Authors: Congzhen Shi, Ryan Rezai, Jiaxi Yang, Qi Dou, Xiaoxiao Li
Abstract: The rapid advancement of foundation models in medical imaging represents a significant leap toward enhancing diagnostic accuracy and personalized treatment. However, the deployment of foundation models in healthcare necessitates a rigorous examination of their trustworthiness, encompassing privacy, robustness, reliability, explainability, and fairness. The current body of survey literature on foundation models in medical imaging reveals considerable gaps, particularly in the area of trustworthiness. Additionally, extant surveys on the trustworthiness of foundation models fail to address their specific variations and applications within the medical imaging domain. This survey paper reviews the current research on foundation models in the major medical imaging applications, with a focus on segmentation, medical report generation, medical question and answering (Q&A), and disease diagnosis, which includes trustworthiness discussion in their manuscripts. We explore the complex challenges of making foundation models for medical image analysis trustworthy, associated with each application, and summarize the current concerns and strategies to enhance trustworthiness. Furthermore, we explore the future promises of these models in revolutionizing patient care. Our analysis underscores the imperative for advancing towards trustworthy AI in medical image analysis, advocating for a balanced approach that fosters innovation while ensuring ethical and equitable healthcare delivery.
Authors: Mauro Figueiredo, Jo\~ao Pereira, Jo\~ao Oliveira, Bruno Araujo
Abstract: Point cloud models are a common shape representation for several reasons. Three-dimensional scanning devices are widely used nowadays and points are an attractive primitive for rendering complex geometry. Nevertheless, there is not much literature on collision detection for point cloud models. This paper presents a novel collision detection algorithm for large point cloud models using voxels, octrees and bounding spheres hierarchies (BSH). The scene graph is divided in voxels. The objects of each voxel are organized into an octree. Due to the high number of points in the scene, each non-empty cell of the octree is organized in a bounding sphere hierarchy, based on an R-tree hierarchy like structure. The BSH hierarchies are used to group neighboring points and filter out very quickly parts of objects that do not interact with other models. Points derived from laser scanned data typically are not segmented and can have arbitrary spatial resolution thus introducing computational and modeling issues. We address these issues and our results show that the proposed collision detection algorithm effectively finds intersections between point cloud models since it is able to reduce the number of bounding volume checks and updates.
Authors: Wei-Lun Huang, Davood Tashayyod, Amir Gandjbakhche, Michael Kazhdan, Mehran Armand
Abstract: The depth of field of a camera is a limiting factor for applications that require taking images at a short subject-to-camera distance or using a large focal length, such as total body photography, archaeology, and other close-range photogrammetry applications. Furthermore, in multi-view capture, where the target is larger than the camera's field of view, an efficient way to optimize surface coverage captured with quality remains a challenge. Given the 3D mesh of the target object and camera poses, we propose a novel method to derive a focus distance for each camera that optimizes the quality of the covered surface area. We first design an Expectation-Minimization (EM) algorithm to assign points on the mesh uniquely to cameras and then solve for a focus distance for each camera given the associated point set. We further improve the quality surface coverage by proposing a $k$-view algorithm that solves for the points assignment and focus distances by considering multiple views simultaneously. We demonstrate the effectiveness of the proposed method under various simulations for total body photography. The EM and $k$-view algorithms improve the relative cost of the baseline single-view methods by at least $24$% and $28$% respectively, corresponding to increasing the in-focus surface area by roughly $1550$ cm$^2$ and $1780$ cm$^2$. We believe the algorithms can be useful in a number of vision applications that require photogrammetric details but are limited by the depth of field.
Authors: Zheng Chong, Xiao Dong, Haoxiang Li, Shiyue Zhang, Wenqing Zhang, Xujie Zhang, Hanqing Zhao, Xiaodan Liang
Abstract: Virtual try-on methods based on diffusion models achieve realistic try-on effects but often replicate the backbone network as a ReferenceNet or use additional image encoders to process condition inputs, leading to high training and inference costs. In this work, we rethink the necessity of ReferenceNet and image encoders and innovate the interaction between garment and person by proposing CatVTON, a simple and efficient virtual try-on diffusion model. CatVTON facilitates the seamless transfer of in-shop or worn garments of any category to target persons by simply concatenating them in spatial dimensions as inputs. The efficiency of our model is demonstrated in three aspects: (1) Lightweight network: Only the original diffusion modules are used, without additional network modules. The text encoder and cross-attentions for text injection in the backbone are removed, reducing the parameters by 167.02M. (2) Parameter-efficient training: We identified the try-on relevant modules through experiments and achieved high-quality try-on effects by training only 49.57M parameters, approximately 5.51 percent of the backbone network's parameters. (3) Simplified inference: CatVTON eliminates all unnecessary conditions and preprocessing steps, including pose estimation, human parsing, and text input, requiring only a garment reference, target person image, and mask for the virtual try-on process. Extensive experiments demonstrate that CatVTON achieves superior qualitative and quantitative results with fewer prerequisites and trainable parameters than baseline methods. Furthermore, CatVTON shows good generalization in in-the-wild scenarios despite using open-source datasets with only 73K samples.
Authors: Jingchen Sun, Rohan Sharma, Vishnu Suresh Lokhande, Changyou Chen
Abstract: Prompt Tuning has emerged as a prominent research paradigm for adapting vision-language models to various downstream tasks. However, recent research indicates that prompt tuning methods often lead to overfitting due to limited training samples. In this paper, we propose a \textbf{Cr}oss-modal \textbf{a}ligned \textbf{f}eature \textbf{t}uning (\textbf{Craft}) method to address this issue. Cross-modal alignment is conducted by first selecting anchors from the alternative domain and deriving relative representations of the embeddings for the selected anchors. Optimizing for a feature alignment loss over anchor-aligned text and image modalities creates a more unified text-image common space. Overfitting in prompt tuning also deteriorates model performance on out-of-distribution samples. To further improve the prompt model's robustness, we propose minimizing Maximum Mean Discrepancy (MMD) over the anchor-aligned feature spaces to mitigate domain shift. The experiment on four different prompt tuning structures consistently shows the improvement of our method, with increases of up to $6.1\%$ in the Base-to-Novel generalization task, $5.8\%$ in the group robustness task, and $2.7\%$ in the out-of-distribution tasks. The code will be available at \href{https://github.com/Jingchensun/Craft}
Authors: Raza Imam, Hanan Gani, Muhammad Huzaifa, Karthik Nandakumar
Abstract: The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, ie, test-time prompt tuning. This paper introduces Test-Time Low-rank adaptation (TTL) as an alternative to prompt tuning for zero-shot generalization of large-scale VLMs. Taking inspiration from recent advancements in efficiently fine-tuning large language models, TTL offers a test-time parameter-efficient adaptation approach that updates the attention weights of the transformer encoder by maximizing prediction confidence. The self-supervised confidence maximization objective is specified using a weighted entropy loss that enforces consistency among predictions of augmented samples. TTL introduces only a small amount of trainable parameters for low-rank adapters in the model space while keeping the prompts and backbone frozen. Extensive experiments on a variety of natural distribution and cross-domain tasks show that TTL can outperform other techniques for test-time optimization of VLMs in strict zero-shot settings. Specifically, TTL outperforms test-time prompt tuning baselines with a significant improvement on average. Our code is available at at https://github.com/Razaimam45/TTL-Test-Time-Low-Rank-Adaptation.
URLs: https://github.com/Razaimam45/TTL-Test-Time-Low-Rank-Adaptation.
Authors: David Keaton, Amol S. Joshi, Jeremy Dawson, Nasser M. Nasrabadi
Abstract: The challenge of deblurring fingerphoto images, or generating a sharp fingerphoto from a given blurry one, is a significant problem in the realm of computer vision. To address this problem, we propose a fingerphoto deblurring architecture referred to as Fingerphoto Deblurring using Wavelet Style Transfer (FDWST), which aims to utilize the information transmission of Style Transfer techniques to deblur fingerphotos. Additionally, we incorporate the Discrete Wavelet Transform (DWT) for its ability to split images into different frequency bands. By combining these two techniques, we can perform Style Transfer over a wide array of wavelet frequency bands, thereby increasing the quality and variety of sharpness information transferred from sharp to blurry images. Using this technique, our model was able to drastically increase the quality of the generated fingerphotos compared to their originals, and achieve a peak matching accuracy of 0.9907 when tasked with matching a deblurred fingerphoto to its sharp counterpart, outperforming multiple other state-of-the-art deblurring and style transfer techniques.
Authors: Sijun Dong, Yuwei Zhu, Geng Chen, Xiaoliang Meng
Abstract: With the widespread application of remote sensing technology in environmental monitoring, the demand for efficient and accurate remote sensing image change detection (CD) for natural environments is growing. We propose a novel deep learning framework named EfficientCD, specifically designed for remote sensing image change detection. The framework employs EfficientNet as its backbone network for feature extraction. To enhance the information exchange between bi-temporal image feature maps, we have designed a new Feature Pyramid Network module targeted at remote sensing change detection, named ChangeFPN. Additionally, to make full use of the multi-level feature maps in the decoding stage, we have developed a layer-by-layer feature upsampling module combined with Euclidean distance to improve feature fusion and reconstruction during the decoding stage. The EfficientCD has been experimentally validated on four remote sensing datasets: LEVIR-CD, SYSU-CD, CLCD, and WHUCD. The experimental results demonstrate that EfficientCD exhibits outstanding performance in change detection accuracy. The code and pretrained models will be released at https://github.com/dyzy41/mmrscd.
Authors: Zhen Wang, Dylan G. Ildefonzo, Linbing Wang
Abstract: Due to the varying intensity of pavement cracks, the complexity of topological structure, and the noise of texture background, image classification for asphalt pavement cracking has proven to be a challenging problem. Fatigue cracking, also known as alligator cracking, is one of the common distresses of asphalt pavement. It is thus important to detect and monitor the condition of alligator cracking on roadway pavements. Most research in this area has typically focused on pixel-level detection of cracking using limited datasets. A novel deep convolutional neural network that can achieve two objectives is proposed. The first objective of the proposed neural network is to classify presence of fatigue cracking based on pavement surface images. The second objective is to classify the fatigue cracking severity level based on the Distress Identification Manual (DIM) standard. In this paper, a databank of 4484 high-resolution pavement surface images is established in which images are taken locally in the Town of Blacksburg, Virginia, USA. In the data pre-preparation, over 4000 images are labeled into 4 categories manually according to DIM standards. A four-layer convolutional neural network model is then built to achieve the goal of classification of images by pavement crack severity category. The trained model reached the highest accuracy among all existing methods. After only 30 epochs of training, the model achieved a crack existence classification accuracy of 96.23% and a severity level classification accuracy of 96.74%. After 20 epochs of training, the model achieved a pavement marking presence classification accuracy of 97.64%.
Authors: H{\aa}kon Maric Solberg, Mehdi Houshmand Sarkhoosh, Sushant Gautam, Saeed Shafiee Sabet, P{\aa}l Halvorsen, Cise Midoglu
Abstract: In the rapidly evolving field of sports analytics, the automation of targeted video processing is a pivotal advancement. We propose PlayerTV, an innovative framework which harnesses state-of-the-art AI technologies for automatic player tracking and identification in soccer videos. By integrating object detection and tracking, Optical Character Recognition (OCR), and color analysis, PlayerTV facilitates the generation of player-specific highlight clips from extensive game footage, significantly reducing the manual labor traditionally associated with such tasks. Preliminary results from the evaluation of our core pipeline, tested on a dataset from the Norwegian Eliteserien league, indicate that PlayerTV can accurately and efficiently identify teams and players, and our interactive Graphical User Interface (GUI) serves as a user-friendly application wrapping this functionality for streamlined use.
Authors: Aditya Krishnan, Jayneel Vora, Prasant Mohapatra
Abstract: Semantic segmentation has emerged as a pivotal area of study in computer vision, offering profound implications for scene understanding and elevating human-machine interactions across various domains. While 2D semantic segmentation has witnessed significant strides in the form of lightweight, high-precision models, transitioning to 3D semantic segmentation poses distinct challenges. Our research focuses on achieving efficiency and lightweight design for 3D semantic segmentation models, similar to those achieved for 2D models. Such a design impacts applications of 3D semantic segmentation where memory and latency are of concern. This paper introduces a novel approach to 3D semantic segmentation, distinguished by incorporating a hybrid blend of 2D and 3D computer vision techniques, enabling a streamlined, efficient process. We conduct 2D semantic segmentation on RGB images linked to 3D point clouds and extend the results to 3D using an extrusion technique for specific class labels, reducing the point cloud subspace. We perform rigorous evaluations with the DeepViewAgg model on the complete point cloud as our baseline by measuring the Intersection over Union (IoU) accuracy, inference time latency, and memory consumption. This model serves as the current state-of-the-art 3D semantic segmentation model on the KITTI-360 dataset. We can achieve heightened accuracy outcomes, surpassing the baseline for 6 out of the 15 classes while maintaining a marginal 1% deviation below the baseline for the remaining class labels. Our segmentation approach demonstrates a 1.347x speedup and about a 43% reduced memory usage compared to the baseline.
Authors: Jiahe Liu, Youran Qu, Qi Yan, Xiaohui Zeng, Lele Wang, Renjie Liao
Abstract: Significant advancements have been made in video generative models recently. Unlike image generation, video generation presents greater challenges, requiring not only generating high-quality frames but also ensuring temporal consistency across these frames. Despite the impressive progress, research on metrics for evaluating the quality of generated videos, especially concerning temporal and motion consistency, remains underexplored. To bridge this research gap, we propose Fr\'echet Video Motion Distance (FVMD) metric, which focuses on evaluating motion consistency in video generation. Specifically, we design explicit motion features based on key point tracking, and then measure the similarity between these features via the Fr\'echet distance. We conduct sensitivity analysis by injecting noise into real videos to verify the effectiveness of FVMD. Further, we carry out a large-scale human study, demonstrating that our metric effectively detects temporal noise and aligns better with human perceptions of generated video quality than existing metrics. Additionally, our motion features can consistently improve the performance of Video Quality Assessment (VQA) models, indicating that our approach is also applicable to unary video quality evaluation. Code is available at https://github.com/ljh0v0/FMD-frechet-motion-distance.
URLs: https://github.com/ljh0v0/FMD-frechet-motion-distance.
Authors: Sojin Lee, Dogyun Park, Inho Kong, Hyunwoo J. Kim
Abstract: Recent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors. These attempts have paved the way for using diffusion models in a wide range of inverse problems. However, the existing methods entail computationally demanding iterative sampling procedures and optimize a separate solution for each measurement, which leads to limited scalability and lack of generalization capability across unseen samples. To address these limitations, we propose a novel approach, Diffusion prior-based Amortized Variational Inference (DAVI) that solves inverse problems with a diffusion prior from an amortized variational inference perspective. Specifically, instead of separate measurement-wise optimization, our amortized inference learns a function that directly maps measurements to the implicit posterior distributions of corresponding clean data, enabling a single-step posterior sampling even for unseen measurements. Extensive experiments on image restoration tasks, e.g., Gaussian deblur, 4$\times$ super-resolution, and box inpainting with two benchmark datasets, demonstrate our approach's superior performance over strong baselines. Code is available at https://github.com/mlvlab/DAVI.
Authors: Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang, Hubert P. H. Shum
Abstract: Image inpainting, or image completion, is a crucial task in computer vision that aims to restore missing or damaged regions of images with semantically coherent content. This technique requires a precise balance of local texture replication and global contextual understanding to ensure the restored image integrates seamlessly with its surroundings. Traditional methods using Convolutional Neural Networks (CNNs) are effective at capturing local patterns but often struggle with broader contextual relationships due to the limited receptive fields. Recent advancements have incorporated transformers, leveraging their ability to understand global interactions. However, these methods face computational inefficiencies and struggle to maintain fine-grained details. To overcome these challenges, we introduce MxT composed of the proposed Hybrid Module (HM), which combines Mamba with the transformer in a synergistic manner. Mamba is adept at efficiently processing long sequences with linear computational costs, making it an ideal complement to the transformer for handling long-scale data interactions. Our HM facilitates dual-level interaction learning at both pixel and patch levels, greatly enhancing the model to reconstruct images with high quality and contextual accuracy. We evaluate MxT on the widely-used CelebA-HQ and Places2-standard datasets, where it consistently outperformed existing state-of-the-art methods.
Authors: Yanwu Yang, Hairui Chen, Jiesi Hu, Xutao Guo, Ting Ma
Abstract: Recent advancements in deep learning have shifted the development of brain imaging analysis. However, several challenges remain, such as heterogeneity, individual variations, and the contradiction between the high dimensionality and small size of brain imaging datasets. These issues complicate the learning process, preventing models from capturing intrinsic, meaningful patterns and potentially leading to suboptimal performance due to biases and overfitting. Curriculum learning (CL) presents a promising solution by organizing training examples from simple to complex, mimicking the human learning process, and potentially fostering the development of more robust and accurate models. Despite its potential, the inherent limitations posed by small initial training datasets present significant challenges, including overfitting and poor generalization. In this paper, we introduce the Progressive Self-Paced Distillation (PSPD) framework, employing an adaptive and progressive pacing and distillation mechanism. This allows for dynamic curriculum adjustments based on the states of both past and present models. The past model serves as a teacher, guiding the current model with gradually refined curriculum knowledge and helping prevent the loss of previously acquired knowledge. We validate PSPD's efficacy and adaptability across various convolutional neural networks using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, underscoring its superiority in enhancing model performance and generalization capabilities. The source code for this approach will be released at https://github.com/Hrychen7/PSPD.
Authors: Weiying Xie, Yusi Zhang, Tianlin Hui, Jiaqing Zhang, Jie Lei, Yunsong Li
Abstract: Multimodal object detection offers a promising prospect to facilitate robust detection in various visual conditions. However, existing two-stream backbone networks are challenged by complex fusion and substantial parameter increments. This is primarily due to large data distribution biases of multimodal homogeneous information. In this paper, we propose a novel multimodal object detector, named Low-rank Modal Adaptors (LMA) with a shared backbone. The shared parameters enhance the consistency of homogeneous information, while lightweight modal adaptors focus on modality unique features. Furthermore, we design an adaptive rank allocation strategy to adapt to the varying heterogeneity at different feature levels. When applied to two multimodal object detection datasets, experiments validate the effectiveness of our method. Notably, on DroneVehicle, LMA attains a 10.4% accuracy improvement over the state-of-the-art method with a 149M-parameters reduction. The code is available at https://github.com/zyszxhy/FoRA. Our work was submitted to ACM MM in April 2024, but was rejected. We will continue to refine our work and paper writing next, mainly including proof of theory and multi-task applications of FoRA.
Authors: Yiyang Su, Minchul Kim, Feng Liu, Anil Jain, Xiaoming Liu
Abstract: Biometric recognition has primarily addressed closed-set identification, assuming all probe subjects are in the gallery. However, most practical applications involve open-set biometrics, where probe subjects may or may not be present in the gallery. This poses distinct challenges in effectively distinguishing individuals in the gallery while minimizing false detections. While it is commonly believed that powerful biometric models can excel in both closed- and open-set scenarios, existing loss functions are inconsistent with open-set evaluation. They treat genuine (mated) and imposter (non-mated) similarity scores symmetrically and neglect the relative magnitudes of imposter scores. To address these issues, we simulate open-set evaluation using minibatches during training and introduce novel loss functions: (1) the identification-detection loss optimized for open-set performance under selective thresholds and (2) relative threshold minimization to reduce the maximum negative score for each probe. Across diverse biometric tasks, including face recognition, gait recognition, and person re-identification, our experiments demonstrate the effectiveness of the proposed loss functions, significantly enhancing open-set performance while positively impacting closed-set performance. Our code and models are available at https://github.com/prevso1088/open-set-biometrics.
Authors: Jie Zhao, Jianing Li, Weihan Chen, Wentong Wang, Pengfei Yuan, Xu Zhang, Deshu Peng
Abstract: Human pose estimation remains a multifaceted challenge in computer vision, pivotal across diverse domains such as behavior recognition, human-computer interaction, and pedestrian tracking. This paper proposes an improved method based on the spatial-temporal graph convolution net-work (UGCN) to address the issue of missing human posture skeleton sequences in single-view videos. We present the improved UGCN, which allows the network to process 3D human pose data and improves the 3D human pose skeleton sequence, thereby resolving the occlusion issue.
Authors: Kyu Ri Park, Hong Joo Lee, Jung Uk Kim
Abstract: Recent Audio-Visual Question Answering (AVQA) methods rely on complete visual and audio input to answer questions accurately. However, in real-world scenarios, issues such as device malfunctions and data transmission errors frequently result in missing audio or visual modality. In such cases, existing AVQA methods suffer significant performance degradation. In this paper, we propose a framework that ensures robust AVQA performance even when a modality is missing. First, we propose a Relation-aware Missing Modal (RMM) generator with Relation-aware Missing Modal Recalling (RMMR) loss to enhance the ability of the generator to recall missing modal information by understanding the relationships and context among the available modalities. Second, we design an Audio-Visual Relation-aware (AVR) diffusion model with Audio-Visual Enhancing (AVE) loss to further enhance audio-visual features by leveraging the relationships and shared cues between the audio-visual modalities. As a result, our method can provide accurate answers by effectively utilizing available information even when input modalities are missing. We believe our method holds potential applications not only in AVQA research but also in various multi-modal scenarios.
Authors: Jiyeop Kim, Jongwoo Lim
Abstract: We present a novel approach for 3D indoor scene reconstruction that combines 3D Gaussian Splatting (3DGS) with mesh representations. We use meshes for the room layout of the indoor scene, such as walls, ceilings, and floors, while employing 3D Gaussians for other objects. This hybrid approach leverages the strengths of both representations, offering enhanced flexibility and ease of editing. However, joint training of meshes and 3D Gaussians is challenging because it is not clear which primitive should affect which part of the rendered image. Objects close to the room layout often struggle during training, particularly when the room layout is textureless, which can lead to incorrect optimizations and unnecessary 3D Gaussians. To overcome these challenges, we employ Segment Anything Model (SAM) to guide the selection of primitives. The SAM mask loss enforces each instance to be represented by either Gaussians or meshes, ensuring clear separation and stable training. Furthermore, we introduce an additional densification stage without resetting the opacity after the standard densification. This stage mitigates the degradation of image quality caused by a limited number of 3D Gaussians after the standard densification.
Authors: Shuai Chen, Fanman Meng, Chenhao Wu, Haoran Wei, Runtong Zhang, Qingbo Wu, Linfeng Xu, Hongliang Li
Abstract: Few-Shot Segmentation (FSS) aims to segment novel classes using only a few annotated images. Despite considerable process under pixel-wise support annotation, current FSS methods still face three issues: the inflexibility of backbone upgrade without re-training, the inability to uniformly handle various types of annotations (e.g., scribble, bounding box, mask and text), and the difficulty in accommodating different annotation quantity. To address these issues simultaneously, we propose DiffUp, a novel FSS method that conceptualizes the FSS task as a conditional generative problem using a diffusion process. For the first issue, we introduce a backbone-agnostic feature transformation module that converts different segmentation cues into unified coarse priors, facilitating seamless backbone upgrade without re-training. For the second issue, due to the varying granularity of transformed priors from diverse annotation types, we conceptualize these multi-granular transformed priors as analogous to noisy intermediates at different steps of a diffusion model. This is implemented via a self-conditioned modulation block coupled with a dual-level quality modulation branch. For the third issue, we incorporates an uncertainty-aware information fusion module that harmonizing the variability across zero-shot, one-shot and many-shot scenarios. Evaluated through rigorous benchmarks, DiffUp significantly outperforms existing FSS models in terms of flexibility and accuracy.
Authors: Zicheng Pan, Xiaohan Yu, Yongsheng Gao
Abstract: Source-free domain adaptation (SFDA) aims to transfer knowledge from a labelled source domain to an unlabelled target domain. A major challenge in SFDA is deriving accurate categorical information for the target domain, especially when sample embeddings from different classes appear similar. This issue is particularly pronounced in fine-grained visual categorization tasks, where inter-class differences are subtle. To overcome this challenge, we introduce a novel ETF-Informed Attention Network (EIANet) to separate class prototypes by utilizing attention and neural collapse principles. More specifically, EIANet employs a simplex Equiangular Tight Frame (ETF) classifier in conjunction with an attention mechanism, facilitating the model to focus on discriminative features and ensuring maximum class prototype separation. This innovative approach effectively enlarges the feature difference between different classes in the latent space by locating salient regions, thereby preventing the misclassification of similar but distinct category samples and providing more accurate categorical information to guide the fine-tuning process on the target domain. Experimental results across four SFDA datasets validate EIANet's state-of-the-art performance. Code is available at: https://github.com/zichengpan/EIANet.
Authors: Hajin Shim, Changhun Kim, Eunho Yang
Abstract: 3D point clouds captured from real-world sensors frequently encompass noisy points due to various obstacles, such as occlusion, limited resolution, and variations in scale. These challenges hinder the deployment of pre-trained point cloud recognition models trained on clean point clouds, leading to significant performance degradation. While test-time adaptation (TTA) strategies have shown promising results on this issue in the 2D domain, their application to 3D point clouds remains under-explored. Among TTA methods, an input adaptation approach, which directly converts test instances to the source domain using a pre-trained diffusion model, has been proposed in the 2D domain. Despite its robust TTA performance in practical situations, naively adopting this into the 3D domain may be suboptimal due to the neglect of inherent properties of point clouds, and its prohibitive computational cost. Motivated by these limitations, we propose CloudFixer, a test-time input adaptation method tailored for 3D point clouds, employing a pre-trained diffusion model. Specifically, CloudFixer optimizes geometric transformation parameters with carefully designed objectives that leverage the geometric properties of point clouds. We also substantially improve computational efficiency by avoiding backpropagation through the diffusion model and a prohibitive generation process. Furthermore, we propose an online model adaptation strategy by aligning the original model prediction with that of the adapted input. Extensive experiments showcase the superiority of CloudFixer over various TTA baselines, excelling in handling common corruptions and natural distribution shifts across diverse real-world scenarios. Our code is available at https://github.com/shimazing/CloudFixer
Authors: Yukai Ma, Jianbiao Mei, Xuemeng Yang, Licheng Wen, Weihua Xu, Jiangning Zhang, Botian Shi, Yong Liu, Xingxing Zuo
Abstract: Semantic Scene Completion (SSC) is pivotal in autonomous driving perception, frequently confronted with the complexities of weather and illumination changes. The long-term strategy involves fusing multi-modal information to bolster the system's robustness. Radar, increasingly utilized for 3D target detection, is gradually replacing LiDAR in autonomous driving applications, offering a robust sensing alternative. In this paper, we focus on the potential of 3D radar in semantic scene completion, pioneering cross-modal refinement techniques for improved robustness against weather and illumination changes, and enhancing SSC performance.Regarding model architecture, we propose a three-stage tight fusion approach on BEV to realize a fusion framework for point clouds and images. Based on this foundation, we designed three cross-modal distillation modules-CMRD, BRD, and PDD. Our approach enhances the performance in both radar-only (R-LiCROcc) and radar-camera (RC-LiCROcc) settings by distilling to them the rich semantic and structural information of the fused features of LiDAR and camera. Finally, our LC-Fusion (teacher model), R-LiCROcc and RC-LiCROcc achieve the best performance on the nuScenes-Occupancy dataset, with mIOU exceeding the baseline by 22.9%, 44.1%, and 15.5%, respectively. The project page is available at https://hr-zju.github.io/LiCROcc/.
Authors: Yiwei Ma, Zhibin Wang, Xiaoshuai Sun, Weihuang Lin, Qiang Zhou, Jiayi Ji, Rongrong Ji
Abstract: With advancements in data availability and computing resources, Multimodal Large Language Models (MLLMs) have showcased capabilities across various fields. However, the quadratic complexity of the vision encoder in MLLMs constrains the resolution of input images. Most current approaches mitigate this issue by cropping high-resolution images into smaller sub-images, which are then processed independently by the vision encoder. Despite capturing sufficient local details, these sub-images lack global context and fail to interact with one another. To address this limitation, we propose a novel MLLM, INF-LLaVA, designed for effective high-resolution image perception. INF-LLaVA incorporates two innovative components. First, we introduce a Dual-perspective Cropping Module (DCM), which ensures that each sub-image contains continuous details from a local perspective and comprehensive information from a global perspective. Second, we introduce Dual-perspective Enhancement Module (DEM) to enable the mutual enhancement of global and local features, allowing INF-LLaVA to effectively process high-resolution images by simultaneously capturing detailed local information and comprehensive global context. Extensive ablation studies validate the effectiveness of these components, and experiments on a diverse set of benchmarks demonstrate that INF-LLaVA outperforms existing MLLMs. Code and pretrained model are available at https://github.com/WeihuangLin/INF-LLaVA.
Authors: Liang Zhao, Qing Guo, Xiaoguang Li, Song Wang
Abstract: Image inpainting aims to fill missing pixels in damaged images and has achieved significant progress with cut-edging learning techniques. Nevertheless, state-of-the-art inpainting methods are mainly designed for nature images and cannot correctly recover text within scene text images, and training existing models on the scene text images cannot fix the issues. In this work, we identify the visual-text inpainting task to achieve high-quality scene text image restoration and text completion: Given a scene text image with unknown missing regions and the corresponding text with unknown missing characters, we aim to complete the missing information in both images and text by leveraging their complementary information. Intuitively, the input text, even if damaged, contains language priors of the contents within the images and can guide the image inpainting. Meanwhile, the scene text image includes the appearance cues of the characters that could benefit text recovery. To this end, we design the cross-modal predictive interaction (CLII) model containing two branches, i.e., ImgBranch and TxtBranch, for scene text inpainting and text completion, respectively while leveraging their complementary effectively. Moreover, we propose to embed our model into the SOTA scene text spotting method and significantly enhance its robustness against missing pixels, which demonstrates the practicality of the newly developed task. To validate the effectiveness of our method, we construct three real datasets based on existing text-related datasets, containing 1838 images and covering three scenarios with curved, incidental, and styled texts, and conduct extensive experiments to show that our method outperforms baselines significantly.
Authors: Jinting Luo, Ru Li, Chengzhi Jiang, Mingyan Han, Xiaoming Zhang, Ting Jiang, Haoqiang Fan, Shuaicheng Liu
Abstract: We propose Diff-Shadow, a global-guided diffusion model for high-quality shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but ignore global information, resulting in inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to realize shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextural information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on three publicly standard datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the SRD dataset. Codes will be released.
Authors: Ke Sun, Jian Cao, Qi Wang, Linrui Tian, Xindi Zhang, Lian Zhuo, Bang Zhang, Liefeng Bo, Wenbo Zhou, Weiming Zhang, Daiheng Gao
Abstract: Virtual Try-On (VTON) has become a transformative technology, empowering users to experiment with fashion without ever having to physically try on clothing. However, existing methods often struggle with generating high-fidelity and detail-consistent results. While diffusion models, such as Stable Diffusion series, have shown their capability in creating high-quality and photorealistic images, they encounter formidable challenges in conditional generation scenarios like VTON. Specifically, these models struggle to maintain a balance between control and consistency when generating images for virtual clothing trials. OutfitAnyone addresses these limitations by leveraging a two-stream conditional diffusion model, enabling it to adeptly handle garment deformation for more lifelike results. It distinguishes itself with scalability-modulating factors such as pose, body shape and broad applicability, extending from anime to in-the-wild images. OutfitAnyone's performance in diverse scenarios underscores its utility and readiness for real-world deployment. For more details and animated results, please see \url{https://humanaigc.github.io/outfit-anyone/}.
Authors: Dinh Phu Tran, Dao Duy Hung, Daeyoung Kim
Abstract: Recently, window-based attention methods have shown great potential for computer vision tasks, particularly in Single Image Super-Resolution (SISR). However, it may fall short in capturing long-range dependencies and relationships between distant tokens. Additionally, we find that learning on spatial domain does not convey the frequency content of the image, which is a crucial aspect in SISR. To tackle these issues, we propose a new Channel-Partitioned Attention Transformer (CPAT) to better capture long-range dependencies by sequentially expanding windows along the height and width of feature maps. In addition, we propose a novel Spatial-Frequency Interaction Module (SFIM), which incorporates information from spatial and frequency domains to provide a more comprehensive information from feature maps. This includes information about the frequency content and enhances the receptive field across the entire image. Experimental findings demonstrate the effectiveness of our proposed modules and architecture. In particular, CPAT surpasses current state-of-the-art methods by up to 0.31dB.
Authors: Yiping Zhang, Yuntao Shou, Tao Meng, Wei Ai, Keqin Li
Abstract: The age estimation task aims to use facial features to predict the age of people and is widely used in public security, marketing, identification, and other fields. However, the features are mainly concentrated in facial keypoints, and existing CNN and Transformer-based methods have inflexibility and redundancy for modeling complex irregular structures. Therefore, this paper proposes a Multi-view Mask Contrastive Learning Graph Convolutional Neural Network (MMCL-GCN) for age estimation. Specifically, the overall structure of the MMCL-GCN network contains a feature extraction stage and an age estimation stage. In the feature extraction stage, we introduce a graph structure to construct face images as input and then design a Multi-view Mask Contrastive Learning (MMCL) mechanism to learn complex structural and semantic information about face images. The learning mechanism employs an asymmetric siamese network architecture, which utilizes an online encoder-decoder structure to reconstruct the missing information from the original graph and utilizes the target encoder to learn latent representations for contrastive learning. Furthermore, to promote the two learning mechanisms better compatible and complementary, we adopt two augmentation strategies and optimize the joint losses. In the age estimation stage, we design a Multi-layer Extreme Learning Machine (ML-IELM) with identity mapping to fully use the features extracted by the online encoder. Then, a classifier and a regressor were constructed based on ML-IELM, which were used to identify the age grouping interval and accurately estimate the final age. Extensive experiments show that MMCL-GCN can effectively reduce the error of age estimation on benchmark datasets such as Adience, MORPH-II, and LAP-2016.
Authors: Muhammad Irzam Liaqat, Shah Nawaz, Muhammad Zaigham Zaheer, Muhammad Saad Saeed, Hassan Sajjad, Tom De Schepper, Karthik Nandakumar, Muhammad Haris Khan Markus Schedl
Abstract: Multimodal learning has demonstrated remarkable performance improvements over unimodal architectures. However, multimodal learning methods often exhibit deteriorated performances if one or more modalities are missing. This may be attributed to the commonly used multi-branch design containing modality-specific streams making the models reliant on the availability of a complete set of modalities. In this work, we propose a robust textual-visual multimodal learning method, Chameleon, that completely deviates from the conventional multi-branch design. To enable this, we present the unification of input modalities into one format by encoding textual modality into visual representations. As a result, our approach does not require modality-specific branches to learn modality-independent multimodal representations making it robust to missing modalities. Extensive experiments are performed on four popular challenging datasets including Hateful Memes, UPMC Food-101, MM-IMDb, and Ferramenta. Chameleon not only achieves superior performance when all modalities are present at train/test time but also demonstrates notable resilience in the case of missing modalities.
Authors: Shuyi Ouyang, Hongyi Wang, Ziwei Niu, Zhenjia Bai, Shiao Xie, Yingying Xu, Ruofeng Tong, Yen-Wei Chen, Lanfen Lin
Abstract: The task of multi-label image classification involves recognizing multiple objects within a single image. Considering both valuable semantic information contained in the labels and essential visual features presented in the image, tight visual-linguistic interactions play a vital role in improving classification performance. Moreover, given the potential variance in object size and appearance within a single image, attention to features of different scales can help to discover possible objects in the image. Recently, Transformer-based methods have achieved great success in multi-label image classification by leveraging the advantage of modeling long-range dependencies, but they have several limitations. Firstly, existing methods treat visual feature extraction and cross-modal fusion as separate steps, resulting in insufficient visual-linguistic alignment in the joint semantic space. Additionally, they only extract visual features and perform cross-modal fusion at a single scale, neglecting objects with different characteristics. To address these issues, we propose a Hierarchical Scale-Aware Vision-Language Transformer (HSVLT) with two appealing designs: (1)~A hierarchical multi-scale architecture that involves a Cross-Scale Aggregation module, which leverages joint multi-modal features extracted from multiple scales to recognize objects of varying sizes and appearances in images. (2)~Interactive Visual-Linguistic Attention, a novel attention mechanism module that tightly integrates cross-modal interaction, enabling the joint updating of visual, linguistic and multi-modal features. We have evaluated our method on three benchmark datasets. The experimental results demonstrate that HSVLT surpasses state-of-the-art methods with lower computational cost.
Authors: Xiaowan Hu, Yiyi Chen, Yan Li, Minquan Wang, Haoqian Wang, Quan Chen, Han Li, Peng Jiang
Abstract: With the rapid expansion of e-commerce, more consumers have become accustomed to making purchases via livestreaming. Accurately identifying the products being sold by salespeople, i.e., livestreaming product retrieval (LPR), poses a fundamental and daunting challenge. The LPR task encompasses three primary dilemmas in real-world scenarios: 1) the recognition of intended products from distractor products present in the background; 2) the video-image heterogeneity that the appearance of products showcased in live streams often deviates substantially from standardized product images in stores; 3) there are numerous confusing products with subtle visual nuances in the shop. To tackle these challenges, we propose the Spatiotemporal Graphing Multi-modal Network (SGMN). First, we employ a text-guided attention mechanism that leverages the spoken content of salespeople to guide the model to focus toward intended products, emphasizing their salience over cluttered background products. Second, a long-range spatiotemporal graph network is further designed to achieve both instance-level interaction and frame-level matching, solving the misalignment caused by video-image heterogeneity. Third, we propose a multi-modal hard example mining, assisting the model in distinguishing highly similar products with fine-grained features across the video-image-text domain. Through extensive quantitative and qualitative experiments, we demonstrate the superior performance of our proposed SGMN model, surpassing the state-of-the-art methods by a substantial margin. The code is available at \url{https://github.com/Huxiaowan/SGMN}.
Authors: Zizheng Yan, Jiapeng Zhou, Fanpeng Meng, Yushuang Wu, Lingteng Qiu, Zisheng Ye, Shuguang Cui, Guanying Chen, Xiaoguang Han
Abstract: Text-to-3D generation has recently seen significant progress. To enhance its practicality in real-world applications, it is crucial to generate multiple independent objects with interactions, similar to layer-compositing in 2D image editing. However, existing text-to-3D methods struggle with this task, as they are designed to generate either non-independent objects or independent objects lacking spatially plausible interactions. Addressing this, we propose DreamDissector, a text-to-3D method capable of generating multiple independent objects with interactions. DreamDissector accepts a multi-object text-to-3D NeRF as input and produces independent textured meshes. To achieve this, we introduce the Neural Category Field (NeCF) for disentangling the input NeRF. Additionally, we present the Category Score Distillation Sampling (CSDS), facilitated by a Deep Concept Mining (DCM) module, to tackle the concept gap issue in diffusion models. By leveraging NeCF and CSDS, we can effectively derive sub-NeRFs from the original scene. Further refinement enhances geometry and texture. Our experimental results validate the effectiveness of DreamDissector, providing users with novel means to control 3D synthesis at the object level and potentially opening avenues for various creative applications in the future.
Authors: Shreyank N Gowda, David A. Clifton
Abstract: Contemporary medical contrastive learning faces challenges from inconsistent semantics and sample pair morphology, leading to dispersed and converging semantic shifts. The variability in text reports, due to multiple authors, complicates semantic consistency. To tackle these issues, we propose a two-step approach. Initially, text reports are converted into a standardized triplet format, laying the groundwork for our novel concept of ``observations'' and ``verdicts''. This approach refines the {Entity, Position, Exist} triplet into binary questions, guiding towards a clear ``verdict''. We also innovate in visual pre-training with a Meijering-based masking, focusing on features representative of medical images' local context. By integrating this with our text conversion method, our model advances cross-modal representation in a multimodal contrastive learning framework, setting new benchmarks in medical image analysis.
Authors: Ayan Igali, Pakizar Shamoi
Abstract: Nowadays, deep learning models are increasingly required to be both interpretable and highly accurate. We present an approach that integrates Kolmogorov-Arnold Network (KAN) classification heads and Fuzzy Pooling into convolutional neural networks (CNNs). By utilizing the interpretability of KAN and the uncertainty handling capabilities of fuzzy logic, the integration shows potential for improved performance in image classification tasks. Our comparative analysis demonstrates that the modified CNN architecture with KAN and Fuzzy Pooling achieves comparable or higher accuracy than traditional models. The findings highlight the effectiveness of combining fuzzy logic and KAN to develop more interpretable and efficient deep learning models. Future work will aim to expand this approach across larger datasets.
Authors: Fangqin Zhou, Mert Kilickaya, Joaquin Vanschoren, Ran Piao
Abstract: Hyperspectral Imaging (HSI) plays an increasingly critical role in precise vision tasks within remote sensing, capturing a wide spectrum of visual data. Transformer architectures have significantly enhanced HSI task performance, while advancements in Transformer Architecture Search (TAS) have improved model discovery. To harness these advancements for HSI classification, we make the following contributions: i) We propose HyTAS, the first benchmark on transformer architecture search for Hyperspectral imaging, ii) We comprehensively evaluate 12 different methods to identify the optimal transformer over 5 different datasets, iii) We perform an extensive factor analysis on the Hyperspectral transformer search performance, greatly motivating future research in this direction. All benchmark materials are available at HyTAS.
Authors: Haicheng Liao, Yongkang Li, Chengyue Wang, Yanchen Guan, KaHou Tam, Chunlin Tian, Li Li, Chengzhong Xu, Zhenning Li
Abstract: As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount. Traditional accident anticipation models primarily utilizing dashcam videos are adept at predicting when an accident may occur but fall short in localizing the incident and identifying involved entities. Addressing this gap, this study introduces a novel framework that integrates Large Language Models (LLMs) to enhance predictive capabilities across multiple dimensions--what, when, and where accidents might occur. We develop an innovative chain-based attention mechanism that dynamically adjusts to prioritize high-risk elements within complex driving scenes. This mechanism is complemented by a three-stage model that processes outputs from smaller models into detailed multimodal inputs for LLMs, thus enabling a more nuanced understanding of traffic dynamics. Empirical validation on the DAD, CCD, and A3D datasets demonstrates superior performance in Average Precision (AP) and Mean Time-To-Accident (mTTA), establishing new benchmarks for accident prediction technology. Our approach not only advances the technological framework for autonomous driving safety but also enhances human-AI interaction, making predictive insights generated by autonomous systems more intuitive and actionable.
Authors: Hansol Kim, Hoyeol Choi, Youngjun Kwak
Abstract: Federated Learning (FL) for face recognition aggregates locally optimized models from individual clients to construct a generalized face recognition model. However, previous studies present two major challenges: insufficient incorporation of self-supervised learning and the necessity for clients to accommodate multiple subjects. To tackle these limitations, we propose FedFS (Federated Learning for personalized Face recognition via intra-subject Self-supervised learning framework), a novel federated learning architecture tailored to train personalized face recognition models without imposing subjects. Our proposed FedFS comprises two crucial components that leverage aggregated features of the local and global models to cooperate with representations of an off-the-shelf model. These components are (1) adaptive soft label construction, utilizing dot product operations to reformat labels within intra-instances, and (2) intra-subject self-supervised learning, employing cosine similarity operations to strengthen robust intra-subject representations. Additionally, we introduce a regularization loss to prevent overfitting and ensure the stability of the optimized model. To assess the effectiveness of FedFS, we conduct comprehensive experiments on the DigiFace-1M and VGGFace datasets, demonstrating superior performance compared to previous methods.
Authors: Hongyang Li, Hao Zhang, Shilong Liu, Zhaoyang Zeng, Feng Li, Tianhe Ren, Bohan Li, Lei Zhang
Abstract: In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-like algorithms. TAPTRv2 improves TAPTR by addressing a critical issue regarding its reliance on cost-volume,which contaminates the point query\'s content feature and negatively impacts both visibility prediction and cost-volume computation. In TAPTRv2, we propose a novel attention-based position update (APU) operation and use key-aware deformable attention to realize. For each query, this operation uses key-aware attention weights to combine their corresponding deformable sampling positions to predict a new query position. This design is based on the observation that local attention is essentially the same as cost-volume, both of which are computed by dot-production between a query and its surrounding features. By introducing this new operation, TAPTRv2 not only removes the extra burden of cost-volume computation, but also leads to a substantial performance improvement. TAPTRv2 surpasses TAPTR and achieves state-of-the-art performance on many challenging datasets, demonstrating the superiority
Authors: Aditya Kapoor, Harshad Khadilkar, Jayvardhana Gubbi
Abstract: Distortion identification and rectification in images and videos is vital for achieving good performance in downstream vision applications. Instead of relying on fixed trial-and-error based image processing pipelines, we propose a two-level sequential planning approach for automated image distortion classification and rectification. At the higher level it detects the class of corruptions present in the input image, if any. The lower level selects a specific algorithm to be applied, from a set of externally provided candidate algorithms. The entire two-level setup runs in the form of a single forward pass during inference and it is to be queried iteratively until the retrieval of the original image. We demonstrate improvements compared to three baselines on the object detection task on COCO image dataset with rich set of distortions. The advantage of our approach is its dynamic reconfiguration, conditioned on the input image and generalisability to unseen candidate algorithms at inference time, since it relies only on the comparison of their output of the image embeddings.
Authors: Lingtong Kong, Bo Li, Yike Xiong, Hao Zhang, Hong Gu, Jinwei Chen
Abstract: Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great success by either following the alignment and fusion pipeline or utilizing attention mechanism. However, the large computation cost and inference delay hinder them from deploying on resource limited devices. In this paper, to achieve better efficiency, a novel Selective Alignment Fusion Network (SAFNet) for HDR imaging is proposed. After extracting pyramid features, it jointly refines valuable area masks and cross-exposure motion in selected regions with shared decoders, and then fuses high quality HDR image in an explicit way. This approach can focus the model on finding valuable regions while estimating their easily detectable and meaningful motion. For further detail enhancement, a lightweight refine module is introduced which enjoys privileges from previous optical flow, selection masks and initial prediction. Moreover, to facilitate learning on samples with large motion, a new window partition cropping method is presented during training. Experiments on public and newly developed challenging datasets show that proposed SAFNet not only exceeds previous SOTA competitors quantitatively and qualitatively, but also runs order of magnitude faster. Code and dataset is available at https://github.com/ltkong218/SAFNet.
Authors: Maniru Ibrahim, Thales Vieira
Abstract: Multidimensional projections (MP) are among the most essential approaches in the visual analysis of multidimensional data. It transforms multidimensional data into two-dimensional representations that may be shown as scatter plots while preserving their similarity with the original data. Human visual perception is frequently used to evaluate the quality of MP. In this work, we propose to study and improve on a well-known map called Local Affine Multidimensional Projection (LAMP), which takes a multidimensional instance and embeds it in Cartesian space via moving least squares deformation. We propose a new visual quality metric based on human perception. The new metric combines three previously used metrics: silhouette coefficient, neighborhood preservation, and silhouette ratio. We show that the proposed metric produces more precise results in analyzing the quality of MP than other previously used metrics. Finally, we describe an algorithm that attempts to overcome a limitation of the LAMP method which requires a similar scale for control points and their counterparts in the Cartesian space.
Authors: Xiaodong Chen, Wu Liu, Qian Bao, Xinchen Liu, Quanwei Yang, Ruoli Dai, Tao Mei
Abstract: Human motion capture is the foundation for many computer vision and graphics tasks. While industrial motion capture systems with complex camera arrays or expensive wearable sensors have been widely adopted in movie and game production, consumer-affordable and easy-to-use solutions for personal applications are still far from mature. To utilize a mixture of a monocular camera and very few inertial measurement units (IMUs) for accurate multi-modal human motion capture in daily life, we contribute MINIONS in this paper, a large-scale Motion capture dataset collected from INertial and visION Sensors. MINIONS has several featured properties: 1) large scale of over five million frames and 400 minutes duration; 2) multi-modality data of IMUs signals and RGB videos labeled with joint positions, joint rotations, SMPL parameters, etc.; 3) a diverse set of 146 fine-grained single and interactive actions with textual descriptions. With the proposed MINIONS, we conduct experiments on multi-modal motion capture and explore the possibilities of consumer-affordable motion capture using a monocular camera and very few IMUs. The experiment results emphasize the unique advantages of inertial and vision sensors, showcasing the promise of consumer-affordable multi-modal motion capture and providing a valuable resource for further research and development.
Authors: Wenbo Huang, Jinghui Zhang, Xuwei Qian, Zhen Wu, Meng Wang, Lei Zhang
Abstract: High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional data-driven training. However, samples are not always sufficient in real-world scenarios, promoting few-shot action recognition (FSAR) research. We observe that most recent FSAR works build spatio-temporal relation of video samples via temporal alignment after spatial feature extraction, cutting apart spatial and temporal features within samples. They also capture motion information via narrow perspectives between adjacent frames without considering density, leading to insufficient motion information capturing. Therefore, we propose a novel plug-and-play architecture for FSAR called Spatio-tempOral frAme tuPle enhancer (SOAP) in this paper. The model we designed with such architecture refers to SOAP-Net. Temporal connections between different feature channels and spatio-temporal relation of features are considered instead of simple feature extraction. Comprehensive motion information is also captured, using frame tuples with multiple frames containing more motion information than adjacent frames. Combining frame tuples of diverse frame counts further provides a broader perspective. SOAP-Net achieves new state-of-the-art performance across well-known benchmarks such as SthSthV2, Kinetics, UCF101, and HMDB51. Extensive empirical evaluations underscore the competitiveness, pluggability, generalization, and robustness of SOAP. The code is released at https://github.com/wenbohuang1002/SOAP.
Authors: Jinpeng Chen, Runmin Cong, Yuxuan Luo, Horace Ho Shing Ip, Sam Kwong
Abstract: This study explores the emerging area of continual panoptic segmentation, highlighting three key balances. First, we introduce past-class backtrace distillation to balance the stability of existing knowledge with the adaptability to new information. This technique retraces the features associated with past classes based on the final label assignment results, performing knowledge distillation targeting these specific features from the previous model while allowing other features to flexibly adapt to new information. Additionally, we introduce a class-proportional memory strategy, which aligns the class distribution in the replay sample set with that of the historical training data. This strategy maintains a balanced class representation during replay, enhancing the utility of the limited-capacity replay sample set in recalling prior classes. Moreover, recognizing that replay samples are annotated only for the classes of their original step, we devise balanced anti-misguidance losses, which combat the impact of incomplete annotations without incurring classification bias. Building upon these innovations, we present a new method named Balanced Continual Panoptic Segmentation (BalConpas). Our evaluation on the challenging ADE20K dataset demonstrates its superior performance compared to existing state-of-the-art methods. The official code is available at https://github.com/jinpeng0528/BalConpas.
Authors: Zhen Zhao, Jingqun Tang, Binghong Wu, Chunhui Lin, Shu Wei, Hao Liu, Xin Tan, Zhizhong Zhang, Can Huang, Yuan Xie
Abstract: In this work, we present TextHarmony, a unified and versatile multimodal generative model proficient in comprehending and generating visual text. Simultaneously generating images and texts typically results in performance degradation due to the inherent inconsistency between vision and language modalities. To overcome this challenge, existing approaches resort to modality-specific data for supervised fine-tuning, necessitating distinct model instances. We propose Slide-LoRA, which dynamically aggregates modality-specific and modality-agnostic LoRA experts, partially decoupling the multimodal generation space. Slide-LoRA harmonizes the generation of vision and language within a singular model instance, thereby facilitating a more unified generative process. Additionally, we develop a high-quality image caption dataset, DetailedTextCaps-100K, synthesized with a sophisticated closed-source MLLM to enhance visual text generation capabilities further. Comprehensive experiments across various benchmarks demonstrate the effectiveness of the proposed approach. Empowered by Slide-LoRA, TextHarmony achieves comparable performance to modality-specific fine-tuning results with only a 2% increase in parameters and shows an average improvement of 2.5% in visual text comprehension tasks and 4.0% in visual text generation tasks. Our work delineates the viability of an integrated approach to multimodal generation within the visual text domain, setting a foundation for subsequent inquiries.
Authors: Kilian Zepf, Jes Frellsen, Aasa Feragen
Abstract: We address the selection and evaluation of uncertain segmentation methods in medical imaging and present two case studies: prostate segmentation, illustrating that for minimal annotator variation simple deterministic models can suffice, and lung lesion segmentation, highlighting the limitations of the Generalized Energy Distance (GED) in model selection. Our findings lead to guidelines for accurately choosing and developing uncertain segmentation models, that integrate aleatoric and epistemic components. These guidelines are designed to aid researchers and practitioners in better developing, selecting, and evaluating uncertain segmentation methods, thereby facilitating enhanced adoption and effective application of segmentation uncertainty in practice.
Authors: Yunfei Lu, Pengfei Gu, Chaoli Wang
Abstract: We present FCNR, a fast compressive neural representation for tens of thousands of visualization images under varying viewpoints and timesteps. The existing NeRVI solution, albeit enjoying a high compression ratio, incurs slow speeds in encoding and decoding. Built on the recent advances in stereo image compression, FCNR assimilates stereo context modules and joint context transfer modules to compress image pairs. Our solution significantly improves encoding and decoding speed while maintaining high reconstruction quality and satisfying compression ratio. To demonstrate its effectiveness, we compare FCNR with state-of-the-art neural compression methods, including E-NeRV, HNeRV, NeRVI, and ECSIC. The source code can be found at https://github.com/YunfeiLu0112/FCNR.
Authors: Koushikey Chhapariya, Alexandre Benoit, Krishna Mohan Buddhiraju, Anil Kumar
Abstract: Multitask learning is a widely recognized technique in the field of computer vision and deep learning domain. However, it is still a research question in remote sensing, particularly for hyperspectral imaging. Moreover, most of the research in the remote sensing domain focuses on small and single-task-based annotated datasets, which limits the generalizability and scalability of the developed models to more diverse and complex real-world scenarios. Thus, in this study, we propose a multitask deep learning model designed to perform multiple classification and regression tasks simultaneously on hyperspectral images. We validated our approach on a large hyperspectral dataset called TAIGA, which contains 13 forest variables, including three categorical variables and ten continuous variables with different biophysical parameters. We design a sharing encoder and task-specific decoder network to streamline feature learning while allowing each task-specific decoder to focus on the unique aspects of its respective task. Additionally, a dense atrous pyramid pooling layer and attention network were integrated to extract multi-scale contextual information and enable selective information processing by prioritizing task-specific features. Further, we computed multitask loss and optimized its parameters for the proposed framework to improve the model performance and efficiency across diverse tasks. A comprehensive qualitative and quantitative analysis of the results shows that the proposed method significantly outperforms other state-of-the-art methods. We trained our model across 10 seeds/trials to ensure robustness. Our proposed model demonstrates higher mean performance while maintaining lower or equivalent variability. To make the work reproducible, the codes will be available at https://github.com/Koushikey4596/Multitask-Deep-Learning-Model-for-Taiga-datatset.
URLs: https://github.com/Koushikey4596/Multitask-Deep-Learning-Model-for-Taiga-datatset.
Authors: Longtao Jiang, Min Wang, Zecheng Li, Yao Fang, Wengang Zhou, Houqiang Li
Abstract: Different from traditional video retrieval, sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. Previous works typically only encode RGB videos to obtain high-level semantic features, resulting in local action details drowned in a large amount of visual information redundancy. Furthermore, existing RGB-based sign retrieval works suffer from the huge memory cost of dense visual data embedding in end-to-end training, and adopt offline RGB encoder instead, leading to suboptimal feature representation. To address these issues, we propose a novel sign language representation framework called Semantically Enhanced Dual-Stream Encoder (SEDS), which integrates Pose and RGB modalities to represent the local and global information of sign language videos. Specifically, the Pose encoder embeds the coordinates of keypoints corresponding to human joints, effectively capturing detailed action features. For better context-aware fusion of two video modalities, we propose a Cross Gloss Attention Fusion (CGAF) module to aggregate the adjacent clip features with similar semantic information from intra-modality and inter-modality. Moreover, a Pose-RGB Fine-grained Matching Objective is developed to enhance the aggregated fusion feature by contextual matching of fine-grained dual-stream features. Besides the offline RGB encoder, the whole framework only contains learnable lightweight networks, which can be trained end-to-end. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods on various datasets.
Authors: Wenyuan Zhang, Kanle Shi, Yu-Shen Liu, Zhizhong Han
Abstract: Unsigned distance functions (UDFs) have been a vital representation for open surfaces. With different differentiable renderers, current methods are able to train neural networks to infer a UDF by minimizing the rendering errors on the UDF to the multi-view ground truth. However, these differentiable renderers are mainly handcrafted, which makes them either biased on ray-surface intersections, or sensitive to unsigned distance outliers, or not scalable to large scale scenes. To resolve these issues, we present a novel differentiable renderer to infer UDFs more accurately. Instead of using handcrafted equations, our differentiable renderer is a neural network which is pre-trained in a data-driven manner. It learns how to render unsigned distances into depth images, leading to a prior knowledge, dubbed volume rendering priors. To infer a UDF for an unseen scene from multiple RGB images, we generalize the learned volume rendering priors to map inferred unsigned distances in alpha blending for RGB image rendering. Our results show that the learned volume rendering priors are unbiased, robust, scalable, 3D aware, and more importantly, easy to learn. We evaluate our method on both widely used benchmarks and real scenes, and report superior performance over the state-of-the-art methods.
Authors: Haoran Wang, Xinji Mai, Zeng Tao, Yan Wang, Jiawen Yu, Ziheng Zhou, Xuan Tong, Shaoqi Yan, Qing Zhao, Shuyong Gao, Wenqiang Zhang
Abstract: Affective Forecasting, a research direction in psychology that predicts individuals future emotions, is often constrained by numerous external factors like social influence and temporal distance. To address this, we transform Affective Forecasting into a Deep Learning problem by designing an Emotion Forecasting paradigm based on two-party interactions. We propose a novel Emotion Forecasting (EF) task grounded in the theory that an individuals emotions are easily influenced by the emotions or other information conveyed during interactions with another person. To tackle this task, we have developed a specialized dataset, Human-interaction-based Emotion Forecasting (Hi-EF), which contains 3069 two-party Multilayered-Contextual Interaction Samples (MCIS) with abundant affective-relevant labels and three modalities. Hi-EF not only demonstrates the feasibility of the EF task but also highlights its potential. Additionally, we propose a methodology that establishes a foundational and referential baseline model for the EF task and extensive experiments are provided. The dataset and code is available at https://github.com/Anonymize-Author/Hi-EF.
Authors: Kai Liu, Zhihang Fu, Sheng Jin, Ze Chen, Fan Zhou, Rongxin Jiang, Yaowu Chen, Jieping Ye
Abstract: Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code will be made public soon.
Authors: Kai Liu, Zhihang Fu, Sheng Jin, Chao Chen, Ze Chen, Rongxin Jiang, Fan Zhou, Yaowu Chen, Jieping Ye
Abstract: Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions. In real-world scenarios, however, the efficacy of existing OOD detection methods is often impeded by the inherent imbalance of in-distribution (ID) data, which causes significant performance decline. Through statistical observations, we have identified two common challenges faced by different OOD detectors: misidentifying tail class ID samples as OOD, while erroneously predicting OOD samples as head class from ID. To explain this phenomenon, we introduce a generalized statistical framework, termed ImOOD, to formulate the OOD detection problem on imbalanced data distribution. Consequently, the theoretical analysis reveals that there exists a class-aware bias item between balanced and imbalanced OOD detection, which contributes to the performance gap. Building upon this finding, we present a unified training-time regularization technique to mitigate the bias and boost imbalanced OOD detectors across architecture designs. Our theoretically grounded method translates into consistent improvements on the representative CIFAR10-LT, CIFAR100-LT, and ImageNet-LT benchmarks against several state-of-the-art OOD detection approaches. Code will be made public soon.
Authors: Youngmin Oh, Hyung-Il Kim, Seong Tae Kim, Jung Uk Kim
Abstract: Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability to handle changes in weather conditions, such as foggy weather, not just clear weather. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature. This serves an attention role in indicating how much improvement is needed for the input feature according to the weather conditions. To achieve this goal, we introduce a weather-adaptive enhancement loss to enhance the feature representation under both clear and foggy weather conditions. Extensive experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection. The code and dataset are released at https://github.com/VisualAIKHU/MonoWAD.
Authors: Zhuxian Guo, Amine Marzouki, Jean-Fran\c{c}ois Emile, Henning M\"uller, Camille Kurtz, Nicolas Lom\'enie
Abstract: Lymphoid infiltration at tumor margins is a key prognostic marker in solid tumors, playing a crucial role in guiding immunotherapy decisions. Current assessment methods, heavily reliant on immunohistochemistry (IHC), face challenges in tumor margin delineation and are affected by tissue preservation conditions. In contrast, we propose a Hematoxylin and Eosin (H&E) staining-based approach, underpinned by an advanced lymphocyte segmentation model trained on a public dataset for the precise detection of CD3+ and CD20+ lymphocytes. In our colorectal cancer study, we demonstrate that our H&E-based method offers a compelling alternative to traditional IHC, achieving comparable results in many cases. Our method's validity is further explored through a Turing test, involving blinded assessments by a pathologist of anonymized curves from H&E and IHC slides. This approach invites the medical community to consider Turing tests as a standard for evaluating medical applications involving expert human evaluation, thereby opening new avenues for enhancing cancer management and immunotherapy planning.
Authors: Shishuai Wang, Hua Ma, Juan A. Hernandez-Tamames, Stefan Klein, Dirk H. J. Poot
Abstract: Quantitative MRI (qMRI) offers significant advantages over weighted images by providing objective parameters related to tissue properties. Deep learning-based methods have demonstrated effectiveness in estimating quantitative maps from series of weighted images. In this study, we present qMRI Diffusor, a novel approach to qMRI utilising deep generative models. Specifically, we implemented denoising diffusion probabilistic models (DDPM) for T1 quantification in the brain, framing the estimation of quantitative maps as a conditional generation task. The proposed method is compared with the residual neural network (ResNet) and the recurrent inference machine (RIM) on both phantom and in vivo data. The results indicate that our method achieves improved accuracy and precision in parameter estimation, along with superior visual performance. Moreover, our method inherently incorporates stochasticity, enabling straightforward quantification of uncertainty. Hence, the proposed method holds significant promise for quantitative MR mapping.
Authors: Trinh Le Ba Khanh, Huy-Hung Nguyen, Long Hoang Pham, Duong Nguyen-Ngoc Tran, Jae Wook Jeon
Abstract: In object detection, unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, UDA's reliance on labeled source data restricts its adaptability in privacy-related scenarios. This study focuses on source-free object detection (SFOD), which adapts a source-trained detector to an unlabeled target domain without using labeled source data. Recent advancements in self-training, particularly with the Mean Teacher (MT) framework, show promise for SFOD deployment. However, the absence of source supervision significantly compromises the stability of these approaches. We identify two primary issues, (1) uncontrollable degradation of the teacher model due to inopportune updates from the student model, and (2) the student model's tendency to replicate errors from incorrect pseudo labels, leading to it being trapped in a local optimum. Both factors contribute to a detrimental circular dependency, resulting in rapid performance degradation in recent self-training frameworks. To tackle these challenges, we propose the Dynamic Retraining-Updating (DRU) mechanism, which actively manages the student training and teacher updating processes to achieve co-evolutionary training. Additionally, we introduce Historical Student Loss to mitigate the influence of incorrect pseudo labels. Our method achieves state-of-the-art performance in the SFOD setting on multiple domain adaptation benchmarks, comparable to or even surpassing advanced UDA methods. The code will be released at https://github.com/lbktrinh/DRU
Authors: Shreyas Singh, Aryan Garg, Kaushik Mitra
Abstract: The recent advent of 3D Gaussian Splatting (3DGS) has revolutionized the 3D scene reconstruction space enabling high-fidelity novel view synthesis in real-time. However, with the exception of RawNeRF, all prior 3DGS and NeRF-based methods rely on 8-bit tone-mapped Low Dynamic Range (LDR) images for scene reconstruction. Such methods struggle to achieve accurate reconstructions in scenes that require a higher dynamic range. Examples include scenes captured in nighttime or poorly lit indoor spaces having a low signal-to-noise ratio, as well as daylight scenes with shadow regions exhibiting extreme contrast. Our proposed method HDRSplat tailors 3DGS to train directly on 14-bit linear raw images in near darkness which preserves the scenes' full dynamic range and content. Our key contributions are two-fold: Firstly, we propose a linear HDR space-suited loss that effectively extracts scene information from noisy dark regions and nearly saturated bright regions simultaneously, while also handling view-dependent colors without increasing the degree of spherical harmonics. Secondly, through careful rasterization tuning, we implicitly overcome the heavy reliance and sensitivity of 3DGS on point cloud initialization. This is critical for accurate reconstruction in regions of low texture, high depth of field, and low illumination. HDRSplat is the fastest method to date that does 14-bit (HDR) 3D scene reconstruction in $\le$15 minutes/scene ($\sim$30x faster than prior state-of-the-art RawNeRF). It also boasts the fastest inference speed at $\ge$120fps. We further demonstrate the applicability of our HDR scene reconstruction by showcasing various applications like synthetic defocus, dense depth map extraction, and post-capture control of exposure, tone-mapping and view-point.
Authors: Zhenhua Wu, Yanlin Jin, Liangdong Qiu, Xiaoguang Han, Xiang Wan, Guanbin Li
Abstract: Visualizing colonoscopy is crucial for medical auxiliary diagnosis to prevent undetected polyps in areas that are not fully observed. Traditional feature-based and depth-based reconstruction approaches usually end up with undesirable results due to incorrect point matching or imprecise depth estimation in realistic colonoscopy videos. Modern deep-based methods often require a sufficient number of ground truth samples, which are generally hard to obtain in optical colonoscopy. To address this issue, self-supervised and domain adaptation methods have been explored. However, these methods neglect geometry constraints and exhibit lower accuracy in predicting detailed depth. We thus propose a novel reconstruction pipeline with a bi-directional adaptation architecture named ToDER to get precise depth estimations. Furthermore, we carefully design a TNet module in our adaptation architecture to yield geometry constraints and obtain better depth quality. Estimated depth is finally utilized to reconstruct a reliable colon model for visualization. Experimental results demonstrate that our approach can precisely predict depth maps in both realistic and synthetic colonoscopy videos compared with other self-supervised and domain adaptation methods. Our method on realistic colonoscopy also shows the great potential for visualizing unobserved regions and preventing misdiagnoses.
Authors: Zhenyu Xie, Haoye Dong, Yufei Gao, Zehua Ma, Xiaodan Liang
Abstract: Image-based 3D Virtual Try-ON (VTON) aims to sculpt the 3D human according to person and clothes images, which is data-efficient (i.e., getting rid of expensive 3D data) but challenging. Recent text-to-3D methods achieve remarkable improvement in high-fidelity 3D human generation, demonstrating its potential for 3D virtual try-on. Inspired by the impressive success of personalized diffusion models (e.g., Dreambooth and LoRA) for 2D VTON, it is straightforward to achieve 3D VTON by integrating the personalization technique into the diffusion-based text-to-3D framework. However, employing the personalized module in a pre-trained diffusion model (e.g., StableDiffusion (SD)) would degrade the model's capability for multi-view or multi-domain synthesis, which is detrimental to the geometry and texture optimization guided by Score Distillation Sampling (SDS) loss. In this work, we propose a novel customizing 3D human try-on model, named \textbf{DreamVTON}, to separately optimize the geometry and texture of the 3D human. Specifically, a personalized SD with multi-concept LoRA is proposed to provide the generative prior about the specific person and clothes, while a Densepose-guided ControlNet is exploited to guarantee consistent prior about body pose across various camera views. Besides, to avoid the inconsistent multi-view priors from the personalized SD dominating the optimization, DreamVTON introduces a template-based optimization mechanism, which employs mask templates for geometry shape learning and normal/RGB templates for geometry/texture details learning. Furthermore, for the geometry optimization phase, DreamVTON integrates a normal-style LoRA into personalized SD to enhance normal map generative prior, facilitating smooth geometry modeling.
Authors: Habib Hajimolahoseini, Walid Ahmed, Austin Wen, Yang Liu
Abstract: In this paper, we present a comprehensive study and propose several novel techniques for implementing 3D convolutional blocks using 2D and/or 1D convolutions with only 4D and/or 3D tensors. Our motivation is that 3D convolutions with 5D tensors are computationally very expensive and they may not be supported by some of the edge devices used in real-time applications such as robots. The existing approaches mitigate this by splitting the 3D kernels into spatial and temporal domains, but they still use 3D convolutions with 5D tensors in their implementations. We resolve this issue by introducing some appropriate 4D/3D tensor reshaping as well as new combination techniques for spatial and temporal splits. The proposed implementation methods show significant improvement both in terms of efficiency and accuracy. The experimental results confirm that the proposed spatio-temporal processing structure outperforms the original model in terms of speed and accuracy using only 4D tensors with fewer parameters.
Authors: Aristeidis Panos, Rahaf Aljundi, Daniel Olmeda Reino, Richard E Turner
Abstract: Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained and frozen vision encoders (such as CLIP). Despite CLIP's robustness across diverse domains, it still exhibits non-negligible image understanding errors. These errors propagate to the VLM responses, resulting in sub-optimal performance. In our work, we propose an efficient and robust method for updating vision encoders within VLMs. Our approach selectively and locally updates encoders, leading to substantial performance improvements on data where previous mistakes occurred, while maintaining overall robustness. Furthermore, we demonstrate the effectiveness of our method during continual few-shot updates. Theoretical grounding, generality, and computational efficiency characterize our approach.
Authors: Qizhi Xie, Kun Yuan, Yunpeng Qu, Mingda Wu, Ming Sun, Chao Zhou, Jihong Zhu
Abstract: Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms of generalization. Although masked image modeling (MIM) has achieved noteworthy advancements across various high-level tasks (e.g., classification, detection etc.). In this work, we take on a novel perspective to investigate its capabilities in terms of quality- and aesthetics-awareness. To this end, we propose Quality- and aesthetics-aware pretraining (QPT V2), the first pretraining framework based on MIM that offers a unified solution to quality and aesthetics assessment. To perceive the high-level semantics and fine-grained details, pretraining data is curated. To comprehensively encompass quality- and aesthetics-related factors, degradation is introduced. To capture multi-scale quality and aesthetic information, model structure is modified. Extensive experimental results on 11 downstream benchmarks clearly show the superior performance of QPT V2 in comparison with current state-of-the-art approaches and other pretraining paradigms. Code and models will be released at \url{https://github.com/KeiChiTse/QPT-V2}.
Authors: Liyun Zhang
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable multimodal emotion recognition capabilities, integrating multimodal cues from visual, acoustic, and linguistic contexts in the video to recognize human emotional states. However, existing methods ignore capturing local facial features of temporal dynamics of micro-expressions and do not leverage the contextual dependencies of the utterance-aware temporal segments in the video, thereby limiting their expected effectiveness to a certain extent. In this work, we propose MicroEmo, a time-sensitive MLLM aimed at directing attention to the local facial micro-expression dynamics and the contextual dependencies of utterance-aware video clips. Our model incorporates two key architectural contributions: (1) a global-local attention visual encoder that integrates global frame-level timestamp-bound image features with local facial features of temporal dynamics of micro-expressions; (2) an utterance-aware video Q-Former that captures multi-scale and contextual dependencies by generating visual token sequences for each utterance segment and for the entire video then combining them. Preliminary qualitative experiments demonstrate that in a new Explainable Multimodal Emotion Recognition (EMER) task that exploits multi-modal and multi-faceted clues to predict emotions in an open-vocabulary (OV) manner, MicroEmo demonstrates its effectiveness compared with the latest methods.
Authors: Weiming Zhuang, Jian Xu, Chen Chen, Jingtao Li, Lingjuan Lyu
Abstract: We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize into three levels: task, data, and model. At the task level, COALA extends support from simple classification to 15 computer vision tasks, including object detection, segmentation, pose estimation, and more. It also facilitates federated multiple-task learning, allowing clients to tackle multiple tasks simultaneously. At the data level, COALA goes beyond supervised FL to benchmark both semi-supervised FL and unsupervised FL. It also benchmarks feature distribution shifts other than commonly considered label distribution shifts. In addition to dealing with static data, it supports federated continual learning for continuously changing data in real-world scenarios. At the model level, COALA benchmarks FL with split models and different models in different clients. COALA platform offers three degrees of customization for these practical FL scenarios, including configuration customization, components customization, and workflow customization. We conduct systematic benchmarking experiments for the practical FL scenarios and highlight potential opportunities for further advancements in FL. Codes are open sourced at https://github.com/SonyResearch/COALA.
Authors: Xiangmin Xu, Zhen Meng, Yichi Zhang, Changyang She, Philip G. Zhao
Abstract: Real-time three-dimensional (3D) scene representations serve as one of the building blocks that bolster various innovative applications, e.g., digital manufacturing, Virtual/Augmented/Extended/Mixed Reality (VR/AR/XR/MR), and the metaverse. Despite substantial efforts that have been made to real-time communications and computing, real-time 3D scene representations remain a challenging task. This paper investigates the tradeoff between timeliness and fidelity in real-time 3D scene representations. Specifically, we establish a framework to evaluate the impact of communication delay on the tradeoff, where the real-world scenario is monitored by multiple cameras that communicate with an edge server. To improve fidelity for 3D scene representations, we propose to use a single-step Proximal Policy Optimization (PPO) method that leverages the Age of Information (AoI) to decide if the received image needs to be involved in 3D scene representations and rendering. We test our framework and the proposed approach with different well-known 3D scene representation methods. Simulation results reveal that real-time 3D scene representation can be sensitively affected by communication delay, and our proposed method can achieve optimal 3D scene representation results.
Authors: Xi Shi, Lingli Chen, Peng Wei, Xi Wu, Tian Jiang, Yonggang Luo, Lecheng Xie
Abstract: Existing Gaussian splatting methods struggle to achieve satisfactory novel view synthesis in driving scenes due to the lack of crafty design and geometric constraints of related elements. This paper introduces a novel method called Decoupled Hybrid Gaussian Splatting (DHGS), which aims at promoting the rendering quality of novel view synthesis for driving scenes. The novelty of this work lies in the decoupled and hybrid pixel-level blender for road and non-road layers, without conventional unified differentiable rendering logic for the entire scene, meanwhile maintaining consistent and continuous superimposition through the proposed depth-ordered rendering strategy. Beyond that, an implicit road representation comprised of Signed Distance Field (SDF) is trained to supervise the road surface with subtle geometric attributes. Accompanied by the use of auxiliary transmittance loss and consistency loss, novel images with imperceptible boundary and elevated fidelity are ultimately obtained. Substantial experiments on Waymo dataset prove that DHGS outperforms the state-of-the-art methods.
Authors: Peiwen Sun, Honggang Zhang, Di Hu
Abstract: Community researchers have developed a range of advanced audio-visual segmentation models aimed at improving the quality of sounding objects' masks. While masks created by these models may initially appear plausible, they occasionally exhibit anomalies with incorrect grounding logic. We attribute this to real-world inherent preferences and distributions as a simpler signal for learning than the complex audio-visual grounding, which leads to the disregard of important modality information. Generally, the anomalous phenomena are often complex and cannot be directly observed systematically. In this study, we made a pioneering effort with the proper synthetic data to categorize and analyze phenomena as two types "audio priming bias" and "visual prior" according to the source of anomalies. For audio priming bias, to enhance audio sensitivity to different intensities and semantics, a perception module specifically for audio perceives the latent semantic information and incorporates information into a limited set of queries, namely active queries. Moreover, the interaction mechanism related to such active queries in the transformer decoder is customized to adapt to the need for interaction regulating among audio semantics. For visual prior, multiple contrastive training strategies are explored to optimize the model by incorporating a biased branch, without even changing the structure of the model. During experiments, observation demonstrates the presence and the impact that has been produced by the biases of the existing model. Finally, through experimental evaluation of AVS benchmarks, we demonstrate the effectiveness of our methods in handling both types of biases, achieving competitive performance across all three subsets.
Authors: Anam Manzoor, Aryan Singh, Ganesh Sistu, Reenu Mohandas, Eoin Grua, Anthony Scanlan, Ciar\'an Eising
Abstract: This study investigates the effectiveness of modern Deformable Convolutional Neural Networks (DCNNs) for semantic segmentation tasks, particularly in autonomous driving scenarios with fisheye images. These images, providing a wide field of view, pose unique challenges for extracting spatial and geometric information due to dynamic changes in object attributes. Our experiments focus on segmenting the WoodScape fisheye image dataset into ten distinct classes, assessing the Deformable Networks' ability to capture intricate spatial relationships and improve segmentation accuracy. Additionally, we explore different loss functions to address class imbalance issues and compare the performance of conventional CNN architectures with Deformable Convolution-based CNNs, including Vanilla U-Net and Residual U-Net architectures. The significant improvement in mIoU score resulting from integrating Deformable CNNs demonstrates their effectiveness in handling the geometric distortions present in fisheye imagery, exceeding the performance of traditional CNN architectures. This underscores the significant role of Deformable convolution in enhancing semantic segmentation performance for fisheye imagery.
Authors: Maciej Chrabaszcz, Hubert Baniecki, Piotr Komorowski, Szymon P{\l}otka, Przemyslaw Biecek
Abstract: Analysis of 3D segmentation models, especially in the context of medical imaging, is often limited to segmentation performance metrics that overlook the crucial aspect of explainability and bias. Currently, effectively explaining these models with saliency maps is challenging due to the high dimensions of input images multiplied by the ever-growing number of segmented class labels. To this end, we introduce Agg^2Exp, a methodology for aggregating fine-grained voxel attributions of the segmentation model's predictions. Unlike classical explanation methods that primarily focus on the local feature attribution, Agg^2Exp enables a more comprehensive global view on the importance of predicted segments in 3D images. Our benchmarking experiments show that gradient-based voxel attributions are more faithful to the model's predictions than perturbation-based explanations. As a concrete use-case, we apply Agg^2Exp to discover knowledge acquired by the Swin UNEt TRansformer model trained on the TotalSegmentator v2 dataset for segmenting anatomical structures in computed tomography medical images. Agg^2Exp facilitates the explanatory analysis of large segmentation models beyond their predictive performance.
Authors: Canyu Zhao, Mingyu Liu, Wen Wang, Jianlong Yuan, Hao Chen, Bo Zhang, Chunhua Shen
Abstract: Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended periods, which is essential for long-form video production like movies. We propose MovieDreamer, a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering to pioneer long-duration video generation with intricate plot progressions and high visual fidelity. Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering. This method is akin to traditional movie production processes, where complex stories are factorized down into manageable scene capturing. Further, we employ a multimodal script that enriches scene descriptions with detailed character information and visual style, enhancing continuity and character identity across scenes. We present extensive experiments across various movie genres, demonstrating that our approach not only achieves superior visual and narrative quality but also effectively extends the duration of generated content significantly beyond current capabilities. Homepage: https://aim-uofa.github.io/MovieDreamer/.
Authors: Thomas Hummel, Shyamgopal Karthik, Mariana-Iuliana Georgescu, Zeynep Akata
Abstract: In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this challenging task, the first step is to acquire large-scale training datasets and collect high-quality benchmarks for evaluation. In this work, we introduce EgoCVR, a new evaluation benchmark for fine-grained Composed Video Retrieval using large-scale egocentric video datasets. EgoCVR consists of 2,295 queries that specifically focus on high-quality temporal video understanding. We find that existing Composed Video Retrieval frameworks do not achieve the necessary high-quality temporal video understanding for this task. To address this shortcoming, we adapt a simple training-free method, propose a generic re-ranking framework for Composed Video Retrieval, and demonstrate that this achieves strong results on EgoCVR. Our code and benchmark are freely available at https://github.com/ExplainableML/EgoCVR.
Authors: Khadija Iddrisu, Waseem Shariff, Suzanne Little
Abstract: Saccades are extremely rapid movements of both eyes that occur simultaneously, typically observed when an individual shifts their focus from one object to another. These movements are among the swiftest produced by humans and possess the potential to achieve velocities greater than that of blinks. The peak angular speed of the eye during a saccade can reach as high as 700{\deg}/s in humans, especially during larger saccades that cover a visual angle of 25{\deg}. Previous research has demonstrated encouraging outcomes in comprehending neurological conditions through the study of saccades. A necessary step in saccade detection involves accurately identifying the precise location of the pupil within the eye, from which additional information such as gaze angles can be inferred. Conventional frame-based cameras often struggle with the high temporal precision necessary for tracking very fast movements, resulting in motion blur and latency issues. Event cameras, on the other hand, offer a promising alternative by recording changes in the visual scene asynchronously and providing high temporal resolution and low latency. By bridging the gap between traditional computer vision and event-based vision, we present events as frames that can be readily utilized by standard deep learning algorithms. This approach harnesses YOLOv8, a state-of-the-art object detection technology, to process these frames for pupil tracking using the publicly accessible Ev-Eye dataset. Experimental results demonstrate the framework's effectiveness, highlighting its potential applications in neuroscience, ophthalmology, and human-computer interaction.
Authors: Yuyan Bu, Qiang Sheng, Juan Cao, Peng Qi, Danding Wang, Jintao Li
Abstract: As short-form video-sharing platforms become a significant channel for news consumption, fake news in short videos has emerged as a serious threat in the online information ecosystem, making developing detection methods for this new scenario an urgent need. Compared with that in text and image formats, fake news on short video platforms contains rich but heterogeneous information in various modalities, posing a challenge to effective feature utilization. Unlike existing works mostly focusing on analyzing what is presented, we introduce a novel perspective that considers how it might be created. Through the lens of the creative process behind news video production, our empirical analysis uncovers the unique characteristics of fake news videos in material selection and editing. Based on the obtained insights, we design FakingRecipe, a creative process-aware model for detecting fake news short videos. It captures the fake news preferences in material selection from sentimental and semantic aspects and considers the traits of material editing from spatial and temporal aspects. To improve evaluation comprehensiveness, we first construct FakeTT, an English dataset for this task, and conduct experiments on both FakeTT and the existing Chinese FakeSV dataset. The results show FakingRecipe's superiority in detecting fake news on short video platforms.
Authors: Pengfei Chen, Lingxi Xie, Xinyue Huo, Xuehui Yu, Xiaopeng Zhang, Yingfei Sun, Zhenjun Han, Qi Tian
Abstract: The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. This paper presents SAM-CP, a simple approach that establishes two types of composable prompts beyond SAM and composes them for versatile segmentation. Specifically, given a set of classes (in texts) and a set of SAM patches, the Type-I prompt judges whether a SAM patch aligns with a text label, and the Type-II prompt judges whether two SAM patches with the same text label also belong to the same instance. To decrease the complexity in dealing with a large number of semantic classes and patches, we establish a unified framework that calculates the affinity between (semantic and instance) queries and SAM patches and merges patches with high affinity to the query. Experiments show that SAM-CP achieves semantic, instance, and panoptic segmentation in both open and closed domains. In particular, it achieves state-of-the-art performance in open-vocabulary segmentation. Our research offers a novel and generalized methodology for equipping vision foundation models like SAM with multi-grained semantic perception abilities.
Authors: Junyi Li, Junfeng Wu, Weizhi Zhao, Song Bai, Xiang Bai
Abstract: We present PartGLEE, a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, PartGLEE accomplishes detection, segmentation, and grounding of instances at any granularity in the open world scenario. Specifically, we propose a Q-Former to construct the hierarchical relationship between objects and parts, parsing every object into corresponding semantic parts. By incorporating a large amount of object-level data, the hierarchical relationships can be extended, enabling PartGLEE to recognize a rich variety of parts. We conduct comprehensive studies to validate the effectiveness of our method, PartGLEE achieves the state-of-the-art performance across various part-level tasks and obtain competitive results on object-level tasks. The proposed PartGLEE significantly enhances hierarchical modeling capabilities and part-level perception over our previous GLEE model. Further analysis indicates that the hierarchical cognitive ability of PartGLEE is able to facilitate a detailed comprehension in images for mLLMs. The model and code will be released at https://provencestar.github.io/PartGLEE-Vision/ .
Authors: Wenxuan Li, Chongyu Qu, Xiaoxi Chen, Pedro R. A. S. Bassi, Yijia Shi, Yuxiang Lai, Qian Yu, Huimin Xue, Yixiong Chen, Xiaorui Lin, Yutong Tang, Yining Cao, Haoqi Han, Zheyuan Zhang, Jiawei Liu, Tiezheng Zhang, Yujiu Ma, Jincheng Wang, Guang Zhang, Alan Yuille, Zongwei Zhou
Abstract: We introduce the largest abdominal CT dataset (termed AbdomenAtlas) of 20,460 three-dimensional CT volumes sourced from 112 hospitals across diverse populations, geographies, and facilities. AbdomenAtlas provides 673K high-quality masks of anatomical structures in the abdominal region annotated by a team of 10 radiologists with the help of AI algorithms. We start by having expert radiologists manually annotate 22 anatomical structures in 5,246 CT volumes. Following this, a semi-automatic annotation procedure is performed for the remaining CT volumes, where radiologists revise the annotations predicted by AI, and in turn, AI improves its predictions by learning from revised annotations. Such a large-scale, detailed-annotated, and multi-center dataset is needed for two reasons. Firstly, AbdomenAtlas provides important resources for AI development at scale, branded as large pre-trained models, which can alleviate the annotation workload of expert radiologists to transfer to broader clinical applications. Secondly, AbdomenAtlas establishes a large-scale benchmark for evaluating AI algorithms -- the more data we use to test the algorithms, the better we can guarantee reliable performance in complex clinical scenarios. An ISBI & MICCAI challenge named BodyMaps: Towards 3D Atlas of Human Body was launched using a subset of our AbdomenAtlas, aiming to stimulate AI innovation and to benchmark segmentation accuracy, inference efficiency, and domain generalizability. We hope our AbdomenAtlas can set the stage for larger-scale clinical trials and offer exceptional opportunities to practitioners in the medical imaging community. Codes, models, and datasets are available at https://www.zongweiz.com/dataset
Authors: Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi
Abstract: We present a novel approach designed to address the complexities posed by challenging, out-of-distribution data in the single-image depth estimation task. Starting with images that facilitate depth prediction due to the absence of unfavorable factors, we systematically generate new, user-defined scenes with a comprehensive set of challenges and associated depth information. This is achieved by leveraging cutting-edge text-to-image diffusion models with depth-aware control, known for synthesizing high-quality image content from textual prompts while preserving the coherence of 3D structure between generated and source imagery. Subsequent fine-tuning of any monocular depth network is carried out through a self-distillation protocol that takes into account images generated using our strategy and its own depth predictions on simple, unchallenging scenes. Experiments on benchmarks tailored for our purposes demonstrate the effectiveness and versatility of our proposal.
Authors: Chenyu Zhang, Mingwang Hu, Wenhui Li, Lanjun Wang
Abstract: Recently, the text-to-image diffusion model has gained considerable attention from the community due to its exceptional image generation capability. A representative model, Stable Diffusion, amassed more than 10 million users within just two months of its release. This surge in popularity has facilitated studies on the robustness and safety of the model, leading to the proposal of various adversarial attack methods. Simultaneously, there has been a marked increase in research focused on defense methods to improve the robustness and safety of these models. In this survey, we provide a comprehensive review of the literature on adversarial attacks and defenses targeting text-to-image diffusion models. We begin with an overview of text-to-image diffusion models, followed by an introduction to a taxonomy of adversarial attacks and an in-depth review of existing attack methods. We then present a detailed analysis of current defense methods that improve model robustness and safety. Finally, we discuss ongoing challenges and explore promising future research directions. For a complete list of the adversarial attack and defense methods covered in this survey, please refer to our curated repository at https://github.com/datar001/Awesome-AD-on-T2IDM.
Authors: Honggui Li, Sinan Chen, Nahid Md Lokman Hossain, Maria Trocan, Beata Mikovicova, Muhammad Fahimullah, Dimitri Galayko, Mohamad Sawan
Abstract: Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC dramatically degraded. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the theory of automatic control, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Talor series expansion. The proposed CIC method possesses the property of Post-Training and plug-and-play which can be built on any existing advanced SIC methods. Experimental results on five public image compression datasets demonstrate that the proposed CIC outperforms five open-source state-of-the-art competing SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns.
Authors: Kamil Adamczewski, Yawei Li, Luc van Gool
Abstract: Neural network pruning is a rich field with a variety of approaches. In this work, we propose to connect the existing pruning concepts such as leave-one-out pruning and oracle pruning and develop them into a more general Shapley value-based framework that targets the compression of convolutional neural networks. To allow for practical applications in utilizing the Shapley value, this work presents the Shapley value approximations, and performs the comparative analysis in terms of cost-benefit utility for the neural network compression. The proposed ranks are evaluated against a new benchmark, Oracle rank, constructed based on oracle sets. The broad experiments show that the proposed normative ranking and its approximations show practical results, obtaining state-of-the-art network compression.
Authors: Mathieu Labb\'e, Fran\c{c}ois Michaud
Abstract: Loop closure detection is the process involved when trying to find a match between the current and a previously visited locations in SLAM. Over time, the amount of time required to process new observations increases with the size of the internal map, which may influence real-time processing. In this paper, we present a novel real-time loop closure detection approach for large-scale and long-term SLAM. Our approach is based on a memory management method that keeps computation time for each new observation under a fixed limit. Results demonstrate the approach's adaptability and scalability using four standard data sets.
Authors: Aur\'elien Bourquard, Jeff Yan
Abstract: Developed at MIT CSAIL, the Wallcamera has captivated the public's imagination. Here, we show that the key insight underlying the Wallcamera is the same one that underpins the concept and the prototype of differential imaging forensics (DIF), both of which were validated and reported several years prior to the Wallcamera's debut. Rather than being the first to extract and amplify invisible signals -- aka latent evidence in the forensics context -- from wall reflections in a video, or the first to propose activity recognition following that approach, the Wallcamera's actual innovation is achieving activity recognition at a finer granularity than DIF demonstrated. In addition to activity recognition, DIF as conceived has a number of other applications in forensics, including 1) the recovery of a photographer's personal identifiable information such as body width, height, and even the color of their clothing, from a single photo, and 2) the detection of image tampering and deepfake videos.
Authors: Jia Shi, Gautam Gare, Jinjin Tian, Siqi Chai, Zhiqiu Lin, Arun Vasudevan, Di Feng, Francesco Ferroni, Shu Kong
Abstract: We tackle the challenge of predicting models' Out-of-Distribution (OOD) performance using in-distribution (ID) measurements without requiring OOD data. Existing evaluations with "Effective Robustness", which use ID accuracy as an indicator of OOD accuracy, encounter limitations when models are trained with diverse supervision and distributions, such as class labels (Vision Models, VMs, on ImageNet) and textual descriptions (Visual-Language Models, VLMs, on LAION). VLMs often generalize better to OOD data than VMs despite having similar or lower ID performance. To improve the prediction of models' OOD performance from ID measurements, we introduce the Lowest Common Ancestor (LCA)-on-the-Line framework. This approach revisits the established concept of LCA distance, which measures the hierarchical distance between labels and predictions within a predefined class hierarchy, such as WordNet. We assess 75 models using ImageNet as the ID dataset and five significantly shifted OOD variants, uncovering a strong linear correlation between ID LCA distance and OOD top-1 accuracy. Our method provides a compelling alternative for understanding why VLMs tend to generalize better. Additionally, we propose a technique to construct a taxonomic hierarchy on any dataset using K-means clustering, demonstrating that LCA distance is robust to the constructed taxonomic hierarchy. Moreover, we demonstrate that aligning model predictions with class taxonomies, through soft labels or prompt engineering, can enhance model generalization. Open source code in our Project Page: https://elvishelvis.github.io/papers/lca/.
Authors: Renming Huang, Yunqiang Pei, Guoqing Wang, Yangming Zhang, Yang Yang, Peng Wang, Hengtao Shen
Abstract: Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes they require. In this paper, we address this problem by decomposing the sampling process of diffusion models into two decoupled subprocesses: 1) generating a feasible trajectory, which is a time-consuming process, and 2) optimizing the trajectory. With this decomposition approach, we are able to partially separate efficiency and quality factors, enabling us to simultaneously gain efficiency advantages and ensure quality assurance. We propose the Trajectory Diffuser, which utilizes a faster autoregressive model to handle the generation of feasible trajectories while retaining the trajectory optimization process of diffusion models. This allows us to achieve more efficient planning without sacrificing capability. To evaluate the effectiveness and efficiency of the Trajectory Diffuser, we conduct experiments on the D4RL benchmarks. The results demonstrate that our method achieves $\it 3$-$\it 10 \times$ faster inference speed compared to previous sequence modeling methods, while also outperforming them in terms of overall performance. https://github.com/RenMing-Huang/TrajectoryDiffuser Keywords: Reinforcement Learning and Efficient Planning and Diffusion Model
Authors: Dipika Khullar, Emmett Goodman, Negin Sokhandan
Abstract: Through a simple multiple choice language prompt a VQA model can operate as a zero-shot image classifier, producing a classification label. Compared to typical image encoders, VQA models offer an advantage: VQA-produced image embeddings can be infused with the most relevant visual information through tailored language prompts. Nevertheless, for most tasks, zero-shot VQA performance is lacking, either because of unfamiliar category names, or dissimilar pre-training data and test data distributions. We propose a simple method to boost VQA performance for image classification using only a handful of labeled examples and a multiple-choice question. This few-shot method is training-free and maintains the dynamic and flexible advantages of the VQA model. Rather than relying on the final language output, our approach uses multiple-choice questions to extract prompt-specific latent representations, which are enriched with relevant visual information. These representations are combined to create a final overall image embedding, which is decoded via reference to latent class prototypes constructed from the few labeled examples. We demonstrate this method outperforms both pure visual encoders and zero-shot VQA baselines to achieve impressive performance on common few-shot tasks including MiniImageNet, Caltech-UCSD Birds, and CIFAR-100. Finally, we show our approach does particularly well in settings with numerous diverse visual attributes such as the fabric, article-style, texture, and view of different articles of clothing, where other few-shot approaches struggle, as we can tailor our image representations only on the semantic features of interest.
Authors: Tao Zhan, Yuanyuan Zhu, Jie Lan, Qianlong Dang
Abstract: In the remote sensing community, multimodal change detection (MCD) is particularly critical due to its ability to track changes across different imaging conditions and sensor types, making it highly applicable to a wide range of real-world scenarios. This paper focuses on addressing the challenges of MCD, especially the difficulty in comparing images from different sensors with varying styles and statistical characteristics of geospatial objects. Traditional MCD methods often struggle with these variations, leading to inaccurate and unreliable results. To overcome these limitations, a novel unsupervised cross-domain separable translation network (CSTN) is proposed, which uniquely integrates a within-domain self-reconstruction and a cross-domain image translation and cycle-reconstruction workflow with change detection constraints. The model is optimized by implementing both the tasks of image translation and MCD simultaneously, thereby guaranteeing the comparability of learned features from multimodal images. Specifically, a simple yet efficient dual-branch convolutional architecture is employed to separate the content and style information of multimodal images. This process generates a style-independent content-comparable feature space, which is crucial for achieving accurate change detection even in the presence of significant sensor variations. Extensive experimental results demonstrate the effectiveness of the proposed method, showing remarkable improvements over state-of-the-art approaches in terms of accuracy and efficacy for MCD. The implementation of our method will be publicly available at \url{https://github.com/OMEGA-RS/CSTN}
Authors: Xingli Fang, Jung-Eun Kim
Abstract: The privacy-preserving approaches to machine learning (ML) models have made substantial progress in recent years. However, it is still opaque in which circumstances and conditions the model becomes privacy-vulnerable, leading to a challenge for ML models to maintain both performance and privacy. In this paper, we first explore the disparity between member and non-member data in the representation of models under common training frameworks. We identify how the representation magnitude disparity correlates with privacy vulnerability and address how this correlation impacts privacy vulnerability. Based on the observations, we propose Saturn Ring Classifier Module (SRCM), a plug-in model-level solution to mitigate membership privacy leakage. Through a confined yet effective representation space, our approach ameliorates models' privacy vulnerability while maintaining generalizability. The code of this work can be found here: \url{https://github.com/JEKimLab/AIES2024_SRCM}
Authors: Liheng Jiang, Xuechun yang, Chang Yu, Zhizhong Wu, Yuting Wang
Abstract: Trauma is a significant cause of mortality and disability, particularly among individuals under forty. Traditional diagnostic methods for traumatic injuries, such as X-rays, CT scans, and MRI, are often time-consuming and dependent on medical expertise, which can delay critical interventions. This study explores the application of artificial intelligence (AI) and machine learning (ML) to improve the speed and accuracy of abdominal trauma diagnosis. We developed an advanced AI-based model combining 3D segmentation, 2D Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) to enhance diagnostic performance. Our model processes abdominal CT scans to provide real-time, precise assessments, thereby improving clinical decision-making and patient outcomes. Comprehensive experiments demonstrated that our approach significantly outperforms traditional diagnostic methods, as evidenced by rigorous evaluation metrics. This research sets a new benchmark for automated trauma detection, leveraging the strengths of AI and ML to revolutionize trauma care.
Authors: Hiroyuki Tokunaga, Joel Nicholls, Daria Vazhenina, Atsunori Kanemura
Abstract: By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant functions face the issue of how to represent originally high-bit input data with low-bit values. To fully quantize deep neural networks, we propose pixel embedding, which replaces each float-valued input pixel with a vector of quantized values by using a lookup table. The lookup table or low-bit representation of pixels is differentiable and trainable by backpropagation. Such replacement of inputs with vectors is similar to word embedding in the natural language processing field. Experiments on ImageNet and CIFAR-100 show that pixel embedding reduces the top-5 error gap caused by quantizing the floating points at the first layer to only 1% for the ImageNet dataset, and the top-1 error gap caused by quantizing first and last layers to slightly over 1% for the CIFAR-100 dataset. The usefulness of pixel embedding is further demonstrated by inference time measurements, which demonstrate over 1.7 times speedup compared to floating point precision first layer.
Authors: Romeo Valentin, Sydney M. Katz, Joonghyun Lee, Don Walker, Matthew Sorgenfrei, Mykel J. Kochenderfer
Abstract: This paper addresses the challenge of probabilistic parameter estimation given measurement uncertainty in real-time. We provide a general formulation and apply this to pose estimation for an autonomous visual landing system. We present three probabilistic parameter estimators: a least-squares sampling approach, a linear approximation method, and a probabilistic programming estimator. To evaluate these estimators, we introduce novel closed-form expressions for measuring calibration and sharpness specifically for multivariate normal distributions. Our experimental study compares the three estimators under various noise conditions. We demonstrate that the linear approximation estimator can produce sharp and well-calibrated pose predictions significantly faster than the other methods but may yield overconfident predictions in certain scenarios. Additionally, we demonstrate that these estimators can be integrated with a Kalman filter for continuous pose estimation during a runway approach where we observe a 50\% improvement in sharpness while maintaining marginal calibration. This work contributes to the integration of data-driven computer vision models into complex safety-critical aircraft systems and provides a foundation for developing rigorous certification guidelines for such systems.
Authors: Jingyun Sun, Chengxiao Dai, Zhongze Luo, Yangbo Chang, Yang Li
Abstract: Large Language Models (LLMs) demonstrate substantial potential in delivering legal consultation services to users without a legal background, attributed to their superior text comprehension and generation capabilities. Nonetheless, existing Chinese legal LLMs limit interaction to a single model-user dialogue, unlike the collaborative consultations typical of law firms, where multiple staff members contribute to a single consultation. This limitation prevents an authentic consultation experience. Additionally, extant Chinese legal LLMs suffer from critical limitations: (1) insufficient control over the quality of instruction fine-tuning data; (2) increased model hallucination resulting from users' ambiguous queries; and (3) a reduction in the model's ability to follow instructions over multiple dialogue turns. In response to these challenges, we propose a novel legal dialogue framework that leverages the collaborative capabilities of multiple LLM agents, termed LawLuo. This framework encompasses four agents: a receptionist, a lawyer, a secretary, and a boss, each responsible for different functionalities, collaboratively providing a comprehensive legal consultation to users. Additionally, we constructed two high-quality legal dialogue datasets, KINLED and MURLED, and fine-tuned ChatGLM-3-6b using these datasets. We propose a legal query clarification algorithm called ToLC. Experimental results demonstrate that LawLuo outperforms baseline LLMs, including GPT-4, across three dimensions: lawyer-like language style, the usefulness of legal advice, and the accuracy of legal knowledge. Our code and datasets are available at https://github.com/NEFUJing/LawLuo.
Authors: Ioannis A. Vezakis, Konstantinos Georgas, Dimitrios Fotiadis, George K. Matsopoulos
Abstract: This work introduces EffiSegNet, a novel segmentation framework leveraging transfer learning with a pre-trained Convolutional Neural Network (CNN) classifier as its backbone. Deviating from traditional architectures with a symmetric U-shape, EffiSegNet simplifies the decoder and utilizes full-scale feature fusion to minimize computational cost and the number of parameters. We evaluated our model on the gastrointestinal polyp segmentation task using the publicly available Kvasir-SEG dataset, achieving state-of-the-art results. Specifically, the EffiSegNet-B4 network variant achieved an F1 score of 0.9552, mean Dice (mDice) 0.9483, mean Intersection over Union (mIoU) 0.9056, Precision 0.9679, and Recall 0.9429 with a pre-trained backbone - to the best of our knowledge, the highest reported scores in the literature for this dataset. Additional training from scratch also demonstrated exceptional performance compared to previous work, achieving an F1 score of 0.9286, mDice 0.9207, mIoU 0.8668, Precision 0.9311 and Recall 0.9262. These results underscore the importance of a well-designed encoder in image segmentation networks and the effectiveness of transfer learning approaches.
Authors: Andrea Moglia, Matteo Cavicchioli, Luca Mainardi, Pietro Cerveri
Abstract: Pancreas segmentation has been traditionally challenging due to its small size in computed tomography abdominal volumes, high variability of shape and positions among patients, and blurred boundaries due to low contrast between the pancreas and surrounding organs. Many deep learning models for pancreas segmentation have been proposed in the past few years. We present a thorough systematic review based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement. The literature search was conducted on PubMed, Web of Science, Scopus, and IEEE Xplore on original studies published in peer-reviewed journals from 2013 to 2023. Overall, 130 studies were retrieved. We initially provided an overview of the technical background of the most common network architectures and publicly available datasets. Then, the analysis of the studies combining visual presentation in tabular form and text description was reported. The tables grouped the studies specifying the application, dataset size, design (model architecture, learning strategy, and loss function), results, and main contributions. We first analyzed the studies focusing on parenchyma segmentation using coarse-to-fine approaches, multi-organ segmentation, semi-supervised learning, and unsupervised learning, followed by those studies on generalization to other datasets and those concerning the design of new loss functions. Then, we analyzed the studies on segmentation of tumors, cysts, and inflammation reporting multi-stage methods, semi-supervised learning, generalization to other datasets, and design of new loss functions. Finally, we provided a critical discussion on the subject based on the published evidence underlining current issues that need to be addressed before clinical translation.
Authors: Youqian Zhang, Chunxi Yang, Eugene Y. Fu, Qinhong Jiang, Chen Yan, Sze-Yiu Chau, Grace Ngai, Hong-Va Leong, Xiapu Luo, Wenyuan Xu
Abstract: Object detection can localize and identify objects in images, and it is extensively employed in critical multimedia applications such as security surveillance and autonomous driving. Despite the success of existing object detection models, they are often evaluated in ideal scenarios where captured images guarantee the accurate and complete representation of the detecting scenes. However, images captured by image sensors may be affected by different factors in real applications, including cyber-physical attacks. In particular, attackers can exploit hardware properties within the systems to inject electromagnetic interference so as to manipulate the images. Such attacks can cause noisy or incomplete information about the captured scene, leading to incorrect detection results, potentially granting attackers malicious control over critical functions of the systems. This paper presents a research work that comprehensively quantifies and analyzes the impacts of such attacks on state-of-the-art object detection models in practice. It also sheds light on the underlying reasons for the incorrect detection outcomes.
Authors: Maniru Ibrahim
Abstract: The growing prevalence of high-dimensional data has fostered the development of multidimensional projection (MP) techniques, such as t-SNE, UMAP, and LAMP, for data visualization and exploration. However, conventional MP methods typically employ generic quality metrics, neglecting individual user preferences. This study proposes a new framework that tailors MP techniques based on user-specific quality criteria, enhancing projection interpretability. Our approach combines three visual quality metrics, stress, neighborhood preservation, and silhouette score, to create a composite metric for a precise MP evaluation. We then optimize the projection scale by maximizing the composite metric value. We conducted an experiment involving two users with different projection preferences, generating projections using t-SNE, UMAP, and LAMP. Users rate projections according to their criteria, producing two training sets. We derive optimal weights for each set and apply them to other datasets to determine the best projections per user. Our findings demonstrate that personalized projections effectively capture user preferences, fostering better data exploration and enabling more informed decision-making. This user-centric approach promotes advancements in multidimensional projection techniques that accommodate diverse user preferences and enhance interpretability.
Authors: Deniz Daum, Richard Osuala, Anneliese Riess, Georgios Kaissis, Julia A. Schnabel, Maxime Di Folco
Abstract: Generally, the small size of public medical imaging datasets coupled with stringent privacy concerns, hampers the advancement of data-hungry deep learning models in medical imaging. This study addresses these challenges for 3D cardiac MRI images in the short-axis view. We propose Latent Diffusion Models that generate synthetic images conditioned on medical attributes, while ensuring patient privacy through differentially private model training. To our knowledge, this is the first work to apply and quantify differential privacy in 3D medical image generation. We pre-train our models on public data and finetune them with differential privacy on the UK Biobank dataset. Our experiments reveal that pre-training significantly improves model performance, achieving a Fr\'echet Inception Distance (FID) of 26.77 at $\epsilon=10$, compared to 92.52 for models without pre-training. Additionally, we explore the trade-off between privacy constraints and image quality, investigating how tighter privacy budgets affect output controllability and may lead to degraded performance. Our results demonstrate that proper consideration during training with differential privacy can substantially improve the quality of synthetic cardiac MRI images, but there are still notable challenges in achieving consistent medical realism.
Authors: Jean-Jacques Godeme, Jalal Fadili
Abstract: In this paper, we study the phase retrieval problem in the situation where the vector to be recovered has an a priori structure that can encoded into a regularization term. This regularizer is intended to promote solutions conforming to some notion of simplicity or low complexity. We investigate both noiseless recovery and stability to noise and provide a very general and unified analysis framework that goes far beyond the sparse phase retrieval mostly considered in the literature. In the noiseless case we provide sufficient conditions under which exact recovery, up to global sign change, is possible. For Gaussian measurement maps, we also provide a sample complexity bound for exact recovery. This bound depends on the Gaussian width of the descent cone at the soughtafter vector which is a geometric measure of the complexity of the latter. In the noisy case, we consider both the constrained (Mozorov) and penalized (Tikhonov) formulations. We provide sufficient conditions for stable recovery and prove linear convergence for sufficiently small noise. For Gaussian measurements, we again give a sample complexity bound for linear convergence to hold with high probability. This bound scales linearly in the intrinsic dimension of the sought-after vector but only logarithmically in the ambient dimension.
Authors: Zidian Qiu, Zongyao He, Zhi Jin
Abstract: In recent years, the field of learned video compression has witnessed rapid advancement, exemplified by the latest neural video codecs DCVC-DC that has outperformed the upcoming next-generation codec ECM in terms of compression ratio. Despite this, learned video compression frameworks often exhibit low encoding and decoding speeds primarily due to their increased computational complexity and unnecessary high-resolution spatial operations, which hugely hinder their applications in reality. In this work, we introduce an efficiency-optimized framework for learned video compression that focuses on low-resolution representation learning, aiming to significantly enhance the encoding and decoding speeds. Firstly, we diminish the computational load by reducing the resolution of inter-frame propagated features obtained from reused features of decoded frames, including I-frames. We implement a joint training strategy for both the I-frame and P-frame models, further improving the compression ratio. Secondly, our approach efficiently leverages multi-frame priors for parameter prediction, minimizing computation at the decoding end. Thirdly, we revisit the application of the Online Encoder Update (OEU) strategy for high-resolution sequences, achieving notable improvements in compression ratio without compromising decoding efficiency. Our efficiency-optimized framework has significantly improved the balance between compression ratio and speed for learned video compression. In comparison to traditional codecs, our method achieves performance levels on par with the low-decay P configuration of the H.266 reference software VTM. Furthermore, when contrasted with DCVC-HEM, our approach delivers a comparable compression ratio while boosting encoding and decoding speeds by a factor of 3 and 7, respectively. On RTX 2080Ti, our method can decode each 1080p frame under 100ms.
Authors: Junyan Wu, Wei Lu, Xiangyang Luo, Rui Yang, Qian Wang, Xiaochun Cao
Abstract: Recently, a novel form of audio partial forgery has posed challenges to its forensics, requiring advanced countermeasures to detect subtle forgery manipulations within long-duration audio. However, existing countermeasures still serve a classification purpose and fail to perform meaningful analysis of the start and end timestamps of partial forgery segments. To address this challenge, we introduce a novel coarse-to-fine proposal refinement framework (CFPRF) that incorporates a frame-level detection network (FDN) and a proposal refinement network (PRN) for audio temporal forgery detection and localization. Specifically, the FDN aims to mine informative inconsistency cues between real and fake frames to obtain discriminative features that are beneficial for roughly indicating forgery regions. The PRN is responsible for predicting confidence scores and regression offsets to refine the coarse-grained proposals derived from the FDN. To learn robust discriminative features, we devise a difference-aware feature learning (DAFL) module guided by contrastive representation learning to enlarge the sensitive differences between different frames induced by minor manipulations. We further design a boundary-aware feature enhancement (BAFE) module to capture the contextual information of multiple transition boundaries and guide the interaction between boundary information and temporal features via a cross-attention mechanism. Extensive experiments show that our CFPRF achieves state-of-the-art performance on various datasets, including LAV-DF, ASVS2019PS, and HAD.
Authors: Daniela L. Ramos, Hector J. Hortua
Abstract: Colorectal polyps are generally benign alterations that, if not identified promptly and managed successfully, can progress to cancer and cause affectations on the colon mucosa, known as adenocarcinoma. Today advances in Deep Learning have demonstrated the ability to achieve significant performance in image classification and detection in medical diagnosis applications. Nevertheless, these models are prone to overfitting, and making decisions based only on point estimations may provide incorrect predictions. Thus, to obtain a more informed decision, we must consider point estimations along with their reliable uncertainty quantification. In this paper, we built different Bayesian neural network approaches based on the flexibility of posterior distribution to develop semantic segmentation of colorectal polyp images. We found that these models not only provide state-of-the-art performance on the segmentation of this medical dataset but also, yield accurate uncertainty estimates. We applied multiplicative normalized flows(MNF) and reparameterization trick on the UNET, FPN, and LINKNET architectures tested with multiple backbones in deterministic and Bayesian versions. We report that the FPN + EfficientnetB7 architecture with MNF is the most promising option given its IOU of 0.94 and Expected Calibration Error (ECE) of 0.004, combined with its superiority in identifying difficult-to-detect colorectal polyps, which is effective in clinical areas where early detection prevents the development of colon cancer.
Authors: Haojun Yu, Youcheng Li, Nan Zhang, Zihan Niu, Xuantong Gong, Yanwen Luo, Quanlin Wu, Wangyan Qin, Mengyuan Zhou, Jie Han, Jia Tao, Ziwei Zhao, Di Dai, Di He, Dong Wang, Binghui Tang, Ling Huo, Qingli Zhu, Yong Wang, Liwei Wang
Abstract: Data-driven deep learning models have shown great capabilities to assist radiologists in breast ultrasound (US) diagnoses. However, their effectiveness is limited by the long-tail distribution of training data, which leads to inaccuracies in rare cases. In this study, we address a long-standing challenge of improving the diagnostic model performance on rare cases using long-tailed data. Specifically, we introduce a pipeline, TAILOR, that builds a knowledge-driven generative model to produce tailored synthetic data. The generative model, using 3,749 lesions as source data, can generate millions of breast-US images, especially for error-prone rare cases. The generated data can be further used to build a diagnostic model for accurate and interpretable diagnoses. In the prospective external evaluation, our diagnostic model outperforms the average performance of nine radiologists by 33.5% in specificity with the same sensitivity, improving their performance by providing predictions with an interpretable decision-making process. Moreover, on ductal carcinoma in situ (DCIS), our diagnostic model outperforms all radiologists by a large margin, with only 34 DCIS lesions in the source data. We believe that TAILOR can potentially be extended to various diseases and imaging modalities.
Authors: Seamie Hayes, Sushil Sharma, Ciar\'an Eising
Abstract: Fusing different sensor modalities can be a difficult task, particularly if they are asynchronous. Asynchronisation may arise due to long processing times or improper synchronisation during calibration, and there must exist a way to still utilise this previous information for the purpose of safe driving, and object detection in ego vehicle/ multi-agent trajectory prediction. Difficulties arise in the fact that the sensor modalities have captured information at different times and also at different positions in space. Therefore, they are not spatially nor temporally aligned. This paper will investigate the challenge of radar and LiDAR sensors being asynchronous relative to the camera sensors, for various time latencies. The spatial alignment will be resolved before lifting into BEV space via the transformation of the radar/LiDAR point clouds into the new ego frame coordinate system. Only after this can we concatenate the radar/LiDAR point cloud and lifted camera features. Temporal alignment will be remedied for radar data only, we will implement a novel method of inferring the future radar point positions using the velocity information. Our approach to resolving the issue of sensor asynchrony yields promising results. We demonstrate velocity information can drastically improve IoU for asynchronous datasets, as for a time latency of 360 milliseconds (ms), IoU improves from 49.54 to 53.63. Additionally, for a time latency of 550ms, the camera+radar (C+R) model outperforms the camera+LiDAR (C+L) model by 0.18 IoU. This is an advancement in utilising the often-neglected radar sensor modality, which is less favoured than LiDAR for autonomous driving purposes.
Authors: Jiayu Lei, Xiaoman Zhang, Chaoyi Wu, Lisong Dai, Ya Zhang, Yanyong Zhang, Yanfeng Wang, Weidi Xie, Yuehua Li
Abstract: Radiologists are tasked with interpreting a large number of images in a daily base, with the responsibility of generating corresponding reports. This demanding workload elevates the risk of human error, potentially leading to treatment delays, increased healthcare costs, revenue loss, and operational inefficiencies. To address these challenges, we initiate a series of work on grounded Automatic Report Generation (AutoRG), starting from the brain MRI interpretation system, which supports the delineation of brain structures, the localization of anomalies, and the generation of well-organized findings. We make contributions from the following aspects, first, on dataset construction, we release a comprehensive dataset encompassing segmentation masks of anomaly regions and manually authored reports, termed as RadGenome-Brain MRI. This data resource is intended to catalyze ongoing research and development in the field of AI-assisted report generation systems. Second, on system design, we propose AutoRG-Brain, the first brain MRI report generation system with pixel-level grounded visual clues. Third, for evaluation, we conduct quantitative assessments and human evaluations of brain structure segmentation, anomaly localization, and report generation tasks to provide evidence of its reliability and accuracy. This system has been integrated into real clinical scenarios, where radiologists were instructed to write reports based on our generated findings and anomaly segmentation masks. The results demonstrate that our system enhances the report-writing skills of junior doctors, aligning their performance more closely with senior doctors, thereby boosting overall productivity.
Authors: Xingjiao Wu, Luwei Xiao, Xiangcheng Du, Yingbin Zheng, Xin Li, Tianlong Ma, Cheng Jin, Liang He
Abstract: The document layout analysis (DLA) aims to decompose document images into high-level semantic areas (i.e., figures, tables, texts, and background). Creating a DLA framework with strong generalization capabilities is a challenge due to document objects are diversity in layout, size, aspect ratio, texture, etc. Many researchers devoted this challenge by synthesizing data to build large training sets. However, the synthetic training data has different styles and erratic quality. Besides, there is a large gap between the source data and the target data. In this paper, we propose an unsupervised cross-domain DLA framework based on document style guidance. We integrated the document quality assessment and the document cross-domain analysis into a unified framework. Our framework is composed of three components, Document Layout Generator (GLD), Document Elements Decorator(GED), and Document Style Discriminator(DSD). The GLD is used to document layout generates, the GED is used to document layout elements fill, and the DSD is used to document quality assessment and cross-domain guidance. First, we apply GLD to predict the positions of the generated document. Then, we design a novel algorithm based on aesthetic guidance to fill the document positions. Finally, we use contrastive learning to evaluate the quality assessment of the document. Besides, we design a new strategy to change the document quality assessment component into a document cross-domain style guide component. Our framework is an unsupervised document layout analysis framework. We have proved through numerous experiments that our proposed method has achieved remarkable performance.
Authors: Alessandro Flaborea, Guido D'Amely, Stefano D'Arrigo, Marco Aurelio Sterpa, Alessio Sampieri, Fabio Galasso
Abstract: Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex since anomalous events are rare and because it is an open set recognition task, i.e., what is anomalous at inference has not been observed at training. We propose COSKAD, a novel model that encodes skeletal human motion by a graph convolutional network and learns to COntract SKeletal kinematic embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. We propose three latent spaces: the commonly-adopted Euclidean and the novel spherical and hyperbolic. All variants outperform the state-of-the-art on the most recent UBnormal dataset, for which we contribute a human-related version with annotated skeletons. COSKAD sets a new state-of-the-art on the human-related versions of ShanghaiTech Campus and CUHK Avenue, with performance comparable to video-based methods. Source code and dataset will be released upon acceptance.
Authors: Wonwoong Cho, Hareesh Ravi, Midhun Harikumar, Vinh Khuc, Krishna Kumar Singh, Jingwan Lu, David I. Inouye, Ajinkya Kale
Abstract: As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion Models. However, how to train Diffusion Models to have the disentangled latent spaces and how to naturally incorporate the disentangled conditions during the sampling process have been underexplored. In this paper, we present a training framework for feature disentanglement of Diffusion Models (FDiff). We further propose two sampling methods that can boost the realism of our Diffusion Models and also enhance the controllability. Concisely, we train Diffusion Models conditioned on two latent features, a spatial content mask, and a flattened style embedding. We rely on the inductive bias of the denoising process of Diffusion Models to encode pose/layout information in the content feature and semantic/style information in the style feature. Regarding the sampling methods, we first generalize Composable Diffusion Models (GCDM) by breaking the conditional independence assumption to allow for some dependence between conditional inputs, which is shown to be effective in realistic generation in our experiments. Second, we propose timestep-dependent weight scheduling for content and style features to further improve the performance. We also observe better controllability of our proposed methods compared to existing methods in image manipulation and image translation.
Authors: Chencan Fu, Lin Li, Jianbiao Mei, Yukai Ma, Linpeng Peng, Xiangrui Zhao, Yong Liu
Abstract: Place recognition is a challenging but crucial task in robotics. Current description-based methods may be limited by representation capabilities, while pairwise similarity-based methods require exhaustive searches, which is time-consuming. In this paper, we present a novel coarse-to-fine approach to address these problems, which combines BEV (Bird's Eye View) feature extraction, coarse-grained matching and fine-grained verification. In the coarse stage, our approach utilizes an attention-guided network to generate attention-guided descriptors. We then employ a fast affinity-based candidate selection process to identify the Top-K most similar candidates. In the fine stage, we estimate pairwise overlap among the narrowed-down place candidates to determine the final match. Experimental results on the KITTI and KITTI-360 datasets demonstrate that our approach outperforms state-of-the-art methods. The code will be released publicly soon.
Authors: Kilian Zepf, Selma Wanna, Marco Miani, Juston Moore, Jes Frellsen, S{\o}ren Hauberg, Frederik Warburg, Aasa Feragen
Abstract: Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images. This is a common scenario in the medical domain due to variations in equipment, acquisition sites, or image corruptions. This work addresses the challenge of OOD detection by proposing Laplacian Segmentation Networks (LSN): methods which jointly model epistemic (model) and aleatoric (data) uncertainty for OOD detection. In doing so, we propose the first Laplace approximation of the weight posterior that scales to large neural networks with skip connections that have high-dimensional outputs. We demonstrate on three datasets that the LSN-modeled parameter distributions, in combination with suitable uncertainty measures, gives superior OOD detection.
Authors: Ce Zheng, Xianpeng Liu, Qucheng Peng, Tianfu Wu, Pu Wang, Chen Chen
Abstract: Human mesh recovery (HMR) provides rich human body information for various real-world applications. While image-based HMR methods have achieved impressive results, they often struggle to recover humans in dynamic scenarios, leading to temporal inconsistencies and non-smooth 3D motion predictions due to the absence of human motion. In contrast, video-based approaches leverage temporal information to mitigate this issue. In this paper, we present DiffMesh, an innovative motion-aware Diffusion-like framework for video-based HMR. DiffMesh establishes a bridge between diffusion models and human motion, efficiently generating accurate and smooth output mesh sequences by incorporating human motion within the forward process and reverse process in the diffusion model. Extensive experiments are conducted on the widely used datasets (Human3.6M \cite{h36m_pami} and 3DPW \cite{pw3d2018}), which demonstrate the effectiveness and efficiency of our DiffMesh. Visual comparisons in real-world scenarios further highlight DiffMesh's suitability for practical applications.
Authors: Chong Zhong, Yang Li, Danjuan Yang, Meiyan Li, Xingyao Zhou, Bo Fu, Catherine C. Liu, A. H. Welsh
Abstract: The ultra-widefield (UWF) fundus image is an attractive 3D biomarker in AI-aided myopia screening because it provides much richer myopia-related information. Though axial length (AL) has been acknowledged to be highly related to the two key targets of myopia screening, Spherical Equivalence (SE) measuring and high myopia diagnosis, its prediction based on the UWF fundus image is rarely considered. To save the high expense and time costs of measuring SE and AL, we propose the Copula-enhanced Convolutional Neural Network (CeCNN), a one-stop UWF-based ophthalmic AI framework to jointly predict SE, AL, and myopia status. The CeCNN formulates a multiresponse regression that relates multiple dependent discrete-continuous responses and the image covariate, where the nonlinearity of the association is modeled by a backbone CNN. To thoroughly describe the dependence structure among the responses, we model and incorporate the conditional dependence among responses in a CNN through a new copula-likelihood loss. We provide statistical interpretations of the conditional dependence among responses, and reveal that such dependence is beyond the dependence explained by the image covariate. We heuristically justify that the proposed loss can enhance the estimation efficiency of the CNN weights. We apply the CeCNN to the UWF dataset collected by us and demonstrate that the CeCNN sharply enhances the predictive capability of various backbone CNNs. Our study evidences the ophthalmology view that besides SE, AL is also an important measure to myopia.
Authors: Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu
Abstract: Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are compared by their classification accuracy on ImageNet. However, this single metric does not fully capture performance nuances critical for specialized tasks. In this work, we conduct an in-depth comparative analysis of model behaviors beyond ImageNet accuracy, for both ConvNet and Vision Transformer architectures, each across supervised and CLIP training paradigms. Although our selected models have similar ImageNet accuracies and compute requirements, we find that they differ in many other aspects: types of mistakes, output calibration, transferability, and feature invariance, among others. This diversity in model characteristics, not captured by traditional metrics, highlights the need for more nuanced analysis when choosing among different models. Our code is available at https://github.com/kirill-vish/Beyond-INet.
Authors: Haoran Li, Long Ma, Haolin Shi, Yanbin Hao, Yong Liao, Lechao Cheng, Pengyuan Zhou
Abstract: The current GAN inversion methods typically can only edit the appearance and shape of a single object and background while overlooking spatial information. In this work, we propose a 3D editing framework, 3D-GOI, to enable multifaceted editing of affine information (scale, translation, and rotation) on multiple objects. 3D-GOI realizes the complex editing function by inverting the abundance of attribute codes (object shape/appearance/scale/rotation/translation, background shape/appearance, and camera pose) controlled by GIRAFFE, a renowned 3D GAN. Accurately inverting all the codes is challenging, 3D-GOI solves this challenge following three main steps. First, we segment the objects and the background in a multi-object image. Second, we use a custom Neural Inversion Encoder to obtain coarse codes of each object. Finally, we use a round-robin optimization algorithm to get precise codes to reconstruct the image. To the best of our knowledge, 3D-GOI is the first framework to enable multifaceted editing on multiple objects. Both qualitative and quantitative experiments demonstrate that 3D-GOI holds immense potential for flexible, multifaceted editing in complex multi-object scenes.Our project and code are released at https://3d-goi.github.io .
URLs: https://3d-goi.github.io
Authors: Zuoyan Zhao, Hui Xue, Pengfei Fang, Shipeng Zhu
Abstract: Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text images, visual structure and semantic information, affect the recognition performance significantly. To mitigate the effects from these factors, this paper proposes a Prior-Enhanced Attention Network (PEAN). Specifically, an attention-based modulation module is leveraged to understand scene text images by neatly perceiving the local and global dependence of images, despite the shape of the text. Meanwhile, a diffusion-based module is developed to enhance the text prior, hence offering better guidance for the SR network to generate SR images with higher semantic accuracy. Additionally, a multi-task learning paradigm is employed to optimize the network, enabling the model to generate legible SR images. As a result, PEAN establishes new SOTA results on the TextZoom benchmark. Experiments are also conducted to analyze the importance of the enhanced text prior as a means of improving the performance of the SR network. Code is available at https://github.com/jdfxzzy/PEAN.
Authors: Junhao Zhuang, Yanhong Zeng, Wenran Liu, Chun Yuan, Kai Chen
Abstract: Advancing image inpainting is challenging as it requires filling user-specified regions for various intents, such as background filling and object synthesis. Existing approaches focus on either context-aware filling or object synthesis using text descriptions. However, achieving both tasks simultaneously is challenging due to differing training strategies. To overcome this challenge, we introduce PowerPaint, the first high-quality and versatile inpainting model that excels in multiple inpainting tasks. First, we introduce learnable task prompts along with tailored fine-tuning strategies to guide the model's focus on different inpainting targets explicitly. This enables PowerPaint to accomplish various inpainting tasks by utilizing different task prompts, resulting in state-of-the-art performance. Second, we demonstrate the versatility of the task prompt in PowerPaint by showcasing its effectiveness as a negative prompt for object removal. Moreover, we leverage prompt interpolation techniques to enable controllable shape-guided object inpainting, enhancing the model's applicability in shape-guided applications. Finally, we conduct extensive experiments and applications to verify the effectiveness of PowerPaint. We release our codes and models on our project page: https://powerpaint.github.io/.
Authors: Mingxiang Cao, Weiying Xie, Jie Lei, Jiaqing Zhang, Daixun Li, Yunsong Li
Abstract: Deep learning has driven significant progress in object detection using Synthetic Aperture Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle to effectively integrate local and global information, particularly direction-aware features. This paper proposes SAR-Net, a novel framework specifically designed for global fusion of direction-aware information in SAR object detection. SAR-Net leverages two key innovations: the Unity Compensation Mechanism (UCM) and the Direction-aware Attention Module (DAM). UCM facilitates the establishment of complementary relationships among features across different scales, enabling efficient global information fusion and transmission. Additionally, DAM, through bidirectional attention polymerization, captures direction-aware information, effectively eliminating background interference. Extensive experiments demonstrate the effectiveness of SAR-Net, achieving state-of-the-art results on aircraft (SAR-AIRcraft-1.0) and ship datasets (SSDD, HRSID), confirming its generalization capability and robustness.
Authors: Haibo Wang, Chenghang Lai, Yixuan Sun, Weifeng Ge
Abstract: Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal with VideoQA insufficiently, by simply taking uniformly sampled frames as visual inputs, which ignores question-relevant visual clues. Moreover, there are no human annotations for question-critical timestamps in existing VideoQA datasets. In light of this, we propose a novel weakly supervised framework to enforce the LMMs to reason out the answers with question-critical moments as visual inputs. Specifically, we first fuse the question and answer pairs as event descriptions to find multiple keyframes as target moments and pseudo-labels, with the visual-language alignment capability of the CLIP models. With these pseudo-labeled keyframes as additionally weak supervision, we devise a lightweight Gaussian-based Contrastive Grounding (GCG) module. GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs. Extensive experiments on several benchmarks verify the effectiveness of our framework, and we achieve substantial improvements compared to previous state-of-the-art methods.
Authors: Lingting Zhu, Zhao Wang, Jiahao Cui, Zhenchao Jin, Guying Lin, Lequan Yu
Abstract: Surgical 3D reconstruction is a critical area of research in robotic surgery, with recent works adopting variants of dynamic radiance fields to achieve success in 3D reconstruction of deformable tissues from single-viewpoint videos. However, these methods often suffer from time-consuming optimization or inferior quality, limiting their adoption in downstream tasks. Inspired by 3D Gaussian Splatting, a recent trending 3D representation, we present EndoGS, applying Gaussian Splatting for deformable endoscopic tissue reconstruction. Specifically, our approach incorporates deformation fields to handle dynamic scenes, depth-guided supervision with spatial-temporal weight masks to optimize 3D targets with tool occlusion from a single viewpoint, and surface-aligned regularization terms to capture the much better geometry. As a result, EndoGS reconstructs and renders high-quality deformable endoscopic tissues from a single-viewpoint video, estimated depth maps, and labeled tool masks. Experiments on DaVinci robotic surgery videos demonstrate that EndoGS achieves superior rendering quality. Code is available at https://github.com/HKU-MedAI/EndoGS.
Authors: Hyeonwoo Kim, Sookwan Han, Patrick Kwon, Hanbyul Joo
Abstract: Understanding the inherent human knowledge in interacting with a given environment (e.g., affordance) is essential for improving AI to better assist humans. While existing approaches primarily focus on human-object contacts during interactions, such affordance representation cannot fully address other important aspects of human-object interactions (HOIs), i.e., patterns of relative positions and orientations. In this paper, we introduce a novel affordance representation, named Comprehensive Affordance (ComA). Given a 3D object mesh, ComA models the distribution of relative orientation and proximity of vertices in interacting human meshes, capturing plausible patterns of contact, relative orientations, and spatial relationships. To construct the distribution, we present a novel pipeline that synthesizes diverse and realistic 3D HOI samples given any 3D object mesh. The pipeline leverages a pre-trained 2D inpainting diffusion model to generate HOI images from object renderings and lifts them into 3D. To avoid the generation of false affordances, we propose a new inpainting framework, Adaptive Mask Inpainting. Since ComA is built on synthetic samples, it can extend to any object in an unbounded manner. Through extensive experiments, we demonstrate that ComA outperforms competitors that rely on human annotations in modeling contact-based affordance. Importantly, we also showcase the potential of ComA to reconstruct human-object interactions in 3D through an optimization framework, highlighting its advantage in incorporating both contact and non-contact properties.
Authors: Peter H\"onig, Stefan Thalhammer, Jean-Baptiste Weibel, Matthias Hirschmanner, Markus Vincze
Abstract: Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address his issue, we propose a strategy for inducing a shape bias to CNN training. In particular, by randomizing textures applied to object surfaces during data rendering, we create training data without consistent textural cues. This methodology allows for seamless integration into existing data rendering engines, and results in negligible computational overhead for data rendering and network training. Our findings demonstrate that the shape bias we induce via randomized texturing, improves over existing approaches using style transfer. We evaluate with three detectors and two pose estimators. For the most recent object detector and for pose estimation in general, estimation accuracy improves for textureless and metallic objects. Additionally we show that our approach increases the pose estimation accuracy in the presence of image noise and strong illumination changes. Code and datasets are publicly available at github.com/hoenigpeter/randomized_texturing.
Authors: Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania
Abstract: Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the efficacy of continually learned representations, as representations are learned alongside classifiers throughout the learning process. Our primary contribution is empirically demonstrating that existing online continually trained deep networks produce inferior representations compared to a simple pre-defined random transforms. Our approach embeds raw pixels using a fixed random transform, approximating an RBF-Kernel initialized before any data is seen. We then train a simple linear classifier on top without storing any exemplars, processing one sample at a time in an online continual learning setting. This method, called RanDumb, significantly outperforms state-of-the-art continually learned representations across all standard online continual learning benchmarks. Our study reveals the significant limitations of representation learning, particularly in low-exemplar and online continual learning scenarios. Extending our investigation to popular exemplar-free scenarios with pretrained models, we find that training only a linear classifier on top of pretrained representations surpasses most continual fine-tuning and prompt-tuning strategies. Overall, our investigation challenges the prevailing assumptions about effective representation learning in online continual learning. Our code is available at://github.com/drimpossible/RanDumb.
Authors: Yutian Chen, Shi Guo, Fangzheng Yu, Feng Zhang, Jinwei Gu, Tianfan Xue
Abstract: Detecting and magnifying imperceptible high-frequency motions in real-world scenarios has substantial implications for industrial and medical applications. These motions are characterized by small amplitudes and high frequencies. Traditional motion magnification methods rely on costly high-speed cameras or active light sources, which limit the scope of their applications. In this work, we propose a dual-camera system consisting of an event camera and a conventional RGB camera for video motion magnification, providing temporally-dense information from the event stream and spatially-dense data from the RGB images. This innovative combination enables a broad and cost-effective amplification of high-frequency motions. By revisiting the physical camera model, we observe that estimating motion direction and magnitude necessitates the integration of event streams with additional image features. On this basis, we propose a novel deep network tailored for event-based motion magnification. Our approach utilizes the Second-order Recurrent Propagation module to proficiently interpolate multiple frames while addressing artifacts and distortions induced by magnified motions. Additionally, we employ a temporal filter to distinguish between noise and useful signals, thus minimizing the impact of noise. We also introduced the first event-based motion magnification dataset, which includes a synthetic subset and a real-captured subset for training and benchmarking. Through extensive experiments in magnifying small-amplitude, high-frequency motions, we demonstrate the effectiveness and accuracy of our dual-camera system and network, offering a cost-effective and flexible solution for motion detection and magnification.
Authors: Anju Rani, Daniel Ortiz-Arroyo, Petar Durdevic
Abstract: In recent years, 3D point clouds (PCs) have gained significant attention due to their diverse applications across various fields, such as computer vision (CV), condition monitoring (CM), virtual reality, robotics, autonomous driving, etc. Deep learning (DL) has proven effective in leveraging 3D PCs to address various challenges encountered in 2D vision. However, applying deep neural networks (DNNs) to process 3D PCs presents unique challenges. This paper provides an in-depth review of recent advancements in DL-based industrial CM using 3D PCs, with a specific focus on defect shape classification and segmentation within industrial applications. Recognizing the crucial role of these aspects in industrial maintenance, the paper offers insightful observations on the strengths and limitations of the reviewed DL-based PC processing methods. This knowledge synthesis aims to contribute to understanding and enhancing CM processes, particularly within the framework of remaining useful life (RUL), in industrial systems.
Authors: Yusu Qian, Haotian Zhang, Yinfei Yang, Zhe Gan
Abstract: The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the context of handling deceptive information in prompts, thus producing hallucinated responses under such conditions. To quantitatively assess this vulnerability, we present MAD-Bench, a carefully curated benchmark that contains 1000 test samples divided into 5 categories, such as non-existent objects, count of objects, and spatial relationship. We provide a comprehensive analysis of popular MLLMs, ranging from GPT-4v, Reka, Gemini-Pro, to open-sourced models, such as LLaVA-NeXT and MiniCPM-Llama3. Empirically, we observe significant performance gaps between GPT-4o and other models; and previous robust instruction-tuned models are not effective on this new benchmark. While GPT-4o achieves 82.82% accuracy on MAD-Bench, the accuracy of any other model in our experiments ranges from 9% to 50%. We further propose a remedy that adds an additional paragraph to the deceptive prompts to encourage models to think twice before answering the question. Surprisingly, this simple method can even double the accuracy; however, the absolute numbers are still too low to be satisfactory. We hope MAD-Bench can serve as a valuable benchmark to stimulate further research to enhance model resilience against deceptive prompts.
Authors: Zihao Liu, Xiaoyu Zhang, Guangwei Liu, Ji Zhao, Ningyi Xu
Abstract: In autonomous driving, the high-definition (HD) map plays a crucial role in localization and planning. Recently, several methods have facilitated end-to-end online map construction in DETR-like frameworks. However, little attention has been paid to the potential capabilities of exploring the query mechanism for map elements. This paper introduces MapQR, an end-to-end method with an emphasis on enhancing query capabilities for constructing online vectorized maps. To probe desirable information efficiently, MapQR utilizes a novel query design, called scatter-and-gather query, which is modelled by separate content and position parts explicitly. The base map instance queries are scattered to different reference points and added with positional embeddings to probe information from BEV features. Then these scatted queries are gathered back to enhance information within each map instance. Together with a simple and effective improvement of a BEV encoder, the proposed MapQR achieves the best mean average precision (mAP) and maintains good efficiency on both nuScenes and Argoverse 2. In addition, integrating our query design into other models can boost their performance significantly. The source code is available at https://github.com/HXMap/MapQR.
Authors: Huiming Sun, Jiacheng Guo, Zibo Meng, Tianyun Zhang, Jianwu Fang, Yuewei Lin, Hongkai Yu
Abstract: Vehicle detection in Unmanned Aerial Vehicle (UAV) captured images has wide applications in aerial photography and remote sensing. There are many public benchmark datasets proposed for the vehicle detection and tracking in UAV images. Recent studies show that adding an adversarial patch on objects can fool the well-trained deep neural networks based object detectors, posing security concerns to the downstream tasks. However, the current public UAV datasets might ignore the diverse altitudes, vehicle attributes, fine-grained instance-level annotation in mostly side view with blurred vehicle roof, so none of them is good to study the adversarial patch based vehicle detection attack problem. In this paper, we propose a new dataset named EVD4UAV as an altitude-sensitive benchmark to evade vehicle detection in UAV with 6,284 images and 90,886 fine-grained annotated vehicles. The EVD4UAV dataset has diverse altitudes (50m, 70m, 90m), vehicle attributes (color, type), fine-grained annotation (horizontal and rotated bounding boxes, instance-level mask) in top view with clear vehicle roof. One white-box and two black-box patch based attack methods are implemented to attack three classic deep neural networks based object detectors on EVD4UAV. The experimental results show that these representative attack methods could not achieve the robust altitude-insensitive attack performance.
Authors: Fudong Ge, Yiwei Zhang, Shuhan Shen, Yue Wang, Weiming Hu, Jin Gao
Abstract: In this paper, we propose a new image-based visual place recognition (VPR) framework by exploiting the structural cues in bird's-eye view (BEV) from a single monocular camera. The motivation arises from two key observations about place recognition methods based on both appearance and structure: 1) For the methods relying on LiDAR sensors, the integration of LiDAR in robotic systems has led to increased expenses, while the alignment of data between different sensors is also a major challenge. 2) Other image-/camera-based methods, involving integrating RGB images and their derived variants (eg, pseudo depth images, pseudo 3D point clouds), exhibit several limitations, such as the failure to effectively exploit the explicit spatial relationships between different objects. To tackle the above issues, we design a new BEV-enhanced VPR framework, namely BEV$^2$PR, generating a composite descriptor with both visual cues and spatial awareness based on a single camera. The key points lie in: 1) We use BEV features as an explicit source of structural knowledge in constructing global features. 2) The lower layers of the pre-trained backbone from BEV generation are shared for visual and structural streams in VPR, facilitating the learning of fine-grained local features in the visual stream. 3) The complementary visual and structural features can jointly enhance VPR performance. Our BEV$^2$PR framework enables consistent performance improvements over several popular aggregation modules for RGB global features. The experiments on our collected VPR-NuScenes dataset demonstrate an absolute gain of 2.47% on Recall@1 for the strong Conv-AP baseline to achieve the best performance in our setting, and notably, a 18.06% gain on the hard set. The code and dataset will be available at https://github.com/FudongGe/BEV2PR.
Authors: Jiaxu Zhang, Xin Chen, Gang Yu, Zhigang Tu
Abstract: Stylized motion breathes life into characters. However, the fixed skeleton structure and style representation hinder existing data-driven motion synthesis methods from generating stylized motion for various characters. In this work, we propose a generative motion stylization pipeline, named MotionS, for synthesizing diverse and stylized motion on cross-structure characters using cross-modality style prompts. Our key insight is to embed motion style into a cross-modality latent space and perceive the cross-structure skeleton topologies, allowing for motion stylization within a canonical motion space. Specifically, the large-scale Contrastive-Language-Image-Pre-training (CLIP) model is leveraged to construct the cross-modality latent space, enabling flexible style representation within it. Additionally, two topology-encoded tokens are learned to capture the canonical and specific skeleton topologies, facilitating cross-structure topology shifting. Subsequently, the topology-shifted stylization diffusion is designed to generate motion content for the particular skeleton and stylize it in the shifted canonical motion space using multi-modality style descriptions. Through an extensive set of examples, we demonstrate the flexibility and generalizability of our pipeline across various characters and style descriptions. Qualitative and quantitative comparisons show the superiority of our pipeline over state-of-the-arts, consistently delivering high-quality stylized motion across a broad spectrum of skeletal structures.
Authors: Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Gl\"ockler, Alex B\"auerle, Timo Ropinski
Abstract: Recent AI-based text-to-image models not only excel at generating realistic images, they also give designers more and more fine-grained control over the image content. Consequently, these approaches have gathered increased attention within the computer graphics research community, which has been historically devoted towards traditional rendering techniques that offer precise control over scene parameters such as objects, materials, and lighting, when generating realistic images. While the quality of rendered images is traditionally assessed through well-established image quality metrics, such as SSIM or PSNR, the unique challenges presented by text-to-image models, which in contrast to rendering interweave the control of scene and rendering parameters, necessitate the development of novel image quality metrics. Therefore, within this survey, we provide a comprehensive overview of existing text-to-image quality metrics addressing their nuances and the need for alignment with human preferences. Based on our findings, we propose a new taxonomy for categorizing these metrics, which is grounded in the assumption that there are two main quality criteria, namely compositionality and generality, which ideally map to human preferences. Ultimately, we derive guidelines for practitioners conducting text-to-image evaluation, discuss open challenges of evaluation mechanisms, and surface limitations of current metrics.
Authors: Sibi Catley-Chandar, Richard Shaw, Gregory Slabaugh, Eduardo Perez-Pellitero
Abstract: Recent advances in neural rendering have enabled highly photorealistic 3D scene reconstruction and novel view synthesis. Despite this progress, current state-of-the-art methods struggle to reconstruct high frequency detail, due to factors such as a low-frequency bias of radiance fields and inaccurate camera calibration. One approach to mitigate this issue is to enhance images post-rendering. 2D enhancers can be pre-trained to recover some detail but are agnostic to scene geometry and do not easily generalize to new distributions of image degradation. Conversely, existing 3D enhancers are able to transfer detail from nearby training images in a generalizable manner, but suffer from inaccurate camera calibration and can propagate errors from the geometry into rendered images. We propose a neural rendering enhancer, RoGUENeRF, which exploits the best of both paradigms. Our method is pre-trained to learn a general enhancer while also leveraging information from nearby training images via robust 3D alignment and geometry-aware fusion. Our approach restores high-frequency textures while maintaining geometric consistency and is also robust to inaccurate camera calibration. We show that RoGUENeRF substantially enhances the rendering quality of a wide range of neural rendering baselines, e.g. improving the PSNR of MipNeRF360 by 0.63dB and Nerfacto by 1.34dB on the real world 360v2 dataset.
Authors: Yixuan Wu, Yizhou Wang, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Philip Torr, Jian Wu
Abstract: We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired by high-precision detection priors and a new Chain-of-Thought to implement these prompts. Specifically, the prompts in the toolkit are designed to guide the MLLM to focus on regional information (e.g., zooming in), read coordinates according to measure standards (e.g., overlaying rulers and compasses), and infer from the contextual information (e.g., overlaying scene graphs). Building upon these tools, the new detection chain-of-thought can automatically decompose the task into simple subtasks, diagnose the predictions, and plan for progressive box refinements. The effectiveness of our framework is demonstrated across a spectrum of detection tasks, especially hard cases. Compared to existing state-of-the-art methods, GPT-4V with our DetToolChain improves state-of-the-art object detectors by +21.5% AP50 on MS COCO Novel class set for open-vocabulary detection, +24.23% Acc on RefCOCO val set for zero-shot referring expression comprehension, +14.5% AP on D-cube describe object detection FULL setting.
Authors: Jaywon Koo, Ziyan Yang, Paola Cascante-Bonilla, Baishakhi Ray, Vicente Ordonez
Abstract: Visual Programming has recently emerged as an alternative to end-to-end black-box visual reasoning models. This type of method leverages Large Language Models (LLMs) to generate the source code for an executable computer program that solves a given problem. This strategy has the advantage of offering an interpretable reasoning path and does not require finetuning a model with task-specific data. We propose PropTest, a general strategy that improves visual programming by further using an LLM to generate code that tests for visual properties in an initial round of proposed solutions. Our method generates tests for data-type consistency, output syntax, and semantic properties. PropTest achieves comparable results to state-of-the-art methods while using publicly available LLMs. This is demonstrated across different benchmarks on visual question answering and referring expression comprehension. Particularly, PropTest improves ViperGPT by obtaining 46.1\% accuracy (+6.0\%) on GQA using Llama3-8B and 59.5\% (+8.1\%) on RefCOCO+ using CodeLlama-34B.
Authors: Qiao Gu, Zhaoyang Lv, Duncan Frost, Simon Green, Julian Straub, Chris Sweeney
Abstract: In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically designed for egocentric data where scenes contain hundreds of objects captured from natural (non-scanning) motion. EgoLifter adopts 3D Gaussians as the underlying representation of 3D scenes and objects and uses segmentation masks from the Segment Anything Model (SAM) as weak supervision to learn flexible and promptable definitions of object instances free of any specific object taxonomy. To handle the challenge of dynamic objects in ego-centric videos, we design a transient prediction module that learns to filter out dynamic objects in the 3D reconstruction. The result is a fully automatic pipeline that is able to reconstruct 3D object instances as collections of 3D Gaussians that collectively compose the entire scene. We created a new benchmark on the Aria Digital Twin dataset that quantitatively demonstrates its state-of-the-art performance in open-world 3D segmentation from natural egocentric input. We run EgoLifter on various egocentric activity datasets which shows the promise of the method for 3D egocentric perception at scale.
Authors: Qiran Zou, Shangyuan Yuan, Shian Du, Yu Wang, Chang Liu, Yi Xu, Jie Chen, Xiangyang Ji
Abstract: We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts. Moreover, introducing finer-grained part concepts poses computational complexity challenges. In this paper, we propose Part-Coordinating Text-to-Motion Synthesis (ParCo), endowed with enhanced capabilities for understanding part motions and communication among different part motion generators, ensuring a coordinated and fined-grained motion synthesis. Specifically, we discretize whole-body motion into multiple part motions to establish the prior concept of different parts. Afterward, we employ multiple lightweight generators designed to synthesize different part motions and coordinate them through our part coordination module. Our approach demonstrates superior performance on common benchmarks with economic computations, including HumanML3D and KIT-ML, providing substantial evidence of its effectiveness. Code is available at https://github.com/qrzou/ParCo .
Authors: Zhenyu Wang, Yali Li, Taichi Liu, Hengshuang Zhao, Shengjin Wang
Abstract: In the current state of 3D object detection research, the severe scarcity of annotated 3D data, substantial disparities across different data modalities, and the absence of a unified architecture, have impeded the progress towards the goal of universality. In this paper, we propose \textbf{OV-Uni3DETR}, a unified open-vocabulary 3D detector via cycle-modality propagation. Compared with existing 3D detectors, OV-Uni3DETR offers distinct advantages: 1) Open-vocabulary 3D detection: During training, it leverages various accessible data, especially extensive 2D detection images, to boost training diversity. During inference, it can detect both seen and unseen classes. 2) Modality unifying: It seamlessly accommodates input data from any given modality, effectively addressing scenarios involving disparate modalities or missing sensor information, thereby supporting test-time modality switching. 3) Scene unifying: It provides a unified multi-modal model architecture for diverse scenes collected by distinct sensors. Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities. 2D semantic knowledge from large-vocabulary learning guides novel class discovery in the 3D domain, and 3D geometric knowledge provides localization supervision for 2D detection images. OV-Uni3DETR achieves the state-of-the-art performance on various scenarios, surpassing existing methods by more than 6\% on average. Its performance using only RGB images is on par with or even surpasses that of previous point cloud based methods. Code and pre-trained models will be released later.
Authors: Taekyung Ki, Dongchan Min, Gyeongsu Chae
Abstract: In this paper, we present Export3D, a one-shot 3D-aware portrait animation method that is able to control the facial expression and camera view of a given portrait image. To achieve this, we introduce a tri-plane generator with an effective expression conditioning method, which directly generates a tri-plane of 3D prior by transferring the expression parameter of 3DMM into the source image. The tri-plane is then decoded into the image of different view through a differentiable volume rendering. Existing portrait animation methods heavily rely on image warping to transfer the expression in the motion space, challenging on disentanglement of appearance and expression. In contrast, we propose a contrastive pre-training framework for appearance-free expression parameter, eliminating undesirable appearance swap when transferring a cross-identity expression. Extensive experiments show that our pre-training framework can learn the appearance-free expression representation hidden in 3DMM, and our model can generate 3D-aware expression controllable portrait images without appearance swap in the cross-identity manner.
Authors: Gousia Habib, Tausifa jan Saleem, Sheikh Musa Kaleem, Tufail Rouf, Brejesh Lall
Abstract: Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent examples. However, deep learning models suffer from significant drawbacks when deployed in resource-constrained environments due to their large model size and high complexity. Knowledge Distillation is one of the prominent solutions to overcome this challenge. This review paper examines the current state of research on knowledge distillation, a technique for compressing complex models into smaller and simpler ones. The paper provides an overview of the major principles and techniques associated with knowledge distillation and reviews the applications of knowledge distillation in the domain of computer vision. The review focuses on the benefits of knowledge distillation, as well as the problems that must be overcome to improve its effectiveness.
Authors: Jinfeng Xu, Siyuan Yang, Xianzhi Li, Yuan Tang, Yixue Hao, Long Hu, Min Chen
Abstract: Existing point cloud semantic segmentation networks cannot identify unknown classes and update their knowledge, due to a closed-set and static perspective of the real world, which would induce the intelligent agent to make bad decisions. To address this problem, we propose a Probability-Driven Framework (PDF) for open world semantic segmentation that includes (i) a lightweight U-decoder branch to identify unknown classes by estimating the uncertainties, (ii) a flexible pseudo-labeling scheme to supply geometry features along with probability distribution features of unknown classes by generating pseudo labels, and (iii) an incremental knowledge distillation strategy to incorporate novel classes into the existing knowledge base gradually. Our framework enables the model to behave like human beings, which could recognize unknown objects and incrementally learn them with the corresponding knowledge. Experimental results on the S3DIS and ScanNetv2 datasets demonstrate that the proposed PDF outperforms other methods by a large margin in both important tasks of open world semantic segmentation.
Authors: Eric Dexheimer, Andrew J. Davison
Abstract: We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. Decoding anchor point projections into dense geometry via per-keyframe depth covariance functions guarantees that depth maps are joined together at visible anchor points. The representation enables joint optimization of camera poses and dense geometry, intrinsic 3D consistency, and efficient second-order inference. To maintain a compact yet expressive map, we introduce a frontend that leverages the covariance function for tracking and initializing potentially visually indistinct 3D points across frames. Altogether, we introduce a real-time system capable of estimating accurate poses and consistent geometry.
Authors: Jun Li, Su Hwan Kim, Philip M\"uller, Lina Felsner, Daniel Rueckert, Benedikt Wiestler, Julia A. Schnabel, Cosmin I. Bercea
Abstract: This research explores the integration of language models and unsupervised anomaly detection in medical imaging, addressing two key questions: (1) Can language models enhance the interpretability of anomaly detection maps? and (2) Can anomaly maps improve the generalizability of language models in open-set anomaly detection tasks? To investigate these questions, we introduce a new dataset for multi-image visual question-answering on brain magnetic resonance images encompassing multiple conditions. We propose KQ-Former (Knowledge Querying Transformer), which is designed to optimally align visual and textual information in limited-sample contexts. Our model achieves a 60.81% accuracy on closed questions, covering disease classification and severity across 15 different classes. For open questions, KQ-Former demonstrates a 70% improvement over the baseline with a BLEU-4 score of 0.41, and achieves the highest entailment ratios (up to 71.9%) and lowest contradiction ratios (down to 10.0%) among various natural language inference models. Furthermore, integrating anomaly maps results in an 18% accuracy increase in detecting open-set anomalies, thereby enhancing the language model's generalizability to previously unseen medical conditions. The code and dataset are available at https://github.com/compai-lab/miccai-2024-junli?tab=readme-ov-file
URLs: https://github.com/compai-lab/miccai-2024-junli?tab=readme-ov-file
Authors: Haojian Huang, Xiaozhen Qiao, Zhuo Chen, Haodong Chen, Bingyu Li, Zhe Sun, Mulin Chen, Xuelong Li
Abstract: Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in identifying class-specific visual features, thus facilitating visual-semantic alignment and improving ZSL performance. However, real-world challenges such as distribution imbalances and attribute co-occurrence among instances often hinder the discernment of local variances in images, a problem exacerbated by the scarcity of fine-grained, region-specific attribute annotations. Moreover, the variability in visual presentation within categories can also skew attribute-category associations. In response, we propose a bidirectional cross-modal ZSL approach CREST. It begins by extracting representations for attribute and visual localization and employs Evidential Deep Learning (EDL) to measure underlying epistemic uncertainty, thereby enhancing the model's resilience against hard negatives. CREST incorporates dual learning pathways, focusing on both visual-category and attribute-category alignments, to ensure robust correlation between latent and observable spaces. Moreover, we introduce an uncertainty-informed cross-modal fusion technique to refine visual-attribute inference. Extensive experiments demonstrate our model's effectiveness and unique explainability across multiple datasets. Our code and data are available at: https://github.com/JethroJames/CREST
Authors: Qi Guo, Shanmin Pang, Xiaojun Jia, Yang Liu, Qing Guo
Abstract: Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a more thorough examination of potential security flaws before deployment. However, previous transfer-based adversarial attacks incur high costs due to high iteration counts and complex method structure. Furthermore, due to the unnaturalness of adversarial semantics, the generated adversarial examples have low transferability. These issues limit the utility of existing methods for assessing robustness. To address these issues, we propose AdvDiffVLM, which uses diffusion models to generate natural, unrestricted and targeted adversarial examples via score matching. Specifically, AdvDiffVLM uses Adaptive Ensemble Gradient Estimation to modify the score during the diffusion model's reverse generation process, ensuring that the produced adversarial examples have natural adversarial targeted semantics, which improves their transferability. Simultaneously, to improve the quality of adversarial examples, we use the GradCAM-guided Mask method to disperse adversarial semantics throughout the image rather than concentrating them in a single area. Finally, AdvDiffVLM embeds more target semantics into adversarial examples after multiple iterations. Experimental results show that our method generates adversarial examples 5x to 10x faster than state-of-the-art transfer-based adversarial attacks while maintaining higher quality adversarial examples. Furthermore, compared to previous transfer-based adversarial attacks, the adversarial examples generated by our method have better transferability. Notably, AdvDiffVLM can successfully attack a variety of commercial VLMs in a black-box environment, including GPT-4V.
Authors: Sina Sharifi, Taha Entesari, Bardia Safaei, Vishal M. Patel, Mahyar Fazlyab
Abstract: One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addressing this issue is known as Out-of-Distribution (OOD) detection. Many state-of-the-art OOD methods employ an auxiliary dataset as a surrogate for OOD data during training to achieve improved performance. However, these methods fail to fully exploit the local information embedded in the auxiliary dataset. In this work, we propose the idea of leveraging the information embedded in the gradient of the loss function during training to enable the network to not only learn a desired OOD score for each sample but also to exhibit similar behavior in a local neighborhood around each sample. We also develop a novel energy-based sampling method to allow the network to be exposed to more informative OOD samples during the training phase. This is especially important when the auxiliary dataset is large. We demonstrate the effectiveness of our method through extensive experiments on several OOD benchmarks, improving the existing state-of-the-art FPR95 by 4% on our ImageNet experiment. We further provide a theoretical analysis through the lens of certified robustness and Lipschitz analysis to showcase the theoretical foundation of our work. Our code is available at https://github.com/o4lc/Greg-OOD.
Authors: Zirui Wang, Wenjing Bian, Victor Adrian Prisacariu
Abstract: We introduce a novel cross-reference image quality assessment method that effectively fills the gap in the image assessment landscape, complementing the array of established evaluation schemes -- ranging from full-reference metrics like SSIM, no-reference metrics such as NIQE, to general-reference metrics including FID, and Multi-modal-reference metrics, e.g., CLIPScore. Utilising a neural network with the cross-attention mechanism and a unique data collection pipeline from NVS optimisation, our method enables accurate image quality assessment without requiring ground truth references. By comparing a query image against multiple views of the same scene, our method addresses the limitations of existing metrics in novel view synthesis (NVS) and similar tasks where direct reference images are unavailable. Experimental results show that our method is closely correlated to the full-reference metric SSIM, while not requiring ground truth references.
Authors: Cameron Smith, David Charatan, Ayush Tewari, Vincent Sitzmann
Abstract: This paper introduces FlowMap, an end-to-end differentiable method that solves for precise camera poses, camera intrinsics, and per-frame dense depth of a video sequence. Our method performs per-video gradient-descent minimization of a simple least-squares objective that compares the optical flow induced by depth, intrinsics, and poses against correspondences obtained via off-the-shelf optical flow and point tracking. Alongside the use of point tracks to encourage long-term geometric consistency, we introduce differentiable re-parameterizations of depth, intrinsics, and pose that are amenable to first-order optimization. We empirically show that camera parameters and dense depth recovered by our method enable photo-realistic novel view synthesis on 360-degree trajectories using Gaussian Splatting. Our method not only far outperforms prior gradient-descent based bundle adjustment methods, but surprisingly performs on par with COLMAP, the state-of-the-art SfM method, on the downstream task of 360-degree novel view synthesis (even though our method is purely gradient-descent based, fully differentiable, and presents a complete departure from conventional SfM).
Authors: Sander Elias Magnussen Helgesen, Kazuto Nakashima, Jim T{\o}rresen, Ryo Kurazume
Abstract: The search for refining 3D LiDAR data has attracted growing interest motivated by recent techniques such as supervised learning or generative model-based methods. Existing approaches have shown the possibilities for using diffusion models to generate refined LiDAR data with high fidelity, although the performance and speed of such methods have been limited. These limitations make it difficult to execute in real-time, causing the approaches to struggle in real-world tasks such as autonomous navigation and human-robot interaction. In this work, we introduce a novel approach based on conditional diffusion models for fast and high-quality sparse-to-dense upsampling of 3D scene point clouds through an image representation. Our method employs denoising diffusion probabilistic models trained with conditional inpainting masks, which have been shown to give high performance on image completion tasks. We introduce a series of experiments, including multiple datasets, sampling steps, and conditional masks. This paper illustrates that our method outperforms the baselines in sampling speed and quality on upsampling tasks using the KITTI-360 dataset. Furthermore, we illustrate the generalization ability of our approach by simultaneously training on real-world and synthetic datasets, introducing variance in quality and environments.
Authors: Parth Padalkar, Natalia \'Slusarz, Ekaterina Komendantskaya, Gopal Gupta
Abstract: Recent efforts in interpreting Convolutional Neural Networks (CNNs) focus on translating the activation of CNN filters into stratified Answer Set Programming (ASP) rule-sets. The CNN filters are known to capture high-level image concepts, thus the predicates in the rule-set are mapped to the concept that their corresponding filter represents. Hence, the rule-set effectively exemplifies the decision-making process of the CNN in terms of the concepts that it learns for any image classification task. These rule-sets help expose and understand the biases in CNNs, although correcting the biases effectively remains a challenge. We introduce a neurosymbolic framework called NeSyBiCor for bias correction in a trained CNN. Given symbolic concepts that the CNN is biased towards, expressed as ASP constraints, we convert the undesirable and desirable concepts to their corresponding vector representations. Then, the CNN is retrained using our novel semantic similarity loss that pushes the filters away from the representations of concepts that are undesirable while pushing them closer to the concepts that are desirable. The final ASP rule-set obtained after retraining, satisfies the constraints to a high degree, thus showing the revision in the knowledge of the CNN for the image classification task. We demonstrate that our NeSyBiCor framework successfully corrects the biases of CNNs trained with subsets of classes from the Places dataset while sacrificing minimal accuracy and improving interpretability, by greatly decreasing the size of the final bias-corrected rule-set w.r.t. the initial rule-set.
Authors: Changhoon Kim, Kyle Min, Yezhou Yang
Abstract: In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability to generate high-quality images from textual descriptions faces challenges with the potential misuse of reproducing sensitive content. To address this critical issue, we introduce \textbf{R}obust \textbf{A}dversarial \textbf{C}oncept \textbf{E}rase (RACE), a novel approach designed to mitigate these risks by enhancing the robustness of concept erasure method for T2I models. RACE utilizes a sophisticated adversarial training framework to identify and mitigate adversarial text embeddings, significantly reducing the Attack Success Rate (ASR). Impressively, RACE achieves a 30 percentage point reduction in ASR for the ``nudity'' concept against the leading white-box attack method. Our extensive evaluations demonstrate RACE's effectiveness in defending against both white-box and black-box attacks, marking a significant advancement in protecting T2I diffusion models from generating inappropriate or misleading imagery. This work underlines the essential need for proactive defense measures in adapting to the rapidly advancing field of adversarial challenges. Our code is publicly available: \url{https://github.com/chkimmmmm/R.A.C.E.}
Authors: Tanqiu Qiao, Ruochen Li, Frederick W. B. Li, Hubert P. H. Shum
Abstract: Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made significant strides, effectively integrating geometric and visual features to model dynamic relationships between humans and objects in a graph framework remains a challenge. In this work, we propose a novel end-to-end category to scenery framework, CATS, starting by generating geometric features for various categories through graphs respectively, then fusing them with corresponding visual features. Subsequently, we construct a scenery interactive graph with these enhanced geometric-visual features as nodes to learn the relationships among human and object categories. This methodological advance facilitates a deeper, more structured comprehension of interactions, bridging category-specific insights with broad scenery dynamics. Our method demonstrates state-of-the-art performance on two pivotal HOI benchmarks, including the MPHOI-72 dataset for multi-person HOIs and the single-person HOI CAD-120 dataset.
Authors: Haodong Chen, Haojian Huang, Junhao Dong, Mingzhe Zheng, Dian Shao
Abstract: Dynamic Facial Expression Recognition (DFER) is crucial for understanding human behavior. However, current methods exhibit limited performance mainly due to the scarcity of high-quality data, the insufficient utilization of facial dynamics, and the ambiguity of expression semantics, etc. To this end, we propose a novel framework, named Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs (FineCLIPER), incorporating the following novel designs: 1) To better distinguish between similar facial expressions, we extend the class labels to textual descriptions from both positive and negative aspects, and obtain supervision by calculating the cross-modal similarity based on the CLIP model; 2) Our FineCLIPER adopts a hierarchical manner to effectively mine useful cues from DFE videos. Specifically, besides directly embedding video frames as input (low semantic level), we propose to extract the face segmentation masks and landmarks based on each frame (middle semantic level) and utilize the Multi-modal Large Language Model (MLLM) to further generate detailed descriptions of facial changes across frames with designed prompts (high semantic level). Additionally, we also adopt Parameter-Efficient Fine-Tuning (PEFT) to enable efficient adaptation of large pre-trained models (i.e., CLIP) for this task. Our FineCLIPER achieves SOTA performance on the DFEW, FERV39k, and MAFW datasets in both supervised and zero-shot settings with few tunable parameters. Project Page: https://haroldchen19.github.io/FineCLIPER-Page/
Authors: Hang Xu, Chen Long, Wenxiao Zhang, Yuan Liu, Zhen Cao, Zhen Dong, Bisheng Yang
Abstract: In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a partial one with a single view image. In comparison with previous methods that relied on the global semantics of input images, EGIInet efficiently combines the information from two modalities by leveraging the geometric nature of the completion task. Specifically, we propose an explicitly guided information interaction strategy supported by modal alignment for point cloud completion. First, in contrast to previous methods which simply use 2D and 3D backbones to encode features respectively, we unified the encoding process to promote modal alignment. Second, we propose a novel explicitly guided information interaction strategy that could help the network identify critical information within images, thus achieving better guidance for completion. Extensive experiments demonstrate the effectiveness of our framework, and we achieved a new state-of-the-art (+16% CD over XMFnet) in benchmark datasets despite using fewer parameters than the previous methods. The pre-trained model and code and are available at https://github.com/WHU-USI3DV/EGIInet.
Authors: Arindam Dutta, Rohit Lal, Yash Garg, Calvin-Khang Ta, Dripta S. Raychaudhuri, Hannah Dela Cruz, Amit K. Roy-Chowdhury
Abstract: Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision. However, these algorithms exhibit severe performance drops in the face of domain shifts, leading to inaccurate segmentation masks. To tackle this issue, we introduce POSTURE: \underline{Po}se Guided Un\underline{s}upervised Domain Adap\underline{t}ation for H\underline{u}man Body Pa\underline{r}t S\underline{e}gmentation - an innovative pseudo-labelling approach designed to improve segmentation performance on the unlabeled target data. Distinct from conventional domain adaptive methods for general semantic segmentation, POSTURE stands out by considering the underlying structure of the human body and uses anatomical guidance from pose keypoints to drive the adaptation process. This strong inductive prior translates to impressive performance improvements, averaging 8\% over existing state-of-the-art domain adaptive semantic segmentation methods across three benchmark datasets. Furthermore, the inherent flexibility of our proposed approach facilitates seamless extension to source-free settings (SF-POSTURE), effectively mitigating potential privacy and computational concerns, with negligible drop in performance.
Authors: Mainak Singha, Ankit Jha, Divyam Gupta, Pranav Singla, Biplab Banerjee
Abstract: We address the challenges inherent in sketch-based image retrieval (SBIR) across various settings, including zero-shot SBIR, generalized zero-shot SBIR, and fine-grained zero-shot SBIR, by leveraging the vision-language foundation model CLIP. While recent endeavors have employed CLIP to enhance SBIR, these approaches predominantly follow uni-modal prompt processing and overlook to exploit CLIP's integrated visual and textual capabilities fully. To bridge this gap, we introduce SpLIP, a novel multi-modal prompt learning scheme designed to operate effectively with frozen CLIP backbones. We diverge from existing multi-modal prompting methods that treat visual and textual prompts independently or integrate them in a limited fashion, leading to suboptimal generalization. SpLIP implements a bi-directional prompt-sharing strategy that enables mutual knowledge exchange between CLIP's visual and textual encoders, fostering a more cohesive and synergistic prompt processing mechanism that significantly reduces the semantic gap between the sketch and photo embeddings. In addition to pioneering multi-modal prompt learning, we propose two innovative strategies for further refining the embedding space. The first is an adaptive margin generation for the sketch-photo triplet loss, regulated by CLIP's class textual embeddings. The second introduces a novel task, termed conditional cross-modal jigsaw, aimed at enhancing fine-grained sketch-photo alignment by implicitly modeling sketches' viable patch arrangement using knowledge of unshuffled photos. Our comprehensive experimental evaluations across multiple benchmarks demonstrate the superior performance of SpLIP in all three SBIR scenarios. Project page: https://mainaksingha01.github.io/SpLIP/ .
Authors: Sushil Sharma, Arindam Das, Ganesh Sistu, Mark Halton, Ciar\'an Eising
Abstract: Predicting ego vehicle trajectories remains a critical challenge, especially in urban and dense areas due to the unpredictable behaviours of other vehicles and pedestrians. Multimodal trajectory prediction enhances decision-making by considering multiple possible future trajectories based on diverse sources of environmental data. In this approach, we leverage ResNet-50 to extract image features from high-definition map data and use IMU sensor data to calculate speed, acceleration, and yaw rate. A temporal probabilistic network is employed to compute potential trajectories, selecting the most accurate and highly probable trajectory paths. This method integrates HD map data to improve the robustness and reliability of trajectory predictions for autonomous vehicles.
Authors: Yiran Yang, Jinchao Zhang, Ying Deng, Jie Zhou
Abstract: Inspired by the success of the text-to-image (T2I) generation task, many researchers are devoting themselves to the text-to-video (T2V) generation task. Most of the T2V frameworks usually inherit from the T2I model and add extra-temporal layers of training to generate dynamic videos, which can be viewed as a fine-tuning task. However, the traditional 3D-Unet is a serial mode and the temporal layers follow the spatial layers, which will result in high GPU memory and training time consumption according to its serial feature flow. We believe that this serial mode will bring more training costs with the large diffusion model and massive datasets, which are not environmentally friendly and not suitable for the development of the T2V. Therefore, we propose a highly efficient spatial-temporal parallel training paradigm for T2V tasks, named Mobius. In our 3D-Unet, the temporal layers and spatial layers are parallel, which optimizes the feature flow and backpropagation. The Mobius will save 24% GPU memory and 12% training time, which can greatly improve the T2V fine-tuning task and provide a novel insight for the AIGC community. We will release our codes in the future.
Authors: Wenqi Zhang, Zhenglin Cheng, Yuanyu He, Mengna Wang, Yongliang Shen, Zeqi Tan, Guiyang Hou, Mingqian He, Yanna Ma, Weiming Lu, Yueting Zhuang
Abstract: Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite rudimentary. They often struggle with simple daily tasks, such as reading time from a clock, understanding a flowchart, or planning a route using a road map. In light of this, we design a multi-modal self-instruct, utilizing large language models and their code capabilities to synthesize massive abstract images and visual reasoning instructions across daily scenarios. Our strategy effortlessly creates a multimodal benchmark with 11,193 instructions for eight visual scenarios: charts, tables, simulated maps, dashboards, flowcharts, relation graphs, floor plans, and visual puzzles. \textbf{This benchmark, constructed with simple lines and geometric elements, exposes the shortcomings of most advanced LMMs} like Claude-3.5-Sonnet and GPT-4o in abstract image understanding, spatial relations reasoning, and visual element induction. Besides, to verify the quality of our synthetic data, we fine-tune an LMM using 62,476 synthetic chart, table and road map instructions. The results demonstrate improved chart understanding and map navigation performance, and also demonstrate potential benefits for other visual reasoning tasks. Our code is available at: \url{https://github.com/zwq2018/Multi-modal-Self-instruct}.
Authors: Ilya Trofimov, Daria Voronkova, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov
Abstract: We propose a new topological tool for computer vision - Scalar Function Topology Divergence (SFTD), which measures the dissimilarity of multi-scale topology between sublevel sets of two functions having a common domain. Functions can be defined on an undirected graph or Euclidean space of any dimensionality. Most of the existing methods for comparing topology are based on Wasserstein distance between persistence barcodes and they don't take into account the localization of topological features. The minimization of SFTD ensures that the corresponding topological features of scalar functions are located in the same places. The proposed tool provides useful visualizations depicting areas where functions have topological dissimilarities. We provide applications of the proposed method to 3D computer vision. In particular, experiments demonstrate that SFTD as an additional loss improves the reconstruction of cellular 3D shapes from 2D fluorescence microscopy images, and helps to identify topological errors in 3D segmentation. Additionally, we show that SFTD outperforms Betti matching loss in 2D segmentation problems.
Authors: Ziming Zhong, Yanxu Xu, Jing Li, Jiale Xu, Zhengxin Li, Chaohui Yu, Shenghua Gao
Abstract: We present MeshSegmenter, a simple yet effective framework designed for zero-shot 3D semantic segmentation. This model successfully extends the powerful capabilities of 2D segmentation models to 3D meshes, delivering accurate 3D segmentation across diverse meshes and segment descriptions. Specifically, our model leverages the Segment Anything Model (SAM) model to segment the target regions from images rendered from the 3D shape. In light of the importance of the texture for segmentation, we also leverage the pretrained stable diffusion model to generate images with textures from 3D shape, and leverage SAM to segment the target regions from images with textures. Textures supplement the shape for segmentation and facilitate accurate 3D segmentation even in geometrically non-prominent areas, such as segmenting a car door within a car mesh. To achieve the 3D segments, we render 2D images from different views and conduct segmentation for both textured and untextured images. Lastly, we develop a multi-view revoting scheme that integrates 2D segmentation results and confidence scores from various views onto the 3D mesh, ensuring the 3D consistency of segmentation results and eliminating inaccuracies from specific perspectives. Through these innovations, MeshSegmenter offers stable and reliable 3D segmentation results both quantitatively and qualitatively, highlighting its potential as a transformative tool in the field of 3D zero-shot segmentation. The code is available at \url{https://github.com/zimingzhong/MeshSegmenter}.
Authors: Yurong Zhang, Honghao Chen, Xinyu Zhang, Xiangxiang Chu, Li Song
Abstract: Parameter-efficient transfer learning (PETL) is a promising task, aiming to adapt the large-scale pre-trained model to downstream tasks with a relatively modest cost. However, current PETL methods struggle in compressing computational complexity and bear a heavy inference burden due to the complete forward process. This paper presents an efficient visual recognition paradigm, called Dynamic Adapter (Dyn-Adapter), that boosts PETL efficiency by subtly disentangling features in multiple levels. Our approach is simple: first, we devise a dynamic architecture with balanced early heads for multi-level feature extraction, along with adaptive training strategy. Second, we introduce a bidirectional sparsity strategy driven by the pursuit of powerful generalization ability. These qualities enable us to fine-tune efficiently and effectively: we reduce FLOPs during inference by 50%, while maintaining or even yielding higher recognition accuracy. Extensive experiments on diverse datasets and pretrained backbones demonstrate the potential of Dyn-Adapter serving as a general efficiency booster for PETL in vision recognition tasks.
Authors: Jialiang Li, Haoyue Wang, Sheng Li, Zhenxing Qian, Xinpeng Zhang, Athanasios V. Vasilakos
Abstract: Recently, a vast number of image generation models have been proposed, which raises concerns regarding the misuse of these artificial intelligence (AI) techniques for generating fake images. To attribute the AI-generated images, existing schemes usually design and train deep neural networks (DNNs) to learn the model fingerprints, which usually requires a large amount of data for effective learning. In this paper, we aim to answer the following two questions for AI-generated image attribution, 1) is it possible to design useful handcrafted filters to facilitate the fingerprint learning? and 2) how we could reduce the amount of training data after we incorporate the handcrafted filters? We first propose a set of Multi-Directional High-Pass Filters (MHFs) which are capable to extract the subtle fingerprints from various directions. Then, we propose a Directional Enhanced Feature Learning network (DEFL) to take both the MHFs and randomly-initialized filters into consideration. The output of the DEFL is fused with the semantic features to produce a compact fingerprint. To make the compact fingerprint discriminative among different models, we propose a Dual-Margin Contrastive (DMC) loss to tune our DEFL. Finally, we propose a reference based fingerprint classification scheme for image attribution. Experimental results demonstrate that it is indeed helpful to use our MHFs for attributing the AI-generated images. The performance of our proposed method is significantly better than the state-of-the-art for both the closed-set and open-set image attribution, where only a small amount of images are required for training.
Authors: Yunlong Lin, Tian Ye, Sixiang Chen, Zhenqi Fu, Yingying Wang, Wenhao Chai, Zhaohu Xing, Lei Zhu, Xinghao Ding
Abstract: Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents a non-trivial problem. To overcome them, we propose the Attribute Guidance Diffusion framework (AGLLDiff), a training-free method for effective real-world LIE. Instead of specifically defining the degradation process, AGLLDiff shifts the paradigm and models the desired attributes, such as image exposure, structure and color of normal-light images. These attributes are readily available and impose no assumptions about the degradation process, which guides the diffusion sampling process to a reliable high-quality solution space. Extensive experiments demonstrate that our approach outperforms the current leading unsupervised LIE methods across benchmarks in terms of distortion-based and perceptual-based metrics, and it performs well even in sophisticated wild degradation.
Authors: Xiaomeng Chu, Jiajun Deng, Guoliang You, Yifan Duan, Yao Li, Yanyong Zhang
Abstract: The recent advances in query-based multi-camera 3D object detection are featured by initializing object queries in the 3D space, and then sampling features from perspective-view images to perform multi-round query refinement. In such a framework, query points near the same camera ray are likely to sample similar features from very close pixels, resulting in ambiguous query features and degraded detection accuracy. To this end, we introduce RayFormer, a camera-ray-inspired query-based 3D object detector that aligns the initialization and feature extraction of object queries with the optical characteristics of cameras. Specifically, RayFormer transforms perspective-view image features into bird's eye view (BEV) via the lift-splat-shoot method and segments the BEV map to sectors based on the camera rays. Object queries are uniformly and sparsely initialized along each camera ray, facilitating the projection of different queries onto different areas in the image to extract distinct features. Besides, we leverage the instance information of images to supplement the uniformly initialized object queries by further involving additional queries along the ray from 2D object detection boxes. To extract unique object-level features that cater to distinct queries, we design a ray sampling method that suitably organizes the distribution of feature sampling points on both images and bird's eye view. Extensive experiments are conducted on the nuScenes dataset to validate our proposed ray-inspired model design. The proposed RayFormer achieves 55.5% mAP and 63.3% NDS, respectively. Our codes will be made available.
Authors: Jianxin Liang, Xiaojun Meng, Yueqian Wang, Chang Liu, Qun Liu, Dongyan Zhao
Abstract: Video Question Answering (VideoQA) has emerged as a challenging frontier in the field of multimedia processing, requiring intricate interactions between visual and textual modalities. Simply uniformly sampling frames or indiscriminately aggregating frame-level visual features often falls short in capturing the nuanced and relevant contexts of videos to well perform VideoQA. To mitigate these issues, we propose VidF4, a novel VideoQA framework equipped with tailored frame selection strategy for effective and efficient VideoQA. We propose three frame-scoring mechanisms that consider both question relevance and inter-frame similarity to evaluate the importance of each frame for a given question on the video. Furthermore, we design a differentiable adaptive frame sampling mechanism to facilitate end-to-end training for the frame selector and answer generator. The experimental results across three widely adopted benchmarks demonstrate that our model consistently outperforms existing VideoQA methods, establishing a new SOTA across NExT-QA (+0.3%), STAR (+0.9%), and TVQA (+1.0%). Furthermore, through both quantitative and qualitative analyses, we validate the effectiveness of each design choice.
Authors: Yiyang Jiang, Wengyu Zhang, Xulu Zhang, Xiaoyong Wei, Chang Wen Chen, Qing Li
Abstract: In this paper, we investigate the feasibility of leveraging large language models (LLMs) for integrating general knowledge and incorporating pseudo-events as priors for temporal content distribution in video moment retrieval (VMR) models. The motivation behind this study arises from the limitations of using LLMs as decoders for generating discrete textual descriptions, which hinders their direct application to continuous outputs like salience scores and inter-frame embeddings that capture inter-frame relations. To overcome these limitations, we propose utilizing LLM encoders instead of decoders. Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings. We also show that the refinement capability of LLM encoders can be transferred to other embeddings, such as BLIP and T5, as long as these embeddings exhibit similar inter-concept similarity patterns to CLIP embeddings. We present a general framework for integrating LLM encoders into existing VMR architectures, specifically within the fusion module. Through experimental validation, we demonstrate the effectiveness of our proposed methods by achieving state-of-the-art performance in VMR. The source code can be accessed at https://github.com/fletcherjiang/LLMEPET.
Authors: Yiqun Zhao, Chenming Wu, Binbin Huang, Yihao Zhi, Chen Zhao, Jingdong Wang, Shenghua Gao
Abstract: Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This paper introduces the Surfel-based Gaussian Inverse Avatar (SGIA) method, which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage. We exhibit more results in our project page: https://GS-IA.github.io.
URLs: https://GS-IA.github.io.
Authors: Yu Li, Yifan Chen, Gongye Liu, Jie Wu, Yujiu Yang
Abstract: Layout generation is the foundation task of intelligent design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually appealing layouts, including blocking, overlap, or spatial misalignment between layouts, which are closely related to the spatial structure of graphic layouts. We find that these methods overly focus on content information and lack constraints on layout spatial structure, resulting in an imbalance of learning content-aware and graphic-aware features. To tackle this issue, we propose Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model (CGB-DM). Specifically, we first design a regulator that balances the predicted content and graphic weight, overcoming the tendency of paying more attention to the content on canvas. Secondly, we introduce a graphic constraint of saliency bounding box to further enhance the alignment of geometric features between layout representations and images. In addition, we adapt a transformer-based diffusion model as the backbone, whose powerful generation capability ensures the quality in layout generation. Extensive experimental results indicate that our method has achieved state-of-the-art performance in both quantitative and qualitative evaluations. Our model framework can also be expanded to other graphic design fields.
Authors: Hanjun Luo, Haoyu Huang, Ziye Deng, Xuecheng Liu, Ruizhe Chen, Zuozhu Liu
Abstract: Text-to-Image (T2I) generative models are becoming more crucial in terms of their ability to generate complex and high-quality images, which also raises concerns about the social biases in their outputs, especially in human generation. Sociological research has established systematic classifications of bias; however, existing research of T2I models often conflates different types of bias, hindering the progress of these methods. In this paper, we introduce BIGbench, a unified benchmark for Biases of Image Generation with a well-designed dataset. In contrast to existing benchmarks, BIGbench classifies and evaluates complex biases into four dimensions: manifestation of bias, visibility of bias, acquired attributes, and protected attributes. Additionally, BIGbench applies advanced multi-modal large language models (MLLM), achieving fully automated evaluation while maintaining high accuracy. We apply BIGbench to evaluate eight recent general T2I models and three debiased methods. We also conduct human evaluation, whose results demonstrated the effectiveness of BIGbench in aligning images and identifying various biases. Besides, our study also revealed new research directions about biases, including the side-effect of irrelevant protected attributes and distillation. Our dataset and benchmark is openly accessible to the research community to ensure the reproducibility.
Authors: Jiahao Lyu, Minghua Zhao, Jing Hu, Runtao Xi, Xuewen Huang, Shuangli Du, Cheng Shi, Tian Ma
Abstract: With the widespread deployment of video surveillance devices and the demand for intelligent system development, video anomaly detection (VAD) has become an important part of constructing intelligent surveillance systems. Expanding the discriminative boundary between normal and abnormal events to enhance performance is the common goal and challenge of VAD. To address this problem, we propose a Bidirectional Skip-frame Prediction (BiSP) network based on a dual-stream autoencoder, from the perspective of learning the intra-domain disparity between different features. The BiSP skips frames in the training phase to achieve the forward and backward frame prediction respectively, and in the testing phase, it utilizes bidirectional consecutive frames to co-predict the same intermediate frames, thus expanding the degree of disparity between normal and abnormal events. The BiSP designs the variance channel attention and context spatial attention from the perspectives of movement patterns and object scales, respectively, thus ensuring the maximization of the disparity between normal and abnormal in the feature extraction and delivery with different dimensions. Extensive experiments from four benchmark datasets demonstrate the effectiveness of the proposed BiSP, which substantially outperforms state-of-the-art competing methods.
Authors: Yihao Ai, Yifei Qi, Bo Wang, Yu Cheng, Xinchao Wang, Robby T. Tan
Abstract: Existing 2D human pose estimation research predominantly concentrates on well-lit scenarios, with limited exploration of poor lighting conditions, which are a prevalent aspect of daily life. Recent studies on low-light pose estimation require the use of paired well-lit and low-light images with ground truths for training, which are impractical due to the inherent challenges associated with annotation on low-light images. To this end, we introduce a novel approach that eliminates the need for low-light ground truths. Our primary novelty lies in leveraging two complementary-teacher networks to generate more reliable pseudo labels, enabling our model achieves competitive performance on extremely low-light images without the need for training with low-light ground truths. Our framework consists of two stages. In the first stage, our model is trained on well-lit data with low-light augmentations. In the second stage, we propose a dual-teacher framework to utilize the unlabeled low-light data, where a center-based main teacher produces the pseudo labels for relatively visible cases, while a keypoints-based complementary teacher focuses on producing the pseudo labels for the missed persons of the main teacher. With the pseudo labels from both teachers, we propose a person-specific low-light augmentation to challenge a student model in training to outperform the teachers. Experimental results on real low-light dataset (ExLPose-OCN) show, our method achieves 6.8% (2.4 AP) improvement over the state-of-the-art (SOTA) method, despite no low-light ground-truth data is used in our approach, in contrast to the SOTA method. Our code will be available at:https://github.com/ayh015-dev/DA-LLPose.
Authors: Anis Amziane
Abstract: Multispectral (MS) snapshot cameras equipped with a MS filter array (MSFA), capture multiple spectral bands in a single shot, resulting in a raw mosaic image where each pixel holds only one channel value. The fully-defined MS image is estimated from the raw one through $\textit{demosaicing}$, which inevitably introduces spatio-spectral artifacts. Moreover, training on fully-defined MS images can be computationally intensive, particularly with deep neural networks (DNNs), and may result in features lacking discrimination power due to suboptimal learning of spatio-spectral interactions. Furthermore, outdoor MS image acquisition occurs under varying lighting conditions, leading to illumination-dependent features. This paper presents an original approach to learn discriminant and illumination-robust features directly from raw images. It involves: $\textit{raw spectral constancy}$ to mitigate the impact of illumination, $\textit{MSFA-preserving}$ transformations suited for raw image augmentation to train DNNs on diverse raw textures, and $\textit{raw-mixing}$ to capture discriminant spatio-spectral interactions in raw images. Experiments on MS image classification show that our approach outperforms both handcrafted and recent deep learning-based methods, while also requiring significantly less computational effort.
Authors: Xiangyan Qu, Jing Yu, Keke Gai, Jiamin Zhuang, Yuanmin Tang, Gang Xiong, Gaopeng Gou, Qi Wu
Abstract: Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they disregard that semantic information is not equivalent between them, resulting in a suboptimal alignment. In this work, we propose a novel network to extract multi-view semantic concepts from documents and images and align the matching rather than entire concepts. Specifically, we propose a semantic decomposition module to generate multi-view semantic embeddings from visual and textual sides, providing the basic concepts for partial alignment. To alleviate the issue of information redundancy among embeddings, we propose the local-to-semantic variance loss to capture distinct local details and multiple semantic diversity loss to enforce orthogonality among embeddings. Subsequently, two losses are introduced to partially align visual-semantic embedding pairs according to their semantic relevance at the view and word-to-patch levels. Consequently, we consistently outperform state-of-the-art methods under two document sources in three standard benchmarks for document-based zero-shot learning. Qualitatively, we show that our model learns the interpretable partial association.
Authors: Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Yuan-Fang Li, Cunjian Chen, Yu Qiao
Abstract: Diffusion models have achieved great progress in image animation due to powerful generative capabilities. However, maintaining spatio-temporal consistency with detailed information from the input static image over time (e.g., style, background, and object of the input static image) and ensuring smoothness in animated video narratives guided by textual prompts still remains challenging. In this paper, we introduce Cinemo, a novel image animation approach towards achieving better motion controllability, as well as stronger temporal consistency and smoothness. In general, we propose three effective strategies at the training and inference stages of Cinemo to accomplish our goal. At the training stage, Cinemo focuses on learning the distribution of motion residuals, rather than directly predicting subsequent via a motion diffusion model. Additionally, a structural similarity index-based strategy is proposed to enable Cinemo to have better controllability of motion intensity. At the inference stage, a noise refinement technique based on discrete cosine transformation is introduced to mitigate sudden motion changes. Such three strategies enable Cinemo to produce highly consistent, smooth, and motion-controllable results. Compared to previous methods, Cinemo offers simpler and more precise user controllability. Extensive experiments against several state-of-the-art methods, including both commercial tools and research approaches, across multiple metrics, demonstrate the effectiveness and superiority of our proposed approach.
Authors: Jinfu Liu, Chen Chen, Mengyuan Liu
Abstract: Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other multimodal methods require substantial inference resources and are inefficient when using multimodal data during both training and inference stages. To address this and fully harness the complementary multimodal features, we propose a novel multi-modality co-learning (MMCL) framework by leveraging the multimodal large language models (LLMs) as auxiliary networks for efficient skeleton-based action recognition, which engages in multi-modality co-learning during the training stage and keeps efficiency by employing only concise skeletons in inference. Our MMCL framework primarily consists of two modules. First, the Feature Alignment Module (FAM) extracts rich RGB features from video frames and aligns them with global skeleton features via contrastive learning. Second, the Feature Refinement Module (FRM) uses RGB images with temporal information and text instruction to generate instructive features based on the powerful generalization of multimodal LLMs. These instructive text features will further refine the classification scores and the refined scores will enhance the model's robustness and generalization in a manner similar to soft labels. Extensive experiments on NTU RGB+D, NTU RGB+D 120 and Northwestern-UCLA benchmarks consistently verify the effectiveness of our MMCL, which outperforms the existing skeleton-based action recognition methods. Meanwhile, experiments on UTD-MHAD and SYSU-Action datasets demonstrate the commendable generalization of our MMCL in zero-shot and domain-adaptive action recognition. Our code is publicly available at: https://github.com/liujf69/MMCL-Action.
Authors: Guiqiu Liao, Matjaz Jogan, Sai Koushik, Eric Eaton, Daniel A. Hashimoto
Abstract: Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring an extensive training dataset of object masks, relying instead on coarse video labels indicating object presence. Current state-of-the-art methods either require multiple independent stages of processing that employ motion cues or, in the case of end-to-end trainable networks, lack in segmentation accuracy, in part due to the difficulty of learning segmentation maps from videos with transient object presence. This limits the application of WSVOS for semantic annotation of surgical videos where multiple surgical tools frequently move in and out of the field of view, a problem that is more difficult than typically encountered in WSVOS. This paper introduces Video Spatio-Temporal Disentanglement Networks (VDST-Net), a framework to disentangle spatiotemporal information using semi-decoupled knowledge distillation to predict high-quality class activation maps (CAMs). A teacher network designed to resolve temporal conflicts when specifics about object location and timing in the video are not provided works with a student network that integrates information over time by leveraging temporal dependencies. We demonstrate the efficacy of our framework on a public reference dataset and on a more challenging surgical video dataset where objects are, on average, present in less than 60\% of annotated frames. Our method outperforms state-of-the-art techniques and generates superior segmentation masks under video-level weak supervision.
Authors: Ben Adcock, Matthew J. Colbrook, Maksym Neyra-Nesterenko
Abstract: Sharpness is an almost generic assumption in continuous optimization that bounds the distance from minima by objective function suboptimality. It facilitates the acceleration of first-order methods through restarts. However, sharpness involves problem-specific constants that are typically unknown, and restart schemes typically reduce convergence rates. Moreover, these schemes are challenging to apply in the presence of noise or with approximate model classes (e.g., in compressive imaging or learning problems), and they generally assume that the first-order method used produces feasible iterates. We consider the assumption of approximate sharpness, a generalization of sharpness that incorporates an unknown constant perturbation to the objective function error. This constant offers greater robustness (e.g., with respect to noise or relaxation of model classes) for finding approximate minimizers. By employing a new type of search over the unknown constants, we design a restart scheme that applies to general first-order methods and does not require the first-order method to produce feasible iterates. Our scheme maintains the same convergence rate as when the constants are known. The convergence rates we achieve for various first-order methods match the optimal rates or improve on previously established rates for a wide range of problems. We showcase our restart scheme in several examples and highlight potential future applications and developments of our framework and theory.
Authors: Nicholas Konz, Haoyu Dong, Maciej A. Mazurowski
Abstract: Automated tumor detection in Digital Breast Tomosynthesis (DBT) is a difficult task due to natural tumor rarity, breast tissue variability, and high resolution. Given the scarcity of abnormal images and the abundance of normal images for this problem, an anomaly detection/localization approach could be well-suited. However, most anomaly localization research in machine learning focuses on non-medical datasets, and we find that these methods fall short when adapted to medical imaging datasets. The problem is alleviated when we solve the task from the image completion perspective, in which the presence of anomalies can be indicated by a discrepancy between the original appearance and its auto-completion conditioned on the surroundings. However, there are often many valid normal completions given the same surroundings, especially in the DBT dataset, making this evaluation criterion less precise. To address such an issue, we consider pluralistic image completion by exploring the distribution of possible completions instead of generating fixed predictions. This is achieved through our novel application of spatial dropout on the completion network during inference time only, which requires no additional training cost and is effective at generating diverse completions. We further propose minimum completion distance (MCD), a new metric for detecting anomalies, thanks to these stochastic completions. We provide theoretical as well as empirical support for the superiority over existing methods of using the proposed method for anomaly localization. On the DBT dataset, our model outperforms other state-of-the-art methods by at least 10\% AUROC for pixel-level detection.
Authors: Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting
Abstract: The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy attacks. Unfortunately, the task of removing specific information from the models without sacrificing performance is not straightforward and has proven to be challenging. We propose a rather easy yet effective defense based on backdoor attacks to remove private information, such as names and faces of individuals, from vision-language models by fine-tuning them for only a few minutes instead of re-training them from scratch. Specifically, by strategically inserting backdoors into text encoders, we align the embeddings of sensitive phrases with those of neutral terms-"a person" instead of the person's actual name. For image encoders, we map individuals' embeddings to be removed from the model to a universal, anonymous embedding. The results of our extensive experimental evaluation demonstrate the effectiveness of our backdoor-based defense on CLIP by assessing its performance using a specialized privacy attack for zero-shot classifiers. Our approach provides a new "dual-use" perspective on backdoor attacks and presents a promising avenue to enhance the privacy of individuals within models trained on uncurated web-scraped data.
Authors: Iain Xie Weissburg, Mehir Arora, Xinyi Wang, Liangming Pan, William Yang Wang
Abstract: As the number of accepted papers at AI and ML conferences reaches into the thousands, it has become unclear how researchers access and read research publications. In this paper, we investigate the role of social media influencers in enhancing the visibility of machine learning research, particularly the citation counts of papers they share. We have compiled a comprehensive dataset of over 8,000 papers, spanning tweets from December 2018 to October 2023, alongside controls precisely matched by 9 key covariates. Our statistical and causal inference analysis reveals a significant increase in citations for papers endorsed by these influencers, with median citation counts 2-3 times higher than those of the control group. Additionally, the study delves into the geographic, gender, and institutional diversity of highlighted authors. Given these findings, we advocate for a responsible approach to curation, encouraging influencers to uphold the journalistic standard that includes showcasing diverse research topics, authors, and institutions.
Authors: Yutao Feng, Xiang Feng, Yintong Shang, Ying Jiang, Chang Yu, Zeshun Zong, Tianjia Shao, Hongzhi Wu, Kun Zhou, Chenfanfu Jiang, Yin Yang
Abstract: We demonstrate the feasibility of integrating physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS. Leveraging the coherence of the Gaussian Splatting and Position-Based Dynamics (PBD) in the underlying representation, we manage rendering, view synthesis, and the dynamics of solids and fluids in a cohesive manner. Similar to GaussianShader, we enhance each Gaussian kernel with an added normal, aligning the kernel's orientation with the surface normal to refine the PBD simulation. This approach effectively eliminates spiky noises that arise from rotational deformation in solids. It also allows us to integrate physically based rendering to augment the dynamic surface reflections on fluids. Consequently, our framework is capable of realistically reproducing surface highlights on dynamic fluids and facilitating interactions between scene objects and fluids from new views. For more information, please visit our project page at \url{https://gaussiansplashing.github.io/}.
Authors: Bartlomiej Sobieski, Przemys{\l}aw Biecek
Abstract: Despite increasing progress in development of methods for generating visual counterfactual explanations, especially with the recent rise of Denoising Diffusion Probabilistic Models, previous works consider them as an entirely local technique. In this work, we take the first step at globalizing them. Specifically, we discover that the latent space of Diffusion Autoencoders encodes the inference process of a given classifier in the form of global directions. We propose a novel proxy-based approach that discovers two types of these directions with the use of only single image in an entirely black-box manner. Precisely, g-directions allow for flipping the decision of a given classifier on an entire dataset of images, while h-directions further increase the diversity of explanations. We refer to them in general as Global Counterfactual Directions (GCDs). Moreover, we show that GCDs can be naturally combined with Latent Integrated Gradients resulting in a new black-box attribution method, while simultaneously enhancing the understanding of counterfactual explanations. We validate our approach on existing benchmarks and show that it generalizes to real-world use-cases.
Authors: \c{S}\"ukr\"u \"Ozt\"urk, Hacer Yalim Keles
Abstract: This study introduces the continuous Educational Turkish Sign Language (E-TSL) dataset, collected from online Turkish language lessons for 5th, 6th, and 8th grades. The dataset comprises 1,410 videos totaling nearly 24 hours and includes performances from 11 signers. Turkish, an agglutinative language, poses unique challenges for sign language translation, particularly with a vocabulary where 64% are singleton words and 85% are rare words, appearing less than five times. We developed two baseline models to address these challenges: the Pose to Text Transformer (P2T-T) and the Graph Neural Network based Transformer (GNN-T) models. The GNN-T model achieved 19.13% BLEU-1 score and 3.28% BLEU-4 score, presenting a significant challenge compared to existing benchmarks. The P2T-T model, while demonstrating slightly lower performance in BLEU scores, achieved a higher ROUGE-L score of 22.09%. Additionally, we benchmarked our model using the well-known PHOENIX-Weather 2014T dataset to validate our approach.
Authors: Minyoung Huh, Brian Cheung, Tongzhou Wang, Phillip Isola
Abstract: We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato's concept of an ideal reality. We term such a representation the platonic representation and discuss several possible selective pressures toward it. Finally, we discuss the implications of these trends, their limitations, and counterexamples to our analysis.
Authors: Alireza Aghelan, Ali Amiryan, Abolfazl Zarghani, Behnoush Hatami, Modjtaba Rouhani
Abstract: In the field of single image super-resolution (SISR), transformer-based models, have demonstrated significant advancements. However, the potential and efficiency of these models in applied fields such as real-world image super-resolution have been less noticed and there are substantial opportunities for improvement. Recently, composite fusion attention transformer (CFAT), outperformed previous state-of-the-art (SOTA) models in classic image super-resolution. This paper extends the CFAT model to an improved GAN-based model called IG-CFAT to effectively exploit the performance of transformers in real-world image super-resolution. IG-CFAT incorporates a semantic-aware discriminator to reconstruct fine details more accurately. Moreover, our model utilizes an adaptive degradation model to better simulate real-world degradations. Our methodology adds wavelet loss to conventional loss functions of GAN-based super-resolution models to recover high-frequency details more efficiently. Empirical results demonstrate that IG-CFAT sets new benchmarks in real-world image super-resolution, outperforming SOTA models in quantitative and qualitative metrics.
Authors: Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
Abstract: The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental prerequisite to measure progress towards those challenges. Similar datasets are largely absent in the medical imaging community which lacks a comprehensive benchmark that spans across imaging modalities and applications. To address this gap, we create and open-source MedMNIST-C, a benchmark dataset based on the MedMNIST+ collection covering 12 datasets and 9 imaging modalities. We simulate task and modality-specific image corruptions of varying severity to comprehensively evaluate the robustness of established algorithms against real-world artifacts and distribution shifts. We further provide quantitative evidence that our simple-to-use artificial corruptions allow for highly performant, lightweight data augmentation to enhance model robustness. Unlike traditional, generic augmentation strategies, our approach leverages domain knowledge, exhibiting significantly higher robustness when compared to widely adopted methods. By introducing MedMNIST-C and open-sourcing the corresponding library allowing for targeted data augmentations, we contribute to the development of increasingly robust methods tailored to the challenges of medical imaging. The code is available at https://github.com/francescodisalvo05/medmnistc-api .
Authors: Shiyi Wang, Yang Nan, Sheng Zhang, Federico Felder, Xiaodan Xing, Yingying Fang, Javier Del Ser, Simon L F Walsh, Guang Yang
Abstract: In pulmonary tracheal segmentation, the scarcity of annotated data is a prevalent issue in medical segmentation. Additionally, Deep Learning (DL) methods face challenges: the opacity of 'black box' models and the need for performance enhancement. Our Human-Computer Interaction (HCI) based models (RS_UNet, LC_UNet, UUNet, and WD_UNet) address these challenges by combining diverse query strategies with various DL models. We train four HCI models and repeat these steps: (1) Query Strategy: The HCI models select samples that provide the most additional representative information when labeled in each iteration and identify unlabeled samples with the greatest predictive disparity using Wasserstein Distance, Least Confidence, Entropy Sampling, and Random Sampling. (2) Central line correction: Selected samples are used for expert correction of system-generated tracheal central lines in each training round. (3) Update training dataset: Experts update the training dataset after each DL model's training epoch, enhancing the trustworthiness and performance of the models. (4) Model training: The HCI model is trained using the updated dataset and an enhanced UNet version. Experimental results confirm the effectiveness of these HCI-based approaches, showing that WD-UNet, LC-UNet, UUNet, and RS-UNet achieve comparable or superior performance to state-of-the-art DL models. Notably, WD-UNet achieves this with only 15%-35% of the training data, reducing physician annotation time by 65%-85%.
Authors: Eric A. F. Reinhardt, P. R. Dinesh, Sergei Gleyzer
Abstract: Recent work has established an alternative to traditional multi-layer perceptron neural networks in the form of Kolmogorov-Arnold Networks (KAN). The general KAN framework uses learnable activation functions on the edges of the computational graph followed by summation on nodes. The learnable edge activation functions in the original implementation are basis spline functions (B-Spline). Here, we present a model in which learnable grids of B-Spline activation functions are replaced by grids of re-weighted sine functions. We show that this leads to better or comparable numerical performance to B-Spline KAN models on the MNIST benchmark, while also providing a substantial speed increase on the order of 4-8 times.
Authors: Maziar Sabouri, Shadab Ahamed, Azin Asadzadeh, Atlas Haddadi Avval, Soroush Bagheri, Mohsen Arabi, Seyed Rasoul Zakavi, Emran Askari, Ali Rasouli, Atena Aghaee, Mohaddese Sehati, Fereshteh Yousefirizi, Carlos Uribe, Ghasem Hajianfar, Habib Zaidi, Arman Rahmim
Abstract: The objective of this study was to develop an automated pipeline that enhances thyroid disease classification using thyroid scintigraphy images, aiming to decrease assessment time and increase diagnostic accuracy. Anterior thyroid scintigraphy images from 2,643 patients were collected and categorized into diffuse goiter (DG), multinodal goiter (MNG), and thyroiditis (TH) based on clinical reports, and then segmented by an expert. A ResUNet model was trained to perform auto-segmentation. Radiomic features were extracted from both physician (scenario 1) and ResUNet segmentations (scenario 2), followed by omitting highly correlated features using Spearman's correlation, and feature selection using Recursive Feature Elimination (RFE) with XGBoost as the core. All models were trained under leave-one-center-out cross-validation (LOCOCV) scheme, where nine instances of algorithms were iteratively trained and validated on data from eight centers and tested on the ninth for both scenarios separately. Segmentation performance was assessed using the Dice similarity coefficient (DSC), while classification performance was assessed using metrics, such as precision, recall, F1-score, accuracy, area under the Receiver Operating Characteristic (ROC AUC), and area under the precision-recall curve (PRC AUC). ResUNet achieved DSC values of 0.84$\pm$0.03, 0.71$\pm$0.06, and 0.86$\pm$0.02 for MNG, TH, and DG, respectively. Classification in scenario 1 achieved an accuracy of 0.76$\pm$0.04 and a ROC AUC of 0.92$\pm$0.02 while in scenario 2, classification yielded an accuracy of 0.74$\pm$0.05 and a ROC AUC of 0.90$\pm$0.02. The automated pipeline demonstrated comparable performance to physician segmentations on several classification metrics across different classes, effectively reducing assessment time while maintaining high diagnostic accuracy. Code available at: https://github.com/ahxmeds/thyroidiomics.git.
Authors: Karim Kadry, Shreya Gupta, Jonas Sogbadji, Michiel Schaap, Kersten Petersen, Takuya Mizukami, Carlos Collet, Farhad R. Nezami, Elazer R. Edelman
Abstract: Virtual interventions enable the physics-based simulation of device deployment within coronary arteries. This framework allows for counterfactual reasoning by deploying the same device in different arterial anatomies. However, current methods to create such counterfactual arteries face a trade-off between controllability and realism. In this study, we investigate how Latent Diffusion Models (LDMs) can custom synthesize coronary anatomy for virtual intervention studies based on mid-level anatomic constraints such as topological validity, local morphological shape, and global skeletal structure. We also extend diffusion model guidance strategies to the context of morpho-skeletal conditioning and propose a novel guidance method for continuous attributes that adaptively updates the negative guiding condition throughout sampling. Our framework enables the generation and editing of coronary anatomy in a controllable manner, allowing device designers to derive mechanistic insights regarding anatomic variation and simulated device deployment.