpensive and readily available optical scanners, the proposed method promised to make accurate assessment of hepatic steatosis more accessible.
Authors: Jignesh Patel, Yannis Spyridis, Vasileios Argyriou
Abstract: Aerodynamic design optimisation plays a crucial role in improving the performance and efficiency of automotive vehicles. This paper presents a novel approach for aerodynamic optimisation in car design using deep reinforcement learning (DRL). Traditional optimisation methods often face challenges in handling the complexity of the design space and capturing non-linear relationships between design parameters and aerodynamic performance metrics. This study addresses these challenges by employing DRL to learn optimal aerodynamic design strategies in a voxelised model representation. The proposed approach utilises voxelised models to discretise the vehicle geometry into a grid of voxels, allowing for a detailed representation of the aerodynamic flow field. The Proximal Policy Optimisation (PPO) algorithm is then employed to train a DRL agent to optimise the design parameters of the vehicle with respect to drag force, kinetic energy, and voxel collision count. Experimental results demonstrate the effectiveness and efficiency of the proposed approach in achieving significant results in aerodynamic performance. The findings highlight the potential of DRL techniques for addressing complex aerodynamic design optimisation problems in automotive engineering, with implications for improving vehicle performance, fuel efficiency, and environmental sustainability.
Authors: Shani Goren, Ido Galil, Ran El-Yaniv
Abstract: Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy constraint with high probability. Lastly, we conduct extensive empirical studies on over a thousand ImageNet classifiers, revealing that training regimes such as CLIP, pretraining on ImageNet21k and knowledge distillation boost hierarchical selective performance.
Authors: Carlo Alberto Barbano, Riccardo Renzulli, Marco Grosso, Domenico Basile, Marco Busso, Marco Grangetto
Abstract: In this paper, we present the major results from the Covid Radiographic imaging System based on AI (Co.R.S.A.) project, which took place in Italy. This project aims to develop a state-of-the-art AI-based system for diagnosing Covid-19 pneumonia from Chest X-ray (CXR) images. The contributions of this work are manyfold: the release of the public CORDA dataset, a deep learning pipeline for Covid-19 detection, and the clinical validation of the developed solution by expert radiologists. The proposed detection model is based on a two-step approach that, paired with state-of-the-art debiasing, provides reliable results. Most importantly, our investigation includes the actual usage of the diagnosis aid tool by radiologists, allowing us to assess the real benefits in terms of accuracy and time efficiency. Project homepage: https://corsa.di.unito.it/
Authors: Zishan Gu, Fenglin Liu, Changchang Yin, Ping Zhang
Abstract: The adoption of large language models (LLMs) in healthcare has attracted significant research interest. However, their performance in healthcare remains under-investigated and potentially limited, due to i) they lack rich domain-specific knowledge and medical reasoning skills; and ii) most state-of-the-art LLMs are unimodal, text-only models that cannot directly process multimodal inputs. To this end, we propose a multimodal medical collaborative reasoning framework \textbf{MultiMedRes}, which incorporates a learner agent to proactively gain essential information from domain-specific expert models, to solve medical multimodal reasoning problems. Our method includes three steps: i) \textbf{Inquire}: The learner agent first decomposes given complex medical reasoning problems into multiple domain-specific sub-problems; ii) \textbf{Interact}: The agent then interacts with domain-specific expert models by repeating the ``ask-answer'' process to progressively obtain different domain-specific knowledge; iii) \textbf{Integrate}: The agent finally integrates all the acquired domain-specific knowledge to accurately address the medical reasoning problem. We validate the effectiveness of our method on the task of difference visual question answering for X-ray images. The experiments demonstrate that our zero-shot prediction achieves state-of-the-art performance, and even outperforms the fully supervised methods. Besides, our approach can be incorporated into various LLMs and multimodal LLMs to significantly boost their performance.
Authors: Tharun V. Puthanveettil, Abhijay Singh, Yashveer Jain, Vinay Bukka, Sameer Arjun S
Abstract: The work introduces a bio-inspired leader-follower system based on an innovative mechanism proposed as software latching that aims to improve collaboration and coordination between a leader agent and the associated autonomous followers. The system utilizes software latching to establish real-time communication and synchronization between the leader and followers. A layered architecture is proposed, encompassing perception, decision-making, and control modules. Challenges such as uncertainty, dynamic environments, and communication latency are addressed using Deep learning and real-time data processing pipelines. The follower robot is equipped with sensors and communication modules that enable it to track and trace the agent of interest or avoid obstacles. The followers track the leader and dynamically avoid obstacles while maintaining a safe distance from it. The experimental results demonstrate the proposed system's effectiveness, making it a promising solution for achieving success in tasks that demand multi-robot systems capable of navigating complex dynamic environments.
Authors: Shao-Yuan Lo, Vishal M. Patel
Abstract: Deep networks are vulnerable to adversarial examples. Adversarial Training (AT) has been a standard foundation of modern adversarial defense approaches due to its remarkable effectiveness. However, AT is extremely time-consuming, refraining it from wide deployment in practical applications. In this paper, we aim at a non-AT defense: How to design a defense method that gets rid of AT but is still robust against strong adversarial attacks? To answer this question, we resort to adaptive Batch Normalization (BN), inspired by the recent advances in test-time domain adaptation. We propose a novel defense accordingly, referred to as the Adaptive Batch Normalization Network (ABNN). ABNN employs a pre-trained substitute model to generate clean BN statistics and sends them to the target model. The target model is exclusively trained on clean data and learns to align the substitute model's BN statistics. Experimental results show that ABNN consistently improves adversarial robustness against both digital and physically realizable attacks on both image and video datasets. Furthermore, ABNN can achieve higher clean data performance and significantly lower training time complexity compared to AT-based approaches.
Authors: Hikmat Khan, Ghulam Rasool, Nidhal Carla Bouaynaya
Abstract: Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. However, these approaches suffer from a problem called "rehearsal memory overfitting, " where the model becomes too specialized on limited memory samples and loses its ability to generalize effectively. As a result, the effectiveness of the rehearsal memory progressively decays, ultimately resulting in catastrophic forgetting of the learned tasks. We introduce the Adversarially Diversified Rehearsal Memory (ADRM) to address the memory overfitting challenge. This novel method is designed to enrich memory sample diversity and bolster resistance against natural and adversarial noise disruptions. ADRM employs the FGSM attacks to introduce adversarially modified memory samples, achieving two primary objectives: enhancing memory diversity and fostering a robust response to continual feature drifts in memory samples. Our contributions are as follows: Firstly, ADRM addresses overfitting in rehearsal memory by employing FGSM to diversify and increase the complexity of the memory buffer. Secondly, we demonstrate that ADRM mitigates memory overfitting and significantly improves the robustness of CL models, which is crucial for safety-critical applications. Finally, our detailed analysis of features and visualization demonstrates that ADRM mitigates feature drifts in CL memory samples, significantly reducing catastrophic forgetting and resulting in a more resilient CL model. Additionally, our in-depth t-SNE visualizations of feature distribution and the quantification of the feature similarity further enrich our understanding of feature representation in existing CL approaches. Our code is publically available at https://github.com/hikmatkhan/ADRM.
Authors: Siyu Lou, Yuntian Chen, Xiaodan Liang, Liang Lin, Quanshi Zhang
Abstract: In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation. These effects are formulated as non-linear interactions between tokens/words encoded by the LLM. Specifically, the axiomatic system enables us to categorize the memorization effects into foundational memorization effects and chaotic memorization effects, and further classify in-context reasoning effects into enhanced inference patterns, eliminated inference patterns, and reversed inference patterns. Besides, the decomposed effects satisfy the sparsity property and the universal matching property, which mathematically guarantee that the LLM's confidence score can be faithfully decomposed into the memorization effects and in-context reasoning effects. Experiments show that the clear disentanglement of memorization effects and in-context reasoning effects enables a straightforward examination of detailed inference patterns encoded by LLMs.
Authors: W. Spencer Smith, Ao Dong, Jacques Carette, Michael D. Noseworthy
Abstract: We selected 29 medical imaging projects from 48 candidates, assessed 10 software qualities by answering 108 questions for each software project, and interviewed 8 of the 29 development teams. Based on the quantitative data, we ranked the MI software with the Analytic Hierarchy Process (AHP). The four top-ranked software products are 3D Slicer, ImageJ, Fiji, and OHIF Viewer. Generally, MI software is in a healthy state as shown by the following: we observed 88% of the documentation artifacts recommended by research software development guidelines, 100% of MI projects use version control tools, and developers appear to use the common quasi-agile research software development process. However, the current state of the practice deviates from the existing guidelines because of the rarity of some recommended artifacts, low usage of continuous integration (17% of the projects), low use of unit testing (about 50% of projects), and room for improvement with documentation (six of nine developers felt their documentation was not clear enough). From interviewing the developers, we identified five pain points and two qualities of potential concern: lack of development time, lack of funding, technology hurdles, ensuring correctness, usability, maintainability, and reproducibility. The interviewees proposed strategies to improve the state of the practice, to address the identified pain points, and to improve software quality. Combining their ideas with ours, we have the following list of recommendations: increase documentation, increase testing by enriching datasets, increase continuous integration usage, move to web applications, employ linters, use peer reviews, design for change, add assurance cases, and incorporate a "Generate All Things" approach.
Authors: Yudie Wang, Zhiwei Li, Chao Zeng, Gui-Song Xia, Huanfeng Shen
Abstract: Urban water is important for the urban ecosystem. Accurate and efficient detection of urban water with remote sensing data is of great significance for urban management and planning. In this paper, we proposed a new method to combine Google Earth Engine (GEE) with multiscale convolutional neural network (MSCNN) to extract urban water from Landsat images, which is summarized as offline training and online prediction (OTOP). That is, the training of MSCNN was completed offline, and the process of urban water extraction was implemented on GEE with the trained parameters of MSCNN. The OTOP can give full play to the respective advantages of GEE and CNN, and make the use of deep learning method on GEE more flexible. It can process available satellite images with high performance without data download and storage, and the overall performance of urban water extraction is also higher than that of the modified normalized difference water index (MNDWI) and random forest. The mean kappa, F1-score and intersection over union (IoU) of urban water extraction with the OTOP in Changchun, Wuhan, Kunming and Guangzhou reached 0.924, 0.930 and 0.869, respectively. The results of the extended validation in the other major cities of China also show that the OTOP is robust and can be used to extract different types of urban water, which benefits from the structural design and training of the MSCNN. Therefore, the OTOP is especially suitable for the study of large-scale and long-term urban water change detection in the background of urbanization.
Authors: Minjung Shin, Seongho Choi, Yu-Jung Heo, Minsu Lee, Byoung-Tak Zhang, Jeh-Kwang Ryu
Abstract: We introduce CogME, a cognition-inspired, multi-dimensional evaluation metric designed for AI models focusing on story understanding. CogME is a framework grounded in human thinking strategies and story elements that involve story understanding. With a specific breakdown of the questions, this approach provides a nuanced assessment revealing not only AI models' particular strengths and weaknesses but also the characteristics of the benchmark dataset. Our case study with the DramaQA dataset demonstrates a refined analysis of the model and the benchmark dataset. We argue the need for metrics based on understanding the nature of tasks and designed to align closely with human cognitive processes. This approach provides insights beyond traditional overall scores and paves the way for more sophisticated AI development targeting higher cognitive functions.
Authors: Mohammed A. M. Elhassan, Chenhui Yang, Chenxi Huang, Tewodros Legesse Munea, Xin Hong, Abuzar B. M. Adam, Amina Benabid
Abstract: Modern high-performance semantic segmentation methods employ a heavy backbone and dilated convolution to extract the relevant feature. Although extracting features with both contextual and semantic information is critical for the segmentation tasks, it brings a memory footprint and high computation cost for real-time applications. This paper presents a new model to achieve a trade-off between accuracy/speed for real-time road scene semantic segmentation. Specifically, we proposed a lightweight model named Scale-aware Strip Attention Guided Feature Pyramid Network (S$^2$-FPN). Our network consists of three main modules: Attention Pyramid Fusion (APF) module, Scale-aware Strip Attention Module (SSAM), and Global Feature Upsample (GFU) module. APF adopts an attention mechanisms to learn discriminative multi-scale features and help close the semantic gap between different levels. APF uses the scale-aware attention to encode global context with vertical stripping operation and models the long-range dependencies, which helps relate pixels with similar semantic label. In addition, APF employs channel-wise reweighting block (CRB) to emphasize the channel features. Finally, the decoder of S$^2$-FPN then adopts GFU, which is used to fuse features from APF and the encoder. Extensive experiments have been conducted on two challenging semantic segmentation benchmarks, which demonstrate that our approach achieves better accuracy/speed trade-off with different model settings. The proposed models have achieved a results of 76.2\%mIoU/87.3FPS, 77.4\%mIoU/67FPS, and 77.8\%mIoU/30.5FPS on Cityscapes dataset, and 69.6\%mIoU,71.0\% mIoU, and 74.2\% mIoU on Camvid dataset. The code for this work will be made available at \url{https://github.com/mohamedac29/S2-FPN
Authors: Colin Decourt, Rufin VanRullen, Didier Salle, Thomas Oberlin
Abstract: Automotive radar sensors provide valuable information for advanced driving assistance systems (ADAS). Radars can reliably estimate the distance to an object and the relative velocity, regardless of weather and light conditions. However, radar sensors suffer from low resolution and huge intra-class variations in the shape of objects. Exploiting the time information (e.g., multiple frames) has been shown to help to capture better the dynamics of objects and, therefore, the variation in the shape of objects. Most temporal radar object detectors use 3D convolutions to learn spatial and temporal information. However, these methods are often non-causal and unsuitable for real-time applications. This work presents RECORD, a new recurrent CNN architecture for online radar object detection. We propose an end-to-end trainable architecture mixing convolutions and ConvLSTMs to learn spatio-temporal dependencies between successive frames. Our model is causal and requires only the past information encoded in the memory of the ConvLSTMs to detect objects. Our experiments show such a method's relevance for detecting objects in different radar representations (range-Doppler, range-angle) and outperform state-of-the-art models on the ROD2021 and CARRADA datasets while being less computationally expensive.
Authors: Ethan Brewer, Zhonghui Lv, Dan Runfola
Abstract: Due to insufficient or difficult to obtain data on development in inaccessible regions, remote sensing data is an important tool for interested stakeholders to collect information on economic growth. To date, no studies have utilized deep learning to estimate industrial growth at the level of individual sites. In this study, we harness high-resolution panchromatic imagery to estimate development over time at 419 industrial sites in the People's Republic of China using a multi-tier computer vision framework. We present two methods for approximating development: (1) structural area coverage estimated through a Mask R-CNN segmentation algorithm, and (2) imputing development directly with visible & infrared radiance from the Visible Infrared Imaging Radiometer Suite (VIIRS). Labels generated from these methods are comparatively evaluated and tested. On a dataset of 2,078 50 cm resolution images spanning 19 years, the results indicate that two dimensions of industrial development can be estimated using high-resolution daytime imagery, including (a) the total square meters of industrial development (average error of 0.021 $\textrm{km}^2$), and (b) the radiance of lights (average error of 9.8 $\mathrm{\frac{nW}{cm^{2}sr}}$). Trend analysis of the techniques reveal estimates from a Mask R-CNN-labeled CNN-LSTM track ground truth measurements most closely. The Mask R-CNN estimates positive growth at every site from the oldest image to the most recent, with an average change of 4,084 $\textrm{m}^2$.
Authors: Yuren Cong, Wentong Liao, Bodo Rosenhahn, Michael Ying Yang
Abstract: Learning similarity between scene graphs and images aims to estimate a similarity score given a scene graph and an image. There is currently no research dedicated to this task, although it is critical for scene graph generation and downstream applications. Scene graph generation is conventionally evaluated by Recall$@K$ and mean Recall$@K$, which measure the ratio of predicted triplets that appear in the human-labeled triplet set. However, such triplet-oriented metrics fail to demonstrate the overall semantic difference between a scene graph and an image and are sensitive to annotation bias and noise. Using generated scene graphs in the downstream applications is therefore limited. To address this issue, for the first time, we propose a Scene graPh-imAge coNtrastive learning framework, SPAN, that can measure the similarity between scene graphs and images. Our novel framework consists of a graph Transformer and an image Transformer to align scene graphs and their corresponding images in the shared latent space. We introduce a novel graph serialization technique that transforms a scene graph into a sequence with structural encodings. Based on our framework, we propose R-Precision measuring image retrieval accuracy as a new evaluation metric for scene graph generation. We establish new benchmarks on the Visual Genome and Open Images datasets. Extensive experiments are conducted to verify the effectiveness of SPAN, which shows great potential as a scene graph encoder.
Authors: Stephen Parsons, C. Seth Parker, Christy Chapman, Mami Hayashida, W. Brent Seales
Abstract: We present a complete software pipeline for revealing the hidden texts of the Herculaneum papyri using X-ray CT images. This enhanced virtual unwrapping pipeline combines machine learning with a novel geometric framework linking 3D and 2D images. We also present EduceLab-Scrolls, a comprehensive open dataset representing two decades of research effort on this problem. EduceLab-Scrolls contains a set of volumetric X-ray CT images of both small fragments and intact, rolled scrolls. The dataset also contains 2D image labels that are used in the supervised training of an ink detection model. Labeling is enabled by aligning spectral photography of scroll fragments with X-ray CT images of the same fragments, thus creating a machine-learnable mapping between image spaces and modalities. This alignment permits supervised learning for the detection of "invisible" carbon ink in X-ray CT, a task that is "impossible" even for human expert labelers. To our knowledge, this is the first aligned dataset of its kind and is the largest dataset ever released in the heritage domain. Our method is capable of revealing accurate lines of text on scroll fragments with known ground truth. Revealed text is verified using visual confirmation, quantitative image metrics, and scholarly review. EduceLab-Scrolls has also enabled the discovery, for the first time, of hidden texts from the Herculaneum papyri, which we present here. We anticipate that the EduceLab-Scrolls dataset will generate more textual discovery as research continues.
Authors: Shuangkang Fang, Yufeng Wang, Yi Yang, Weixin Xu, Heng Wang, Wenrui Ding, Shuchang Zhou
Abstract: Neural Radiance Fields (NeRF) have been widely adopted as practical and versatile representations for 3D scenes, facilitating various downstream tasks. However, different architectures, including the plain Multi-Layer Perceptron (MLP), Tensors, low-rank Tensors, Hashtables, and their combinations, entail distinct trade-offs. For instance, representations based on Hashtables enable faster rendering but lack clear geometric meaning, thereby posing challenges for spatial-relation-aware editing. To address this limitation and maximize the potential of each architecture, we propose Progressive Volume Distillation with Active Learning (PVD-AL), a systematic distillation method that enables any-to-any conversion between diverse architectures. PVD-AL decomposes each structure into two parts and progressively performs distillation from shallower to deeper volume representation, leveraging effective information retrieved from the rendering process. Additionally, a three-level active learning technique provides continuous feedback from teacher to student during the distillation process, achieving high-performance outcomes. Experimental evidence showcases the effectiveness of our method across multiple benchmark datasets. For instance, PVD-AL can distill an MLP-based model from a Hashtables-based model at a 10~20X faster speed and 0.8dB~2dB higher PSNR than training the MLP-based model from scratch. Moreover, PVD-AL permits the fusion of diverse features among distinct structures, enabling models with multiple editing properties and providing a more efficient model to meet real-time requirements like mobile devices. Project website: https://sk-fun.fun/PVD-AL.
Authors: Nico Catalano, Matteo Matteucci
Abstract: Semantic segmentation, vital for applications ranging from autonomous driving to robotics, faces significant challenges in domains where collecting large annotated datasets is difficult or prohibitively expensive. In such contexts, such as medicine and agriculture, the scarcity of training images hampers progress. Introducing Few-Shot Semantic Segmentation, a novel task in computer vision, which aims at designing models capable of segmenting new semantic classes with only a few examples. This paper consists of a comprehensive survey of Few-Shot Semantic Segmentation, tracing its evolution and exploring various model designs, from the more popular conditional and prototypical networks to the more niche latent space optimization methods, presenting also the new opportunities offered by recent foundational models. Through a chronological narrative, we dissect influential trends and methodologies, providing insights into their strengths and limitations. A temporal timeline offers a visual roadmap, marking key milestones in the field's progression. Complemented by quantitative analyses on benchmark datasets and qualitative showcases of seminal works, this survey equips readers with a deep understanding of the topic. By elucidating current challenges, state-of-the-art models, and prospects, we aid researchers and practitioners in navigating the intricacies of Few-Shot Semantic Segmentation and provide ground for future development.
Authors: Md Yousuf Harun, Christopher Kanan
Abstract: Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting in revenue loss or unhappy users. To mitigate model decay, DNNs are retrained from scratch using old and new data. This is computationally expensive, so retraining happens only once performance has significantly decreased. Here, we study how continual learning (CL) could potentially overcome model decay in large pre-trained DNNs and also greatly reduce computational costs for keeping DNNs up-to-date. We identify the ``stability gap'' as a major obstacle in our setting. The stability gap refers to a phenomenon where learning new data causes large drops in performance for past tasks before CL mitigation methods eventually compensate for this drop. We test two hypotheses for why the stability gap occurs and identify a method that vastly reduces this gap. In large-scale experiments for both easy and hard CL distributions (e.g., class incremental learning), we demonstrate that our method reduces the stability gap and greatly increases computational efficiency. Our work aligns CL with the goals of the production setting, where CL is needed for many applications.
Authors: Luchao Qi, Jiaye Wu, Annie N. Wang, Shengze Wang, Roni Sengupta
Abstract: In recent years, generative 3D face models (e.g., EG3D) have been developed to tackle the problem of synthesizing photo-realistic faces. However, these models are often unable to capture facial features unique to each individual, highlighting the importance of personalization. Some prior works have shown promise in personalizing generative face models, but these studies primarily focus on 2D settings. Also, these methods require both fine-tuning and storing a large number of parameters for each user, posing a hindrance to achieving scalable personalization. Another challenge of personalization is the limited number of training images available for each individual, which often leads to overfitting when using full fine-tuning methods. Our proposed approach, My3DGen, generates a personalized 3D prior of an individual using as few as 50 training images. My3DGen allows for novel view synthesis, semantic editing of a given face (e.g. adding a smile), and synthesizing novel appearances, all while preserving the original person's identity. We decouple the 3D facial features into global features and personalized features by freezing the pre-trained EG3D and training additional personalized weights through low-rank decomposition. As a result, My3DGen introduces only $\textbf{240K}$ personalized parameters per individual, leading to a $\textbf{127}\times$ reduction in trainable parameters compared to the $\textbf{30.6M}$ required for fine-tuning the entire parameter space. Despite this significant reduction in storage, our model preserves identity features without compromising the quality of downstream applications.
Authors: Jian Ma, Junhao Liang, Chen Chen, Haonan Lu
Abstract: Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}
Authors: Yao Liu, Hang Shao, Bing Bai
Abstract: This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance on the image classification task, it allows for the modification of the weights via a continuous group of symmetry. This is a significant shift from traditional models where the architecture and weights are essentially fixed. We wish to promote the (internal) symmetry as a new desirable property for a neural network, and to draw attention to the PDE perspective in analyzing and interpreting ConvNets in the broader Deep Learning community.
Authors: Chuanxin Song, Hanbo Wu, Xin Ma, Yibin Li
Abstract: Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting challenge emerges as object information extraction techniques require heavy computational costs, thereby burdening the network considerably. This limitation often renders object-assisted approaches incompatible with edge devices in practical deployment. In contrast, this paper proposes a semantic knowledge-based similarity prototype, which can help the scene recognition network achieve superior accuracy without increasing the computational cost in practice. It is simple and can be plug-and-played into existing pipelines. More specifically, a statistical strategy is introduced to depict semantic knowledge in scenes as class-level semantic representations. These representations are used to explore correlations between scene classes, ultimately constructing a similarity prototype. Furthermore, we propose to leverage the similarity prototype to support network training from the perspective of Gradient Label Softening and Batch-level Contrastive Loss, respectively. Comprehensive evaluations on multiple benchmarks show that our similarity prototype enhances the performance of existing networks, all while avoiding any additional computational burden in practical deployments. Code and the statistical similarity prototype will be available at https://github.com/ChuanxinSong/SimilarityPrototype
Authors: Lucas Brynte, Jos\'e Pedro Iglesias, Carl Olsson, Fredrik Kahl
Abstract: In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks. SfM is a classic computer vision problem that is solved though iterative minimization of reprojection errors, referred to as Bundle Adjustment (BA), starting from a good initialization. In order to obtain a good enough initialization to BA, conventional methods rely on a sequence of sub-problems (such as pairwise pose estimation, pose averaging or triangulation) which provide an initial solution that can then be refined using BA. In this work we replace these sub-problems by learning a model that takes as input the 2D keypoints detected across multiple views, and outputs the corresponding camera poses and 3D keypoint coordinates. Our model takes advantage of graph neural networks to learn SfM-specific primitives, and we show that it can be used for fast inference of the reconstruction for new and unseen sequences. The experimental results show that the proposed model outperforms competing learning-based methods, and challenges COLMAP while having lower runtime. Our code is available at https://github.com/lucasbrynte/gasfm/.
Authors: Yuxiang Yang, Yingqi Deng, Jing Zhang, Jiahao Nie, Zheng-Jun Zha
Abstract: 3D Single Object Tracking (SOT) is a fundamental task of computer vision, proving essential for applications like autonomous driving. It remains challenging to localize the target from surroundings due to appearance variations, distractors, and the high sparsity of point clouds. To address these issues, prior Siamese and motion-centric trackers both require elaborate designs and solving multiple subtasks. In this paper, we propose BEVTrack, a simple yet effective baseline method. By estimating the target motion in Bird's-Eye View (BEV) to perform tracking, BEVTrack demonstrates surprising simplicity from various aspects, i.e., network designs, training objectives, and tracking pipeline, while achieving superior performance. Besides, to achieve accurate regression for targets with diverse attributes (e.g., sizes and motion patterns), BEVTrack constructs the likelihood function with the learned underlying distributions adapted to different targets, rather than making a fixed Laplacian or Gaussian assumption as in previous works. This provides valuable priors for tracking and thus further boosts performance. While only using a single regression loss with a plain convolutional architecture, BEVTrack achieves state-of-the-art performance on three large-scale datasets, KITTI, NuScenes, and Waymo Open Dataset while maintaining a high inference speed of about 200 FPS. The code will be released at https://github.com/xmm-prio/BEVTrack.
Authors: Kaouther Mouheb, Mobina Ghojogh Nejad, Lavsen Dahal, Ehsan Samei, Kyle J. Lafata, W. Paul Segars, Joseph Y. Lo
Abstract: Accurate 3D modeling of human organs plays a crucial role in building computational phantoms for virtual imaging trials. However, generating anatomically plausible reconstructions of organ surfaces from computed tomography scans remains challenging for many structures in the human body. This challenge is particularly evident when dealing with the large intestine. In this study, we leverage recent advancements in geometric deep learning and denoising diffusion probabilistic models to refine the segmentation results of the large intestine. We begin by representing the organ as point clouds sampled from the surface of the 3D segmentation mask. Subsequently, we employ a hierarchical variational autoencoder to obtain global and local latent representations of the organ's shape. We train two conditional denoising diffusion models in the hierarchical latent space to perform shape refinement. To further enhance our method, we incorporate a state-of-the-art surface reconstruction model, allowing us to generate smooth meshes from the obtained complete point clouds. Experimental results demonstrate the effectiveness of our approach in capturing both the global distribution of the organ's shape and its fine details. Our complete refinement pipeline demonstrates remarkable enhancements in surface representation compared to the initial segmentation, reducing the Chamfer distance by 70%, the Hausdorff distance by 32%, and the Earth Mover's distance by 6%. By combining geometric deep learning, denoising diffusion models, and advanced surface reconstruction techniques, our proposed method offers a promising solution for accurately modeling the large intestine's surface and can easily be extended to other anatomical structures.
Authors: Jiaming Chu, Lei Jin, Junliang Xing, Jian Zhao
Abstract: Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through separate branches and distinct output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level segmentation results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By virtual of unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We will release our source code, pretrained models, and online demos to facilitate future studies.
Authors: Longyun Liao, Rong Zheng, Andrew Mitchell
Abstract: In this paper, we present the novel task of estimating the extrinsic parameters of a virtual camera relative to a real camera in exercise videos with a mirror. This task poses a significant challenge in scenarios where the views from the real and mirrored cameras have no overlap or share salient features. To address this issue, prior knowledge of a human body and 2D joint locations are utilized to estimate the camera extrinsic parameters when a person is in front of a mirror. We devise a modified eight-point algorithm to obtain an initial estimation from 2D joint locations. The 2D joint locations are then refined subject to human body constraints. Finally, a RANSAC algorithm is employed to remove outliers by comparing their epipolar distances to a predetermined threshold. MirrorCalib achieves a rotation error of 1.82{\deg} and a translation error of 69.51 mm on a collected real-world dataset, which outperforms the state-of-art method.
Authors: Xin Zheng, Ziang Peng, Yuan Cao, Hongming Shan, Junping Zhang
Abstract: Video prediction, predicting future frames from the previous ones, has broad applications such as autonomous driving and weather forecasting. Existing state-of-the-art methods typically focus on extracting either spatial, temporal, or spatiotemporal features from videos. Different feature focuses, resulting from different network architectures, may make the resultant models excel at some video prediction tasks but perform poorly on others. Towards a more generic video prediction solution, we explicitly model these features in a unified encoder-decoder framework and propose a novel simple alternating Mixer (SIAM). The novelty of SIAM lies in the design of dimension alternating mixing (DaMi) blocks, which can model spatial, temporal, and spatiotemporal features through alternating the dimensions of the feature maps. Extensive experimental results demonstrate the superior performance of the proposed SIAM on four benchmark video datasets covering both synthetic and real-world scenarios.
Authors: Junyu Gao, Xuan Yao, Changsheng Xu
Abstract: The ability to accurately comprehend natural language instructions and navigate to the target location is essential for an embodied agent. Such agents are typically required to execute user instructions in an online manner, leading us to explore the use of unlabeled test samples for effective online model adaptation. However, for online Vision-and-Language Navigation (VLN), due to the intrinsic nature of inter-sample online instruction execution and intra-sample multi-step action decision, frequent updates can result in drastic changes in model parameters, while occasional updates can make the model ill-equipped to handle dynamically changing environments. Therefore, we propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for online VLN by performing joint decomposition-accumulation analysis for both gradients and parameters in a unified framework. Extensive experiments show that our method obtains impressive performance gains on four popular benchmarks. Code is available at https://github.com/Feliciaxyao/ICML2024-FSTTA.
Authors: Zhenning Shi, Haoshuai Zheng, Chen Xu, Changsheng Dong, Bin Pan, Xueshuo Xie, Along He, Tao Li, Huazhu Fu
Abstract: Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https://github.com/nkicsl/Resfusion.
Authors: Mengxi Zhang, Yiming Liu, Kang Rong
Abstract: Referring image segmentation (RIS) aims to segment a particular region based on a language expression prompt. Existing methods incorporate linguistic features into visual features and obtain multi-modal features for mask decoding. However, these methods may segment the visually salient entity instead of the correct referring region, as the multi-modal features are dominated by the abundant visual context. In this paper, we propose MARIS, a referring image segmentation method that leverages the Segment Anything Model (SAM) and introduces a mutual-aware attention mechanism to enhance the cross-modal fusion via two parallel branches. Specifically, our mutual-aware attention mechanism consists of Vision-Guided Attention and Language-Guided Attention, which bidirectionally model the relationship between visual and linguistic features. Correspondingly, we design a Mask Decoder to enable explicit linguistic guidance for more consistent segmentation with the language expression. To this end, a multi-modal query token is proposed to integrate linguistic information and interact with visual information simultaneously. Extensive experiments on three benchmark datasets show that our method outperforms the state-of-the-art RIS methods. Our code will be publicly available.
Authors: Linqi Zhou, Andy Shih, Chenlin Meng, Stefano Ermon
Abstract: Recent methods such as Score Distillation Sampling (SDS) and Variational Score Distillation (VSD) using 2D diffusion models for text-to-3D generation have demonstrated impressive generation quality. However, the long generation time of such algorithms significantly degrades the user experience. To tackle this problem, we propose DreamPropeller, a drop-in acceleration algorithm that can be wrapped around any existing text-to-3D generation pipeline based on score distillation. Our framework generalizes Picard iterations, a classical algorithm for parallel sampling an ODE path, and can account for non-ODE paths such as momentum-based gradient updates and changes in dimensions during the optimization process as in many cases of 3D generation. We show that our algorithm trades parallel compute for wallclock time and empirically achieves up to 4.7x speedup with a negligible drop in generation quality for all tested frameworks.
Authors: Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou
Abstract: Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but there is limited research focusing on their ability to generate data by converting unlabeled images into visual instruction tuning data. To this end, this paper is the first to explore the potential of empowering MLLM to generate data rather than prompting GPT-4. We introduce Genixer, a holistic data generation pipeline consisting of four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLMs, and (iv) data generation and filtering. Additionally, we outline two modes of data generation: task-agnostic and task-specific, enabling controllable output. We demonstrate that a synthetic VQA-like dataset trained with LLaVA1.5 enhances performance on 10 out of 12 multimodal benchmarks. Additionally, the grounding MLLM Shikra, when trained with a REC-like synthetic dataset, shows improvements on 7 out of 8 REC datasets. Through experiments and synthetic data analysis, our findings are: (1) current MLLMs can serve as robust data generators without assistance from GPT-4V; (2) MLLMs trained with task-specific datasets can surpass GPT-4V in generating complex instruction tuning data; (3) synthetic datasets enhance performance across various multimodal benchmarks and help mitigate model hallucinations. The data, code, and models can be found at https://github.com/zhaohengyuan1/Genixer.
Authors: Kabita Parajuli, Shashidhar Ram Joshi
Abstract: Video captioning in Nepali, a language written in the Devanagari script, presents a unique challenge due to the lack of existing academic work in this domain. This work develops a novel encoder-decoder paradigm for Nepali video captioning to tackle this difficulty. LSTM and GRU sequence-to-sequence models are used in the model to produce related textual descriptions based on features retrieved from video frames using CNNs. Using Google Translate and manual post-editing, a Nepali video captioning dataset is generated from the Microsoft Research Video Description Corpus (MSVD) dataset created using Google Translate, and manual post-editing work. The efficiency of the model for Devanagari-scripted video captioning is demonstrated by BLEU, METOR, and ROUGE measures, which are used to assess its performance.
Authors: Shiyun Chen, Li Lin, Pujin Cheng, Xiaoying Tang
Abstract: Liver tumor segmentation is essential for computer-aided diagnosis, surgical planning, and prognosis evaluation. However, obtaining and maintaining a large-scale dataset with dense annotations is challenging. Semi-Supervised Learning (SSL) is a common technique to address these challenges. Recently, Segment Anything Model (SAM) has shown promising performance in some medical image segmentation tasks, but it performs poorly for liver tumor segmentation. In this paper, we propose a novel semi-supervised framework, named ASLseg, which can effectively adapt the SAM to the SSL setting and combine both domain-specific and general knowledge of liver tumors. Specifically, the segmentation model trained with a specific SSL paradigm provides the generated pseudo-labels as prompts to the fine-tuned SAM. An adaptation network is then used to refine the SAM-predictions and generate higher-quality pseudo-labels. Finally, the reliable pseudo-labels are selected to expand the labeled set for iterative training. Extensive experiments on the LiTS dataset demonstrate overwhelming performance of our ASLseg.
Authors: Conghan Yue, Zhengwei Peng, Junlong Ma, Shiyan Du, Pengxu Wei, Dongyu Zhang
Abstract: Diffusion models exhibit powerful generative capabilities enabling noise mapping to data via reverse stochastic differential equations. However, in image restoration, the focus is on the mapping relationship from low-quality to high-quality images. Regarding this issue, we introduce the Generalized Ornstein-Uhlenbeck Bridge (GOUB) model. By leveraging the natural mean-reverting property of the generalized OU process and further eliminating the variance of its steady-state distribution through the Doob's h-transform, we achieve diffusion mappings from point to point enabling the recovery of high-quality images from low-quality ones. Moreover, we unravel the fundamental mathematical essence shared by various bridge models, all of which are special instances of GOUB and empirically demonstrate the optimality of our proposed models. Additionally, we present the corresponding Mean-ODE model adept at capturing both pixel-level details and structural perceptions. Experimental outcomes showcase the state-of-the-art performance achieved by both models across diverse tasks, including inpainting, deraining, and super-resolution. Code is available at \url{https://github.com/Hammour-steak/GOUB}.
Authors: Saarthak Kapse, Pushpak Pati, Srijan Das, Jingwei Zhang, Chao Chen, Maria Vakalopoulou, Joel Saltz, Dimitris Samaras, Rajarsi R. Gupta, Prateek Prasanna
Abstract: Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides. Traditionally, MIL interpretability is limited to identifying salient regions deemed pertinent for downstream tasks, offering little insight to the end-user (pathologist) regarding the rationale behind these selections. To address this, we propose Self-Interpretable MIL (SI-MIL), a method intrinsically designed for interpretability from the very outset. SI-MIL employs a deep MIL framework to guide an interpretable branch grounded on handcrafted pathological features, facilitating linear predictions. Beyond identifying salient regions, SI-MIL uniquely provides feature-level interpretations rooted in pathological insights for WSIs. Notably, SI-MIL, with its linear prediction constraints, challenges the prevalent myth of an inevitable trade-off between model interpretability and performance, demonstrating competitive results compared to state-of-the-art methods on WSI-level prediction tasks across three cancer types. In addition, we thoroughly benchmark the local and global-interpretability of SI-MIL in terms of statistical analysis, a domain expert study, and desiderata of interpretability, namely, user-friendliness and faithfulness.
Authors: Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, Nicu Sebe
Abstract: We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introduce auxiliary gradient supervision to enhance focus on regions with finer details. Furthermore, we outline practical training strategies tailored for DIS to improve map quality and training process. To validate the general applicability of our approach, we conduct extensive experiments on four tasks to evince that BiRefNet exhibits remarkable performance, outperforming task-specific cutting-edge methods across all benchmarks. Our codes are available at https://github.com/ZhengPeng7/BiRefNet.
Authors: Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, Zhaoxiang Zhang
Abstract: 3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussian, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks.
Authors: Yang Qian, Yinan Sun, Ali Kargarandehkordi, Onur Cezmi Mutlu, Saimourya Surabhi, Pingyi Chen, Zain Jabbar, Dennis Paul Wall, Peter Washington
Abstract: The increasing variety and quantity of tagged multimedia content on platforms such as TikTok provides an opportunity to advance computer vision modeling. We have curated a distinctive dataset of 283,582 unique video clips categorized under 386 hashtags relating to modern human actions. We release this dataset as a valuable resource for building domain-specific foundation models for human movement modeling tasks such as action recognition. To validate this dataset, which we name TikTokActions, we perform two sets of experiments. First, we pretrain the state-of-the-art VideoMAEv2 with a ViT-base backbone on TikTokActions subset, and then fine-tune and evaluate on popular datasets such as UCF101 and the HMDB51. We find that the performance of the model pre-trained using our Tik-Tok dataset is comparable to models trained on larger action recognition datasets (95.3% on UCF101 and 53.24% on HMDB51). Furthermore, our investigation into the relationship between pre-training dataset size and fine-tuning performance reveals that beyond a certain threshold, the incremental benefit of larger training sets diminishes. This work introduces a useful TikTok video dataset that is available for public use and provides insights into the marginal benefit of increasing pre-training dataset sizes for video-based foundation models.
Authors: Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang
Abstract: Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images. Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications. Hence, we propose the first universal prompt optimizer for safe T2I (POSI) generation in black-box scenario. We first construct a dataset consisting of toxic-clean prompt pairs by GPT-3.5 Turbo. To guide the optimizer to have the ability of converting toxic prompt to clean prompt while preserving semantic information, we design a novel reward function measuring toxicity and text alignment of generated images and train the optimizer through Proximal Policy Optimization. Experiments show that our approach can effectively reduce the likelihood of various T2I models in generating inappropriate images, with no significant impact on text alignment. It is also flexible to be combined with methods to achieve better performance. Our code is available at https://github.com/wzongyu/POSI.
Authors: Jiyong Oh, Junhaeng Lee, Woongchan Byun, Minsang Kong, Sang Hun Lee
Abstract: Recent studies have focused on enhancing the performance of 3D object detection models. Among various approaches, ground-truth sampling has been proposed as an augmentation technique to address the challenges posed by limited ground-truth data. However, an inherent issue with ground-truth sampling is its tendency to increase false positives. Therefore, this study aims to overcome the limitations of ground-truth sampling and improve the performance of 3D object detection models by developing a new augmentation technique called false-positive sampling. False-positive sampling involves retraining the model using point clouds that are identified as false positives in the model's predictions. We propose an algorithm that utilizes both ground-truth and false-positive sampling and an algorithm for building the false-positive sample database. Additionally, we analyze the principles behind the performance enhancement due to false-positive sampling. Our experiments demonstrate that models utilizing false-positive sampling show a reduction in false positives and exhibit improved object detection performance. On the KITTI and Waymo Open datasets, models with false-positive sampling surpass the baseline models by a large margin.
Authors: Ruizhuo Song, Beiming Yuan
Abstract: Abstract reasoning problems pose challenges to the perception and cognition abilities of AI algorithms, demanding deeper pattern recognition and inductive reasoning beyond mere identification of explicit image features. In this study, we introduce PMoC, a probabilistic model tailored for the Bongard-Logo problem, achieving high reasoning accuracy through the construction of an independent probabilistic model. Additionally, we have designed the Pose-Transformer, an enhanced Transformer-Encoder specifically crafted for complex abstract reasoning tasks, including Bongard-Logo, RAVEN, I-RAVEN, and PGM. Inspired by the pose matrix in capsule networks, Pose-Transformer strengthens the focus on positional relationships between local features when processing image data. When combined with PMoC, it can further enhance reasoning accuracy. Our Pose-Transformer effectively addresses reasoning difficulties associated with changes in the position of abstract entities, outperforming previous models on RAVEN's OIG, D3x3 subsets, and the PGM dataset. Finally, considering the deployment difficulties arising from the large number of Pose-Transformer parameters, this paper presents a lightweight version, Straw Pose-Transformer, which maintains performance while significantly reducing the parameter count. This study contributes to enhancing AI capabilities in abstract reasoning and cognitive pattern recognition.
Authors: Jongwook Choi, Taehoon Kim, Yonghyun Jeong, Seungryul Baek, Jongwon Choi
Abstract: This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos. We discovered that the generated facial videos suffer from the temporal distinctiveness in the temporal changes of style latent vectors, which are inevitable during the generation of temporally stable videos with various facial expressions and geometric transformations. Our framework utilizes the StyleGRU module, trained by contrastive learning, to represent the dynamic properties of style latent vectors. Additionally, we introduce a style attention module that integrates StyleGRU-generated features with content-based features, enabling the detection of visual and temporal artifacts. We demonstrate our approach across various benchmark scenarios in deepfake detection, showing its superiority in cross-dataset and cross-manipulation scenarios. Through further analysis, we also validate the importance of using temporal changes of style latent vectors to improve the generality of deepfake video detection.
Authors: Yuxin Tian, Mouxing Yang, Yunfan Li, Dayiheng Liu, Xingzhang Ren, Xi Peng, Jiancheng Lv
Abstract: Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important factors for various PEFTs, namely, the accessible data size and fine-tunable parameter size. A natural expectation for PEFTs is that the performance of various PEFTs is positively related to the data size and fine-tunable parameter size. However, according to the evaluation of five PEFTs on two downstream vision-language (VL) tasks, we find that such an intuition holds only if the downstream data and task are not consistent with pre-training. For downstream fine-tuning consistent with pre-training, data size no longer affects the performance, while the influence of fine-tunable parameter size is not monotonous. We believe such an observation could guide the choice of training strategy for various PEFTs.
Authors: Tengchuan Kou, Xiaohong Liu, Zicheng Zhang, Chunyi Li, Haoning Wu, Xiongkuo Min, Guangtao Zhai, Ning Liu
Abstract: With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V models have been released for generating high perceptual quality videos, there is still lack of a method to evaluate the quality of these videos quantitatively. To solve this issue, we establish the largest-scale Text-to-Video Quality Assessment DataBase (T2VQA-DB) to date. The dataset is composed of 10,000 videos generated by 9 different T2V models. We also conduct a subjective study to obtain each video's corresponding mean opinion score. Based on T2VQA-DB, we propose a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA). The model extracts features from text-video alignment and video fidelity perspectives, then it leverages the ability of a large language model to give the prediction score. Experimental results show that T2VQA outperforms existing T2V metrics and SOTA video quality assessment models. Quantitative analysis indicates that T2VQA is capable of giving subjective-align predictions, validating its effectiveness. The dataset and code will be released at https://github.com/QMME/T2VQA.
Authors: Guangchi Fang, Bing Wang
Abstract: In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians. Our analysis shifts from traditional graphics and 2D computer vision to the perspective of point clouds, highlighting the inefficient spatial distribution of Gaussian representation as a key limitation in model performance. To address this, we introduce strategies for densification including blur split and depth reinitialization, and simplification through intersection preserving and sampling. These techniques reorganize the spatial positions of the Gaussians, resulting in significant improvements across various datasets and benchmarks in terms of rendering quality, resource consumption, and storage compression. Our Mini-Splatting integrates seamlessly with the original rasterization pipeline, providing a strong baseline for future research in Gaussian-Splatting-based works. \href{https://github.com/fatPeter/mini-splatting}{Code is available}.
Authors: Zining Cheng, Guanzhou Ji
Abstract: This paper presents the use of panoramic 3D estimation in lighting simulation. Conventional lighting simulation necessitates detailed modeling as input, resulting in significant labor effort and time cost. The 3D layout estimation method directly takes a single panorama as input and generates a lighting simulation model with room geometry and window aperture. We evaluate the simulation results by comparing the luminance errors between on-site High Dynamic Range (HDR) photographs, 3D estimation model, and detailed model in panoramic representation and fisheye perspective. Given the selected scene, the results demonstrate the estimated room layout is reliable for lighting simulation.
Authors: Duosheng Chen, Shihao Zhou, Jinshan Pan, Jinglei Shi, Lishen Qu, Jufeng Yang
Abstract: Exploring motion information is important for the motion deblurring task. Recent the window-based transformer approaches have achieved decent performance in image deblurring. Note that the motion causing blurry results is usually composed of translation and rotation movements and the window-shift operation in the Cartesian coordinate system by the window-based transformer approaches only directly explores translation motion in orthogonal directions. Thus, these methods have the limitation of modeling the rotation part. To alleviate this problem, we introduce the polar coordinate-based transformer, which has the angles and distance to explore rotation motion and translation information together. In this paper, we propose a Radial Strip Transformer (RST), which is a transformer-based architecture that restores the blur images in a polar coordinate system instead of a Cartesian one. RST contains a dynamic radial embedding module (DRE) to extract the shallow feature by a radial deformable convolution. We design a polar mask layer to generate the offsets for the deformable convolution, which can reshape the convolution kernel along the radius to better capture the rotation motion information. Furthermore, we proposed a radial strip attention solver (RSAS) as deep feature extraction, where the relationship of windows is organized by azimuth and radius. This attention module contains radial strip windows to reweight image features in the polar coordinate, which preserves more useful information in rotation and translation motion together for better recovering the sharp images. Experimental results on six synthesis and real-world datasets prove that our method performs favorably against other SOTA methods for the image deblurring task.
Authors: Sanghyun Jo, Fei Pan, In-Jae Yu, Kyungsu Kim
Abstract: Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything. However, WSS faces challenges related to minor classes since those are overlooked in images with adjacent multiple classes, a limitation originating from the overfitting of traditional expansion methods like Random Walk. We first address this by employing unsupervised and weakly-supervised feature maps instead of conventional methodologies, allowing for hierarchical mask enhancement. This method distinctly categorizes higher-level classes and subsequently separates their associated lower-level classes, ensuring all classes are correctly restored in the mask without losing minor ones. Our approach, validated through extensive experimentation, significantly improves WSS across five benchmarks (VOC: 79.8\%, COCO: 53.9\%, Context: 49.0\%, ADE: 32.9\%, Stuff: 37.4\%), reducing the gap with fully supervised methods by over 84\% on the VOC validation set. Code is available at https://github.com/shjo-april/DHR.
Authors: Tao Hu, Fangzhou Hong, Zhaoxi Chen, Ziwei Liu
Abstract: We present FashionEngine, an interactive 3D human generation and editing system that creates 3D digital humans via user-friendly multimodal controls such as natural languages, visual perceptions, and hand-drawing sketches. FashionEngine automates the 3D human production with three key components: 1) A pre-trained 3D human diffusion model that learns to model 3D humans in a semantic UV latent space from 2D image training data, which provides strong priors for diverse generation and editing tasks. 2) Multimodality-UV Space encoding the texture appearance, shape topology, and textual semantics of human clothing in a canonical UV-aligned space, which faithfully aligns the user multimodal inputs with the implicit UV latent space for controllable 3D human editing. The multimodality-UV space is shared across different user inputs, such as texts, images, and sketches, which enables various joint multimodal editing tasks. 3) Multimodality-UV Aligned Sampler learns to sample high-quality and diverse 3D humans from the diffusion prior. Extensive experiments validate FashionEngine's state-of-the-art performance for conditional generation/editing tasks. In addition, we present an interactive user interface for our FashionEngine that enables both conditional and unconditional generation tasks, and editing tasks including pose/view/shape control, text-, image-, and sketch-driven 3D human editing and 3D virtual try-on, in a unified framework. Our project page is at: https://taohuumd.github.io/projects/FashionEngine.
Authors: Zhongyu Xia, ZhiWei Lin, Xinhao Wang, Yongtao Wang, Yun Xing, Shengxiang Qi, Nan Dong, Ming-Hsuan Yang
Abstract: Three-dimensional perception from multi-view cameras is a crucial component in autonomous driving systems, which involves multiple tasks like 3D object detection and bird's-eye-view (BEV) semantic segmentation. To improve perception precision, large image encoders, high-resolution images, and long-term temporal inputs have been adopted in recent 3D perception models, bringing remarkable performance gains. However, these techniques are often incompatible in training and inference scenarios due to computational resource constraints. Besides, modern autonomous driving systems prefer to adopt an end-to-end framework for multi-task 3D perception, which can simplify the overall system architecture and reduce the implementation complexity. However, conflict between tasks often arises when optimizing multiple tasks jointly within an end-to-end 3D perception model. To alleviate these issues, we present an end-to-end framework named HENet for multi-task 3D perception in this paper. Specifically, we propose a hybrid image encoding network, using a large image encoder for short-term frames and a small image encoder for long-term temporal frames. Then, we introduce a temporal feature integration module based on the attention mechanism to fuse the features of different frames extracted by the two aforementioned hybrid image encoders. Finally, according to the characteristics of each perception task, we utilize BEV features of different grid sizes, independent BEV encoders, and task decoders for different tasks. Experimental results show that HENet achieves state-of-the-art end-to-end multi-task 3D perception results on the nuScenes benchmark, including 3D object detection and BEV semantic segmentation. The source code and models will be released at https://github.com/VDIGPKU/HENet.
Authors: Yujie Li, Yanbin Wang, Haitao Xu, Bin Liu, Jianguo Sun, Zhenhao Guo, Wenrui Ma
Abstract: Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial noise. However, diffusion-based adversarial training often encounters convergence challenges and high computational expenses. Additionally, diffusion-based purification inevitably causes data shift and is deemed susceptible to stronger adaptive attacks. To tackle these issues, we propose the Truth Maximization Diffusion Classifier (TMDC), a generative Bayesian classifier that builds upon pre-trained diffusion models and the Bayesian theorem. Unlike data-driven classifiers, TMDC, guided by Bayesian principles, utilizes the conditional likelihood from diffusion models to determine the class probabilities of input images, thereby insulating against the influences of data shift and the limitations of adversarial training. Moreover, to enhance TMDC's resilience against more potent adversarial attacks, we propose an optimization strategy for diffusion classifiers. This strategy involves post-training the diffusion model on perturbed datasets with ground-truth labels as conditions, guiding the diffusion model to learn the data distribution and maximizing the likelihood under the ground-truth labels. The proposed method achieves state-of-the-art performance on the CIFAR10 dataset against heavy white-box attacks and strong adaptive attacks. Specifically, TMDC achieves robust accuracies of 82.81% against $l_{\infty}$ norm-bounded perturbations and 86.05% against $l_{2}$ norm-bounded perturbations, respectively, with $\epsilon=0.05$.
Authors: Patrik Vacek, David Hurych, Tom\'a\v{s} Svoboda, Karel Zimmermann
Abstract: We study the problem of self-supervised 3D scene flow estimation from real large-scale raw point cloud sequences, which is crucial to various tasks like trajectory prediction or instance segmentation. In the absence of ground truth scene flow labels, contemporary approaches concentrate on deducing optimizing flow across sequential pairs of point clouds by incorporating structure based regularization on flow and object rigidity. The rigid objects are estimated by a variety of 3D spatial clustering methods. While state-of-the-art methods successfully capture overall scene motion using the Neural Prior structure, they encounter challenges in discerning multi-object motions. We identified the structural constraints and the use of large and strict rigid clusters as the main pitfall of the current approaches and we propose a novel clustering approach that allows for combination of overlapping soft clusters as well as non-overlapping rigid clusters representation. Flow is then jointly estimated with progressively growing non-overlapping rigid clusters together with fixed size overlapping soft clusters. We evaluate our method on multiple datasets with LiDAR point clouds, demonstrating the superior performance over the self-supervised baselines reaching new state of the art results. Our method especially excels in resolving flow in complicated dynamic scenes with multiple independently moving objects close to each other which includes pedestrians, cyclists and other vulnerable road users. Our codes are publicly available on https://github.com/ctu-vras/let-it-flow.
Authors: Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao, Yao Zhao
Abstract: Recently, diffusion-based depth estimation methods have drawn widespread attention due to their elegant denoising patterns and promising performance. However, they are typically unreliable under adverse conditions prevalent in real-world scenarios, such as rainy, snowy, etc. In this paper, we propose a novel robust depth estimation method called D4RD, featuring a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. Concretely, we integrate the strength of knowledge distillation into contrastive learning, building the `trinity' contrastive scheme. This scheme utilizes the sampled noise of the forward diffusion process as a natural reference, guiding the predicted noise in diverse scenes toward a more stable and precise optimum. Moreover, we extend noise-level trinity to encompass more generic feature and image levels, establishing a multi-level contrast to distribute the burden of robust perception across the overall network. Before addressing complex scenarios, we enhance the stability of the baseline diffusion model with three straightforward yet effective improvements, which facilitate convergence and remove depth outliers. Extensive experiments demonstrate that D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions. The code for D4RD will be made available for further exploration and adoption.
Authors: Jie Ma, Min Hu, Pinghui Wang, Wangchun Sun, Lingyun Song, Hongbin Pei, Jun Liu, Youtian Du
Abstract: Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, \textit{MUSIC-AVQA-R}, crafted in two steps: rephrasing questions within the test split of a public dataset (\textit{MUSIC-AVQA}) and subsequently introducing distribution shifts to split questions. The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions. Secondly, we propose a robust architecture that utilizes a multifaceted cycle collaborative debiasing strategy to overcome bias learning. Experimental results show that this architecture achieves state-of-the-art performance on both datasets, especially obtaining a significant improvement of 9.32\% on the proposed dataset. Extensive ablation experiments are conducted on these two datasets to validate the effectiveness of the debiasing strategy. Additionally, we highlight the limited robustness of existing multi-modal QA methods through the evaluation on our dataset.
Authors: Chenhui Wang, Tao Chen, Zhihao Chen, Zhizhong Huang, Taoran Jiang, Qi Wang, Hongming Shan
Abstract: Despite their impressive generative performance, latent diffusion model-based virtual try-on (VTON) methods lack faithfulness to crucial details of the clothes, such as style, pattern, and text. To alleviate these issues caused by the diffusion stochastic nature and latent supervision, we propose a novel Faithful Latent Diffusion Model for VTON, termed FLDM-VTON. FLDM-VTON improves the conventional latent diffusion process in three major aspects. First, we propose incorporating warped clothes as both the starting point and local condition, supplying the model with faithful clothes priors. Second, we introduce a novel clothes flattening network to constrain generated try-on images, providing clothes-consistent faithful supervision. Third, we devise a clothes-posterior sampling for faithful inference, further enhancing the model performance over conventional clothes-agnostic Gaussian sampling. Extensive experimental results on the benchmark VITON-HD and Dress Code datasets demonstrate that our FLDM-VTON outperforms state-of-the-art baselines and is able to generate photo-realistic try-on images with faithful clothing details.
Authors: Wensheng Pan, Timin Gao, Yan Zhang, Runze Hu, Xiawu Zheng, Enwei Zhang, Yuting Gao, Yutao Liu, Yunhang Shen, Ke Li, Shengchuan Zhang, Liujuan Cao, Rongrong Ji
Abstract: Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Currently, leveraging semantic information to enhance IQA is a crucial research direction. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. However, the generalist nature of these pre-trained Vision-Language (VL) models often renders them suboptimal for IQA-specific tasks. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. Existing prompt-based VL models overly focus on incremental semantic information from text, neglecting the rich insights available from visual data analysis. This imbalance limits their performance improvements in IQA tasks. This paper introduces an innovative multi-modal prompt-based methodology for IQA. Our approach employs carefully crafted prompts that synergistically mine incremental semantic information from both visual and linguistic data. Specifically, in the visual branch, we introduce a multi-layer prompt structure to enhance the VL model's adaptability. In the text branch, we deploy a dual-prompt scheme that steers the model to recognize and differentiate between scene category and distortion type, thereby refining the model's capacity to assess image quality. Our experimental findings underscore the effectiveness of our method over existing Blind Image Quality Assessment (BIQA) approaches. Notably, it demonstrates competitive performance across various datasets. Our method achieves Spearman Rank Correlation Coefficient (SRCC) values of 0.961(surpassing 0.946 in CSIQ) and 0.941 (exceeding 0.930 in KADID), illustrating its robustness and accuracy in diverse contexts.
Authors: Zhiwei Wang, Xiaoyu Zeng, Chongwei Wu, Jinxin lv, Xu Zhang, Wei Fang, Qiang Li
Abstract: One-shot segmentation of brain tissue requires training registration-segmentation (reg-seg) dual-model iteratively, where reg-model aims to provide pseudo masks of unlabeled images for seg-model by warping a carefully-labeled atlas. However, the imperfect reg-model induces image-mask misalignment, poisoning the seg-model subsequently. Recent StyleSeg bypasses this bottleneck by replacing the unlabeled images with their warped copies of atlas, but needs to borrow the diverse image patterns via style transformation. Here, we present StyleSeg V2, inherited from StyleSeg but granted the ability of perceiving the registration errors. The motivation is that good registration behaves in a mirrored fashion for mirrored images. Therefore, almost at no cost, StyleSeg V2 can have reg-model itself "speak out" incorrectly-aligned regions by simply mirroring (symmetrically flipping the brain) its input, and the registration errors are symmetric inconsistencies between the outputs of original and mirrored inputs. Consequently, StyleSeg V2 allows the seg-model to make use of correctly-aligned regions of unlabeled images and also enhances the fidelity of style-transformed warped atlas image by weighting the local transformation strength according to registration errors. The experimental results on three public datasets demonstrate that our proposed StyleSeg V2 outperforms other state-of-the-arts by considerable margins, and exceeds StyleSeg by increasing the average Dice by at least 2.4%.
Authors: Jiesong Bai, Yuhao Yin, Qiyuan He, Yuanxian Li, Xiaofeng Zhang
Abstract: In the field of low-light image enhancement, both traditional Retinex methods and advanced deep learning techniques such as Retinexformer have shown distinct advantages and limitations. Traditional Retinex methods, designed to mimic the human eye's perception of brightness and color, decompose images into illumination and reflection components but struggle with noise management and detail preservation under low light conditions. Retinexformer enhances illumination estimation through traditional self-attention mechanisms, but faces challenges with insufficient interpretability and suboptimal enhancement effects. To overcome these limitations, this paper introduces the RetinexMamba architecture. RetinexMamba not only captures the physical intuitiveness of traditional Retinex methods but also integrates the deep learning framework of Retinexformer, leveraging the computational efficiency of State Space Models (SSMs) to enhance processing speed. This architecture features innovative illumination estimators and damage restorer mechanisms that maintain image quality during enhancement. Moreover, RetinexMamba replaces the IG-MSA (Illumination-Guided Multi-Head Attention) in Retinexformer with a Fused-Attention mechanism, improving the model's interpretability. Experimental evaluations on the LOL dataset show that RetinexMamba outperforms existing deep learning approaches based on Retinex theory in both quantitative and qualitative metrics, confirming its effectiveness and superiority in enhancing low-light images.
Authors: Xiongjun Guan, Zhiyu Pan, Jianjiang Feng, Jie Zhou
Abstract: Currently, portable electronic devices are becoming more and more popular. For lightweight considerations, their fingerprint recognition modules usually use limited-size sensors. However, partial fingerprints have few matchable features, especially when there are differences in finger pressing posture or image quality, which makes partial fingerprint verification challenging. Most existing methods regard fingerprint position rectification and identity verification as independent tasks, ignoring the coupling relationship between them -- relative pose estimation typically relies on paired features as anchors, and authentication accuracy tends to improve with more precise pose alignment. Consequently, in this paper we propose a method for joint identity verification and pose alignment of partial fingerprint pairs, aiming to leverage their inherent correlation to improve each other. To achieve this, we propose a multi-task CNN (Convolutional Neural Network)-Transformer hybrid network, and design a pre-training task to enhance the feature extraction capability. Experiments on multiple public datasets (NIST SD14, FVC2002 DB1A & DB3A, FVC2004 DB1A & DB2A, FVC2006 DB1A) and an in-house dataset show that our method achieves state-of-the-art performance in both partial fingerprint verification and relative pose estimation, while being more efficient than previous methods.
Authors: Junyi Ma, Jingyi Xu, Xieyuanli Chen, Hesheng Wang
Abstract: Understanding how humans would behave during hand-object interaction is vital for applications in service robot manipulation and extended reality. To achieve this, some recent works have been proposed to simultaneously forecast hand trajectories and object affordances on human egocentric videos. The joint prediction serves as a comprehensive representation of future hand-object interactions in 2D space, indicating potential human motion and motivation. However, the existing approaches mostly adopt the autoregressive paradigm for unidirectional prediction, which lacks mutual constraints within the holistic future sequence, and accumulates errors along the time axis. Meanwhile, these works basically overlook the effect of camera egomotion on first-person view predictions. To address these limitations, we propose a novel diffusion-based interaction prediction method, namely Diff-IP2D, to forecast future hand trajectories and object affordances concurrently in an iterative non-autoregressive manner. We transform the sequential 2D images into latent feature space and design a denoising diffusion model to predict future latent interaction features conditioned on past ones. Motion features are further integrated into the conditional denoising process to enable Diff-IP2D aware of the camera wearer's dynamics for more accurate interaction prediction. Extensive experiments demonstrate that our method significantly outperforms the state-of-the-art baselines on both the off-the-shelf metrics and our newly proposed evaluation protocol. This highlights the efficacy of leveraging a generative paradigm for 2D hand-object interaction prediction. The code of Diff-IP2D will be released at https://github.com/IRMVLab/Diff-IP2D.
Authors: Huaiyuan Xu, Junliang Chen, Shiyu Meng, Yi Wang, Lap-Pui Chau
Abstract: 3D occupancy perception technology aims to observe and understand dense 3D environments for autonomous vehicles. Owing to its comprehensive perception capability, this technology is emerging as a trend in autonomous driving perception systems, and is attracting significant attention from both industry and academia. Similar to traditional bird's-eye view (BEV) perception, 3D occupancy perception has the nature of multi-source input and the necessity for information fusion. However, the difference is that it captures vertical structures that are ignored by 2D BEV. In this survey, we review the most recent works on 3D occupancy perception, and provide in-depth analyses of methodologies with various input modalities. Specifically, we summarize general network pipelines, highlight information fusion techniques, and discuss effective network training. We evaluate and analyze the occupancy perception performance of the state-of-the-art on the most popular datasets. Furthermore, challenges and future research directions are discussed. We hope this paper will inspire the community and encourage more research work on 3D occupancy perception. A comprehensive list of studies in this survey is publicly available in an active repository that continuously collects the latest work: https://github.com/HuaiyuanXu/3D-Occupancy-Perception.
URLs: https://github.com/HuaiyuanXu/3D-Occupancy-Perception.
Authors: Yu Lei, Haolun Luo, Lituan Wang, Zhenwei Zhang, Lei Zhang
Abstract: In weakly supervised medical image segmentation, the absence of structural priors and the discreteness of class feature distribution present a challenge, i.e., how to accurately propagate supervision signals from local to global regions without excessively spreading them to other irrelevant regions? To address this, we propose a novel weakly supervised medical image segmentation framework named PCLMix, comprising dynamic mix augmentation, pixel-level contrastive learning, and consistency regularization strategies. Specifically, PCLMix is built upon a heterogeneous dual-decoder backbone, addressing the absence of structural priors through a strategy of dynamic mix augmentation during training. To handle the discrete distribution of class features, PCLMix incorporates pixel-level contrastive learning based on prediction uncertainty, effectively enhancing the model's ability to differentiate inter-class pixel differences and intra-class consistency. Furthermore, to reinforce segmentation consistency and robustness, PCLMix employs an auxiliary decoder for dual consistency regularization. In the inference phase, the auxiliary decoder will be dropped and no computation complexity is increased. Extensive experiments on the ACDC dataset demonstrate that PCLMix appropriately propagates local supervision signals to the global scale, further narrowing the gap between weakly supervised and fully supervised segmentation methods. Our code is available at https://github.com/Torpedo2648/PCLMix.
Authors: Jian Liu, Wei Sun, Hui Yang, Zhiwen Zeng, Chongpei Liu, Jin Zheng, Xingyu Liu, Hossein Rahmani, Nicu Sebe, Ajmal Mian
Abstract: Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at https://github.com/CNJianLiu/Awesome-Object-Pose-Estimation.
URLs: https://github.com/CNJianLiu/Awesome-Object-Pose-Estimation.
Authors: Weihao Yu, Xinchao Wang
Abstract: Mamba, an architecture with RNN-like token mixer of state space model (SSM), was recently introduced to address the quadratic complexity of the attention mechanism and subsequently applied to vision tasks. Nevertheless, the performance of Mamba for vision is often underwhelming when compared with convolutional and attention-based models. In this paper, we delve into the essence of Mamba, and conceptually conclude that Mamba is ideally suited for tasks with long-sequence and autoregressive characteristics. For vision tasks, as image classification does not align with either characteristic, we hypothesize that Mamba is not necessary for this task; Detection and segmentation tasks are also not autoregressive, yet they adhere to the long-sequence characteristic, so we believe it is still worthwhile to explore Mamba's potential for these tasks. To empirically verify our hypotheses, we construct a series of models named MambaOut through stacking Mamba blocks while removing their core token mixer, SSM. Experimental results strongly support our hypotheses. Specifically, our MambaOut model surpasses all visual Mamba models on ImageNet image classification, indicating that Mamba is indeed unnecessary for this task. As for detection and segmentation, MambaOut cannot match the performance of state-of-the-art visual Mamba models, demonstrating the potential of Mamba for long-sequence visual tasks. The code is available at https://github.com/yuweihao/MambaOut
Authors: Takahiro Shindo, Taiju Watanabe, Yui Tatsumi, Hiroshi Watanabe
Abstract: As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the scalable coding method proves effective because the tasks require occasional image checking by humans. Existing image compression methods for humans and machines meet these requirements to some extent. However, these compression methods are effective solely for specific image recognition models. We propose a learning-based scalable image coding method for humans and machines that is compatible with numerous image recognition models. We combine an image compression model for machines with a compression model, providing additional information to facilitate image decoding for humans. The features in these compression models are fused using a feature fusion network to achieve efficient image compression. Our method's additional information compression model is adjusted to reduce the number of parameters by enabling combinations of features of different sizes in the feature fusion network. Our approach confirms that the feature fusion network efficiently combines image compression models while reducing the number of parameters. Furthermore, we demonstrate the effectiveness of the proposed scalable coding method by evaluating the image compression performance in terms of decoded image quality and bitrate.
Authors: Xusheng Li, Chengliang Wang, Shumao Wang, Zhuo Zeng, Ji Liu
Abstract: The multi-line LiDAR is widely used in autonomous vehicles, so point cloud-based 3D detectors are essential for autonomous driving. Extracting rich multi-scale features is crucial for point cloud-based 3D detectors in autonomous driving due to significant differences in the size of different types of objects. However, because of the real-time requirements, large-size convolution kernels are rarely used to extract large-scale features in the backbone. Current 3D detectors commonly use feature pyramid networks to obtain large-scale features; however, some objects containing fewer point clouds are further lost during down-sampling, resulting in degraded performance. Since pillar-based schemes require much less computation than voxel-based schemes, they are more suitable for constructing real-time 3D detectors. Hence, we propose the PillarNeXt, a pillar-based scheme. We redesigned the feature encoding, the backbone, and the neck of the 3D detector. We propose the Voxel2Pillar feature encoding, which uses a sparse convolution constructor to construct pillars with richer point cloud features, especially height features. The Voxel2Pillar adds more learnable parameters to the feature encoding, enabling the initial pillars to have higher performance ability. We extract multi-scale and large-scale features in the proposed fully sparse backbone, which does not utilize large-size convolutional kernels; the backbone consists of the proposed multi-scale feature extraction module. The neck consists of the proposed sparse ConvNeXt, whose simple structure significantly improves the performance. We validate the effectiveness of the proposed PillarNeXt on the Waymo Open Dataset, and the object detection accuracy for vehicles, pedestrians, and cyclists is improved. We also verify the effectiveness of each proposed module in detail through ablation studies.
Authors: Xiaosu Zhu, Hualian Sheng, Sijia Cai, Bing Deng, Shaopeng Yang, Qiao Liang, Ken Chen, Lianli Gao, Jingkuan Song, Jieping Ye
Abstract: We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more challenging traffic scenes. The highlights of RoScenes include significantly large perception area, full scene coverage and crowded traffic. More specifically, our dataset achieves surprising 21.13M 3D annotations within 64,000 $m^2$. To relieve the expensive costs of roadside 3D labeling, we present a novel BEV-to-3D joint annotation pipeline to efficiently collect such a large volume of data. After that, we organize a comprehensive study for current BEV methods on RoScenes in terms of effectiveness and efficiency. Tested methods suffer from the vast perception area and variation of sensor layout across scenes, resulting in performance levels falling below expectations. To this end, we propose RoBEV that incorporates feature-guided position embedding for effective 2D-3D feature assignment. With its help, our method outperforms state-of-the-art by a large margin without extra computational overhead on validation set. Our dataset and devkit will be made available at https://github.com/xiaosu-zhu/RoScenes.
Authors: Siliang Ma, Yong Xu
Abstract: Bounding box regression is one of the important steps of object detection. However, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. Most of the existing loss functions for rotated object detection calculate the difference between two bounding boxes only focus on the deviation of area or each points distance (e.g., $\mathcal{L}_{Smooth-\ell 1}$, $\mathcal{L}_{RotatedIoU}$ and $\mathcal{L}_{PIoU}$). The calculation process of some loss functions is extremely complex (e.g. $\mathcal{L}_{KFIoU}$). In order to improve the efficiency and accuracy of bounding box regression for rotated object detection, we proposed a novel metric for arbitrary shapes comparison based on minimum points distance, which takes most of the factors from existing loss functions for rotated object detection into account, i.e., the overlap or nonoverlapping area, the central points distance and the rotation angle. We also proposed a loss function called $\mathcal{L}_{FPDIoU}$ based on four points distance for accurate bounding box regression focusing on faster and high quality anchor boxes. In the experiments, $FPDIoU$ loss has been applied to state-of-the-art rotated object detection (e.g., RTMDET, H2RBox) models training with three popular benchmarks of rotated object detection including DOTA, DIOR, HRSC2016 and two benchmarks of arbitrary orientation scene text detection including ICDAR 2017 RRC-MLT and ICDAR 2019 RRC-MLT, which achieves better performance than existing loss functions.
Authors: Peiying Zhang, Nanxuan Zhao, Jing Liao
Abstract: Vector graphics are widely used in digital art and highly favored by designers due to their scalability and layer-wise properties. However, the process of creating and editing vector graphics requires creativity and design expertise, making it a time-consuming task. Recent advancements in text-to-vector (T2V) generation have aimed to make this process more accessible. However, existing T2V methods directly optimize control points of vector graphics paths, often resulting in intersecting or jagged paths due to the lack of geometry constraints. To overcome these limitations, we propose a novel neural path representation by designing a dual-branch Variational Autoencoder (VAE) that learns the path latent space from both sequence and image modalities. By optimizing the combination of neural paths, we can incorporate geometric constraints while preserving expressivity in generated SVGs. Furthermore, we introduce a two-stage path optimization method to improve the visual and topological quality of generated SVGs. In the first stage, a pre-trained text-to-image diffusion model guides the initial generation of complex vector graphics through the Variational Score Distillation (VSD) process. In the second stage, we refine the graphics using a layer-wise image vectorization strategy to achieve clearer elements and structure. We demonstrate the effectiveness of our method through extensive experiments and showcase various applications. The project page is https://intchous.github.io/T2V-NPR.
Authors: Faegheh Sardari, Armin Mustafa, Philip J. B. Jackson, Adrian Hilton
Abstract: Weakly supervised audio-visual video parsing (AVVP) methods aim to detect audible-only, visible-only, and audible-visible events using only video-level labels. Existing approaches tackle this by leveraging unimodal and cross-modal contexts. However, we argue that while cross-modal learning is beneficial for detecting audible-visible events, in the weakly supervised scenario, it negatively impacts unaligned audible or visible events by introducing irrelevant modality information. In this paper, we propose CoLeaF, a novel learning framework that optimizes the integration of cross-modal context in the embedding space such that the network explicitly learns to combine cross-modal information for audible-visible events while filtering them out for unaligned events. Additionally, as videos often involve complex class relationships, modelling them improves performance. However, this introduces extra computational costs into the network. Our framework is designed to leverage cross-class relationships during training without incurring additional computations at inference. Furthermore, we propose new metrics to better evaluate a method's capabilities in performing AVVP. Our extensive experiments demonstrate that CoLeaF significantly improves the state-of-the-art results by an average of 1.9% and 2.4% F-score on the LLP and UnAV-100 datasets, respectively.
Authors: Yong Lee, Fuqiang Gu, Zeyu Gong, Ding Pan, Wenhui Zeng
Abstract: This paper presents a novel surrogate-based cross-correlation (SBCC) framework to improve the correlation performance for practical particle image velocimetry~(PIV). The basic idea is that an optimized surrogate filter/image, replacing one raw image, will produce a more accurate and robust correlation signal. Specifically, the surrogate image is encouraged to generate perfect Gaussian-shaped correlation map to tracking particles (PIV image pair) while producing zero responses to image noise (context images). And the problem is formularized with an objective function composed of surrogate loss and consistency loss. As a result, the closed-form solution provides an efficient multivariate operator that could consider other negative context images. Compared with the state-of-the-art baseline methods (background subtraction, robust phase correlation, etc.), our SBCC method exhibits significant performance improvement (accuracy and robustness) on the synthetic dataset and several challenging experimental PIV cases. Besides, our implementation with experimental details (\url{https://github.com/yongleex/SBCC}) is also available for interested researchers.
Authors: Hyungjin Chung, Byeongsu Sim, Dohoon Ryu, Jong Chul Ye
Abstract: Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process. However, the current solvers, which recursively apply a reverse diffusion step followed by a projection-based measurement consistency step, often produce suboptimal results. By studying the generative sampling path, here we show that current solvers throw the sample path off the data manifold, and hence the error accumulates. To address this, we propose an additional correction term inspired by the manifold constraint, which can be used synergistically with the previous solvers to make the iterations close to the manifold. The proposed manifold constraint is straightforward to implement within a few lines of code, yet boosts the performance by a surprisingly large margin. With extensive experiments, we show that our method is superior to the previous methods both theoretically and empirically, producing promising results in many applications such as image inpainting, colorization, and sparse-view computed tomography. Code available https://github.com/HJ-harry/MCG_diffusion
Authors: Miguel \'Angel Mu\~noz-Ba\~n\'on, Jan-Hendrik Pauls, Haohao Hu, Christoph Stiller, Francisco A. Candelas, Fernando Torres
Abstract: Localization in aerial imagery-based maps offers many advantages, such as global consistency, geo-referenced maps, and the availability of publicly accessible data. However, the landmarks that can be observed from both aerial imagery and on-board sensors is limited. This leads to ambiguities or aliasing during the data association. Building upon a highly informative representation (that allows efficient data association), this paper presents a complete pipeline for resolving these ambiguities. Its core is a robust self-tuning data association that adapts the search area depending on the entropy of the measurements. Additionally, to smooth the final result, we adjust the information matrix for the associated data as a function of the relative transform produced by the data association process. We evaluate our method on real data from urban and rural scenarios around the city of Karlsruhe in Germany. We compare state-of-the-art outlier mitigation methods with our self-tuning approach, demonstrating a considerable improvement, especially for outer-urban scenarios.
Authors: Hyungjin Chung, Jeongsol Kim, Michael T. Mccann, Marc L. Klasky, Jong Chul Ye
Abstract: Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linear inverse problems in noiseless settings, which significantly under-represents the complexity of real-world problems. In this work, we extend diffusion solvers to efficiently handle general noisy (non)linear inverse problems via approximation of the posterior sampling. Interestingly, the resulting posterior sampling scheme is a blended version of diffusion sampling with the manifold constrained gradient without a strict measurement consistency projection step, yielding a more desirable generative path in noisy settings compared to the previous studies. Our method demonstrates that diffusion models can incorporate various measurement noise statistics such as Gaussian and Poisson, and also efficiently handle noisy nonlinear inverse problems such as Fourier phase retrieval and non-uniform deblurring. Code available at https://github.com/DPS2022/diffusion-posterior-sampling
URLs: https://github.com/DPS2022/diffusion-posterior-sampling
Authors: Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, Alex Smola
Abstract: Large language models (LLMs) have shown impressive performance on complex reasoning by leveraging chain-of-thought (CoT) prompting to generate intermediate reasoning chains as the rationale to infer the answer. However, existing CoT studies have primarily focused on the language modality. We propose Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework that separates rationale generation and answer inference. In this way, answer inference can leverage better generated rationales that are based on multimodal information. Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach. With Multimodal-CoT, our model under 1 billion parameters achieves state-of-the-art performance on the ScienceQA benchmark. Our analysis indicates that Multimodal-CoT offers the advantages of mitigating hallucination and enhancing convergence speed. Code is publicly available at https://github.com/amazon-science/mm-cot.
Authors: Yupeng Jia, Jie He, Runze Chen, Fang Zhao, Haiyong Luo
Abstract: Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This approach, however, typically requires more computational resources than BEV or 2D methods. We propose a novel 3D semantic occupancy perception method, OccupancyDETR, which utilizes a DETR-like object detection, a mixed dense-sparse 3D occupancy decoder. Our approach distinguishes between foreground and background within a scene. Initially, foreground objects are detected using the DETR-like object detection. Subsequently, queries for both foreground and background objects are fed into the mixed dense-sparse 3D occupancy decoder, performing upsampling in dense and sparse methods, respectively. Finally, a MaskFormer is utilized to infer the semantics of the background voxels. Our approach strikes a balance between efficiency and accuracy, achieving faster inference times, lower resource consumption, and improved performance for small object detection. We demonstrate the effectiveness of our proposed method on the SemanticKITTI dataset, showcasing an mIoU of 14 and a processing speed of 10 FPS, thereby presenting a promising solution for real-time 3D semantic occupancy perception.
Authors: Corey Knutson, Zhipeng Cao, Junaed Sattar
Abstract: Autonomous Underwater Vehicles (AUVs) conduct missions underwater without the need for human intervention. A docking station (DS) can extend mission times of an AUV by providing a location for the AUV to recharge its batteries and receive updated mission information. Various methods for locating and tracking a DS exist, but most rely on expensive acoustic sensors, or are vision-based, which is significantly affected by water quality. In this \doctype, we present a vision-based method that utilizes adaptive color LED markers and dynamic color filtering to maximize landmark visibility in varying water conditions. Both AUV and DS utilize cameras to determine the water background color in order to calculate the desired marker color. No communication between AUV and DS is needed to determine marker color. Experiments conducted in a pool and lake show our method performs 10 times better than static color thresholding methods as background color varies. DS detection is possible at a range of 5 meters in clear water with minimal false positives.
Authors: Abhishek Vivekanandan, Ahmed Abouelazm, Philip Sch\"orner, J. Marius Z\"ollner
Abstract: Accurately forecasting the motion of traffic actors is crucial for the deployment of autonomous vehicles at a large scale. Current trajectory forecasting approaches primarily concentrate on optimizing a loss function with a specific metric, which can result in predictions that do not adhere to physical laws or violate external constraints. Our objective is to incorporate explicit knowledge priors that allow a network to forecast future trajectories in compliance with both the kinematic constraints of a vehicle and the geometry of the driving environment. To achieve this, we introduce a non-parametric pruning layer and attention layers to integrate the defined knowledge priors. Our proposed method is designed to ensure reachability guarantees for traffic actors in both complex and dynamic situations. By conditioning the network to follow physical laws, we can obtain accurate and safe predictions, essential for maintaining autonomous vehicles' safety and efficiency in real-world settings.In summary, this paper presents concepts that prevent off-road predictions for safe and reliable motion forecasting by incorporating knowledge priors into the training process.
Authors: Guy Ohayon, Tomer Michaeli, Michael Elad
Abstract: We study the behavior of deterministic methods for solving inverse problems in imaging. These methods are commonly designed to achieve two goals: (1) attaining high perceptual quality, and (2) generating reconstructions that are consistent with the measurements. We provide a rigorous proof that the better a predictor satisfies these two requirements, the larger its Lipschitz constant must be, regardless of the nature of the degradation involved. In particular, to approach perfect perceptual quality and perfect consistency, the Lipschitz constant of the model must grow to infinity. This implies that such methods are necessarily more susceptible to adversarial attacks. We demonstrate our theory on single image super-resolution algorithms, addressing both noisy and noiseless settings. We also show how this undesired behavior can be leveraged to explore the posterior distribution, thereby allowing the deterministic model to imitate stochastic methods.
Authors: Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M. van de Ven
Abstract: Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for incrementally learning new tasks and accumulating knowledge, thus enabling the reuse of trained models for further learning. One potentially suitable continual learning approach is generative replay, where a copy of a generative model trained on previous tasks produces synthetic data that are interleaved with data from the current task. However, standard generative replay applied to diffusion models results in a catastrophic loss in denoising capabilities. In this paper, we propose generative distillation, an approach that distils the entire reverse process of a diffusion model. We demonstrate that our approach substantially improves the continual learning performance of generative replay with only a modest increase in the computational costs.
Authors: Shyam Nuggehalli, Jifan Zhang, Lalit Jain, Robert Nowak
Abstract: Class imbalance is a prevalent issue in real world machine learning applications, often leading to poor performance in rare and minority classes. With an abundance of wild unlabeled data, active learning is perhaps the most effective technique in solving the problem at its root -- collecting a more balanced and informative set of labeled examples during annotation. Label noise is another common issue in data annotation jobs, which is especially challenging for active learning methods. In this work, we conduct the first study of active learning under both class imbalance and label noise. We propose a novel algorithm that robustly identifies the class separation threshold and annotates the most uncertain examples that are closest from it. Through a novel reduction to one-dimensional active learning, our algorithm DIRECT is able to leverage the classic active learning literature to address issues such as batch labeling and tolerance towards label noise. We present extensive experiments on imbalanced datasets with and without label noise. Our results demonstrate that DIRECT can save more than 60% of the annotation budget compared to state-of-art active learning algorithms and more than 80% of annotation budget compared to random sampling.
Authors: Yihao Ding, Lorenzo Vaiani, Caren Han, Jean Lee, Paolo Garza, Josiah Poon, Luca Cagliero
Abstract: This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and coarse-grained levels by facilitating a nuanced correlation between token and entity representations, addressing the complexities inherent in form documents. Additionally, we introduce new inter-grained and cross-grained loss functions to further refine diverse multi-teacher knowledge distillation transfer process, presenting distribution gaps and a harmonised understanding of form documents. Through a comprehensive evaluation across publicly available form document understanding datasets, our proposed model consistently outperforms existing baselines, showcasing its efficacy in handling the intricate structures and content of visually complex form documents.
Authors: Samuel Sze, Lars Kunze
Abstract: In autonomous vehicles, understanding the surrounding 3D environment of the ego vehicle in real-time is essential. A compact way to represent scenes while encoding geometric distances and semantic object information is via 3D semantic occupancy maps. State of the art 3D mapping methods leverage transformers with cross-attention mechanisms to elevate 2D vision-centric camera features into the 3D domain. However, these methods encounter significant challenges in real-time applications due to their high computational demands during inference. This limitation is particularly problematic in autonomous vehicles, where GPU resources must be shared with other tasks such as localization and planning. In this paper, we introduce an approach that extracts features from front-view 2D camera images and LiDAR scans, then employs a sparse convolution network (Minkowski Engine), for 3D semantic occupancy prediction. Given that outdoor scenes in autonomous driving scenarios are inherently sparse, the utilization of sparse convolution is particularly apt. By jointly solving the problems of 3D scene completion of sparse scenes and 3D semantic segmentation, we provide a more efficient learning framework suitable for real-time applications in autonomous vehicles. We also demonstrate competitive accuracy on the nuScenes dataset.
Authors: Yuxuan Wang, Xuanyu Yi, Zike Wu, Na Zhao, Long Chen, Hanwang Zhang
Abstract: The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes.
Authors: Jixiang Luo, Yan Wang, Hongwei Qin
Abstract: Learned Image Compression (LIC) has achieved dramatic progress regarding objective and subjective metrics. MSE-based models aim to improve objective metrics while generative models are leveraged to improve visual quality measured by subjective metrics. However, they all suffer from blurring or deformation at low bit rates, especially at below $0.2bpp$. Besides, deformation on human faces and text is unacceptable for visual quality assessment, and the problem becomes more prominent on small faces and text. To solve this problem, we combine the advantage of MSE-based models and generative models by utilizing region of interest (ROI). We propose Hierarchical-ROI (H-ROI), to split images into several foreground regions and one background region to improve the reconstruction of regions containing faces, text, and complex textures. Further, we propose adaptive quantization by non-linear mapping within the channel dimension to constrain the bit rate while maintaining the visual quality. Exhaustive experiments demonstrate that our methods achieve better visual quality on small faces and text with lower bit rates, e.g., $0.7X$ bits of HiFiC and $0.5X$ bits of BPG.
Authors: Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen
Abstract: This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive metrics for systematic evaluation. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxicity of LLMs within a few tuning steps via only one instance. We further provide an in-depth analysis of the internal mechanism for various detoxifying approaches, demonstrating that previous methods like SFT and DPO may merely suppress the activations of toxic parameters, while DINM mitigates the toxicity of the toxic parameters to a certain extent, making permanent adjustments. We hope that these insights could shed light on future work of developing detoxifying approaches and the underlying knowledge mechanisms of LLMs. Code and benchmark are available at https://github.com/zjunlp/EasyEdit.
Authors: Simran Khanuja, Sathyanarayanan Ramamoorthy, Yueqi Song, Graham Neubig
Abstract: Given the rise of multimedia content, human translators increasingly focus on culturally adapting not only words but also other modalities such as images to convey the same meaning. While several applications stand to benefit from this, machine translation systems remain confined to dealing with language in speech and text. In this work, we take a first step towards translating images to make them culturally relevant. First, we build three pipelines comprising state-of-the-art generative models to do the task. Next, we build a two-part evaluation dataset: i) concept: comprising 600 images that are cross-culturally coherent, focusing on a single concept per image, and ii) application: comprising 100 images curated from real-world applications. We conduct a multi-faceted human evaluation of translated images to assess for cultural relevance and meaning preservation. We find that as of today, image-editing models fail at this task, but can be improved by leveraging LLMs and retrievers in the loop. Best pipelines can only translate 5% of images for some countries in the easier concept dataset and no translation is successful for some countries in the application dataset, highlighting the challenging nature of the task. Our code and data is released here: https://github.com/simran-khanuja/image-transcreation.
URLs: https://github.com/simran-khanuja/image-transcreation.
Authors: Zhuoyuan Wang, Dong Sun, Xiangyun Zeng, Ruodai Wu, Yi Wang
Abstract: The segmentation of organs in volumetric medical images plays an important role in computer-aided diagnosis and treatment/surgery planning. Conventional 2D convolutional neural networks (CNNs) can hardly exploit the spatial correlation of volumetric data. Current 3D CNNs have the advantage to extract more powerful volumetric representations but they usually suffer from occupying excessive memory and computation nevertheless. In this study we aim to enhance the 2D networks with contextual information for better volumetric image segmentation. Accordingly, we propose a contextual embedding learning approach to facilitate 2D CNNs capturing spatial information properly. Our approach leverages the learned embedding and the slice-wisely neighboring matching as a soft cue to guide the network. In such a way, the contextual information can be transferred slice-by-slice thus boosting the volumetric representation of the network. Experiments on challenging prostate MRI dataset (PROMISE12) and abdominal CT dataset (CHAOS) show that our contextual embedding learning can effectively leverage the inter-slice context and improve segmentation performance. The proposed approach is a plug-and-play, and memory-efficient solution to enhance the 2D networks for volumetric segmentation. Our code is publicly available at https://github.com/JuliusWang-7/CE_Block.
Authors: Afonso Oliveira, Nuno Fachada, Jo\~ao P. Matos-Carvalho
Abstract: Raster Forge is a Python library and graphical user interface for raster data manipulation and analysis. The tool is focused on remote sensing applications, particularly in wildfire management. It allows users to import, visualize, and process raster layers for tasks such as image compositing or topographical analysis. For wildfire management, it generates fuel maps using predefined models. Its impact extends from disaster management to hydrological modeling, agriculture, and environmental monitoring. Raster Forge can be a valuable asset for geoscientists and researchers who rely on raster data analysis, enhancing geospatial data processing and visualization across various disciplines.
Authors: Francis Ogoke, Peter Myung-Won Pak, Alexander Myers, Guadalupe Quirarte, Jack Beuth, Jonathan Malen, Amir Barati Farimani
Abstract: Insufficient overlap between the melt pools produced during Laser Powder Bed Fusion (L-PBF) can lead to lack-of-fusion defects and deteriorated mechanical and fatigue performance. In-situ monitoring of the melt pool subsurface morphology requires specialized equipment that may not be readily accessible or scalable. Therefore, we introduce a machine learning framework to correlate in-situ two-color thermal images observed via high-speed color imaging to the two-dimensional profile of the melt pool cross-section. Specifically, we employ a hybrid CNN-Transformer architecture to establish a correlation between single bead off-axis thermal image sequences and melt pool cross-section contours measured via optical microscopy. In this architecture, a ResNet model embeds the spatial information contained within the thermal images to a latent vector, while a Transformer model correlates the sequence of embedded vectors to extract temporal information. Our framework is able to model the curvature of the subsurface melt pool structure, with improved performance in high energy density regimes compared to analytical melt pool models. The performance of this model is evaluated through dimensional and geometric comparisons to the corresponding experimental melt pool observations.
Authors: Zhenya Yang, Kai Chen, Yonghao Long, Qi Dou
Abstract: Surgical scene simulation plays a crucial role in surgical education and simulator-based robot learning. Traditional approaches for creating these environments with surgical scene involve a labor-intensive process where designers hand-craft tissues models with textures and geometries for soft body simulations. This manual approach is not only time-consuming but also limited in the scalability and realism. In contrast, data-driven simulation offers a compelling alternative. It has the potential to automatically reconstruct 3D surgical scenes from real-world surgical video data, followed by the application of soft body physics. This area, however, is relatively uncharted. In our research, we introduce 3D Gaussian as a learnable representation for surgical scene, which is learned from stereo endoscopic video. To prevent over-fitting and ensure the geometrical correctness of these scenes, we incorporate depth supervision and anisotropy regularization into the Gaussian learning process. Furthermore, we apply the Material Point Method, which is integrated with physical properties, to the 3D Gaussians to achieve realistic scene deformations. Our method was evaluated on our collected in-house and public surgical videos datasets. Results show that it can reconstruct and simulate surgical scenes from endoscopic videos efficiently-taking only a few minutes to reconstruct the surgical scene-and produce both visually and physically plausible deformations at a speed approaching real-time. The results demonstrate great potential of our proposed method to enhance the efficiency and variety of simulations available for surgical education and robot learning.
Authors: Srikanth Vemula, Eulises Franco, Michael Frye
Abstract: Intelligent detection and tracking of the vessels on the sea play a significant role in conducting traffic avoidance in unmanned surface vessels(USV). Current traffic avoidance software relies mainly on Automated Identification System (AIS) and radar to track other vessels to avoid collisions and acts as a typical perception system to detect targets. However, in a contested environment, emitting radar energy also presents the vulnerability to detection by adversaries. Deactivating these Radiofrequency transmitting sources will increase the threat of detection and degrade the USV's ability to monitor shipping traffic in the vicinity. Therefore, an intelligent visual perception system based on an onboard camera with passive sensing capabilities that aims to assist USV in addressing this problem is presented in this paper. This paper will present a novel low-cost vision perception system for detecting and tracking vessels in the maritime environment. This novel low-cost vision perception system is introduced using the deep learning framework. A neural network, DisBeaNet, can detect vessels, track, and estimate the vessel's distance and bearing from the monocular camera. The outputs obtained from this neural network are used to determine the latitude and longitude of the identified vessel.
Authors: Ross Greer, Mohan Trivedi
Abstract: This study investigates the use of trajectory and dynamic state information for efficient data curation in autonomous driving machine learning tasks. We propose methods for clustering trajectory-states and sampling strategies in an active learning framework, aiming to reduce annotation and data costs while maintaining model performance. Our approach leverages trajectory information to guide data selection, promoting diversity in the training data. We demonstrate the effectiveness of our methods on the trajectory prediction task using the nuScenes dataset, showing consistent performance gains over random sampling across different data pool sizes, and even reaching sub-baseline displacement errors at just 50% of the data cost. Our results suggest that sampling typical data initially helps overcome the ''cold start problem,'' while introducing novelty becomes more beneficial as the training pool size increases. By integrating trajectory-state-informed active learning, we demonstrate that more efficient and robust autonomous driving systems are possible and practical using low-cost data curation strategies.
Authors: Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, Aman Chadha
Abstract: The rapid advancement of foundation models (FMs) across language, image, audio, and video domains has shown remarkable capabilities in diverse tasks. However, the proliferation of FMs brings forth a critical challenge: the potential to generate hallucinated outputs, particularly in high-stakes applications. The tendency of foundation models to produce hallucinated content arguably represents the biggest hindrance to their widespread adoption in real-world scenarios, especially in domains where reliability and accuracy are paramount. This survey paper presents a comprehensive overview of recent developments that aim to identify and mitigate the problem of hallucination in FMs, spanning text, image, video, and audio modalities. By synthesizing recent advancements in detecting and mitigating hallucination across various modalities, the paper aims to provide valuable insights for researchers, developers, and practitioners. Essentially, it establishes a clear framework encompassing definition, taxonomy, and detection strategies for addressing hallucination in multimodal foundation models, laying the foundation for future research in this pivotal area.
Authors: Shijie Liu, Kang Yan, Feiwei Qin, Changmiao Wang, Ruiquan Ge, Kai Zhang, Jie Huang, Yong Peng, Jin Cao
Abstract: Single image super-resolution (SR) is an established pixel-level vision task aimed at reconstructing a high-resolution image from its degraded low-resolution counterpart. Despite the notable advancements achieved by leveraging deep neural networks for SR, most existing deep learning architectures feature an extensive number of layers, leading to high computational complexity and substantial memory demands. These issues become particularly pronounced in the context of infrared image SR, where infrared devices often have stringent storage and computational constraints. To mitigate these challenges, we introduce a novel, efficient, and precise single infrared image SR model, termed the Lightweight Information Split Network (LISN). The LISN comprises four main components: shallow feature extraction, deep feature extraction, dense feature fusion, and high-resolution infrared image reconstruction. A key innovation within this model is the introduction of the Lightweight Information Split Block (LISB) for deep feature extraction. The LISB employs a sequential process to extract hierarchical features, which are then aggregated based on the relevance of the features under consideration. By integrating channel splitting and shift operations, the LISB successfully strikes an optimal balance between enhanced SR performance and a lightweight framework. Comprehensive experimental evaluations reveal that the proposed LISN achieves superior performance over contemporary state-of-the-art methods in terms of both SR quality and model complexity, affirming its efficacy for practical deployment in resource-constrained infrared imaging applications.