Authors: Frincy Clement, Ji Yang, Irene Cheng
Abstract: Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision fields such as security, finance, health, and manufacturing industries. A lot of focused work has been done to provide interpretable models, intending to deliver meaningful insights into the thoughts and behavior of neural networks. In our research, we compare the state-of-the-art methods in the Activation-based methods (ABM) for interpreting predictions of CNN models, specifically in the application of Image Classification. We then extend the same for eight CNN-based architectures to compare the differences in visualization and thus interpretability. We introduced a novel technique Feature CAM, which falls in the perturbation-activation combination, to create fine-grained, class-discriminative visualizations. The resulting saliency maps from our experiments proved to be 3-4 times better human interpretable than the state-of-the-art in ABM. At the same time it reserves machine interpretability, which is the average confidence scores in classification.
Authors: Lin Zhang, Shentong Mo, Yijing Zhang, Pedro Morgado
Abstract: Current visual generation methods can produce high quality videos guided by texts. However, effectively controlling object dynamics remains a challenge. This work explores audio as a cue to generate temporally synchronized image animations. We introduce Audio Synchronized Visual Animation (ASVA), a task animating a static image to demonstrate motion dynamics, temporally guided by audio clips across multiple classes. To this end, we present AVSync15, a dataset curated from VGGSound with videos featuring synchronized audio visual events across 15 categories. We also present a diffusion model, AVSyncD, capable of generating dynamic animations guided by audios. Extensive evaluations validate AVSync15 as a reliable benchmark for synchronized generation and demonstrate our models superior performance. We further explore AVSyncDs potential in a variety of audio synchronized generation tasks, from generating full videos without a base image to controlling object motions with various sounds. We hope our established benchmark can open new avenues for controllable visual generation. More videos on project webpage https://lzhangbj.github.io/projects/asva/asva.html.
Authors: Chengxu Liu, Xuan Wang, Yuanting Fan, Shuai Li, Xueming Qian
Abstract: Under-display camera (UDC) systems are the foundation of full-screen display devices in which the lens mounts under the display. The pixel array of light-emitting diodes used for display diffracts and attenuates incident light, causing various degradations as the light intensity changes. Unlike general video restoration which recovers video by treating different degradation factors equally, video restoration for UDC systems is more challenging that concerns removing diverse degradation over time while preserving temporal consistency. In this paper, we introduce a novel video restoration network, called D$^2$RNet, specifically designed for UDC systems. It employs a set of Decoupling Attention Modules (DAM) that effectively separate the various video degradation factors. More specifically, a soft mask generation function is proposed to formulate each frame into flare and haze based on the diffraction arising from incident light of different intensities, followed by the proposed flare and haze removal components that leverage long- and short-term feature learning to handle the respective degradations. Such a design offers an targeted and effective solution to eliminating various types of degradation in UDC systems. We further extend our design into multi-scale to overcome the scale-changing of degradation that often occur in long-range videos. To demonstrate the superiority of D$^2$RNet, we propose a large-scale UDC video benchmark by gathering HDR videos and generating realistically degraded videos using the point spread function measured by a commercial UDC system. Extensive quantitative and qualitative evaluations demonstrate the superiority of D$^2$RNet compared to other state-of-the-art video restoration and UDC image restoration methods. Code is available at https://github.com/ChengxuLiu/DDRNet.git
Authors: Jun Wang, Lixing Zhu, Abhir Bhalerao, Yulan He
Abstract: Radiology report generation (RRG) methods often lack sufficient medical knowledge to produce clinically accurate reports. The scene graph contains rich information to describe the objects in an image. We explore enriching the medical knowledge for RRG via a scene graph, which has not been done in the current RRG literature. To this end, we propose the Scene Graph aided RRG (SGRRG) network, a framework that generates region-level visual features, predicts anatomical attributes, and leverages an automatically generated scene graph, thus achieving medical knowledge distillation in an end-to-end manner. SGRRG is composed of a dedicated scene graph encoder responsible for translating the scene graph, and a scene graph-aided decoder that takes advantage of both patch-level and region-level visual information. A fine-grained, sentence-level attention method is designed to better dis-till the scene graph information. Extensive experiments demonstrate that SGRRG outperforms previous state-of-the-art methods in report generation and can better capture abnormal findings.
Authors: Lixu Wang, Xinyu Du, Qi Zhu
Abstract: Cross-domain retrieval (CDR), as a crucial tool for numerous technologies, is finding increasingly broad applications. However, existing efforts face several major issues, with the most critical being the need for accurate supervision, which often demands costly resources and efforts. Cutting-edge studies focus on achieving unsupervised CDR but typically assume that the category spaces across domains are identical, an assumption that is often unrealistic in real-world scenarios. This is because only through dedicated and comprehensive analysis can the category spaces of different domains be confirmed as identical, which contradicts the premise of unsupervised scenarios. Therefore, in this work, we introduce the problem of Universal Unsupervised Cross-Domain Retrieval (U^2CDR) for the first time and design a two-stage semantic feature learning framework to address it. In the first stage, a cross-domain unified prototypical structure is established under the guidance of an instance-prototype-mixed contrastive loss and a semantic-enhanced loss, to counteract category space differences. In the second stage, through a modified adversarial training mechanism, we ensure minimal changes for the established prototypical structure during domain alignment, enabling more accurate nearest-neighbor searching. Extensive experiments across multiple datasets and scenarios, including closet, partial, and open-set CDR, demonstrate that our approach significantly outperforms existing state-of-the-art CDR works and some potentially effective studies from other topics in solving U^2CDR challenges.
Authors: Booy Vitas Faassen, Jorge Serrano, Paul D. Rosero-Montalvo
Abstract: Solar energy is rapidly becoming a robust renewable energy source to conventional finite resources such as fossil fuels. It is harvested using interconnected photovoltaic panels, typically built with crystalline silicon cells, i.e. semiconducting materials that convert effectively the solar radiation into electricity. However, crystalline silicon is fragile and vulnerable to cracking over time or in predictive maintenance tasks, which can lead to electric isolation of parts of the solar cell and even failure, thus affecting the panel performance and reducing electricity generation. This work aims to developing a system for detecting cell cracks in solar panels to anticipate and alaert of a potential failure of the photovoltaic system by using computer vision techniques. Three scenarios are defined where these techniques will bring value. In scenario A, images are taken manually and the system detecting failures in the solar cells is not subject to any computationa constraints. In scenario B, an Edge device is placed near the solar farm, able to make inferences. Finally, in scenario C, a small microcontroller is placed in a drone flying over the solar farm and making inferences about the solar cells' states. Three different architectures are found the most suitable solutions, one for each scenario, namely the InceptionV3 model, an EfficientNetB0 model shrunk into full integer quantization, and a customized CNN architechture built with VGG16 blocks.
Authors: Junde Wu, Jiayuan Zhu, Min Xu, Yueming Jin
Abstract: Some visual recognition tasks are more challenging then the general ones as they require professional categories of images. The previous efforts, like fine-grained vision classification, primarily introduced models tailored to specific tasks, like identifying bird species or car brands with limited scalability and generalizability. This paper aims to design a scalable and explainable model to solve Professional Visual Recognition tasks from a generic standpoint. We introduce a biologically-inspired structure named Pro-NeXt and reveal that Pro-NeXt exhibits substantial generalizability across diverse professional fields such as fashion, medicine, and art-areas previously considered disparate. Our basic-sized Pro-NeXt-B surpasses all preceding task-specific models across 12 distinct datasets within 5 diverse domains. Furthermore, we find its good scaling property that scaling up Pro-NeXt in depth and width with increasing GFlops can consistently enhances its accuracy. Beyond scalability and adaptability, the intermediate features of Pro-NeXt achieve reliable object detection and segmentation performance without extra training, highlighting its solid explainability. We will release the code to foster further research in this area.
Authors: Fan Yang, Benjamin Planche, Meng Zheng, Cheng Chen, Terrence Chen, Ziyan Wu
Abstract: For decades, three-dimensional C-arm Cone-Beam Computed Tomography (CBCT) imaging system has been a critical component for complex vascular and nonvascular interventional procedures. While it can significantly improve multiplanar soft tissue imaging and provide pre-treatment target lesion roadmapping and guidance, the traditional workflow can be cumbersome and time-consuming, especially for less experienced users. To streamline this process and enhance procedural efficiency overall, we proposed a visual perception system, namely AutoCBCT, seamlessly integrated with an angiography suite. This system dynamically models both the patient's body and the surgical environment in real-time. AutoCBCT enables a novel workflow with automated positioning, navigation and simulated test-runs, eliminating the need for manual operations and interactions. The proposed system has been successfully deployed and studied in both lab and clinical settings, demonstrating significantly improved workflow efficiency.
Authors: Siwen Liu, Jinyan Liu, Hanning Yuan, Qi Li, Jing Geng, Ziqiang Yuan, Huaxu Han
Abstract: Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting the performance of existing algorithms from further improvement. To solve this problem, we propose a multi-view clustering framework named Deep Contrastive Multi-view Clustering under Semantic feature guidance (DCMCS) to alleviate the influence of false negative pairs. Specifically, view-specific features are firstly extracted from raw features and fused to obtain fusion view features according to view importance. To mitigate the interference of view-private information, specific view and fusion view semantic features are learned by cluster-level contrastive learning and concatenated to measure the semantic similarity of instances. By minimizing instance-level contrastive loss weighted by semantic similarity, DCMCS adaptively weakens contrastive leaning between false negative pairs. Experimental results on several public datasets demonstrate the proposed framework outperforms the state-of-the-art methods.
Authors: Bingqian Lin, Yanxin Long, Yi Zhu, Fengda Zhu, Xiaodan Liang, Qixiang Ye, Liang Lin
Abstract: Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. Despite significant advances, conventional VLN agents are trained typically under disturbance-free environments and may easily fail in real-world scenarios, since they are unaware of how to deal with various possible disturbances, such as sudden obstacles or human interruptions, which widely exist and may usually cause an unexpected route deviation. In this paper, we present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents, by requiring them to learn towards deviation-robust navigation. Specifically, a simple yet effective path perturbation scheme is introduced to implement the route deviation, with which the agent is required to still navigate successfully following the original instruction. Since directly enforcing the agent to learn perturbed trajectories may lead to inefficient training, a progressively perturbed trajectory augmentation strategy is designed, where the agent can self-adaptively learn to navigate under perturbation with the improvement of its navigation performance for each specific trajectory. For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts. Extensive experiments on R2R show that PROPER can benefit multiple VLN baselines in perturbation-free scenarios. We further collect the perturbed path data to construct an introspection subset based on the R2R, called Path-Perturbed R2R (PP-R2R). The results on PP-R2R show unsatisfying robustness of popular VLN agents and the capability of PROPER in improving the navigation robustness.
Authors: Jincheng Zhang, William Ringle, Andrew R. Willis
Abstract: Manual identification of archaeological features in LiDAR imagery is labor-intensive, costly, and requires archaeological expertise. This paper shows how recent advancements in deep learning (DL) present efficient solutions for accurately segmenting archaeological structures in aerial LiDAR images using the YOLOv8 neural network. The proposed approach uses novel pre-processing of the raw LiDAR data and dataset augmentation methods to produce trained YOLOv8 networks to improve accuracy, precision, and recall for the segmentation of two important Maya structure types: annular structures and platforms. The results show an IoU performance of 0.842 for platforms and 0.809 for annular structures which outperform existing approaches. Further, analysis via domain experts considers the topological consistency of segmented regions and performance vs. area providing important insights. The approach automates time-consuming LiDAR image labeling which significantly accelerates accurate analysis of historical landscapes.
Authors: Lin Tian, Hastings Greer, Roland Kwitt, Francois-Xavier Vialard, Raul San Jose Estepar, Sylvain Bouix, Richard Rushmore, Marc Niethammer
Abstract: Conventional medical image registration approaches directly optimize over the parameters of a transformation model. These approaches have been highly successful and are used generically for registrations of different anatomical regions. Recent deep registration networks are incredibly fast and accurate but are only trained for specific tasks. Hence, they are no longer generic registration approaches. We therefore propose uniGradICON, a first step toward a foundation model for registration providing 1) great performance \emph{across} multiple datasets which is not feasible for current learning-based registration methods, 2) zero-shot capabilities for new registration tasks suitable for different acquisitions, anatomical regions, and modalities compared to the training dataset, and 3) a strong initialization for finetuning on out-of-distribution registration tasks. UniGradICON unifies the speed and accuracy benefits of learning-based registration algorithms with the generic applicability of conventional non-deep-learning approaches. We extensively trained and evaluated uniGradICON on twelve different public datasets. Our code and the uniGradICON model are available at https://github.com/uncbiag/uniGradICON.
Authors: Binghao Lu, Caiwen Ding, Jinbo Bi, Dongjin Song
Abstract: Change detection, which aims to detect spatial changes from a pair of multi-temporal images due to natural or man-made causes, has been widely applied in remote sensing, disaster management, urban management, etc. Most existing change detection approaches, however, are fully supervised and require labor-intensive pixel-level labels. To address this, we develop a novel weakly supervised change detection technique via Knowledge Distillation and Multiscale Sigmoid Inference (KD-MSI) that leverages image-level labels. In our approach, the Class Activation Maps (CAM) are utilized not only to derive a change probability map but also to serve as a foundation for the knowledge distillation process. This is done through a joint training strategy of the teacher and student networks, enabling the student network to highlight potential change areas more accurately than teacher network based on image-level labels. Moreover, we designed a Multiscale Sigmoid Inference (MSI) module as a post processing step to further refine the change probability map from the trained student network. Empirical results on three public datasets, i.e., WHU-CD, DSIFN-CD, and LEVIR-CD, demonstrate that our proposed technique, with its integrated training strategy, significantly outperforms the state-of-the-art.
Authors: Chunwei Tian, Menghua Zheng, Tiancai Jiao, Wangmeng Zuo, Yanning Zhang, Chia-Wen Lin
Abstract: Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal. However, watermarked images do not have reference images in the real world, which results in poor robustness of image watermark removal techniques. In this paper, we propose a self-supervised convolutional neural network (CNN) in image watermark removal (SWCNN). SWCNN uses a self-supervised way to construct reference watermarked images rather than given paired training samples, according to watermark distribution. A heterogeneous U-Net architecture is used to extract more complementary structural information via simple components for image watermark removal. Taking into account texture information, a mixed loss is exploited to improve visual effects of image watermark removal. Besides, a watermark dataset is conducted. Experimental results show that the proposed SWCNN is superior to popular CNNs in image watermark removal.
Authors: Junxiong Lin, Yan Wang, Zeng Tao, Boyang Wang, Qing Zhao, Haorang Wang, Xuan Tong, Xinji Mai, Yuxuan Lin, Wei Song, Jiawen Yu, Shaoqi Yan, Wenqiang Zhang
Abstract: Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue. Nonetheless, prevailing diffusion-based methodologies presently overlook the constraints imposed by degradation information on the diffusion process. Furthermore, these methods fail to consider the spatial variability inherent in the estimated blur kernel, stemming from factors such as motion jitter and out-of-focus elements in open-environment scenarios. This oversight results in a notable deviation of the image super-resolution effect from fundamental realities. To address these concerns, we introduce a framework known as Adaptive Multi-modal Fusion of \textbf{S}patially Variant Kernel Refinement with Diffusion Model for Blind Image \textbf{S}uper-\textbf{R}esolution (SSR). Within the SSR framework, we propose a Spatially Variant Kernel Refinement (SVKR) module. SVKR estimates a Depth-Informed Kernel, which takes the depth information into account and is spatially variant. Additionally, SVKR enhance the accuracy of depth information acquired from LR images, allowing for mutual enhancement between the depth map and blur kernel estimates. Finally, we introduce the Adaptive Multi-Modal Fusion (AMF) module to align the information from three modalities: low-resolution images, depth maps, and blur kernels. This alignment can constrain the diffusion model to generate more authentic SR results. Quantitative and qualitative experiments affirm the superiority of our approach, while ablation experiments corroborate the effectiveness of the modules we have proposed.
Authors: Yonghao Dong, Le Wang, Sanping Zhou, Gang Hua, Changyin Sun
Abstract: Pedestrian trajectory prediction is a crucial component in computer vision and robotics, but remains challenging due to the domain shift problem. Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model. However, such domain adaptation methods are impractical in real-world scenarios, as it is infeasible to collect trajectory data from all potential target domains. In this paper, we study a task named generalized pedestrian trajectory prediction, with the aim of generalizing the model to unseen domains without accessing their trajectories. To tackle this task, we introduce a Recurrent Aligned Network~(RAN) to minimize the domain gap through domain alignment. Specifically, we devise a recurrent alignment module to effectively align the trajectory feature spaces at both time-state and time-sequence levels by the recurrent alignment strategy.Furthermore, we introduce a pre-aligned representation module to combine social interactions with the recurrent alignment strategy, which aims to consider social interactions during the alignment process instead of just target trajectories. We extensively evaluate our method and compare it with state-of-the-art methods on three widely used benchmarks. The experimental results demonstrate the superior generalization capability of our method. Our work not only fills the gap in the generalization setting for practical pedestrian trajectory prediction but also sets strong baselines in this field.
Authors: Gang Zhang, Junnan Chen, Guohuan Gao, Jianmin Li, Si Liu, Xiaolin Hu
Abstract: LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the computational costs introduced by the dense feature maps grow quadratically as the perception range increases, making these models hard to scale up to long-range detection. Some recent works have attempted to construct fully sparse detectors to solve this issue; nevertheless, the resulting models either rely on a complex multi-stage pipeline or exhibit inferior performance. In this work, we propose SAFDNet, a straightforward yet highly effective architecture, tailored for fully sparse 3D object detection. In SAFDNet, an adaptive feature diffusion strategy is designed to address the center feature missing problem. We conducted extensive experiments on Waymo Open, nuScenes, and Argoverse2 datasets. SAFDNet performed slightly better than the previous SOTA on the first two datasets but much better on the last dataset, which features long-range detection, verifying the efficacy of SAFDNet in scenarios where long-range detection is required. Notably, on Argoverse2, SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1x faster, and yielded 2.1% mAP gains over the previous best sparse detector FSDv2 while being 1.3x faster. The code will be available at https://github.com/zhanggang001/HEDNet.
Authors: Xiao Wang, Ju Huang, Shiao Wang, Chuanming Tang, Bo Jiang, Yonghong Tian, Jin Tang, Bin Luo
Abstract: Current event-/frame-event based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios remains unclear. In this paper, we first propose a new long-term and large-scale frame-event single object tracking dataset, termed FELT. It contains 742 videos and 1,594,474 RGB frames and event stream pairs and has become the largest frame-event tracking dataset to date. We re-train and evaluate 15 baseline trackers on our dataset for future works to compare. More importantly, we find that the RGB frames and event streams are naturally incomplete due to the influence of challenging factors and spatially sparse event flow. In response to this, we propose a novel associative memory Transformer network as a unified backbone by introducing modern Hopfield layers into multi-head self-attention blocks to fuse both RGB and event data. Extensive experiments on both FELT and RGB-T tracking dataset LasHeR fully validated the effectiveness of our model. The dataset and source code can be found at \url{https://github.com/Event-AHU/FELT_SOT_Benchmark}.
Authors: Michael Toker, Hadas Orgad, Mor Ventura, Dana Arad, Yonatan Belinkov
Abstract: Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text representation is unknown. We propose the Diffusion Lens, a method for analyzing the text encoder of T2I models by generating images from its intermediate representations. Using the Diffusion Lens, we perform an extensive analysis of two recent T2I models. Exploring compound prompts, we find that complex scenes describing multiple objects are composed progressively and more slowly compared to simple scenes; Exploring knowledge retrieval, we find that representation of uncommon concepts requires further computation compared to common concepts, and that knowledge retrieval is gradual across layers. Overall, our findings provide valuable insights into the text encoder component in T2I pipelines.
Authors: Hanzheng Wang, Wei Li, Xiang-Gen Xia, Qian Du, Jing Tian
Abstract: Hyperspectral video (HSV) offers valuable spatial, spectral, and temporal information simultaneously, making it highly suitable for handling challenges such as background clutter and visual similarity in object tracking. However, existing methods primarily focus on band regrouping and rely on RGB trackers for feature extraction, resulting in limited exploration of spectral information and difficulties in achieving complementary representations of object features. In this paper, a spatial-spectral fusion network with spectral angle awareness (SST-Net) is proposed for hyperspectral (HS) object tracking. Firstly, to address the issue of insufficient spectral feature extraction in existing networks, a spatial-spectral feature backbone ($S^2$FB) is designed. With the spatial and spectral extraction branch, a joint representation of texture and spectrum is obtained. Secondly, a spectral attention fusion module (SAFM) is presented to capture the intra- and inter-modality correlation to obtain the fused features from the HS and RGB modalities. It can incorporate the visual information into the HS spectral context to form a robust representation. Thirdly, to ensure a more accurate response of the tracker to the object position, a spectral angle awareness module (SAAM) investigates the region-level spectral similarity between the template and search images during the prediction stage. Furthermore, we develop a novel spectral angle awareness loss (SAAL) to offer guidance for the SAAM based on similar regions. Finally, to obtain the robust tracking results, a weighted prediction method is considered to combine the HS and RGB predicted motions of objects to leverage the strengths of each modality. Extensive experiments on the HOTC dataset demonstrate the effectiveness of the proposed SSF-Net, compared with state-of-the-art trackers.
Authors: Qihao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, Jun Liu
Abstract: Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models (e.g., large language models, LLMs), LTGC leverages the power of these models to parse and reason over the original tail data to produce diverse tail-class content. We then propose several novel designs for LTGC to ensure the quality of the generated data and to efficiently fine-tune the model using both the generated and original data. The visualization demonstrates the effectiveness of the generation module in LTGC, which produces accurate and diverse tail data. Additionally, the experimental results demonstrate that our LTGC outperforms existing state-of-the-art methods on popular long-tailed benchmarks.
Authors: Boshen Xu, Sipeng Zheng, Qin Jin
Abstract: We humans are good at translating third-person observations of hand-object interactions (HOI) into an egocentric view. However, current methods struggle to replicate this ability of view adaptation from third-person to first-person. Although some approaches attempt to learn view-agnostic representation from large-scale video datasets, they ignore the relationships among multiple third-person views. To this end, we propose a Prompt-Oriented View-agnostic learning (POV) framework in this paper, which enables this view adaptation with few egocentric videos. Specifically, We introduce interactive masking prompts at the frame level to capture fine-grained action information, and view-aware prompts at the token level to learn view-agnostic representation. To verify our method, we establish two benchmarks for transferring from multiple third-person views to the egocentric view. Our extensive experiments on these benchmarks demonstrate the efficiency and effectiveness of our POV framework and prompt tuning techniques in terms of view adaptation and view generalization. Our code is available at \url{https://github.com/xuboshen/pov_acmmm2023}.
Authors: Boshen Xu, Sipeng Zheng, Qin Jin
Abstract: We introduce SPAFormer, an innovative model designed to overcome the combinatorial explosion challenge in the 3D Part Assembly (3D-PA) task. This task requires accurate prediction of each part's pose and shape in sequential steps, and as the number of parts increases, the possible assembly combinations increase exponentially, leading to a combinatorial explosion that severely hinders the efficacy of 3D-PA. SPAFormer addresses this problem by leveraging weak constraints from assembly sequences, effectively reducing the solution space's complexity. Since assembly part sequences convey construction rules similar to sentences being structured through words, our model explores both parallel and autoregressive generation. It further enhances assembly through knowledge enhancement strategies that utilize the attributes of parts and their sequence information, enabling it to capture the inherent assembly pattern and relationships among sequentially ordered parts. We also construct a more challenging benchmark named PartNet-Assembly covering 21 varied categories to more comprehensively validate the effectiveness of SPAFormer. Extensive experiments demonstrate the superior generalization capabilities of SPAFormer, particularly with multi-tasking and in scenarios requiring long-horizon assembly. Codes and model weights will be released at \url{https://github.com/xuboshen/SPAFormer}.
Authors: Runhua Jiang, Yahong Han
Abstract: Existing image restoration models are typically designed for specific tasks and struggle to generalize to out-of-sample degradations not encountered during training. While zero-shot methods can address this limitation by fine-tuning model parameters on testing samples, their effectiveness relies on predefined natural priors and physical models of specific degradations. Nevertheless, determining out-of-sample degradations faced in real-world scenarios is always impractical. As a result, it is more desirable to train restoration models with inherent generalization ability. To this end, this work introduces the Out-of-Sample Restoration (OSR) task, which aims to develop restoration models capable of handling out-of-sample degradations. An intuitive solution involves pre-translating out-of-sample degradations to known degradations of restoration models. However, directly translating them in the image space could lead to complex image translation issues. To address this issue, we propose a model reprogramming framework, which translates out-of-sample degradations by quantum mechanic and wave functions. Specifically, input images are decoupled as wave functions of amplitude and phase terms. The translation of out-of-sample degradation is performed by adapting the phase term. Meanwhile, the image content is maintained and enhanced in the amplitude term. By taking these two terms as inputs, restoration models are able to handle out-of-sample degradations without fine-tuning. Through extensive experiments across multiple evaluation cases, we demonstrate the effectiveness and flexibility of our proposed framework. Our codes are available at \href{https://github.com/ddghjikle/Out-of-sample-restoration}{Github}.
URLs: https://github.com/ddghjikle/Out-of-sample-restoration
Authors: Cuong Pham, Van-Anh Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do
Abstract: Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific form of intermediate feature-based knowledge distillation that uses attention mechanisms to encourage the student to better mimic the teacher. However, most of the previous attention-based distillation approaches perform attention in the spatial domain, which primarily affects local regions in the input image. This may not be sufficient when we need to capture the broader context or global information necessary for effective knowledge transfer. In frequency domain, since each frequency is determined from all pixels of the image in spatial domain, it can contain global information about the image. Inspired by the benefits of the frequency domain, we propose a novel module that functions as an attention mechanism in the frequency domain. The module consists of a learnable global filter that can adjust the frequencies of student's features under the guidance of the teacher's features, which encourages the student's features to have patterns similar to the teacher's features. We then propose an enhanced knowledge review-based distillation model by leveraging the proposed frequency attention module. The extensive experiments with various teacher and student architectures on image classification and object detection benchmark datasets show that the proposed approach outperforms other knowledge distillation methods.
Authors: Xiuzhe Wu, Xiaoyang Lyu, Qihao Huang, Yong Liu, Yang Wu, Ying Shan, Xiaojuan Qi
Abstract: Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dynamic nature of real-world scenes and fails to model the geometry and motion of moving objects. In this paper, we propose a self-supervised method to jointly learn 3D motion and depth from monocular videos. Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion. Depth and motion networks work collaboratively to faithfully model the geometry and dynamics of real-world scenes, which, in turn, benefits both depth and 3D motion estimation. Their predictions are further combined to synthesize a novel video frame for self-supervised training. As a core component of our framework, DO3D is a new motion disentanglement module that learns to predict camera ego-motion and instance-aware 3D object motion separately. To alleviate the difficulties in estimating non-rigid 3D object motions, they are decomposed to object-wise 6-DoF global transformations and a pixel-wise local 3D motion deformation field. Qualitative and quantitative experiments are conducted on three benchmark datasets, including KITTI, Cityscapes, and VKITTI2, where our model delivers superior performance in all evaluated settings. For the depth estimation task, our model outperforms all compared research works in the high-resolution setting, attaining an absolute relative depth error (abs rel) of 0.099 on the KITTI benchmark. Besides, our optical flow estimation results (an overall EPE of 7.09 on KITTI) also surpass state-of-the-art methods and largely improve the estimation of dynamic regions, demonstrating the effectiveness of our motion model. Our code will be available.
Authors: Xueqian Li, Simon Lucey
Abstract: In contrast to current state-of-the-art methods, such as NSFP [25], which employ deep implicit neural functions for modeling scene flow, we present a novel approach that utilizes classical kernel representations. This representation enables our approach to effectively handle dense lidar points while demonstrating exceptional computational efficiency -- compared to recent deep approaches -- achieved through the solution of a linear system. As a runtime optimization-based method, our model exhibits impressive generalizability across various out-of-distribution scenarios, achieving competitive performance on large-scale lidar datasets. We propose a new positional encoding-based kernel that demonstrates state-of-the-art performance in efficient lidar scene flow estimation on large-scale point clouds. An important highlight of our method is its near real-time performance (~150-170 ms) with dense lidar data (~8k-144k points), enabling a variety of practical applications in robotics and autonomous driving scenarios.
Authors: Ximiao Zhang, Min Xu, Xiuzhuang Zhou
Abstract: Self-supervised feature reconstruction methods have shown promising advances in industrial image anomaly detection and localization. Despite this progress, these methods still face challenges in synthesizing realistic and diverse anomaly samples, as well as addressing the feature redundancy and pre-training bias of pre-trained feature. In this work, we introduce RealNet, a feature reconstruction network with realistic synthetic anomaly and adaptive feature selection. It is incorporated with three key innovations: First, we propose Strength-controllable Diffusion Anomaly Synthesis (SDAS), a diffusion process-based synthesis strategy capable of generating samples with varying anomaly strengths that mimic the distribution of real anomalous samples. Second, we develop Anomaly-aware Features Selection (AFS), a method for selecting representative and discriminative pre-trained feature subsets to improve anomaly detection performance while controlling computational costs. Third, we introduce Reconstruction Residuals Selection (RRS), a strategy that adaptively selects discriminative residuals for comprehensive identification of anomalous regions across multiple levels of granularity. We assess RealNet on four benchmark datasets, and our results demonstrate significant improvements in both Image AUROC and Pixel AUROC compared to the current state-o-the-art methods. The code, data, and models are available at https://github.com/cnulab/RealNet.
Authors: Junyi Cao, Zhichao Li, Naiyan Wang, Chao Ma
Abstract: Recent studies have highlighted the promising application of NeRF in autonomous driving contexts. However, the complexity of outdoor environments, combined with the restricted viewpoints in driving scenarios, complicates the task of precisely reconstructing scene geometry. Such challenges often lead to diminished quality in reconstructions and extended durations for both training and rendering. To tackle these challenges, we present Lightning NeRF. It uses an efficient hybrid scene representation that effectively utilizes the geometry prior from LiDAR in autonomous driving scenarios. Lightning NeRF significantly improves the novel view synthesis performance of NeRF and reduces computational overheads. Through evaluations on real-world datasets, such as KITTI-360, Argoverse2, and our private dataset, we demonstrate that our approach not only exceeds the current state-of-the-art in novel view synthesis quality but also achieves a five-fold increase in training speed and a ten-fold improvement in rendering speed. Codes are available at https://github.com/VISION-SJTU/Lightning-NeRF .
Authors: Hao Lu, Xuesong Niu, Jiyao Wang, Yin Wang, Qingyong Hu, Jiaqi Tang, Yuting Zhang, Kaishen Yuan, Bin Huang, Zitong Yu, Dengbo He, Shuiguang Deng, Hao Chen, Yingcong Chen, Shiguang Shan
Abstract: Multimodal language models (MLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. Despite its success in language understanding, it is critical to evaluate the performance of downstream tasks for better human-centric applications. This paper assesses the application of MLMs with 5 crucial abilities for affective computing, spanning from visual affective tasks and reasoning tasks. The results show that GPT4 has high accuracy in facial action unit recognition and micro-expression detection while its general facial expression recognition performance is not accurate. We also highlight the challenges of achieving fine-grained micro-expression recognition and the potential for further study and demonstrate the versatility and potential of GPT4 for handling advanced tasks in emotion recognition and related fields by integrating with task-related agents for more complex tasks, such as heart rate estimation through signal processing. In conclusion, this paper provides valuable insights into the potential applications and challenges of MLMs in human-centric computing. The interesting samples are available at \url{https://github.com/LuPaoPao/GPT4Affectivity}.
Authors: Yanyi Zhang, Qi Jia, Xin Fan, Yu Liu, Ran He
Abstract: Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods based on disentangled representation learning lose sight of the contextual dependency between the A-O primitive pairs. Inspired by this, we propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet). The key insight is to firstly classify one primitive and then specifies the predicted class as a priori for guiding another primitive recognition in a cascaded fashion. To this end, CSCNet constructs Attribute-to-Object and Object-to-Attribute cascaded branches, in addition to a composition branch modeling the two primitives as a whole. Notably, we devise a parametric classifier (ParamCls) to improve the matching between visual and semantic embeddings. By improving the A-O disentanglement, our framework achieves superior results than previous competitive methods.
Authors: Xinlei Shao, Hongruixuan Chen, Kirsty Magson, Jiaqi Wang, Jian Song, Jundong Chen, Jun Sasaki
Abstract: Since coral reef ecosystems face threats from human activities and climate change, coral conservation programs are implemented worldwide. Monitoring coral health provides references for guiding conservation activities. However, current labor-intensive methods result in a backlog of unsorted images, highlighting the need for automated classification. Few studies have simultaneously utilized accurate annotations along with updated algorithms and datasets. This study aimed to create a dataset representing common coral conditions and associated stressors in the Indo-Pacific. Concurrently, it assessed existing classification algorithms and proposed a new multi-label method for automatically detecting coral conditions and extracting ecological information. A dataset containing over 20,000 high-resolution coral images of different health conditions and stressors was constructed based on the field survey. Seven representative deep learning architectures were tested on this dataset, and their performance was quantitatively evaluated using the F1 metric and the match ratio. Based on this evaluation, a new method utilizing the ensemble learning approach was proposed. The proposed method accurately classified coral conditions as healthy, compromised, dead, and rubble; it also identified corresponding stressors, including competition, disease, predation, and physical issues. This method can help develop the coral image archive, guide conservation activities, and provide references for decision-making for reef managers and conservationists. The proposed ensemble learning approach outperforms others on the dataset, showing State-Of-The-Art (SOTA) performance. Future research should improve its generalizability and accuracy to support global coral conservation efforts.
Authors: Roi Ronen, Ilan Koren, Aviad Levis, Eshkol Eytan, Vadim Holodovsky, Yoav Y. Schechner
Abstract: Significant uncertainty in climate prediction and cloud physics is tied to observational gaps relating to shallow scattered clouds. Addressing these challenges requires remote sensing of their three-dimensional (3D) heterogeneous volumetric scattering content. This calls for passive scattering computed tomography (CT). We design a learning-based model (ProbCT) to achieve CT of such clouds, based on noisy multi-view spaceborne images. ProbCT infers - for the first time - the posterior probability distribution of the heterogeneous extinction coefficient, per 3D location. This yields arbitrary valuable statistics, e.g., the 3D field of the most probable extinction and its uncertainty. ProbCT uses a neural-field representation, making essentially real-time inference. ProbCT undergoes supervised training by a new labeled multi-class database of physics-based volumetric fields of clouds and their corresponding images. To improve out-of-distribution inference, we incorporate self-supervised learning through differential rendering. We demonstrate the approach in simulations and on real-world data, and indicate the relevance of 3D recovery and uncertainty to precipitation and renewable energy.
Authors: Cunhui Dong, Haichuan Ma, Haotian Zhang, Changsheng Gao, Li Li, Dong Liu
Abstract: Neural network-based image coding has been developing rapidly since its birth. Until 2022, its performance has surpassed that of the best-performing traditional image coding framework -- H.266/VVC. Witnessing such success, the IEEE 1857.11 working subgroup initializes a neural network-based image coding standard project and issues a corresponding call for proposals (CfP). In response to the CfP, this paper introduces a novel wavelet-like transform-based end-to-end image coding framework -- iWaveV3. iWaveV3 incorporates many new features such as affine wavelet-like transform, perceptual-friendly quality metric, and more advanced training and online optimization strategies into our previous wavelet-like transform-based framework iWave++. While preserving the features of supporting lossy and lossless compression simultaneously, iWaveV3 also achieves state-of-the-art compression efficiency for objective quality and is very competitive for perceptual quality. As a result, iWaveV3 is adopted as a candidate scheme for developing the IEEE Standard for neural-network-based image coding.
Authors: Samuel Schmidgall, Ji Woong Kim, Jeffery Jopling, Axel Krieger
Abstract: The absence of openly accessible data and specialized foundation models is a major barrier for computational research in surgery. Toward this, (i) we open-source the largest dataset of general surgery videos to-date, consisting of 680 hours of surgical videos, including data from robotic and laparoscopic techniques across 28 procedures; (ii) we propose a technique for video pre-training a general surgery vision transformer (GSViT) on surgical videos based on forward video prediction that can run in real-time for surgical applications, toward which we open-source the code and weights of GSViT; (iii) we also release code and weights for procedure-specific fine-tuned versions of GSViT across 10 procedures; (iv) we demonstrate the performance of GSViT on the Cholec80 phase annotation task, displaying improved performance over state-of-the-art single frame predictors.
Authors: Ramin Mousa, Mitra Khezli, Saba Hesaraki
Abstract: Accurate classification of objects in 3D point clouds is a significant problem in several applications, such as autonomous navigation and augmented/virtual reality scenarios, which has become a research hot spot. In this paper, we presented a deep learning strategy for 3D object classification in augmented reality. The proposed approach is a combination of the GRU and LSTM. LSTM networks learn longer dependencies well, but due to the number of gates, it takes longer to train; on the other hand, GRU networks have a weaker performance than LSTM, but their training speed is much higher than GRU, which is The speed is due to its fewer gates. The proposed approach used the combination of speed and accuracy of these two networks. The proposed approach achieved an accuracy of 0.99 in the 4,499,0641 points dataset, which includes eight classes (unlabeled, man-made terrain, natural terrain, high vegetation, low vegetation, buildings, hardscape, scanning artifacts, cars). Meanwhile, the traditional machine learning approaches could achieve a maximum accuracy of 0.9489 in the best case. Keywords: Point Cloud Classification, Virtual Reality, Hybrid Model, GRULSTM, GRU, LSTM
Authors: Dingkang Yang, Kun Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Lihua Zhang
Abstract: Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER methods invariably extract ensemble representations from diverse contexts and subject-centred characteristics to perceive the target person's emotional state. Despite advancements, the biggest challenge remains due to context bias interference. The harmful bias forces the models to rely on spurious correlations between background contexts and emotion labels in likelihood estimation, causing severe performance bottlenecks and confounding valuable context priors. In this paper, we propose a counterfactual emotion inference (CLEF) framework to address the above issue. Specifically, we first formulate a generalized causal graph to decouple the causal relationships among the variables in CAER. Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias. During the inference, we eliminate the direct context effect from the total causal effect by comparing factual and counterfactual outcomes, resulting in bias mitigation and robust prediction. As a model-agnostic framework, CLEF can be readily integrated into existing methods, bringing consistent performance gains.
Authors: Arash Afkanpour, Vahid Reza Khazaie, Sana Ayromlou, Fereshteh Forghani
Abstract: The rapid advancement in self-supervised learning (SSL) has highlighted its potential to leverage unlabeled data for learning powerful visual representations. However, existing SSL approaches, particularly those employing different views of the same image, often rely on a limited set of predefined data augmentations. This constrains the diversity and quality of transformations, which leads to sub-optimal representations. In this paper, we introduce a novel framework that enriches the SSL paradigm by utilizing generative models to produce semantically consistent image augmentations. By directly conditioning generative models on a source image representation, our method enables the generation of diverse augmentations while maintaining the semantics of the source image, thus offering a richer set of data for self-supervised learning. Our experimental results demonstrate that our framework significantly enhances the quality of learned visual representations. This research demonstrates that incorporating generative models into the SSL workflow opens new avenues for exploring the potential of unlabeled visual data. This development paves the way for more robust and versatile representation learning techniques.
Authors: Zhe Huang, Xiaowei Yu, Benjamin S. Wessler, Michael C. Hughes
Abstract: Automated interpretation of ultrasound imaging of the heart (echocardiograms) could improve the detection and treatment of aortic stenosis (AS), a deadly heart disease. However, existing deep learning pipelines for assessing AS from echocardiograms have two key limitations. First, most methods rely on limited 2D cineloops, thereby ignoring widely available Doppler imaging that contains important complementary information about pressure gradients and blood flow abnormalities associated with AS. Second, obtaining labeled data is difficult. There are often far more unlabeled echocardiogram recordings available, but these remain underutilized by existing methods. To overcome these limitations, we introduce Semi-supervised Multimodal Multiple-Instance Learning (SMMIL), a new deep learning framework for automatic interpretation for structural heart diseases like AS. When deployed, SMMIL can combine information from two input modalities, spectral Dopplers and 2D cineloops, to produce a study-level AS diagnosis. During training, SMMIL can combine a smaller labeled set and an abundant unlabeled set of both modalities to improve its classifier. Experiments demonstrate that SMMIL outperforms recent alternatives at 3-level AS severity classification as well as several clinically relevant AS detection tasks.
Authors: Wei Chen, Yunan Li, Yuan Tian
Abstract: We introduce a new approach using computer vision to predict the land surface displacement from subsurface geometry images for Carbon Capture and Sequestration (CCS). CCS has been proved to be a key component for a carbon neutral society. However, scientists see there are challenges along the way including the high computational cost due to the large model scale and limitations to generalize a pre-trained model with complex physics. We tackle those challenges by training models directly from the subsurface geometry images. The goal is to understand the respons of land surface displacement due to carbon injection and utilize our trained models to inform decision making in CCS projects. We implement multiple models (CNN, ResNet, and ResNetUNet) for static mechanics problem, which is a image prediction problem. Next, we use the LSTM and transformer for transient mechanics scenario, which is a video prediction problem. It shows ResNetUNet outperforms the others thanks to its architecture in static mechanics problem, and LSTM shows comparable performance to transformer in transient problem. This report proceeds by outlining our dataset in detail followed by model descriptions in method section. Result and discussion state the key learning, observations, and conclusion with future work rounds out the paper.
Authors: Asal Rouhafzay, Nadia Baaziz, Mohand Said Allili
Abstract: In this paper, we propose a new framework for improving Content Based Image Retrieval (CBIR) for texture images. This is achieved by using a new image representation based on the RCT-Plus transform which is a novel variant of the Redundant Contourlet transform that extracts a richer directional information in the image. Moreover, the process of image search is improved through a learning-based approach where the images of the database are classified using an adapted similarity metric to the statistical modeling of the RCT-Plus transform. A query is then first classified to select the best texture class after which the retained class images are ranked to select top ones. By this, we have achieved significant improvements in the retrieval rates compared to previous CBIR schemes.
Authors: Yi Zhang, Ce Zhang
Abstract: Vision-Language Pre-Trained (VLP) models, such as CLIP, have demonstrated remarkable effectiveness in learning generic visual representations. Several approaches aim to efficiently adapt VLP models to downstream tasks with limited supervision, aiming to leverage the acquired knowledge from VLP models. However, these methods suffer from either introducing biased representations or requiring high computational complexity, which hinders their effectiveness in fine-tuning the CLIP model. Moreover, when a model is trained on data specific to a particular domain, its ability to generalize to uncharted domains diminishes. In this work, we propose Test-Time Distribution LearNing Adapter (TT-DNA) which directly works during the testing period. Specifically, we estimate Gaussian distributions to model visual features of the few-shot support images to capture the knowledge from the support set. The cosine similarity between query image and the feature distribution of support images is used as the prediction of visual adapter. Subsequently, the visual adapter's prediction merges with the original CLIP prediction via a residual connection, resulting in the final prediction. Our extensive experimental results on visual reasoning for human object interaction demonstrate that our proposed TT-DNA outperforms existing state-of-the-art methods by large margins.
Authors: Jiawang Cao, Yongliang Wu, Weiheng Chi, Wenbo Zhu, Ziyue Su, Jay Wu
Abstract: The proliferation of mobile devices and social media has revolutionized content dissemination, with short-form video becoming increasingly prevalent. This shift has introduced the challenge of video reframing to fit various screen aspect ratios, a process that highlights the most compelling parts of a video. Traditionally, video reframing is a manual, time-consuming task requiring professional expertise, which incurs high production costs. A potential solution is to adopt some machine learning models, such as video salient object detection, to automate the process. However, these methods often lack generalizability due to their reliance on specific training data. The advent of powerful large language models (LLMs) open new avenues for AI capabilities. Building on this, we introduce Reframe Any Video Agent (RAVA), a LLM-based agent that leverages visual foundation models and human instructions to restructure visual content for video reframing. RAVA operates in three stages: perception, where it interprets user instructions and video content; planning, where it determines aspect ratios and reframing strategies; and execution, where it invokes the editing tools to produce the final video. Our experiments validate the effectiveness of RAVA in video salient object detection and real-world reframing tasks, demonstrating its potential as a tool for AI-powered video editing.
Authors: Liyang He, Zhenya Huang, Jiayu Liu, Enhong Chen, Fei Wang, Jing Sha, Shijin Wang
Abstract: Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://github.com/hly1998/BRCD.
Authors: Yang He, Lingao Xiao, Joey Tianyi Zhou, Ivor Tsang
Abstract: While dataset condensation effectively enhances training efficiency, its application in on-device scenarios brings unique challenges. 1) Due to the fluctuating computational resources of these devices, there's a demand for a flexible dataset size that diverges from a predefined size. 2) The limited computational power on devices often prevents additional condensation operations. These two challenges connect to the "subset degradation problem" in traditional dataset condensation: a subset from a larger condensed dataset is often unrepresentative compared to directly condensing the whole dataset to that smaller size. In this paper, we propose Multisize Dataset Condensation (MDC) by compressing N condensation processes into a single condensation process to obtain datasets with multiple sizes. Specifically, we introduce an "adaptive subset loss" on top of the basic condensation loss to mitigate the "subset degradation problem". Our MDC method offers several benefits: 1) No additional condensation process is required; 2) reduced storage requirement by reusing condensed images. Experiments validate our findings on networks including ConvNet, ResNet and DenseNet, and datasets including SVHN, CIFAR-10, CIFAR-100 and ImageNet. For example, we achieved 6.40% average accuracy gains on condensing CIFAR-10 to ten images per class. Code is available at: https://github.com/he-y/Multisize-Dataset-Condensation.
URLs: https://github.com/he-y/Multisize-Dataset-Condensation.
Authors: Esmaeil Seraj, Walter Talamonti
Abstract: In the burgeoning field of intelligent transportation systems, enhancing vehicle-driver interaction through facial attribute recognition, such as facial expression, eye gaze, age, etc., is of paramount importance for safety, personalization, and overall user experience. However, the scarcity of comprehensive large-scale, real-world datasets poses a significant challenge for training robust multi-task models. Existing literature often overlooks the potential of synthetic datasets and the comparative efficacy of state-of-the-art vision foundation models in such constrained settings. This paper addresses these gaps by investigating the utility of synthetic datasets for training complex multi-task models that recognize facial attributes of passengers of a vehicle, such as gaze plane, age, and facial expression. Utilizing transfer learning techniques with both pre-trained Vision Transformer (ViT) and Residual Network (ResNet) models, we explore various training and adaptation methods to optimize performance, particularly when data availability is limited. We provide extensive post-evaluation analysis, investigating the effects of synthetic data distributions on model performance in in-distribution data and out-of-distribution inference. Our study unveils counter-intuitive findings, notably the superior performance of ResNet over ViTs in our specific multi-task context, which is attributed to the mismatch in model complexity relative to task complexity. Our results highlight the challenges and opportunities for enhancing the use of synthetic data and vision foundation models in practical applications.
Authors: Maddimsetti Srinivas, Debdoot Sheet
Abstract: The interpretation of reasoning by Deep Neural Networks (DNN) is still challenging due to their perceived black-box nature. Therefore, deploying DNNs in several real-world tasks is restricted by the lack of transparency of these models. We propose a distillation approach by extracting features from the final layer of the convolutional neural network (CNN) to address insights to its reasoning. The feature maps in the final layer of a CNN are transformed into a one-dimensional feature vector using a fully connected layer. Subsequently, the extracted features are used to train a decision tree to achieve the best accuracy under constraints of depth and nodes. We use the medical images of dermaMNIST, octMNIST, and pneumoniaMNIST from the medical MNIST datasets to demonstrate our proposed work. We observed that performance of the decision tree is as good as a CNN with minimum complexity. The results encourage interpreting decisions made by the CNNs using decision trees.
Authors: Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen, Chunhua Shen
Abstract: We show that, simply initializing image understanding models using a pre-trained UNet (or transformer) of diffusion models, it is possible to achieve remarkable transferable performance on fundamental vision perception tasks using a moderate amount of target data (even synthetic data only), including monocular depth, surface normal, image segmentation, matting, human pose estimation, among virtually many others. Previous works have adapted diffusion models for various perception tasks, often reformulating these tasks as generation processes to align with the diffusion process. In sharp contrast, we demonstrate that fine-tuning these models with minimal adjustments can be a more effective alternative, offering the advantages of being embarrassingly simple and significantly faster. As the backbone network of Stable Diffusion models is trained on giant datasets comprising billions of images, we observe very robust generalization capabilities of the diffusion backbone. Experimental results showcase the remarkable transferability of the backbone of diffusion models across diverse tasks and real-world datasets.
Authors: Hanxin Zhu, Tianyu He, Xin Li, Bingchen Li, Zhibo Chen
Abstract: Neural Radiance Field (NeRF) has achieved superior performance for novel view synthesis by modeling the scene with a Multi-Layer Perception (MLP) and a volume rendering procedure, however, when fewer known views are given (i.e., few-shot view synthesis), the model is prone to overfit the given views. To handle this issue, previous efforts have been made towards leveraging learned priors or introducing additional regularizations. In contrast, in this paper, we for the first time provide an orthogonal method from the perspective of network structure. Given the observation that trivially reducing the number of model parameters alleviates the overfitting issue, but at the cost of missing details, we propose the multi-input MLP (mi-MLP) that incorporates the inputs (i.e., location and viewing direction) of the vanilla MLP into each layer to prevent the overfitting issue without harming detailed synthesis. To further reduce the artifacts, we propose to model colors and volume density separately and present two regularization terms. Extensive experiments on multiple datasets demonstrate that: 1) although the proposed mi-MLP is easy to implement, it is surprisingly effective as it boosts the PSNR of the baseline from $14.73$ to $24.23$. 2) the overall framework achieves state-of-the-art results on a wide range of benchmarks. We will release the code upon publication.
Authors: Haoxuanye Ji, Pengpeng Liang, Erkang Cheng
Abstract: Multi-camera-based 3D object detection has made notable progress in the past several years. However, we observe that there are cases (e.g. faraway regions) in which popular 2D object detectors are more reliable than state-of-the-art 3D detectors. In this paper, to improve the performance of query-based 3D object detectors, we present a novel query generating approach termed QAF2D, which infers 3D query anchors from 2D detection results. A 2D bounding box of an object in an image is lifted to a set of 3D anchors by associating each sampled point within the box with depth, yaw angle, and size candidates. Then, the validity of each 3D anchor is verified by comparing its projection in the image with its corresponding 2D box, and only valid anchors are kept and used to construct queries. The class information of the 2D bounding box associated with each query is also utilized to match the predicted boxes with ground truth for the set-based loss. The image feature extraction backbone is shared between the 3D detector and 2D detector by adding a small number of prompt parameters. We integrate QAF2D into three popular query-based 3D object detectors and carry out comprehensive evaluations on the nuScenes dataset. The largest improvement that QAF2D can bring about on the nuScenes validation subset is $2.3\%$ NDS and $2.7\%$ mAP. Code is available at https://github.com/nullmax-vision/QAF2D.
Authors: Wenhao Wang, Yi Yang
Abstract: The arrival of Sora marks a new era for text-to-video diffusion models, bringing significant advancements in video generation and potential applications. However, Sora, as well as other text-to-video diffusion models, highly relies on the prompts, and there is no publicly available dataset featuring a study of text-to-video prompts. In this paper, we introduce VidProM, the first large-scale dataset comprising 1.67 million unique text-to-video prompts from real users. Additionally, the dataset includes 6.69 million videos generated by four state-of-the-art diffusion models and some related data. We initially demonstrate the curation of this large-scale dataset, which is a time-consuming and costly process. Subsequently, we show how the proposed VidProM differs from DiffusionDB, a large-scale prompt-gallery dataset for image generation. Based on the analysis of these prompts, we identify the necessity for a new prompt dataset specifically designed for text-to-video generation and gain insights into the preferences of real users when creating videos. Our large-scale and diverse dataset also inspires many exciting new research areas. For instance, to develop better, more efficient, and safer text-to-video diffusion models, we suggest exploring text-to-video prompt engineering, efficient video generation, and video copy detection for diffusion models. We make the collected dataset VidProM publicly available at GitHub and Hugging Face under the CC-BY- NC 4.0 License.
Authors: Guodong Ding, Hans Golong, Angela Yao
Abstract: Data replay is a successful incremental learning technique for images. It prevents catastrophic forgetting by keeping a reservoir of previous data, original or synthesized, to ensure the model retains past knowledge while adapting to novel concepts. However, its application in the video domain is rudimentary, as it simply stores frame exemplars for action recognition. This paper presents the first exploration of video data replay techniques for incremental action segmentation, focusing on action temporal modeling. We propose a Temporally Coherent Action (TCA) model, which represents actions using a generative model instead of storing individual frames. The integration of a conditioning variable that captures temporal coherence allows our model to understand the evolution of action features over time. Therefore, action segments generated by TCA for replay are diverse and temporally coherent. In a 10-task incremental setup on the Breakfast dataset, our approach achieves significant increases in accuracy for up to 22% compared to the baselines.
Authors: Ruinan Jin, Wenlong Deng, Minghui Chen, Xiaoxiao Li
Abstract: In the era of Foundation Models' (FMs) rising prominence in AI, our study addresses the challenge of biases in medical images while using FM API, particularly spurious correlations between pixels and sensitive attributes. Traditional methods for bias mitigation face limitations due to the restricted access to web-hosted FMs and difficulties in addressing the underlying bias encoded within the FM API. We propose an U(niversal) D(ebiased) E(diting) strategy, termed UDE, which generates UDE noise to mask such spurious correlation. UDE is capable of mitigating bias both within the FM API embedding and the images themselves. Furthermore, UDE is suitable for both white-box and black-box FM APIs, where we introduced G(reedy) (Z)eroth-O(rder) (GeZO) optimization for it when the gradient is inaccessible in black-box APIs. Our whole pipeline enables fairness-aware image editing that can be applied across various medical contexts without requiring direct model manipulation or significant computational resources. Our empirical results demonstrate the method's effectiveness in maintaining fairness and utility across different patient groups and diseases. In the era of AI-driven medicine, this work contributes to making healthcare diagnostics more equitable, showcasing a practical solution for bias mitigation in pre-trained image FMs.
Authors: Frincy Clement, Kirtan Shah, Dhara Pancholi, Gabriel Lugo Bustillo, Dr. Irene Cheng
Abstract: Textureless object recognition has become a significant task in Computer Vision with the advent of Robotics and its applications in manufacturing sector. It has been challenging to obtain good accuracy in real time because of its lack of discriminative features and reflectance properties which makes the techniques for textured object recognition insufficient for textureless objects. A lot of work has been done in the last 20 years, especially in the recent 5 years after the TLess and other textureless dataset were introduced. In this project, by applying image processing techniques we created a robust augmented dataset from initial imbalanced smaller dataset. We extracted edge features, feature combinations and RGB images enhanced with feature/feature combinations to create 15 datasets, each with a size of ~340,000. We then trained four classifiers on these 15 datasets to arrive at a conclusion as to which dataset performs the best overall and whether edge features are important for textureless objects. Based on our experiments and analysis, RGB images enhanced with combination of 3 edge features performed the best compared to all others. Model performance on dataset with HED edges performed comparatively better than other edge detectors like Canny or Prewitt.
Authors: Doanh C. Bui, Thinh V. Le, Hung Ba Ngo, Tae Jong Choi
Abstract: Person attribute recognition and attribute-based retrieval are two core human-centric tasks. In the recognition task, the challenge is specifying attributes depending on a person's appearance, while the retrieval task involves searching for matching persons based on attribute queries. There is a significant relationship between recognition and retrieval tasks. In this study, we demonstrate that if there is a sufficiently robust network to solve person attribute recognition, it can be adapted to facilitate better performance for the retrieval task. Another issue that needs addressing in the retrieval task is the modality gap between attribute queries and persons' images. Therefore, in this paper, we present CLEAR, a unified network designed to address both tasks. We introduce a robust cross-transformers network to handle person attribute recognition. Additionally, leveraging a pre-trained language model, we construct pseudo-descriptions for attribute queries and introduce an effective training strategy to train only a few additional parameters for adapters, facilitating the handling of the retrieval task. Finally, the unified CLEAR model is evaluated on five benchmarks: PETA, PA100K, Market-1501, RAPv2, and UPAR-2024. Without bells and whistles, CLEAR achieves state-of-the-art performance or competitive results for both tasks, significantly outperforming other competitors in terms of person retrieval performance on the widely-used Market-1501 dataset.
Authors: Woo-Jin Ahn, Geun-Yeong Yang, Hyun-Duck Choi, Myo-Taeg Lim
Abstract: Deep learning models for semantic segmentation often experience performance degradation when deployed to unseen target domains unidentified during the training phase. This is mainly due to variations in image texture (\ie style) from different data sources. To tackle this challenge, existing domain generalized semantic segmentation (DGSS) methods attempt to remove style variations from the feature. However, these approaches struggle with the entanglement of style and content, which may lead to the unintentional removal of crucial content information, causing performance degradation. This study addresses this limitation by proposing BlindNet, a novel DGSS approach that blinds the style without external modules or datasets. The main idea behind our proposed approach is to alleviate the effect of style in the encoder whilst facilitating robust segmentation in the decoder. To achieve this, BlindNet comprises two key components: covariance alignment and semantic consistency contrastive learning. Specifically, the covariance alignment trains the encoder to uniformly recognize various styles and preserve the content information of the feature, rather than removing the style-sensitive factor. Meanwhile, semantic consistency contrastive learning enables the decoder to construct discriminative class embedding space and disentangles features that are vulnerable to misclassification. Through extensive experiments, our approach outperforms existing DGSS methods, exhibiting robustness and superior performance for semantic segmentation on unseen target domains.
Authors: Jianping Li, Thien-Minh Nguyen, Shenghai Yuan, Lihua Xie
Abstract: Accurate and consistent construction of point clouds from LiDAR scanning data is fundamental for 3D modeling applications. Current solutions, such as multiview point cloud registration and LiDAR bundle adjustment, predominantly depend on the local plane assumption, which may be inadequate in complex environments lacking of planar geometries or substantial initial pose errors. To mitigate this problem, this paper presents a LiDAR bundle adjustment with progressive spatial smoothing, which is suitable for complex environments and exhibits improved convergence capabilities. The proposed method consists of a spatial smoothing module and a pose adjustment module, which combines the benefits of local consistency and global accuracy. With the spatial smoothing module, we can obtain robust and rich surface constraints employing smoothing kernels across various scales. Then the pose adjustment module corrects all poses utilizing the novel surface constraints. Ultimately, the proposed method simultaneously achieves fine poses and parametric surfaces that can be directly employed for high-quality point cloud reconstruction. The effectiveness and robustness of our proposed approach have been validated on both simulation and real-world datasets. The experimental results demonstrate that the proposed method outperforms the existing methods and achieves better accuracy in complex environments with low planar structures.
Authors: Junhui Yin, Xinyu Zhang, Lin Wu, Xianghua Xie, Xiaojie Wang
Abstract: Existing pre-trained vision-language models, e.g., CLIP, have demonstrated impressive zero-shot generalization capabilities in various downstream tasks. However, the performance of these models will degrade significantly when test inputs present different distributions. To this end, we explore the concept of test-time prompt tuning (TTPT), which enables the adaptation of the CLIP model to novel downstream tasks through only one step of optimization on an unsupervised objective that involves the test sample. Motivated by in-context learning within field of natural language processing (NLP), we propose In-Context Prompt Learning (InCPL) for test-time visual recognition task. InCPL involves associating a new test sample with very few or even just one labeled example as its in-context prompt. As a result, it can reliably estimate a label for the test sample, thereby facilitating the model adaptation process. InCPL first employs a token net to represent language descriptions as visual prompts that the vision encoder of a CLIP model can comprehend. Paired with in-context examples, we further propose a context-aware unsupervised loss to optimize test sample-aware visual prompts. This optimization allows a pre-trained, frozen CLIP model to be adapted to a test sample from any task using its learned adaptive prompt. Our method has demonstrated superior performance and achieved state-of-the-art results across various downstream datasets.
Authors: Pinxue Guo, Lingyi Hong, Xinyu Zhou, Shuyong Gao, Wanyun Li, Jinglun Li, Zhaoyu Chen, Xiaoqiang Li, Wei Zhang, Wenqiang Zhang
Abstract: Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects of interest. To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame. And we provide the extended datasets DAVIS-P and YouTubeVOSP that with point annotations to support this task. ClickVOS is of significant practical applications and research implications due to its only 1-2 seconds interaction time for indicating an object, comparing annotating the mask of an object needs several minutes. However, ClickVOS also presents increased challenges. To address this task, we propose an end-to-end baseline approach named called Attention Before Segmentation (ABS), motivated by the attention process of humans. ABS utilizes the given point in the first frame to perceive the target object through a concise yet effective segmentation attention. Although the initial object mask is possibly inaccurate, in our ABS, as the video goes on, the initially imprecise object mask can self-heal instead of deteriorating due to error accumulation, which is attributed to our designed improvement memory that continuously records stable global object memory and updates detailed dense memory. In addition, we conduct various baseline explorations utilizing off-the-shelf algorithms from related fields, which could provide insights for the further exploration of ClickVOS. The experimental results demonstrate the superiority of the proposed ABS approach. Extended datasets and codes will be available at https://github.com/PinxueGuo/ClickVOS.
Authors: Shilin Lu, Zilan Wang, Leyang Li, Yanzhu Liu, Adams Wai-Kin Kong
Abstract: The rapid expansion of large-scale text-to-image diffusion models has raised growing concerns regarding their potential misuse in creating harmful or misleading content. In this paper, we introduce MACE, a finetuning framework for the task of mass concept erasure. This task aims to prevent models from generating images that embody unwanted concepts when prompted. Existing concept erasure methods are typically restricted to handling fewer than five concepts simultaneously and struggle to find a balance between erasing concept synonyms (generality) and maintaining unrelated concepts (specificity). In contrast, MACE differs by successfully scaling the erasure scope up to 100 concepts and by achieving an effective balance between generality and specificity. This is achieved by leveraging closed-form cross-attention refinement along with LoRA finetuning, collectively eliminating the information of undesirable concepts. Furthermore, MACE integrates multiple LoRAs without mutual interference. We conduct extensive evaluations of MACE against prior methods across four different tasks: object erasure, celebrity erasure, explicit content erasure, and artistic style erasure. Our results reveal that MACE surpasses prior methods in all evaluated tasks. Code is available at https://github.com/Shilin-LU/MACE.
Authors: Yuncheng Yang, Chuyan Zhang, Zuopeng Yang, Yuting Gao, Yulei Qin, Ke Li, Xing Sun, Jie Yang, Yun Gu
Abstract: Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the vision-language alignment of pre-trained models in return for improved performance on specific tasks and classes, leading to poorer generalization. In this paper, we first demonstrate that prompt tuning along only one single branch of CLIP (e.g., language or vision) is the reason why the misalignment occurs. Without proper regularization across the learnable parameters in different modalities, prompt learning violates the original pre-training constraints inherent in the two-tower architecture. To address such misalignment, we first propose feature shift, which is defined as the variation of embeddings after introducing the learned prompts, to serve as an explanatory tool. We dive into its relation with generalizability and thereafter propose RESTORE, a multi-modal prompt learning method that exerts explicit constraints on cross-modal consistency. To be more specific, to prevent feature misalignment, a feature shift consistency is introduced to synchronize inter-modal feature shifts by measuring and regularizing the magnitude of discrepancy during prompt tuning. In addition, we propose a "surgery" block to avoid short-cut hacking, where cross-modal misalignment can still be severe if the feature shift of each modality varies drastically at the same rate. It is implemented as feed-forward adapters upon both modalities to alleviate the misalignment problem. Extensive experiments on 15 datasets demonstrate that our method outperforms the state-of-the-art prompt tuning methods without compromising feature alignment.
Authors: Yaoyao Zhu, Xiuding Cai, Xueyao Wang, Yu Yao
Abstract: Data augmentation is a critical regularization technique for deep neural networks, particularly in medical image classification. Popular data augmentation approaches include image transformation-based methods, generative data augmentation, and automatic data augmentation. However, these approaches encounter notable limitations: image transformation-based and automated data augmentation techniques cannot implement semantic transformations, leading to a constrained variety of augmented samples, and generative data augmentation methods are computationally expensive. In response to these challenges, we proposed Bayesian Random Semantic Data Augmentation (BRSDA), a novel, efficient, and plug-and-play semantic data augmentation method. BRSDA is motivated by a simple translation in the feature space along specific directions that can effectuate semantic transformations. When given a feature, we define its augmentable semantic magnitude as a random variable and estimate its distribution using variational Bayesian, then sample semantic magnitude and add to the randomly selected semantic direction to achieve semantic data augmentation. We demonstrate the effectiveness of BRSDA on five 2D and six 3D medical image datasets covering nine modalities. We also test BRSDA with mainstream neural network architectures, showcasing its robustness. Furthermore, combining BRSDA with other leading data augmentation methods achieves superior performance. Code is available online at \url{https://github.com/YaoyaoZhu19/BRSDA}.
Authors: Changhee Han, Kyohei Shibano, Wataru Ozaki, Keishiro Osaki, Takafumi Haraguchi, Daisuke Hirahara, Shumon Kimura, Yasuyuki Kobayashi, Gento Mogi
Abstract: Deep Learning is advancing medical imaging Research and Development (R&D), leading to the frequent clinical use of Artificial Intelligence/Machine Learning (AI/ML)-based medical devices. However, to advance AI R&D, two challenges arise: 1) significant data imbalance, with most data from Europe/America and under 10% from Asia, despite its 60% global population share; and 2) hefty time and investment needed to curate proprietary datasets for commercial use. In response, we established the first commercial medical imaging platform, encompassing steps like: 1) data collection, 2) data selection, 3) annotation, and 4) pre-processing. Moreover, we focus on harnessing under-represented data from Japan and broader Asia, including Computed Tomography, Magnetic Resonance Imaging, and Whole Slide Imaging scans. Using the collected data, we are preparing/providing ready-to-use datasets for medical AI R&D by 1) offering these datasets to AI firms, biopharma, and medical device makers and 2) using them as training/test data to develop tailored AI solutions for such entities. We also aim to merge Blockchain for data security and plan to synthesize rare disease data via generative AI. DataHub Website: https://medical-datahub.ai/
Authors: Shiyu Xuan, Shiliang Zhang
Abstract: Supervised Contrastive Loss (SCL) is popular in visual representation learning. Given an anchor image, SCL pulls two types of positive samples, i.e., its augmentation and other images from the same class together, while pushes negative images apart to optimize the learned embedding. In the scenario of long-tailed recognition, where the number of samples in each class is imbalanced, treating two types of positive samples equally leads to the biased optimization for intra-category distance. In addition, similarity relationship among negative samples, that are ignored by SCL, also presents meaningful semantic cues. To improve the performance on long-tailed recognition, this paper addresses those two issues of SCL by decoupling the training objective. Specifically, it decouples two types of positives in SCL and optimizes their relations toward different objectives to alleviate the influence of the imbalanced dataset. We further propose a patch-based self distillation to transfer knowledge from head to tail classes to relieve the under-representation of tail classes. It uses patch-based features to mine shared visual patterns among different instances and leverages a self distillation procedure to transfer such knowledge. Experiments on different long-tailed classification benchmarks demonstrate the superiority of our method. For instance, it achieves the 57.7% top-1 accuracy on the ImageNet-LT dataset. Combined with the ensemble-based method, the performance can be further boosted to 59.7%, which substantially outperforms many recent works. The code is available at https://github.com/SY-Xuan/DSCL.
Authors: Huaxin Zhang, Xiang Wang, Xiaohao Xu, Xiaonan Huang, Chuchu Han, Yuehuan Wang, Changxin Gao, Shanjun Zhang, Nong Sang
Abstract: In recent years, video anomaly detection has been extensively investigated in both unsupervised and weakly supervised settings to alleviate costly temporal labeling. Despite significant progress, these methods still suffer from unsatisfactory results such as numerous false alarms, primarily due to the absence of precise temporal anomaly annotation. In this paper, we present a novel labeling paradigm, termed "glance annotation", to achieve a better balance between anomaly detection accuracy and annotation cost. Specifically, glance annotation is a random frame within each abnormal event, which can be easily accessed and is cost-effective. To assess its effectiveness, we manually annotate the glance annotations for two standard video anomaly detection datasets: UCF-Crime and XD-Violence. Additionally, we propose a customized GlanceVAD method, that leverages gaussian kernels as the basic unit to compose the temporal anomaly distribution, enabling the learning of diverse and robust anomaly representations from the glance annotations. Through comprehensive analysis and experiments, we verify that the proposed labeling paradigm can achieve an excellent trade-off between annotation cost and model performance. Extensive experimental results also demonstrate the effectiveness of our GlanceVAD approach, which significantly outperforms existing advanced unsupervised and weakly supervised methods. Code and annotations will be publicly available at https://github.com/pipixin321/GlanceVAD.
Authors: Aakash Agrawal, Stanislas Dehaene
Abstract: Learning to read places a strong challenge on the visual system. Years of expertise lead to a remarkable capacity to separate highly similar letters and encode their relative positions, thus distinguishing words such as FORM and FROM, invariantly over a large range of sizes and absolute positions. How neural circuits achieve invariant word recognition remains unknown. Here, we address this issue by training deep neural network models to recognize written words and then analyzing how reading-specialized units emerge and operate across different layers of the network. With literacy, a small subset of units becomes specialized for word recognition in the learned script, similar to the "visual word form area" of the human brain. We show that these units are sensitive to specific letter identities and their distance from the blank space at the left or right of a word, thus acting as "space bigrams". These units specifically encode ordinal positions and operate by pooling across low and high-frequency detector units from early layers of the network. The proposed neural code provides a mechanistic insight into how information on letter identity and position is extracted and allow for invariant word recognition, and leads to predictions for reading behavior, error patterns, and the neurophysiology of reading.
Authors: Pawe{\l} A. Pierzchlewicz, Caio da Silva, R. James Cotton, Fabian H. Sinz
Abstract: Single camera 3D pose estimation is an ill-defined problem due to inherent ambiguities from depth, occlusion or keypoint noise. Multi-hypothesis pose estimation accounts for this uncertainty by providing multiple 3D poses consistent with the 2D measurements. Current research has predominantly concentrated on generating multiple hypotheses for single frame static pose estimation. In this study we focus on the new task of multi-hypothesis motion estimation. Motion estimation is not simply pose estimation applied to multiple frames, which would ignore temporal correlation across frames. Instead, it requires distributions which are capable of generating temporally consistent samples, which is significantly more challenging. To this end, we introduce Platypose, a framework that uses a diffusion model pretrained on 3D human motion sequences for zero-shot 3D pose sequence estimation. Platypose outperforms baseline methods on multiple hypotheses for motion estimation. Additionally, Platypose also achieves state-of-the-art calibration and competitive joint error when tested on static poses from Human3.6M, MPI-INF-3DHP and 3DPW. Finally, because it is zero-shot, our method generalizes flexibly to different settings such as multi-camera inference.
Authors: Zhili Chen, Kien T. Pham, Maosheng Ye, Zhiqiang Shen, Qifeng Chen
Abstract: We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving. Traditional point-based 3D object detectors often employ architectures that rely on a progressive downsampling of points. While this method effectively reduces computational demands and increases receptive fields, it will compromise the preservation of crucial non-local information for accurate 3D object detection, especially in the complex driving scenarios. To address this, we introduce an intriguing Cross-Cluster Shifting operation to unleash the representation capacity of the point-based detector by efficiently modeling longer-range inter-dependency while including only a negligible overhead. Concretely, the Cross-Cluster Shifting operation enhances the conventional design by shifting partial channels from neighboring clusters, which enables richer interaction with non-local regions and thus enlarges the receptive field of clusters. We conduct extensive experiments on the KITTI, Waymo, and nuScenes datasets, and the results demonstrate the state-of-the-art performance of Shift-SSD in both detection accuracy and runtime efficiency.
Authors: Xiaobin Hu, Xu Peng, Donghao Luo, Xiaozhong Ji, Jinlong Peng, Zhengkai Jiang, Jiangning Zhang, Taisong Jin, Chengjie Wang, Rongrong Ji
Abstract: Due to the difficulty and labor-consuming nature of getting highly accurate or matting annotations, there only exists a limited amount of highly accurate labels available to the public. To tackle this challenge, we propose a DiffuMatting which inherits the strong Everything generation ability of diffusion and endows the power of "matting anything". Our DiffuMatting can 1). act as an anything matting factory with high accurate annotations 2). be well-compatible with community LoRAs or various conditional control approaches to achieve the community-friendly art design and controllable generation. Specifically, inspired by green-screen-matting, we aim to teach the diffusion model to paint on a fixed green screen canvas. To this end, a large-scale greenscreen dataset (Green100K) is collected as a training dataset for DiffuMatting. Secondly, a green background control loss is proposed to keep the drawing board as a pure green color to distinguish the foreground and background. To ensure the synthesized object has more edge details, a detailed-enhancement of transition boundary loss is proposed as a guideline to generate objects with more complicated edge structures. Aiming to simultaneously generate the object and its matting annotation, we build a matting head to make a green color removal in the latent space of the VAE decoder. Our DiffuMatting shows several potential applications (e.g., matting-data generator, community-friendly art design and controllable generation). As a matting-data generator, DiffuMatting synthesizes general object and portrait matting sets, effectively reducing the relative MSE error by 15.4% in General Object Matting and 11.4% in Portrait Matting tasks.
Authors: Yuqin Dai, Wanlu Zhu, Ronghui Li, Zeping Ren, Xiangzheng Zhou, Xiu Li, Jun Li, Jian Yang
Abstract: Creating group choreography from music has gained attention in cultural entertainment and virtual reality, aiming to coordinate visually cohesive and diverse group movements. Despite increasing interest, recent works face challenges in achieving aesthetically appealing choreography, primarily for two key issues: multi-dancer collision and single-dancer foot slide. To address these issues, we propose a Trajectory-Controllable Diffusion (TCDiff), a novel approach that harnesses non-overlapping trajectories to facilitate coherent dance movements. Specifically, to tackle dancer collisions, we introduce a Dance-Beat Navigator capable of generating trajectories for multiple dancers based on the music, complemented by a Distance-Consistency loss to maintain appropriate spacing among trajectories within a reasonable threshold. To mitigate foot sliding, we present a Footwork Adaptor that utilizes trajectory displacement from adjacent frames to enable flexible footwork, coupled with a Relative Forward-Kinematic loss to adjust the positioning of individual dancers' root nodes and joints. Extensive experiments demonstrate that our method achieves state-of-the-art results.
Authors: Houssem Boulahbal
Abstract: Perception of the environment is a critical component for enabling autonomous driving. It provides the vehicle with the ability to comprehend its surroundings and make informed decisions. Depth prediction plays a pivotal role in this process, as it helps the understanding of the geometry and motion of the environment. This thesis focuses on the challenge of depth prediction using monocular self-supervised learning techniques. The problem is approached from a broader perspective first, exploring conditional generative adversarial networks (cGANs) as a potential technique to achieve better generalization was performed. In doing so, a fundamental contribution to the conditional GANs, the acontrario cGAN was proposed. The second contribution entails a single image-to-depth self-supervised method, proposing a solution for the rigid-scene assumption using a novel transformer-based method that outputs a pose for each dynamic object. The third significant aspect involves the introduction of a video-to-depth map forecasting approach. This method serves as an extension of self-supervised techniques to predict future depths. This involves the creation of a novel transformer model capable of predicting the future depth of a given scene. Moreover, the various limitations of the aforementioned methods were addressed and a video-to-video depth maps model was proposed. This model leverages the spatio-temporal consistency of the input and output sequence to predict a more accurate depth sequence output. These methods have significant applications in autonomous driving (AD) and advanced driver assistance systems (ADAS).
Authors: Minjie Zhu, Yichen Zhu, Xin Liu, Ning Liu, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Zhicai Ou, Feifei Feng, Jian Tang
Abstract: Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models, and optimization strategies. We show that without increasing the volume of training data, our Mipha-3B outperforms the state-of-the-art large MLLMs, especially LLaVA-1.5-13B, on multiple benchmarks. Through detailed discussion, we provide insights and guidelines for developing strong MSLMs that rival the capabilities of MLLMs. Our code is available at https://github.com/zhuyiche/Mipha.
Authors: Maxence Boels, Yang Liu, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin
Abstract: Intra-operative recognition of surgical phases holds significant potential for enhancing real-time contextual awareness in the operating room. However, we argue that online recognition, while beneficial, primarily lends itself to post-operative video analysis due to its limited direct impact on the actual surgical decisions and actions during ongoing procedures. In contrast, we contend that the prediction and anticipation of surgical phases are inherently more valuable for intra-operative assistance, as they can meaningfully influence a surgeon's immediate and long-term planning by providing foresight into future steps. To address this gap, we propose a dual approach that simultaneously recognises the current surgical phase and predicts upcoming ones, thus offering comprehensive intra-operative assistance and guidance on the expected remaining workflow. Our novel method, Surgical Phase Recognition and Anticipation (SuPRA), leverages past and current information for accurate intra-operative phase recognition while using future segments for phase prediction. This unified approach challenges conventional frameworks that treat these objectives separately. We have validated SuPRA on two reputed datasets, Cholec80 and AutoLaparo21, where it demonstrated state-of-the-art performance with recognition accuracies of 91.8% and 79.3%, respectively. Additionally, we introduce and evaluate our model using new segment-level evaluation metrics, namely Edit and F1 Overlap scores, for a more temporal assessment of segment classification. In conclusion, SuPRA presents a new multi-task approach that paves the way for improved intra-operative assistance through surgical phase recognition and prediction of future events.
Authors: Xingyi Li, Zhiguo Cao, Yizheng Wu, Kewei Wang, Ke Xian, Zhe Wang, Guosheng Lin
Abstract: Current 3D stylization methods often assume static scenes, which violates the dynamic nature of our real world. To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields. However, stylizing dynamic 3D scenes is inherently challenging due to the limited availability of stylized reference images along the temporal axis. Our key insight lies in introducing additional temporal cues besides the provided reference. To this end, we generate temporal pseudo-references from the given stylized reference. These pseudo-references facilitate the propagation of style information from the reference to the entire dynamic 3D scene. For coarse style transfer, we enforce novel views and times to mimic the style details present in pseudo-references at the feature level. To preserve high-frequency details, we create a collection of stylized temporal pseudo-rays from temporal pseudo-references. These pseudo-rays serve as detailed and explicit stylization guidance for achieving fine style transfer. Experiments on both synthetic and real-world datasets demonstrate that our method yields plausible stylized results of space-time view synthesis on dynamic 3D scenes.
Authors: Roy Miles, Ismail Elezi, Jiankang Deng
Abstract: Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To address this limitation, we propose a novel constrained feature distillation method. This method is derived from a small set of core principles, which results in two emerging components: an orthogonal projection and a task-specific normalisation. Equipped with both of these components, our transformer models can outperform all previous methods on ImageNet and reach up to a 4.4% relative improvement over the previous state-of-the-art methods. To further demonstrate the generality of our method, we apply it to object detection and image generation, whereby we obtain consistent and substantial performance improvements over state-of-the-art. Code and models are publicly available: https://github.com/roymiles/vkd
Authors: Boeun Kim, Jungho Kim, Hyung Jin Chang, Jin Young Choi
Abstract: While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents. This challenge lies in the lack of clear separation between content and style of a motion. To tackle this challenge, we propose a novel motion style transformer that effectively disentangles style from content and generates a plausible motion with transferred style from a source motion. Our distinctive approach to achieving the goal of disentanglement is twofold: (1) a new architecture for motion style transformer with 'part-attentive style modulator across body parts' and 'Siamese encoders that encode style and content features separately'; (2) style disentanglement loss. Our method outperforms existing methods and demonstrates exceptionally high quality, particularly in motion pairs with different contents, without the need for heuristic post-processing. Codes are available at https://github.com/Boeun-Kim/MoST.
Authors: Lin Zhu, Xianzhang Chen, Xiao Wang, Hua Huang
Abstract: As a bio-inspired vision sensor, the spike camera emulates the operational principles of the fovea, a compact retinal region, by employing spike discharges to encode the accumulation of per-pixel luminance intensity. Leveraging its high temporal resolution and bio-inspired neuromorphic design, the spike camera holds significant promise for advancing computer vision applications. Saliency detection mimics the behavior of human beings and captures the most salient region from the scenes. In this paper, we investigate the visual saliency in the continuous spike stream for the first time. To effectively process the binary spike stream, we propose a Recurrent Spiking Transformer (RST) framework, which is based on a full spiking neural network. Our framework enables the extraction of spatio-temporal features from the continuous spatio-temporal spike stream while maintaining low power consumption. To facilitate the training and validation of our proposed model, we build a comprehensive real-world spike-based visual saliency dataset, enriched with numerous light conditions. Extensive experiments demonstrate the superior performance of our Recurrent Spiking Transformer framework in comparison to other spike neural network-based methods. Our framework exhibits a substantial margin of improvement in capturing and highlighting visual saliency in the spike stream, which not only provides a new perspective for spike-based saliency segmentation but also shows a new paradigm for full SNN-based transformer models. The code and dataset are available at \url{https://github.com/BIT-Vision/SVS}.
Authors: Xinmin Qiu, Congying Han, Zicheng Zhang, Bonan Li, Tiande Guo, Pingyu Wang, Xuecheng Nie
Abstract: Developing blind video deflickering (BVD) algorithms to enhance video temporal consistency, is gaining importance amid the flourish of image processing and video generation. However, the intricate nature of video data complicates the training of deep learning methods, leading to high resource consumption and instability, notably under severe lighting flicker. This underscores the critical need for a compact representation beyond pixel values to advance BVD research and applications. Inspired by the classic scale-time equalization (STE), our work introduces the histogram-assisted solution, called BlazeBVD, for high-fidelity and rapid BVD. Compared with STE, which directly corrects pixel values by temporally smoothing color histograms, BlazeBVD leverages smoothed illumination histograms within STE filtering to ease the challenge of learning temporal data using neural networks. In technique, BlazeBVD begins by condensing pixel values into illumination histograms that precisely capture flickering and local exposure variations. These histograms are then smoothed to produce singular frames set, filtered illumination maps, and exposure maps. Resorting to these deflickering priors, BlazeBVD utilizes a 2D network to restore faithful and consistent texture impacted by lighting changes or localized exposure issues. BlazeBVD also incorporates a lightweight 3D network to amend slight temporal inconsistencies, avoiding the resource consumption issue. Comprehensive experiments on synthetic, real-world and generated videos, showcase the superior qualitative and quantitative results of BlazeBVD, achieving inference speeds up to 10x faster than state-of-the-arts.
Authors: Mingyu Lee, Jongwon Choi
Abstract: We propose a text-guided variational image generation method to address the challenge of getting clean data for anomaly detection in industrial manufacturing. Our method utilizes text information about the target object, learned from extensive text library documents, to generate non-defective data images resembling the input image. The proposed framework ensures that the generated non-defective images align with anticipated distributions derived from textual and image-based knowledge, ensuring stability and generality. Experimental results demonstrate the effectiveness of our approach, surpassing previous methods even with limited non-defective data. Our approach is validated through generalization tests across four baseline models and three distinct datasets. We present an additional analysis to enhance the effectiveness of anomaly detection models by utilizing the generated images.
Authors: Xinhao Cai, Qiuxia Lai, Yuwei Wang, Wenguan Wang, Zeren Sun, Yazhou Yao
Abstract: Object detection in remote sensing images (RSIs) often suffers from several increasing challenges, including the large variation in object scales and the diverse-ranging context. Prior methods tried to address these challenges by expanding the spatial receptive field of the backbone, either through large-kernel convolution or dilated convolution. However, the former typically introduces considerable background noise, while the latter risks generating overly sparse feature representations. In this paper, we introduce the Poly Kernel Inception Network (PKINet) to handle the above challenges. PKINet employs multi-scale convolution kernels without dilation to extract object features of varying scales and capture local context. In addition, a Context Anchor Attention (CAA) module is introduced in parallel to capture long-range contextual information. These two components work jointly to advance the performance of PKINet on four challenging remote sensing detection benchmarks, namely DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R.
Authors: Arun Sharma, Shashi Shekhar
Abstract: Given trajectories with gaps (i.e., missing data), we investigate algorithms to identify abnormal gaps in trajectories which occur when a given moving object did not report its location, but other moving objects in the same geographic region periodically did. The problem is important due to its societal applications, such as improving maritime safety and regulatory enforcement for global security concerns such as illegal fishing, illegal oil transfers, and trans-shipments. The problem is challenging due to the difficulty of bounding the possible locations of the moving object during a trajectory gap, and the very high computational cost of detecting gaps in such a large volume of location data. The current literature on anomalous trajectory detection assumes linear interpolation within gaps, which may not be able to detect abnormal gaps since objects within a given region may have traveled away from their shortest path. In preliminary work, we introduced an abnormal gap measure that uses a classical space-time prism model to bound an object's possible movement during the trajectory gap and provided a scalable memoized gap detection algorithm (Memo-AGD). In this paper, we propose a Space Time-Aware Gap Detection (STAGD) approach to leverage space-time indexing and merging of trajectory gaps. We also incorporate a Dynamic Region Merge-based (DRM) approach to efficiently compute gap abnormality scores. We provide theoretical proofs that both algorithms are correct and complete and also provide analysis of asymptotic time complexity. Experimental results on synthetic and real-world maritime trajectory data show that the proposed approach substantially improves computation time over the baseline technique.
Authors: Youyuan Zhang, Xuan Ju, James J. Clark
Abstract: Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling in diffusion models poses challenges for efficient video editing. Existing approaches relying on image generation models for video editing suffer from time-consuming one-shot fine-tuning, additional condition extraction, or DDIM inversion, making real-time applications impractical. In this work, we propose FastVideoEdit, an efficient zero-shot video editing approach inspired by Consistency Models (CMs). By leveraging the self-consistency property of CMs, we eliminate the need for time-consuming inversion or additional condition extraction, reducing editing time. Our method enables direct mapping from source video to target video with strong preservation ability utilizing a special variance schedule. This results in improved speed advantages, as fewer sampling steps can be used while maintaining comparable generation quality. Experimental results validate the state-of-the-art performance and speed advantages of FastVideoEdit across evaluation metrics encompassing editing speed, temporal consistency, and text-video alignment.
Authors: Kwanyoung Kim, Jaa-Yeon Lee, Jong Chul Ye
Abstract: Nakagami imaging holds promise for visualizing and quantifying tissue scattering in ultrasound waves, with potential applications in tumor diagnosis and fat fraction estimation which are challenging to discern by conventional ultrasound B-mode images. Existing methods struggle with optimal window size selection and suffer from estimator instability, leading to degraded resolution images. To address this, here we propose a novel method called UNICORN (Ultrasound Nakagami Imaging via Score Matching and Adaptation), that offers an accurate, closed-form estimator for Nakagami parameter estimation in terms of the score function of ultrasonic envelope. Extensive experiments using simulation and real ultrasound RF data demonstrate UNICORN's superiority over conventional approaches in accuracy and resolution quality.
Authors: Justin Yang, Zhihao Duan, Andrew Peng, Yuning Huang, Jiangpeng He, Fengqing Zhu
Abstract: Image compression emerges as a pivotal tool in the efficient handling and transmission of digital images. Its ability to substantially reduce file size not only facilitates enhanced data storage capacity but also potentially brings advantages to the development of continual machine learning (ML) systems, which learn new knowledge incrementally from sequential data. Continual ML systems often rely on storing representative samples, also known as exemplars, within a limited memory constraint to maintain the performance on previously learned data. These methods are known as memory replay-based algorithms and have proven effective at mitigating the detrimental effects of catastrophic forgetting. Nonetheless, the limited memory buffer size often falls short of adequately representing the entire data distribution. In this paper, we explore the use of image compression as a strategy to enhance the buffer's capacity, thereby increasing exemplar diversity. However, directly using compressed exemplars introduces domain shift during continual ML, marked by a discrepancy between compressed training data and uncompressed testing data. Additionally, it is essential to determine the appropriate compression algorithm and select the most effective rate for continual ML systems to balance the trade-off between exemplar quality and quantity. To this end, we introduce a new framework to incorporate image compression for continual ML including a pre-processing data compression step and an efficient compression rate/algorithm selection method. We conduct extensive experiments on CIFAR-100 and ImageNet datasets and show that our method significantly improves image classification accuracy in continual ML settings.
Authors: Zijun Long, Lipeng Zhuang, George Killick, Richard McCreadie, Gerardo Aragon Camarasa, Paul Henderson
Abstract: Human-annotated vision datasets inevitably contain a fraction of human mislabelled examples. While the detrimental effects of such mislabelling on supervised learning are well-researched, their influence on Supervised Contrastive Learning (SCL) remains largely unexplored. In this paper, we show that human-labelling errors not only differ significantly from synthetic label errors, but also pose unique challenges in SCL, different to those in traditional supervised learning methods. Specifically, our results indicate they adversely impact the learning process in the ~99% of cases when they occur as false positive samples. Existing noise-mitigating methods primarily focus on synthetic label errors and tackle the unrealistic setting of very high synthetic noise rates (40-80%), but they often underperform on common image datasets due to overfitting. To address this issue, we introduce a novel SCL objective with robustness to human-labelling errors, SCL-RHE. SCL-RHE is designed to mitigate the effects of real-world mislabelled examples, typically characterized by much lower noise rates (<5%). We demonstrate that SCL-RHE consistently outperforms state-of-the-art representation learning and noise-mitigating methods across various vision benchmarks, by offering improved resilience against human-labelling errors.
Authors: Debolena Basak, P. K. Srijith, Maunendra Sankar Desarkar
Abstract: In several real-world scenarios like autonomous navigation and mobility, to obtain a better visual understanding of the surroundings, image captioning and object detection play a crucial role. This work introduces a novel multitask learning framework that combines image captioning and object detection into a joint model. We propose TICOD, Transformer-based Image Captioning and Object detection model for jointly training both tasks by combining the losses obtained from image captioning and object detection networks. By leveraging joint training, the model benefits from the complementary information shared between the two tasks, leading to improved performance for image captioning. Our approach utilizes a transformer-based architecture that enables end-to-end network integration for image captioning and object detection and performs both tasks jointly. We evaluate the effectiveness of our approach through comprehensive experiments on the MS-COCO dataset. Our model outperforms the baselines from image captioning literature by achieving a 3.65% improvement in BERTScore.
Authors: Thang Doan, Sima Behpour, Xin Li, Wenbin He, Liang Gou, Liu Ren
Abstract: Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting. The rise of Vision-Language models (VLMs) has unlocked numerous applications, leveraging their existing knowledge to fine-tune on custom data. However, training the whole model is computationally prohibitive, and VLMs while being versatile in general domains still struggle with fine-grained datasets crucial for many applications. We tackle these challenges with two proposed simple modules. The first, Session-Specific Prompts (SSP), enhances the separability of image-text embeddings across sessions. The second, Hyperbolic distance, compresses representations of image-text pairs within the same class while expanding those from different classes, leading to better representations. Experimental results demonstrate an average 10-point increase compared to baselines while requiring at least 8 times fewer trainable parameters. This improvement is further underscored on our three newly introduced fine-grained datasets.
Authors: Soodeh Kalaie, Andy Bulpitt, Alejandro F. Frangi, Ali Gooya
Abstract: Generative modelling for shapes is a prerequisite for In-Silico Clinical Trials (ISCTs), which aim to cost-effectively validate medical device interventions using synthetic anatomical shapes, often represented as 3D surface meshes. However, constructing AI models to generate shapes closely resembling the real mesh samples is challenging due to variable vertex counts, connectivities, and the lack of dense vertex-wise correspondences across the training data. Employing graph representations for meshes, we develop a novel unsupervised geometric deep-learning model to establish refinable shape correspondences in a latent space, construct a population-derived atlas and generate realistic synthetic shapes. We additionally extend our proposed base model to a joint shape generative-clustering multi-atlas framework to incorporate further variability and preserve more details in the generated shapes. Experimental results using liver and left-ventricular models demonstrate the approach's applicability to computational medicine, highlighting its suitability for ISCTs through a comparative analysis.
Authors: Scott Siegel, Jiaqing Zhang, Sabyasachi Bandyopadhyay, Subhash Nerella, Brandon Silva, Tezcan Baslanti, Azra Bihorac, Parisa Rashidi
Abstract: Despite the importance of closely monitoring patients in the Intensive Care Unit (ICU), many aspects are still assessed in a limited manner due to the time constraints imposed on healthcare providers. For example, although excessive visitations during rest hours can potentially exacerbate the risk of circadian rhythm disruption and delirium, it is not captured in the ICU. Likewise, while mobility can be an important indicator of recovery or deterioration in ICU patients, it is only captured sporadically or not captured at all. In the past few years, the computer vision field has found application in many domains by reducing the human burden. Using computer vision systems in the ICU can also potentially enable non-existing assessments or enhance the frequency and accuracy of existing assessments while reducing the staff workload. In this study, we leverage a state-of-the-art noninvasive computer vision system based on depth imaging to characterize ICU visitations and patients' mobility. We then examine the relationship between visitation and several patient outcomes, such as pain, acuity, and delirium. We found an association between deteriorating patient acuity and the incidence of delirium with increased visitations. In contrast, self-reported pain, reported using the Defense and Veteran Pain Rating Scale (DVPRS), was correlated with decreased visitations. Our findings highlight the feasibility and potential of using noninvasive autonomous systems to monitor ICU patients.
Authors: Omnia AlwazzanSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute, Ioannis PatrasSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute, Gregory SlabaughSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute
Abstract: Fusion of multimodal healthcare data holds great promise to provide a holistic view of a patient's health, taking advantage of the complementarity of different modalities while leveraging their correlation. This paper proposes a simple and effective approach, inspired by attention, to fuse discriminative features from different modalities. We propose a novel attention mechanism, called Flattened Outer Arithmetic Attention (FOAA), which relies on outer arithmetic operators (addition, subtraction, product, and division) to compute attention scores from keys, queries and values derived from flattened embeddings of each modality. We demonstrate how FOAA can be implemented for self-attention and cross-attention, providing a reusable component in neural network architectures. We evaluate FOAA on two datasets for multimodal tumor classification and achieve state-of-the-art results, and we demonstrate that features enriched by FOAA are superior to those derived from other fusion approaches. The code is publicly available at \href{https://github.com/omniaalwazzan/FOAA}{https://github.com/omniaalwazzan/FOAA}
URLs: https://github.com/omniaalwazzan/FOAA, https://github.com/omniaalwazzan/FOAA
Authors: Omnia AlwazzanSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute, Abbas KhanSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute, Ioannis PatrasSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute, Gregory SlabaughSchool of Electronic Engineering and Computer Science, Queen Mary University of London, UK, Queen Mary Digital Environment Research Institute
Abstract: Brain tumors are an abnormal growth of cells in the brain. They can be classified into distinct grades based on their growth. Often grading is performed based on a histological image and is one of the most significant predictors of a patients prognosis, the higher the grade, the more aggressive the tumor. Correct diagnosis of a tumor grade remains challenging. Though histopathological grading has been shown to be prognostic, results are subject to interobserver variability, even among experienced pathologists. Recently, the World Health Organization reported that advances in molecular genetics have led to improvements in tumor classification. This paper seeks to integrate histological images and genetic data for improved computer-aided diagnosis. We propose a novel Multi-modal Outer Arithmetic Block (MOAB) based on arithmetic operations to combine latent representations of the different modalities for predicting the tumor grade (Grade \rom{2}, \rom{3} and \rom{4}). Extensive experiments evaluate the effectiveness of our approach. By applying MOAB to The Cancer Genome Atlas (TCGA) glioma dataset, we show that it can improve separation between similar classes (Grade \rom{2} and \rom{3}) and outperform prior state-of-the-art grade classification techniques.
Authors: Mi Luo, Zihui Xue, Alex Dimakis, Kristen Grauman
Abstract: We investigate exocentric-to-egocentric cross-view translation, which aims to generate a first-person (egocentric) view of an actor based on a video recording that captures the actor from a third-person (exocentric) perspective. To this end, we propose a generative framework called Exo2Ego that decouples the translation process into two stages: high-level structure transformation, which explicitly encourages cross-view correspondence between exocentric and egocentric views, and a diffusion-based pixel-level hallucination, which incorporates a hand layout prior to enhance the fidelity of the generated egocentric view. To pave the way for future advancements in this field, we curate a comprehensive exo-to-ego cross-view translation benchmark. It consists of a diverse collection of synchronized ego-exo tabletop activity video pairs sourced from three public datasets: H2O, Aria Pilot, and Assembly101. The experimental results validate that Exo2Ego delivers photorealistic video results with clear hand manipulation details and outperforms several baselines in terms of both synthesis quality and generalization ability to new actions.
Authors: Xing Lei, Longjun Liu, Zhiheng Zhou, Hongbin Sun, Nanning Zheng
Abstract: In this paper, we explore how to design lightweight CNN architecture for embedded computing systems. We propose L-Mobilenet model for ZYNQ based hardware platform. L-Mobilenet can adapt well to the hardware computing and accelerating, and its network structure is inspired by the state-of-the-art work of Inception-ResnetV1 and MobilenetV2, which can effectively reduce parameters and delay while maintaining the accuracy of inference. We deploy our L-Mobilenet model to ZYNQ embedded platform for fully evaluating the performance of our design. By measuring in cifar10 and cifar100 datasets, L-Mobilenet model is able to gain 3x speed up and 3.7x fewer parameters than MobileNetV2 while maintaining a similar accuracy. It also can obtain 2x speed up and 1.5x fewer parameters than ShufflenetV2 while maintaining the same accuracy. Experiments show that our network model can obtain better performance because of the special considerations for hardware accelerating and software-hardware co-design strategies in our L-Mobilenet bottleneck architecture.
Authors: Chaoyi Wang, Yaozhe Song, Yafeng Zhang, Jun Pei, Lijie Xia, Jianpo Liu
Abstract: Currently, various studies have been exploring generation of long videos. However, the generated frames in these videos often exhibit jitter and noise. Therefore, in order to generate the videos without these noise, we propose a novel framework composed of four modules: separate tuning module, average fusion module, combined tuning module, and inter-frame consistency module. By applying our newly proposed modules subsequently, the consistency of the background and foreground in each video frames is optimized. Besides, the experimental results demonstrate that videos generated by our method exhibit a high quality in comparison of the state-of-the-art methods.
Authors: Yulong Liu, Yongqiang Ma, Guibo Zhu, Haodong Jing, Nanning Zheng
Abstract: Deciphering visual content from functional Magnetic Resonance Imaging (fMRI) helps illuminate the human vision system. However, the scarcity of fMRI data and noise hamper brain decoding model performance. Previous approaches primarily employ subject-specific models, sensitive to training sample size. In this paper, we explore a straightforward but overlooked solution to address data scarcity. We propose shallow subject-specific adapters to map cross-subject fMRI data into unified representations. Subsequently, a shared deeper decoding model decodes cross-subject features into the target feature space. During training, we leverage both visual and textual supervision for multi-modal brain decoding. Our model integrates a high-level perception decoding pipeline and a pixel-wise reconstruction pipeline guided by high-level perceptions, simulating bottom-up and top-down processes in neuroscience. Empirical experiments demonstrate robust neural representation learning across subjects for both pipelines. Moreover, merging high-level and low-level information improves both low-level and high-level reconstruction metrics. Additionally, we successfully transfer learned general knowledge to new subjects by training new adapters with limited training data. Compared to previous state-of-the-art methods, notably pre-training-based methods (Mind-Vis and fMRI-PTE), our approach achieves comparable or superior results across diverse tasks, showing promise as an alternative method for cross-subject fMRI data pre-training. Our code and pre-trained weights will be publicly released at https://github.com/YulongBonjour/See_Through_Their_Minds.
URLs: https://github.com/YulongBonjour/See_Through_Their_Minds.
Authors: Shuai Tan, Bin Ji, Yu Ding, Ye Pan
Abstract: Generating stylized talking head with diverse head motions is crucial for achieving natural-looking videos but still remains challenging. Previous works either adopt a regressive method to capture the speaking style, resulting in a coarse style that is averaged across all training data, or employ a universal network to synthesize videos with different styles which causes suboptimal performance. To address these, we propose a novel dynamic-weight method, namely Say Anything withAny Style (SAAS), which queries the discrete style representation via a generative model with a learned style codebook. Specifically, we develop a multi-task VQ-VAE that incorporates three closely related tasks to learn a style codebook as a prior for style extraction. This discrete prior, along with the generative model, enhances the precision and robustness when extracting the speaking styles of the given style clips. By utilizing the extracted style, a residual architecture comprising a canonical branch and style-specific branch is employed to predict the mouth shapes conditioned on any driving audio while transferring the speaking style from the source to any desired one. To adapt to different speaking styles, we steer clear of employing a universal network by exploring an elaborate HyperStyle to produce the style-specific weights offset for the style branch. Furthermore, we construct a pose generator and a pose codebook to store the quantized pose representation, allowing us to sample diverse head motions aligned with the audio and the extracted style. Experiments demonstrate that our approach surpasses state-of-theart methods in terms of both lip-synchronization and stylized expression. Besides, we extend our SAAS to video-driven style editing field and achieve satisfactory performance.
Authors: Shuai Tan, Bin Ji, Ye Pan
Abstract: Although automatically animating audio-driven talking heads has recently received growing interest, previous efforts have mainly concentrated on achieving lip synchronization with the audio, neglecting two crucial elements for generating expressive videos: emotion style and art style. In this paper, we present an innovative audio-driven talking face generation method called Style2Talker. It involves two stylized stages, namely Style-E and Style-A, which integrate text-controlled emotion style and picture-controlled art style into the final output. In order to prepare the scarce emotional text descriptions corresponding to the videos, we propose a labor-free paradigm that employs large-scale pretrained models to automatically annotate emotional text labels for existing audiovisual datasets. Incorporating the synthetic emotion texts, the Style-E stage utilizes a large-scale CLIP model to extract emotion representations, which are combined with the audio, serving as the condition for an efficient latent diffusion model designed to produce emotional motion coefficients of a 3DMM model. Moving on to the Style-A stage, we develop a coefficient-driven motion generator and an art-specific style path embedded in the well-known StyleGAN. This allows us to synthesize high-resolution artistically stylized talking head videos using the generated emotional motion coefficients and an art style source picture. Moreover, to better preserve image details and avoid artifacts, we provide StyleGAN with the multi-scale content features extracted from the identity image and refine its intermediate feature maps by the designed content encoder and refinement network, respectively. Extensive experimental results demonstrate our method outperforms existing state-of-the-art methods in terms of audio-lip synchronization and performance of both emotion style and art style.
Authors: Shuai Tan, Bin Ji, Ye Pan
Abstract: Generating emotional talking faces is a practical yet challenging endeavor. To create a lifelike avatar, we draw upon two critical insights from a human perspective: 1) The connection between audio and the non-deterministic facial dynamics, encompassing expressions, blinks, poses, should exhibit synchronous and one-to-many mapping. 2) Vibrant expressions are often accompanied by emotion-aware high-definition (HD) textures and finely detailed teeth. However, both aspects are frequently overlooked by existing methods. To this end, this paper proposes using normalizing Flow and Vector-Quantization modeling to produce emotional talking faces that satisfy both insights concurrently (FlowVQTalker). Specifically, we develop a flow-based coefficient generator that encodes the dynamics of facial emotion into a multi-emotion-class latent space represented as a mixture distribution. The generation process commences with random sampling from the modeled distribution, guided by the accompanying audio, enabling both lip-synchronization and the uncertain nonverbal facial cues generation. Furthermore, our designed vector-quantization image generator treats the creation of expressive facial images as a code query task, utilizing a learned codebook to provide rich, high-quality textures that enhance the emotional perception of the results. Extensive experiments are conducted to showcase the effectiveness of our approach.
Authors: Lang Nie, Chunyu Lin, Kang Liao, Yun Zhang, Shuaicheng Liu, Yao Zhao
Abstract: In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching. It unveils the temporal instability of warped content in non-overlapping regions, despite image stitching having endeavored to preserve the natural structures. Therefore, in most cases, even if the input videos to be stitched are stable, the stitched video will inevitably cause undesired warping shakes and affect the visual experience. To eliminate the shakes, we propose StabStitch to simultaneously realize video stitching and video stabilization in a unified unsupervised learning framework. Starting from the camera paths in video stabilization, we first derive the expression of stitching trajectories in video stitching by elaborately integrating spatial and temporal warps. Then a warp smoothing model is presented to optimize them with a comprehensive consideration regarding content alignment, trajectory smoothness, spatial consistency, and online collaboration. To establish an evaluation benchmark and train the learning framework, we build a video stitching dataset with a rich diversity in camera motions and scenes. Compared with existing stitching solutions, StabStitch exhibits significant superiority in scene robustness and inference speed in addition to stitching and stabilization performance, contributing to a robust and real-time online video stitching system. The code and dataset will be available at https://github.com/nie-lang/StabStitch.
Authors: Yang Zhang, Teoh Tze Tzun, Lim Wei Hern, Tiviatis Sim, Kenji Kawaguchi
Abstract: Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended semantics of the associated text prompts. We examine cross-attention layers in diffusion models and observe a propensity for these layers to disproportionately focus on certain tokens during the generation process, thereby undermining semantic fidelity. To address the issue of dominant attention, we introduce attention regulation, a computation-efficient on-the-fly optimization approach at inference time to align attention maps with the input text prompt. Notably, our method requires no additional training or fine-tuning and serves as a plug-in module on a model. Hence, the generation capacity of the original model is fully preserved. We compare our approach with alternative approaches across various datasets, evaluation metrics, and diffusion models. Experiment results show that our method consistently outperforms other baselines, yielding images that more faithfully reflect the desired concepts with reduced computation overhead. Code is available at https://github.com/YaNgZhAnG-V5/attention_regulation.
Authors: Jiameng Bai, Sai Wu, Jie Song, Junbo Zhao, Gang Chen
Abstract: As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task. Existing model selection techniques are often constrained in their scope and tend to overlook the nuanced relationships between models and tasks. In this paper, we present a pragmatic framework \textbf{Fennec}, delving into a diverse, large-scale model repository while meticulously considering the intricate connections between tasks and models. The key insight is to map all models and historical tasks into a transfer-related subspace, where the distance between model vectors and task vectors represents the magnitude of transferability. A large vision model, as a proxy, infers a new task's representation in the transfer space, thereby circumventing the computational burden of extensive forward passes. We also investigate the impact of the inherent inductive bias of models on transfer results and propose a novel method called \textbf{archi2vec} to encode the intricate structures of models. The transfer score is computed through straightforward vector arithmetic with a time complexity of $\mathcal{O}(1)$. Finally, we make a substantial contribution to the field by releasing a comprehensive benchmark. We validate the effectiveness of our framework through rigorous testing on two benchmarks. The benchmark and the code will be publicly available in the near future.
Authors: Rukhshanda Hussain, Hui Xian Grace Lim, Borchun Chen, Mubarak Shah, Ser Nam Lim
Abstract: Novel view synthesis has observed tremendous developments since the arrival of NeRFs. However, Nerf models overfit on a single scene, lacking generalization to out of distribution objects. Recently, diffusion models have exhibited remarkable performance on introducing generalization in view synthesis. Inspired by these advancements, we explore the capabilities of a pretrained stable diffusion model for view synthesis without explicit 3D priors. Specifically, we base our method on a personalized text to image model, Dreambooth, given its strong ability to adapt to specific novel objects with a few shots. Our research reveals two interesting findings. First, we observe that Dreambooth can learn the high level concept of a view, compared to arguably more complex strategies which involve finetuning diffusions on large amounts of multi-view data. Second, we establish that the concept of a view can be disentangled and transferred to a novel object irrespective of the original object's identify from which the views are learnt. Motivated by this, we introduce a learning strategy, FSViewFusion, which inherits a specific view through only one image sample of a single scene, and transfers the knowledge to a novel object, learnt from few shots, using low rank adapters. Through extensive experiments we demonstrate that our method, albeit simple, is efficient in generating reliable view samples for in the wild images. Code and models will be released.
Authors: Yuhao Jia, Wenhan Tan
Abstract: Diffusion-driven text-to-image (T2I) generation has achieved remarkable advancements. To further improve T2I models' capability in numerical and spatial reasoning, the layout is employed as an intermedium to bridge large language models and layout-based diffusion models. However, these methods still struggle with generating images from textural prompts with multiple objects and complicated spatial relationships. To tackle this challenge, we introduce a divide-and-conquer approach which decouples the T2I generation task into simple subtasks. Our approach divides the layout prediction stage into numerical \& spatial reasoning and bounding box prediction. Then, the layout-to-image generation stage is conducted in an iterative manner to reconstruct objects from easy ones to difficult ones. We conduct experiments on the HRS and NSR-1K benchmarks and our approach outperforms previous state-of-the-art models with notable margins. In addition, visual results demonstrate that our approach significantly improves the controllability and consistency in generating multiple objects from complex textural prompts.
Authors: Peng Zhang, Ting Wu, Jinsheng Sun, Weiqing Li, Zhiyong Su
Abstract: Existing interactive point cloud segmentation approaches primarily focus on the object segmentation, which aim to determine which points belong to the object of interest guided by user interactions. This paper concentrates on an unexplored yet meaningful task, i.e., interactive point cloud semantic segmentation, which assigns high-quality semantic labels to all points in a scene with user corrective clicks. Concretely, we presents the first interactive framework for point cloud semantic segmentation, named InterPCSeg, which seamlessly integrates with off-the-shelf semantic segmentation networks without offline re-training, enabling it to run in an on-the-fly manner. To achieve online refinement, we treat user interactions as sparse training examples during the test-time. To address the instability caused by the sparse supervision, we design a stabilization energy to regulate the test-time training process. For objective and reproducible evaluation, we develop an interaction simulation scheme tailored for the interactive point cloud semantic segmentation task. We evaluate our framework on the S3DIS and ScanNet datasets with off-the-shelf segmentation networks, incorporating interactions from both the proposed interaction simulator and real users. Quantitative and qualitative experimental results demonstrate the efficacy of our framework in refining the semantic segmentation results with user interactions. The source code will be publicly available.
Authors: Qingdong He, Jinlong Peng, Zhengkai Jiang, Xiaobin Hu, Jiangning Zhang, Qiang Nie, Yabiao Wang, Chengjie Wang
Abstract: Recent success of vision foundation models have shown promising performance for the 2D perception tasks. However, it is difficult to train a 3D foundation network directly due to the limited dataset and it remains under explored whether existing foundation models can be lifted to 3D space seamlessly. In this paper, we present PointSeg, a novel training-free paradigm that leverages off-the-shelf vision foundation models to address 3D scene perception tasks. PointSeg can segment anything in 3D scene by acquiring accurate 3D prompts to align their corresponding pixels across frames. Concretely, we design a two-branch prompts learning structure to construct the 3D point-box prompts pairs, combining with the bidirectional matching strategy for accurate point and proposal prompts generation. Then, we perform the iterative post-refinement adaptively when cooperated with different vision foundation models. Moreover, we design a affinity-aware merging algorithm to improve the final ensemble masks. PointSeg demonstrates impressive segmentation performance across various datasets, all without training. Specifically, our approach significantly surpasses the state-of-the-art specialist model by 13.4$\%$, 11.3$\%$, and 12$\%$ mAP on ScanNet, ScanNet++, and KITTI-360 datasets, respectively. On top of that, PointSeg can incorporate with various segmentation models and even surpasses the supervised methods.
Authors: Weixia Zhang, Dingquan Li, Guangtao Zhai, Xiaokang Yang, Kede Ma
Abstract: Contemporary no-reference image quality assessment (NR-IQA) models can effectively quantify the perceived image quality, with high correlations between model predictions and human perceptual scores on fixed test sets. However, little progress has been made in comparing NR-IQA models from a perceptual optimization perspective. Here, for the first time, we demonstrate that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement. This is achieved by taking the gradients in differentiable and bijective diffusion latents rather than in the raw pixel domain. Different NR-IQA models are likely to induce different enhanced images, which are ultimately subject to psychophysical testing. This leads to a new computational method for comparing NR-IQA models within the analysis-by-synthesis framework. Compared to conventional correlation-based metrics, our method provides complementary insights into the relative strengths and weaknesses of the competing NR-IQA models in the context of perceptual optimization.
Authors: Jiawei Chen, Yue Jiang, Dingkang Yang, Mingcheng Li, Jinjie Wei, Ziyun Qian, Lihua Zhang
Abstract: While large language models (LLMs) excel in world knowledge understanding, adapting them to specific subfields requires precise adjustments. Due to the model's vast scale, traditional global fine-tuning methods for large models can be computationally expensive and impact generalization. To address this challenge, a range of innovative Parameters-Efficient Fine-Tuning (PEFT) methods have emerged and achieved remarkable success in both LLMs and Large Vision-Language Models (LVLMs). In the medical domain, fine-tuning a medical Vision-Language Pretrained (VLP) model is essential for adapting it to specific tasks. Can the fine-tuning methods for large models be transferred to the medical field to enhance transfer learning efficiency? In this paper, we delve into the fine-tuning methods of LLMs and conduct extensive experiments to investigate the impact of fine-tuning methods for large models on existing multimodal models in the medical domain from the training data level and the model structure level. We show the different impacts of fine-tuning methods for large models on medical VLMs and develop the most efficient ways to fine-tune medical VLP models. We hope this research can guide medical domain researchers in optimizing VLMs' training costs, fostering the broader application of VLMs in healthcare fields. Code and dataset will be released upon acceptance.
Authors: Shengji Tang, Weihao Lin, Hancheng Ye, Peng Ye, Chong Yu, Baopu Li, Tao Chen
Abstract: Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of dropped weights, which is regarded as the suppressed sparsification paradigm. However, this paradigm inactivates the dropped parts of networks causing capacity damage before pruning, thereby leading to performance degradation. To alleviate this issue, we first study and reveal the relative sparsity effect in emerging stimulative training and then propose a structured pruning framework, named STP, based on an enhanced sparsification paradigm which maintains the magnitude of dropped weights and enhances the expressivity of kept weights by self-distillation. Besides, to find an optimal architecture for the pruned network, we propose a multi-dimension architecture space and a knowledge distillation-guided exploration strategy. To reduce the huge capacity gap of distillation, we propose a subnet mutating expansion technique. Extensive experiments on various benchmarks indicate the effectiveness of STP. Specifically, without fine-tuning, our method consistently achieves superior performance at different budgets, especially under extremely aggressive pruning scenarios, e.g., remaining 95.11% Top-1 accuracy (72.43% in 76.15%) while reducing 85% FLOPs for ResNet-50 on ImageNet. Codes will be released soon.
Authors: Weixia Zhang, Chengguang Zhu, Jingnan Gao, Yichao Yan, Guangtao Zhai, Xiaokang Yang
Abstract: The rapid advancement of Artificial Intelligence Generated Content (AIGC) technology has propelled audio-driven talking head generation, gaining considerable research attention for practical applications. However, performance evaluation research lags behind the development of talking head generation techniques. Existing literature relies on heuristic quantitative metrics without human validation, hindering accurate progress assessment. To address this gap, we collect talking head videos generated from four generative methods and conduct controlled psychophysical experiments on visual quality, lip-audio synchronization, and head movement naturalness. Our experiments validate consistency between model predictions and human annotations, identifying metrics that align better with human opinions than widely-used measures. We believe our work will facilitate performance evaluation and model development, providing insights into AIGC in a broader context. Code and data will be made available at https://github.com/zwx8981/ADTH-QA.
Authors: Zhenbo Song, Wenhao Gao, Kaihao Zhang, Wenhan Luo, Zhaoxin Fan, Jianfeng Lu
Abstract: Deep learning-based face restoration models, increasingly prevalent in smart devices, have become targets for sophisticated backdoor attacks. These attacks, through subtle trigger injection into input face images, can lead to unexpected restoration outcomes. Unlike conventional methods focused on classification tasks, our approach introduces a unique degradation objective tailored for attacking restoration models. Moreover, we propose the Adaptive Selective Frequency Injection Backdoor Attack (AS-FIBA) framework, employing a neural network for input-specific trigger generation in the frequency domain, seamlessly blending triggers with benign images. This results in imperceptible yet effective attacks, guiding restoration predictions towards subtly degraded outputs rather than conspicuous targets. Extensive experiments demonstrate the efficacy of the degradation objective on state-of-the-art face restoration models. Additionally, it is notable that AS-FIBA can insert effective backdoors that are more imperceptible than existing backdoor attack methods, including WaNet, ISSBA, and FIBA.
Authors: Konyul Park, Yecheol Kim, Junho Koh, Byungwoo Park, Jun Won Choi
Abstract: Developing high-performance, real-time architectures for LiDAR-based 3D object detectors is essential for the successful commercialization of autonomous vehicles. Pillar-based methods stand out as a practical choice for onboard deployment due to their computational efficiency. However, despite their efficiency, these methods can sometimes underperform compared to alternative point encoding techniques such as Voxel-encoding or PointNet++. We argue that current pillar-based methods have not sufficiently captured the fine-grained distributions of LiDAR points within each pillar structure. Consequently, there exists considerable room for improvement in pillar feature encoding. In this paper, we introduce a novel pillar encoding architecture referred to as Fine-Grained Pillar Feature Encoding (FG-PFE). FG-PFE utilizes Spatio-Temporal Virtual (STV) grids to capture the distribution of point clouds within each pillar across vertical, temporal, and horizontal dimensions. Through STV grids, points within each pillar are individually encoded using Vertical PFE (V-PFE), Temporal PFE (T-PFE), and Horizontal PFE (H-PFE). These encoded features are then aggregated through an Attentive Pillar Aggregation method. Our experiments conducted on the nuScenes dataset demonstrate that FG-PFE achieves significant performance improvements over baseline models such as PointPillar, CenterPoint-Pillar, and PillarNet, with only a minor increase in computational overhead.
Authors: Yuhan Bao, Lei Sun, Yuqin Ma, Kaiwei Wang
Abstract: Event cameras, or Dynamic Vision Sensors (DVS) are novel neuromorphic sensors that capture brightness changes as a continuous stream of ``events'' rather than traditional intensity frames. Converting sparse events to dense intensity frames faithfully has long been an ill-posed problem. Previous methods have primarily focused on converting events to video in dynamic scenes or with a moving camera. In this paper, for the first time, we realize events to dense intensity image conversion using a stationary event camera in static scenes. Different from traditional methods that mainly rely on event integration, the proposed Event-Based Temporal Mapping Photography (EvTemMap) measures the time of event emitting for each pixel. Then, the resulting Temporal Matrix is converted to an intensity frame with a temporal mapping neural network. At the hardware level, the proposed EvTemMap is implemented by combining a transmittance adjustment device with a DVS, named Adjustable Transmittance Dynamic Vision Sensor. Additionally, we collected TemMat dataset under various conditions including low-light and high dynamic range scenes. The experimental results showcase the high dynamic range, fine-grained details, and high-grayscale-resolution of the proposed EvTemMap, as well as the enhanced performance on downstream computer vision tasks compared to other methods. The code and TemMat dataset will be made publicly available.
Authors: Guobao Xiao, Jun Yu, Jiayi Ma, Deng-Ping Fan, Ling Shao
Abstract: Estimating reliable geometric model parameters from the data with severe outliers is a fundamental and important task in computer vision. This paper attempts to sample high-quality subsets and select model instances to estimate parameters in the multi-structural data. To address this, we propose an effective method called Latent Semantic Consensus (LSC). The principle of LSC is to preserve the latent semantic consensus in both data points and model hypotheses. Specifically, LSC formulates the model fitting problem into two latent semantic spaces based on data points and model hypotheses, respectively. Then, LSC explores the distributions of points in the two latent semantic spaces, to remove outliers, generate high-quality model hypotheses, and effectively estimate model instances. Finally, LSC is able to provide consistent and reliable solutions within only a few milliseconds for general multi-structural model fitting, due to its deterministic fitting nature and efficiency. Compared with several state-of-the-art model fitting methods, our LSC achieves significant superiority for the performance of both accuracy and speed on synthetic data and real images. The code will be available at https://github.com/guobaoxiao/LSC.
Authors: Guangyang Wu, Xiaohong Liu, Jun Jia, Xuehao Cui, Guangtao Zhai
Abstract: In the digital era, QR codes serve as a linchpin connecting virtual and physical realms. Their pervasive integration across various applications highlights the demand for aesthetically pleasing codes without compromised scannability. However, prevailing methods grapple with the intrinsic challenge of balancing customization and scannability. Notably, stable-diffusion models have ushered in an epoch of high-quality, customizable content generation. This paper introduces Text2QR, a pioneering approach leveraging these advancements to address a fundamental challenge: concurrently achieving user-defined aesthetics and scanning robustness. To ensure stable generation of aesthetic QR codes, we introduce the QR Aesthetic Blueprint (QAB) module, generating a blueprint image exerting control over the entire generation process. Subsequently, the Scannability Enhancing Latent Refinement (SELR) process refines the output iteratively in the latent space, enhancing scanning robustness. This approach harnesses the potent generation capabilities of stable-diffusion models, navigating the trade-off between image aesthetics and QR code scannability. Our experiments demonstrate the seamless fusion of visual appeal with the practical utility of aesthetic QR codes, markedly outperforming prior methods. Codes are available at \url{https://github.com/mulns/Text2QR}
Authors: Yuki Tatsukawa, I-Chao Shen, Anran Qi, Yuki Koyama, Takeo Igarashi, Ariel Shamir
Abstract: Acquiring the desired font for various design tasks can be challenging and requires professional typographic knowledge. While previous font retrieval or generation works have alleviated some of these difficulties, they often lack support for multiple languages and semantic attributes beyond the training data domains. To solve this problem, we present FontCLIP: a model that connects the semantic understanding of a large vision-language model with typographical knowledge. We integrate typography-specific knowledge into the comprehensive vision-language knowledge of a pretrained CLIP model through a novel finetuning approach. We propose to use a compound descriptive prompt that encapsulates adaptively sampled attributes from a font attribute dataset focusing on Roman alphabet characters. FontCLIP's semantic typographic latent space demonstrates two unprecedented generalization abilities. First, FontCLIP generalizes to different languages including Chinese, Japanese, and Korean (CJK), capturing the typographical features of fonts across different languages, even though it was only finetuned using fonts of Roman characters. Second, FontCLIP can recognize the semantic attributes that are not presented in the training data. FontCLIP's dual-modality and generalization abilities enable multilingual and cross-lingual font retrieval and letter shape optimization, reducing the burden of obtaining desired fonts.
Authors: Haoru Tan, Chuang Wang, Sitong Wu, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu
Abstract: Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably, whereas some traditional algorithm-based methods are more robust to feature noises, outlier nodes, and global transformation (e.g.~rotation). In this paper, we propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods. In the GNN framework, we transform traditional graph-matching solvers as single-channel GNNs on the association graph and extend the single-channel architecture to the multi-channel network. The proposed model can be seen as an ensemble method that fuses multiple algorithms at every iteration. Instead of averaging the estimates at the end of the ensemble, in our approach, the independent iterations of the ensembled algorithms exchange their information after each iteration via a 1x1 channel-wise convolution layer. Experiments show that our model improves the performance of traditional algorithms significantly. In addition, we propose a random sampling strategy to reduce the computational complexity and GPU memory usage, so the model applies to matching graphs with thousands of nodes. We evaluate the performance of our method on three tasks: geometric graph matching, semantic feature matching, and few-shot 3D shape classification. The proposed model performs comparably or outperforms the best existing GNN-based methods.
Authors: Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin, Xingyu Ji, Shenghai Yuan, Lihua Xie
Abstract: Multi-modal test-time adaptation (MM-TTA) is proposed to adapt models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. Previous MM-TTA methods rely on predictions of cross-modal information in each input frame, while they ignore the fact that predictions of geometric neighborhoods within consecutive frames are highly correlated, leading to unstable predictions across time. To fulfill this gap, we propose ReLiable Spatial-temporal Voxels (Latte), an MM-TTA method that leverages reliable cross-modal spatial-temporal correspondences for multi-modal 3D segmentation. Motivated by the fact that reliable predictions should be consistent with their spatial-temporal correspondences, Latte aggregates consecutive frames in a slide window manner and constructs ST voxel to capture temporally local prediction consistency for each modality. After filtering out ST voxels with high ST entropy, Latte conducts cross-modal learning for each point and pixel by attending to those with reliable and consistent predictions among both spatial and temporal neighborhoods. Experimental results show that Latte achieves state-of-the-art performance on three different MM-TTA benchmarks compared to previous MM-TTA or TTA methods.
Authors: Xiaoyang Wang, Huihui Bai, Limin Yu, Yao Zhao, Jimin Xiao
Abstract: Semi-supervised semantic segmentation allows model to mine effective supervision from unlabeled data to complement label-guided training. Recent research has primarily focused on consistency regularization techniques, exploring perturbation-invariant training at both the image and feature levels. In this work, we proposed a novel feature-level consistency learning framework named Density-Descending Feature Perturbation (DDFP). Inspired by the low-density separation assumption in semi-supervised learning, our key insight is that feature density can shed a light on the most promising direction for the segmentation classifier to explore, which is the regions with lower density. We propose to shift features with confident predictions towards lower-density regions by perturbation injection. The perturbed features are then supervised by the predictions on the original features, thereby compelling the classifier to explore less dense regions to effectively regularize the decision boundary. Central to our method is the estimation of feature density. To this end, we introduce a lightweight density estimator based on normalizing flow, allowing for efficient capture of the feature density distribution in an online manner. By extracting gradients from the density estimator, we can determine the direction towards less dense regions for each feature. The proposed DDFP outperforms other designs on feature-level perturbations and shows state of the art performances on both Pascal VOC and Cityscapes dataset under various partition protocols. The project is available at https://github.com/Gavinwxy/DDFP.
Authors: Jiuming Liu, Ruiji Yu, Yian Wang, Yu Zheng, Tianchen Deng, Weicai Ye, Hesheng Wang
Abstract: Recently, state space model (SSM) has gained great attention due to its promising performance, linear complexity, and long sequence modeling ability in both language and image domains. However, it is non-trivial to extend SSM to the point cloud field, because of the causality requirement of SSM and the disorder and irregularity nature of point clouds. In this paper, we propose a novel SSM-based point cloud processing backbone, named Point Mamba, with a causality-aware ordering mechanism. To construct the causal dependency relationship, we design an octree-based ordering strategy on raw irregular points, globally sorting points in a z-order sequence and also retaining their spatial proximity. Our method achieves state-of-the-art performance compared with transformer-based counterparts, with 93.4% accuracy and 75.7 mIOU respectively on the ModelNet40 classification dataset and ScanNet semantic segmentation dataset. Furthermore, our Point Mamba has linear complexity, which is more efficient than transformer-based methods. Our method demonstrates the great potential that SSM can serve as a generic backbone in point cloud understanding. Codes are released at https://github.com/IRMVLab/Point-Mamba.
Authors: Bo Li, Yi-ke Li, Zhi-fen He, Bin Liu, Yun-Kun Lai
Abstract: 3D-consistent image generation from a single 2D semantic label is an important and challenging research topic in computer graphics and computer vision. Although some related works have made great progress in this field, most of the existing methods suffer from poor disentanglement performance of shape and appearance, and lack multi-modal control. In this paper, we propose a novel end-to-end 3D-aware image generation and editing model incorporating multiple types of conditional inputs, including pure noise, text and reference image. On the one hand, we dive into the latent space of 3D Generative Adversarial Networks (GANs) and propose a novel disentanglement strategy to separate appearance features from shape features during the generation process. On the other hand, we propose a unified framework for flexible image generation and editing tasks with multi-modal conditions. Our method can generate diverse images with distinct noises, edit the attribute through a text description and conduct style transfer by giving a reference RGB image. Extensive experiments demonstrate that the proposed method outperforms alternative approaches both qualitatively and quantitatively on image generation and editing.
Authors: Jun-Young Oh, In-Gyu Lee, Tae-Eui Kam, Ji-Hoon Jeong
Abstract: In the cutting-edge domain of medical artificial intelligence (AI), remarkable advances have been achieved in areas such as diagnosis, prediction, and therapeutic interventions. Despite these advances, the technology for image segmentation faces the significant barrier of having to produce extensively annotated datasets. To address this challenge, few-shot segmentation (FSS) has been recognized as one of the innovative solutions. Although most of the FSS research has focused on human health care, its application in veterinary medicine, particularly for pet care, remains largely limited. This study has focused on accurate segmentation of the heart and left atrial enlargement on canine chest radiographs using the proposed deep prototype alignment network (DPANet). The PANet architecture is adopted as the backbone model, and experiments are conducted using various encoders based on VGG-19, ResNet-18, and ResNet-50 to extract features. Experimental results demonstrate that the proposed DPANet achieves the highest performance. In the 2way-1shot scenario, it achieves the highest intersection over union (IoU) value of 0.6966, and in the 2way-5shot scenario, it achieves the highest IoU value of 0.797. The DPANet not only signifies a performance improvement, but also shows an improved training speed in the 2way-5shot scenario. These results highlight our model's exceptional capability as a trailblazing solution for segmenting the heart and left atrial enlargement in veterinary applications through FSS, setting a new benchmark in veterinary AI research, and demonstrating its superior potential to veterinary medicine advances.
Authors: Jiaxin Guo, Jiangliu Wang, Zhaoshuo Li, Tongyu Jia, Qi Dou, Yun-Hui Liu
Abstract: Soft tissue tracking is crucial for computer-assisted interventions. Existing approaches mainly rely on extracting discriminative features from the template and videos to recover corresponding matches. However, it is difficult to adopt these techniques in surgical scenes, where tissues are changing in shape and appearance throughout the surgery. To address this problem, we exploit optical flow to naturally capture the pixel-wise tissue deformations and adaptively correct the tracked template. Specifically, we first implement an inter-frame matching mechanism to extract a coarse region of interest based on optical flow from consecutive frames. To accommodate appearance change and alleviate drift, we then propose an adaptive-template matching method, which updates the tracked template based on the reliability of the estimates. Our approach, Ada-Tracker, enjoys both short-term dynamics modeling by capturing local deformations and long-term dynamics modeling by introducing global temporal compensation. We evaluate our approach on the public SurgT benchmark, which is generated from Hamlyn, SCARED, and Kidney boundary datasets. The experimental results show that Ada-Tracker achieves superior accuracy and performs more robustly against prior works. Code is available at https://github.com/wrld/Ada-Tracker.
Authors: Runmin Cong, Hang Xiong, Jinpeng Chen, Wei Zhang, Qingming Huang, Yao Zhao
Abstract: Previous Few-Shot Segmentation (FSS) approaches exclusively utilize support features for prototype generation, neglecting the specific requirements of the query. To address this, we present the Query-guided Prototype Evolution Network (QPENet), a new method that integrates query features into the generation process of foreground and background prototypes, thereby yielding customized prototypes attuned to specific queries. The evolution of the foreground prototype is accomplished through a \textit{support-query-support} iterative process involving two new modules: Pseudo-prototype Generation (PPG) and Dual Prototype Evolution (DPE). The PPG module employs support features to create an initial prototype for the preliminary segmentation of the query image, resulting in a pseudo-prototype reflecting the unique needs of the current query. Subsequently, the DPE module performs reverse segmentation on support images using this pseudo-prototype, leading to the generation of evolved prototypes, which can be considered as custom solutions. As for the background prototype, the evolution begins with a global background prototype that represents the generalized features of all training images. We also design a Global Background Cleansing (GBC) module to eliminate potential adverse components mirroring the characteristics of the current foreground class. Experimental results on the PASCAL-$5^i$ and COCO-$20^i$ datasets attest to the substantial enhancements achieved by QPENet over prevailing state-of-the-art techniques, underscoring the validity of our ideas.
Authors: Jiawen Zhu, Guansong Pang
Abstract: This paper explores the problem of Generalist Anomaly Detection (GAD), aiming to train one single detection model that can generalize to detect anomalies in diverse datasets from different application domains without any further training on the target data. Some recent studies have shown that large pre-trained Visual-Language Models (VLMs) like CLIP have strong generalization capabilities on detecting industrial defects from various datasets, but their methods rely heavily on handcrafted text prompts about defects, making them difficult to generalize to anomalies in other applications, e.g., medical image anomalies or semantic anomalies in natural images. In this work, we propose to train a GAD model with few-shot normal images as sample prompts for AD on diverse datasets on the fly. To this end, we introduce a novel approach that learns an in-context residual learning model for GAD, termed InCTRL. It is trained on an auxiliary dataset to discriminate anomalies from normal samples based on a holistic evaluation of the residuals between query images and few-shot normal sample prompts. Regardless of the datasets, per definition of anomaly, larger residuals are expected for anomalies than normal samples, thereby enabling InCTRL to generalize across different domains without further training.
Authors: Jiun-Man Chen, Yu-Hsuan Chao, Yu-Jie Wang, Ming-Der Shieh, Chih-Chung Hsu, Wei-Fen Lin
Abstract: Transformer-based models have gained widespread popularity in both the computer vision (CV) and natural language processing (NLP) fields. However, significant challenges arise during post-training linear quantization, leading to noticeable reductions in inference accuracy. Our study focuses on uncovering the underlying causes of these accuracy drops and proposing a quantization-friendly fine-tuning method, \textbf{QuantTune}. Firstly, our analysis revealed that, on average, 65\% of quantization errors result from the precision loss incurred by the dynamic range amplification effect of outliers across the target Transformer-based models. Secondly, \textbf{QuantTune} adjusts weights based on the deviation of outlier activations and effectively constrains the dynamic ranges of the problematic activations. As a result, it successfully mitigates the negative impact of outliers on the inference accuracy of quantized models. Lastly, \textbf{QuantTune} can be seamlessly integrated into the back-propagation pass in the fine-tuning process without requiring extra complexity in inference software and hardware design. Our approach showcases significant improvements in post-training quantization across a range of Transformer-based models, including ViT, Bert-base, and OPT. QuantTune reduces accuracy drops by 12.09\% at 8-bit quantization and 33.8\% at 7-bit compared to top calibration methods, outperforming state-of-the-art solutions by over 18.84\% across ViT models.
Authors: Hayeon O, Kunsoo Huh
Abstract: In autonomous driving, 3D detection provides more precise information to downstream tasks, including path planning and motion estimation, compared to 2D detection. Therefore, the need for 3D detection research has emerged. However, although single and multi-view images and depth maps obtained from the camera were used, detection accuracy was relatively low compared to other modality-based detectors due to the lack of geometric information. The proposed multi-modal 3D object detection combines semantic features obtained from images and geometric features obtained from point clouds, but there are difficulties in defining unified representation to fuse data existing in different domains and synchronization between them. In this paper, we propose SeSame : point-wise semantic feature as a new presentation to ensure sufficient semantic information of the existing LiDAR-only based 3D detection. Experiments show that our approach outperforms previous state-of-the-art at different levels of difficulty in car and performance improvement on the KITTI object detection benchmark. Our code is available at https://github.com/HAMA-DL-dev/SeSame
Authors: Chenhao Zhang, Yongyang Zhou, Lei Zhang
Abstract: The neural radiance field (NeRF) has emerged as a prominent methodology for synthesizing realistic images of novel views. While neural radiance representations based on voxels or mesh individually offer distinct advantages, excelling in either rendering quality or speed, each has limitations in the other aspect. In response, we propose a pioneering hybrid representation named Vosh, seamlessly combining both voxel and mesh components in hybrid rendering for view synthesis. Vosh is meticulously crafted by optimizing the voxel grid of NeRF, strategically with selected voxels replaced by mesh. Therefore, it excels in fast rendering scenes with simple geometry and textures through its mesh component, while simultaneously enabling high-quality rendering in intricate regions by leveraging voxel component. The flexibility of Vosh is showcased through the ability to adjust hybrid ratios, providing users the ability to control the balance between rendering quality and speed based on flexible usage. Experimental results demonstrates that our method achieves commendable trade-off between rendering quality and speed, and notably has real-time performance on mobile devices.
Authors: Mingyue Zhao, Han Li, Li Fan, Shiyuan Liu, Xiaolan Qiu, S. Kevin Zhou
Abstract: Fully-supervised airway segmentation has accomplished significant triumphs over the years in aiding pre-operative diagnosis and intra-operative navigation. However, full voxel-level annotation constitutes a labor-intensive and time-consuming task, often plagued by issues such as missing branches, branch annotation discontinuity, or erroneous edge delineation. label-efficient solutions for airway extraction are rarely explored yet primarily demanding in medical practice. To this end, we introduce a novel skeleton-level annotation (SkA) tailored to the airway, which simplifies the annotation workflow while enhancing annotation consistency and accuracy, preserving the complete topology. Furthermore, we propose a skeleton-supervised learning framework to achieve accurate airway segmentation. Firstly, a dual-stream buffer inference is introduced to realize initial label propagation from SkA, avoiding the collapse of direct learning from SkA. Then, we construct a geometry-aware dual-path propagation framework (GDP) to further promote complementary propagation learning, composed of hard geometry-aware propagation learning and soft geometry-aware propagation guidance. Experiments reveal that our proposed framework outperforms the competing methods with SKA, which amounts to only 1.96% airways, and achieves comparable performance with the baseline model that is fully supervised with 100% airways, demonstrating its significant potential in achieving label-efficient segmentation for other tubular structures, such as vessels.
Authors: Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas, Giorgos Stamou
Abstract: Counterfactual explanations (CEs) based on concepts are explanations that consider alternative scenarios to understand which high-level semantic features contributed to particular model predictions. In this work, we propose CEs based on the semantic graphs accompanying input data to achieve more descriptive, accurate, and human-aligned explanations. Building upon state-of-the-art (SoTA) conceptual attempts, we adopt a model-agnostic edit-based approach and introduce leveraging GNNs for efficient Graph Edit Distance (GED) computation. With a focus on the visual domain, we represent images as scene graphs and obtain their GNN embeddings to bypass solving the NP-hard graph similarity problem for all input pairs, an integral part of the CE computation process. We apply our method to benchmark and real-world datasets with varying difficulty and availability of semantic annotations. Testing on diverse classifiers, we find that our CEs outperform previous SoTA explanation models based on semantics, including both white and black-box as well as conceptual and pixel-level approaches. Their superiority is proven quantitatively and qualitatively, as validated by human subjects, highlighting the significance of leveraging semantic edges in the presence of intricate relationships. Our model-agnostic graph-based approach is widely applicable and easily extensible, producing actionable explanations across different contexts.
Authors: Woojung Han, Chanyoung Kim, Dayun Ju, Yumin Shim, Seong Jae Hwang
Abstract: Recent advances in text-conditioned image generation diffusion models have begun paving the way for new opportunities in modern medical domain, in particular, generating Chest X-rays (CXRs) from diagnostic reports. Nonetheless, to further drive the diffusion models to generate CXRs that faithfully reflect the complexity and diversity of real data, it has become evident that a nontrivial learning approach is needed. In light of this, we propose CXRL, a framework motivated by the potential of reinforcement learning (RL). Specifically, we integrate a policy gradient RL approach with well-designed multiple distinctive CXR-domain specific reward models. This approach guides the diffusion denoising trajectory, achieving precise CXR posture and pathological details. Here, considering the complex medical image environment, we present "RL with Comparative Feedback" (RLCF) for the reward mechanism, a human-like comparative evaluation that is known to be more effective and reliable in complex scenarios compared to direct evaluation. Our CXRL framework includes jointly optimizing learnable adaptive condition embeddings (ACE) and the image generator, enabling the model to produce more accurate and higher perceptual CXR quality. Our extensive evaluation of the MIMIC-CXR-JPG dataset demonstrates the effectiveness of our RL-based tuning approach. Consequently, our CXRL generates pathologically realistic CXRs, establishing a new standard for generating CXRs with high fidelity to real-world clinical scenarios.
Authors: Tao Huang, Jiaqi Liu, Shan You, Chang Xu
Abstract: Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy. However, existing methods often demand the generation of a disproportionately large number of images compared to the original dataset, while having only marginal improvements in accuracy. This computationally expensive and time-consuming process hampers the practicality of such approaches. In this paper, we propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model. With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation. It aims to create images akin to the challenging or misclassified samples encountered by the current model and incorporates these generated images into the training set to augment model performance. ActGen introduces an attentive image guidance technique, using real images as guides during the denoising process of a diffusion model. The model's attention on class prompt is leveraged to ensure the preservation of similar foreground object while diversifying the background. Furthermore, we introduce a gradient-based generation guidance method, which employs two losses to generate more challenging samples and prevent the generated images from being too similar to previously generated ones. Experimental results on the CIFAR and ImageNet datasets demonstrate that our method achieves better performance with a significantly reduced number of generated images.
Authors: Zijian Chen, Mei Wang, Weihong Deng, Hongzhi Shi, Dongchao Wen, Yingjie Zhang, Xingchen Cui, Jian Zhao
Abstract: 2D face recognition encounters challenges in unconstrained environments due to varying illumination, occlusion, and pose. Recent studies focus on RGB-D face recognition to improve robustness by incorporating depth information. However, collecting sufficient paired RGB-D training data is expensive and time-consuming, hindering wide deployment. In this work, we first construct a diverse depth dataset generated by 3D Morphable Models for depth model pre-training. Then, we propose a domain-independent pre-training framework that utilizes readily available pre-trained RGB and depth models to separately perform face recognition without needing additional paired data for retraining. To seamlessly integrate the two distinct networks and harness the complementary benefits of RGB and depth information for improved accuracy, we propose an innovative Adaptive Confidence Weighting (ACW). This mechanism is designed to learn confidence estimates for each modality to achieve modality fusion at the score level. Our method is simple and lightweight, only requiring ACW training beyond the backbone models. Experiments on multiple public RGB-D face recognition benchmarks demonstrate state-of-the-art performance surpassing previous methods based on depth estimation and feature fusion, validating the efficacy of our approach.
Authors: Yuxuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang
Abstract: Synthetic Aperture Radar (SAR) object detection has gained significant attention recently due to its irreplaceable all-weather imaging capabilities. However, this research field suffers from both limited public datasets (mostly comprising <2K images with only mono-category objects) and inaccessible source code. To tackle these challenges, we establish a new benchmark dataset and an open-source method for large-scale SAR object detection. Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets, providing a large-scale and diverse dataset for research purposes. To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created. With this high-quality dataset, we conducted comprehensive experiments and uncovered a crucial challenge in SAR object detection: the substantial disparities between the pretraining on RGB datasets and finetuning on SAR datasets in terms of both data domain and model structure. To bridge these gaps, we propose a novel Multi-Stage with Filter Augmentation (MSFA) pretraining framework that tackles the problems from the perspective of data input, domain transition, and model migration. The proposed MSFA method significantly enhances the performance of SAR object detection models while demonstrating exceptional generalizability and flexibility across diverse models. This work aims to pave the way for further advancements in SAR object detection. The dataset and code is available at https://github.com/zcablii/SARDet_100K.
Authors: Jinchen Zhu, Mingjian Zhang, Ling Zheng, Shizhuang Weng
Abstract: Recently, the methods based on implicit neural representations have shown excellent capabilities for arbitrary-scale super-resolution (ASSR). Although these methods represent the features of an image by generating latent codes, these latent codes are difficult to adapt for different magnification factors of super-resolution, which seriously affects their performance. Addressing this, we design Multi-Scale Implicit Transformer (MSIT), consisting of an Multi-scale Neural Operator (MSNO) and Multi-Scale Self-Attention (MSSA). Among them, MSNO obtains multi-scale latent codes through feature enhancement, multi-scale characteristics extraction, and multi-scale characteristics merging. MSSA further enhances the multi-scale characteristics of latent codes, resulting in better performance. Furthermore, to improve the performance of network, we propose the Re-Interaction Module (RIM) combined with the cumulative training strategy to improve the diversity of learned information for the network. We have systematically introduced multi-scale characteristics for the first time in ASSR, extensive experiments are performed to validate the effectiveness of MSIT, and our method achieves state-of-the-art performance in arbitrary super-resolution tasks.
Authors: Baran Ozaydin, Tong Zhang, Deblina Bhattacharjee, Sabine S\"usstrunk, Mathieu Salzmann
Abstract: Unsupervised Semantic Segmentation (USS) involves segmenting images without relying on predefined labels, aiming to alleviate the burden of extensive human labeling. Existing methods utilize features generated by self-supervised models and specific priors for clustering. However, their clustering objectives are not involved in the optimization of the features during training. Additionally, due to the lack of clear class definitions in USS, the resulting segments may not align well with the clustering objective. In this paper, we introduce a novel approach called Optimally Matched Hierarchy (OMH) to simultaneously address the above issues. The core of our method lies in imposing structured sparsity on the feature space, which allows the features to encode information with different levels of granularity. The structure of this sparsity stems from our hierarchy (OMH). To achieve this, we learn a soft but sparse hierarchy among parallel clusters through Optimal Transport. Our OMH yields better unsupervised segmentation performance compared to existing USS methods. Our extensive experiments demonstrate the benefits of OMH when utilizing our differentiable paradigm. We will make our code publicly available.
Authors: Ivo P. C. Kersten, Erkut Akdag, Egor Bondarev, Peter H. N. De With
Abstract: Anomalous behavior detection is a challenging research area within computer vision. Progress in this area enables automated detection of dangerous behavior using surveillance camera feeds. A dangerous behavior that is often overlooked in other research is the throwing action in traffic flow, which is one of the unique requirements of our Smart City project to enhance public safety. This paper proposes a solution for throwing action detection in surveillance videos using deep learning. At present, datasets for throwing actions are not publicly available. To address the use-case of our Smart City project, we first generate the novel public 'Throwing Action' dataset, consisting of 271 videos of throwing actions performed by traffic participants, such as pedestrians, bicyclists, and car drivers, and 130 normal videos without throwing actions. Second, we compare the performance of different feature extractors for our anomaly detection method on the UCF-Crime and Throwing-Action datasets. The explored feature extractors are the Convolutional 3D (C3D) network, the Inflated 3D ConvNet (I3D) network, and the Multi-Fiber Network (MFNet). Finally, the performance of the anomaly detection algorithm is improved by applying the Adam optimizer instead of Adadelta, and proposing a mean normal loss function that covers the multitude of normal situations in traffic. Both aspects yield better anomaly detection performance. Besides this, the proposed mean normal loss function lowers the false alarm rate on the combined dataset. The experimental results reach an area under the ROC curve of 86.10 for the Throwing-Action dataset, and 80.13 on the combined dataset, respectively.
Authors: Stefan Denner, David Zimmerer, Dimitrios Bounias, Markus Bujotzek, Shuhan Xiao, Lisa Kausch, Philipp Schader, Tobias Penzkofer, Paul F. J\"ager, Klaus Maier-Hein
Abstract: Content-based image retrieval (CBIR) has the potential to significantly improve diagnostic aid and medical research in radiology. Current CBIR systems face limitations due to their specialization to certain pathologies, limiting their utility. In response, we propose using vision foundation models as powerful and versatile off-the-shelf feature extractors for content-based medical image retrieval. By benchmarking these models on a comprehensive dataset of 1.6 million 2D radiological images spanning four modalities and 161 pathologies, we identify weakly-supervised models as superior, achieving a P@1 of up to 0.594. This performance not only competes with a specialized model but does so without the need for fine-tuning. Our analysis further explores the challenges in retrieving pathological versus anatomical structures, indicating that accurate retrieval of pathological features presents greater difficulty. Despite these challenges, our research underscores the vast potential of foundation models for CBIR in radiology, proposing a shift towards versatile, general-purpose medical image retrieval systems that do not require specific tuning.
Authors: Erkut Akdag, Zeqi Zhu, Egor Bondarev, Peter H. N. De With
Abstract: Classification and localization of driving actions over time is important for advanced driver-assistance systems and naturalistic driving studies. Temporal localization is challenging because it requires robustness, reliability, and accuracy. In this study, we aim to improve the temporal localization and classification accuracy performance by adapting video action recognition and 2D human-pose estimation networks to one model. Therefore, we design a transformer-based fusion architecture to effectively combine 2D-pose features and spatio-temporal features. The model uses 2D-pose features as the positional embedding of the transformer architecture and spatio-temporal features as the main input to the encoder of the transformer. The proposed solution is generic and independent of the camera numbers and positions, giving frame-based class probabilities as output. Finally, the post-processing step combines information from different camera views to obtain final predictions and eliminate false positives. The model performs well on the A2 test set of the 2023 NVIDIA AI City Challenge for naturalistic driving action recognition, achieving the overlap score of the organizer-defined distracted driver behaviour metric of 0.5079.
Authors: Jongwook Choi, Taehoon Kim, Yonghyun Jeong, Seungryul Baek, Jongwon Choi
Abstract: This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos. We discovered that the generated facial videos suffer from the temporal distinctiveness in the temporal changes of style latent vectors, which are inevitable during the generation of temporally stable videos with various facial expressions and geometric transformations. Our framework utilizes the StyleGRU module, trained by contrastive learning, to represent the dynamic properties of style latent vectors. Additionally, we introduce a style attention module that integrates StyleGRU-generated features with content-based features, enabling the detection of visual and temporal artifacts. We demonstrate our approach across various benchmark scenarios in deepfake detection, showing its superiority in cross-dataset and cross-manipulation scenarios. Through further analysis, we also validate the importance of using temporal changes of style latent vectors to improve the generality of deepfake video detection.
Authors: 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 VPR: 1) For the methods based on both camera and 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 (e.g., 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, nemely BEV2PR, which can generate a composite descriptor with both visual cues and spatial awareness solely based on a single camera. For the visual cues, any popular aggregation module for RGB global features can be integrated into our framework. The key points lie in: 1) We use BEV segmentation features as an explicit source of structural knowledge in constructing global features. 2) The lower layers of the pre-trained backbone from BEV map 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 features and structural features can jointly enhance VPR performance. Our BEV2PR framework enables consistent performance improvements over several popular camera-based VPR aggregation modules when integrating them. 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.
Authors: Alexander H. Berger, Laurin Lux, Suprosanna Shit, Ivan Ezhov, Georgios Kaissis, Martin J. Menten, Daniel Rueckert, Johannes C. Paetzold
Abstract: Direct image-to-graph transformation is a challenging task that solves object detection and relationship prediction in a single model. Due to the complexity of this task, large training datasets are rare in many domains, which makes the training of large networks challenging. This data sparsity necessitates the establishment of pre-training strategies akin to the state-of-the-art in computer vision. In this work, we introduce a set of methods enabling cross-domain and cross-dimension transfer learning for image-to-graph transformers. We propose (1) a regularized edge sampling loss for sampling the optimal number of object relationships (edges) across domains, (2) a domain adaptation framework for image-to-graph transformers that aligns features from different domains, and (3) a simple projection function that allows us to pretrain 3D transformers on 2D input data. We demonstrate our method's utility in cross-domain and cross-dimension experiments, where we pretrain our models on 2D satellite images before applying them to vastly different target domains in 2D and 3D. Our method consistently outperforms a series of baselines on challenging benchmarks, such as retinal or whole-brain vessel graph extraction.
Authors: Fengda Zhang, Qianpei He, Kun Kuang, Jiashuo Liu, Long Chen, Chao Wu, Jun Xiao, Hanwang Zhang
Abstract: Facial Attribute Classification (FAC) holds substantial promise in widespread applications. However, FAC models trained by traditional methodologies can be unfair by exhibiting accuracy inconsistencies across varied data subpopulations. This unfairness is largely attributed to bias in data, where some spurious attributes (e.g., Male) statistically correlate with the target attribute (e.g., Smiling). Most of existing fairness-aware methods rely on the labels of spurious attributes, which may be unavailable in practice. This work proposes a novel, generation-based two-stage framework to train a fair FAC model on biased data without additional annotation. Initially, we identify the potential spurious attributes based on generative models. Notably, it enhances interpretability by explicitly showing the spurious attributes in image space. Following this, for each image, we first edit the spurious attributes with a random degree sampled from a uniform distribution, while keeping target attribute unchanged. Then we train a fair FAC model by fostering model invariance to these augmentation. Extensive experiments on three common datasets demonstrate the effectiveness of our method in promoting fairness in FAC without compromising accuracy. Codes are in https://github.com/heqianpei/DiGA.
Authors: Tunc Alkanat, Erkut Akdag, Egor Bondarev, Peter H. N. De With
Abstract: Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate localization. In this work, we focus on improving the overall performance by efficiently utilizing video action recognition networks and adapting these to the problem of action localization. To this end, we first develop a density-guided label smoothing technique based on label probability distributions to facilitate better learning from boundary video-segments that typically include multiple labels. Second, we design a post-processing step to efficiently fuse information from video-segments and multiple camera views into scene-level predictions, which facilitates elimination of false positives. Our methodology yields a competitive performance on the A2 test set of the naturalistic driving action recognition track of the 2022 NVIDIA AI City Challenge with an F1 score of 0.271.
Authors: Bianca-Cerasela-Zelia Blaga, Sergiu Nedevschi
Abstract: Humans use UAVs to monitor changes in forest environments since they are lightweight and provide a large variety of surveillance data. However, their information does not present enough details for understanding the scene which is needed to assess the degree of deforestation. Deep learning algorithms must be trained on large amounts of data to output accurate interpretations, but ground truth recordings of annotated forest imagery are not available. To solve this problem, we introduce a new large aerial dataset for forest inspection which contains both real-world and virtual recordings of natural environments, with densely annotated semantic segmentation labels and depth maps, taken in different illumination conditions, at various altitudes and recording angles. We test the performance of two multi-scale neural networks for solving the semantic segmentation task (HRNet and PointFlow network), studying the impact of the various acquisition conditions and the capabilities of transfer learning from virtual to real data. Our results showcase that the best results are obtained when the training is done on a dataset containing a large variety of scenarios, rather than separating the data into specific categories. We also develop a framework to assess the deforestation degree of an area.
Authors: Henrique Jesus, Hugo Proen\c{c}a
Abstract: Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands in terms of learning data; 2) the difficulties in generalising between different domains; and 3) the lack of interpretability/explainability, with biometrics being of particular interest, as it is important to provide evidence able to be used for forensics/legal purposes (e.g., in courts). To the best of our knowledge, this paper describes the first recognition framework/strategy that aims at addressing the three weaknesses simultaneously. At first, it relies exclusively in synthetic samples for learning purposes. Instead of requiring a large amount and variety of samples for each subject, the idea is to exclusively enroll a 3D point cloud per identity. Then, using generative strategies, we synthesize a very large (potentially infinite) number of samples, containing all the desired covariates (poses, clothing, distances, perspectives, lighting, occlusions,...). Upon the synthesizing method used, it is possible to adapt precisely to different kind of domains, which accounts for generalization purposes. Such data are then used to learn a model that performs local registration between image pairs, establishing positive correspondences between body parts that are the key, not only to recognition (according to cardinality and distribution), but also to provide an interpretable description of the response (e.g.: "both samples are from the same person, as they have similar facial shape, hair color and legs thickness").
Authors: Batuhan Cengiz, Mert Gulsen, Yusuf H. Sahin, Gozde Unal
Abstract: Point clouds and meshes are widely used 3D data structures for many computer vision applications. While the meshes represent the surfaces of an object, point cloud represents sampled points from the surface which is also the output of modern sensors such as LiDAR and RGB-D cameras. Due to the wide application area of point clouds and the recent advancements in deep neural networks, studies focusing on robust classification of the 3D point cloud data emerged. To evaluate the robustness of deep classifier networks, a common method is to use adversarial attacks where the gradient direction is followed to change the input slightly. The previous studies on adversarial attacks are generally evaluated on point clouds of daily objects. However, considering 3D faces, these adversarial attacks tend to affect the person's facial structure more than the desired amount and cause malformation. Specifically for facial expressions, even a small adversarial attack can have a significant effect on the face structure. In this paper, we suggest an adversarial attack called $\epsilon$-Mesh Attack, which operates on point cloud data via limiting perturbations to be on the mesh surface. We also parameterize our attack by $\epsilon$ to scale the perturbation mesh. Our surface-based attack has tighter perturbation bounds compared to $L_2$ and $L_\infty$ norm bounded attacks that operate on unit-ball. Even though our method has additional constraints, our experiments on CoMA, Bosphorus and FaceWarehouse datasets show that $\epsilon$-Mesh Attack (Perpendicular) successfully confuses trained DGCNN and PointNet models $99.72\%$ and $97.06\%$ of the time, with indistinguishable facial deformations. The code is available at https://github.com/batuceng/e-mesh-attack.
Authors: Xinyuan Gao, Songlin Dong, Yuhang He, Xing Wei, Yihong Gong
Abstract: In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training. In the scenario of more strict privacy protection, storing the old images becomes infeasible, which leads to a more severe plasticity-stability dilemma and classifier bias. To meet the above challenges, we propose a new architecture, named continual expansion and absorption transformer~(CEAT). The model can learn the novel knowledge by extending the expanded-fusion layers in parallel with the frozen previous parameters. After the task ends, we losslessly absorb the extended parameters into the backbone to ensure that the number of parameters remains constant. To improve the learning ability of the model, we designed a novel prototype contrastive loss to reduce the overlap between old and new classes in the feature space. Besides, to address the classifier bias towards the new classes, we propose a novel approach to generate the pseudo-features to correct the classifier. We experiment with our methods on three standard Non-Exemplar Class-Incremental Learning~(NECIL) benchmarks. Extensive experiments demonstrate that our model gets a significant improvement compared with the previous works and achieves 5.38%, 5.20%, and 4.92% improvement on CIFAR-100, TinyImageNet, and ImageNet-Subset.
Authors: Hanxiao Chen
Abstract: Most computer vision applications aim to identify pixels in a scene and use them for diverse purposes. One intriguing application is car damage detection for insurance carriers which tends to detect all car damages by comparing both pre-trip and post-trip images, even requiring two components: (i) car damage detection; (ii) image alignment. Firstly, we implemented a Mask R-CNN model to detect car damages on custom images. Whereas for the image alignment section, we especially propose a novel self-supervised Patch-to-Patch SimCLR inspired alignment approach to find perspective transformations between custom pre/post car rental images except for traditional computer vision methods.
Authors: Shunsuke Yasuki, Masato Taki
Abstract: Recently, convolutional neural networks (CNNs) with large size kernels have attracted much attention in the computer vision field, following the success of the Vision Transformers. Large kernel CNNs have been reported to perform well in downstream vision tasks as well as in classification performance. The reason for the high-performance of large kernel CNNs in downstream tasks has been attributed to the large effective receptive field (ERF) produced by large size kernels, but this view has not been fully tested. We therefore revisit the performance of large kernel CNNs in downstream task, focusing on the weakly supervised object localization (WSOL) task. WSOL, a difficult downstream task that is not fully supervised, provides a new angle to explore the capabilities of the large kernel CNNs. Our study compares the modern large kernel CNNs ConvNeXt, RepLKNet, and SLaK to test the validity of the naive expectation that ERF size is important for improving downstream task performance. Our analysis of the factors contributing to high performance provides a different perspective, in which the main factor is feature map improvement. Furthermore, we find that modern CNNs are robust to the CAM problems of local regions of objects being activated, which has long been discussed in WSOL. CAM is the most classic WSOL method, but because of the above-mentioned problems, it is often used as a baseline method for comparison. However, experiments on the CUB-200-2011 dataset show that simply combining a large kernel CNN, CAM, and simple data augmentation methods can achieve performance (90.99% MaxBoxAcc) comparable to the latest WSOL method, which is CNN-based and requires special training or complex post-processing. The code is available at https://github.com/snskysk/CAM-Back-Again.
Authors: Qilang Ye, Zitong Yu, Xin Liu
Abstract: Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer. Although mining deeper layers of audio-visual information to interact with questions facilitates the multimodal fusion process, the redundancy of audio-visual parameters tends to reduce the generalization of the inference engine to multiple question-answer pairs in a single video. Indeed, the natural heterogeneous relationship between audiovisuals and text makes the perfect fusion challenging, to prevent high-level audio-visual semantics from weakening the network's adaptability to diverse question types, we propose a framework for performing mutual correlation distillation (MCD) to aid question inference. MCD is divided into three main steps: 1) firstly, the residual structure is utilized to enhance the audio-visual soft associations based on self-attention, then key local audio-visual features relevant to the question context are captured hierarchically by shared aggregators and coupled in the form of clues with specific question vectors. 2) Secondly, knowledge distillation is enforced to align audio-visual-text pairs in a shared latent space to narrow the cross-modal semantic gap. 3) And finally, the audio-visual dependencies are decoupled by discarding the decision-level integrations. We evaluate the proposed method on two publicly available datasets containing multiple question-and-answer pairs, i.e., Music-AVQA and AVQA. Experiments show that our method outperforms other state-of-the-art methods, and one interesting finding behind is that removing deep audio-visual features during inference can effectively mitigate overfitting. The source code is released at http://github.com/rikeilong/MCD-forAVQA.
Authors: Jintao Huang, Yiu-Ming Cheung
Abstract: Partial Label Learning (PLL) grapples with learning from ambiguously labelled data, and it has been successfully applied in fields such as image recognition. Nevertheless, traditional PLL methods rely on the closed-world assumption, which can be limiting in open-world scenarios and negatively impact model performance and generalization. To tackle these challenges, our study introduces a novel method called PLL-OOD, which is the first to incorporate Out-of-Distribution (OOD) detection into the PLL framework. PLL-OOD significantly enhances model adaptability and accuracy by merging self-supervised learning with partial label loss and pioneering the Partial-Energy (PE) score for OOD detection. This approach improves data feature representation and effectively disambiguates candidate labels, using a dynamic label confidence matrix to refine predictions. The PE score, adjusted by label confidence, precisely identifies OOD instances, optimizing model training towards in-distribution data. This innovative method markedly boosts PLL model robustness and performance in open-world settings. To validate our approach, we conducted a comprehensive comparative experiment combining the existing state-of-the-art PLL model with multiple OOD scores on the CIFAR-10 and CIFAR-100 datasets with various OOD datasets. The results demonstrate that the proposed PLL-OOD framework is highly effective and effectiveness outperforms existing models, showcasing its superiority and effectiveness.
Authors: Charlie Budd, Tom Vercauteren
Abstract: Relative monocular depth, inferring depth up to shift and scale from a single image, is an active research topic. Recent deep learning models, trained on large and varied meta-datasets, now provide excellent performance in the domain of natural images. However, few datasets exist which provide ground truth depth for endoscopic images, making training such models from scratch unfeasible. This work investigates the transfer of these models into the surgical domain, and presents an effective and simple way to improve on standard supervision through the use of temporal consistency self-supervision. We show temporal consistency significantly improves supervised training alone when transferring to the low-data regime of endoscopy, and outperforms the prevalent self-supervision technique for this task. In addition we show our method drastically outperforms the state-of-the-art method from within the domain of endoscopy. We also release our code, model and ensembled meta-dataset, Meta-MED, establishing a strong benchmark for future work.
Authors: Mert Gulsen, Batuhan Cengiz, Yusuf H. Sahin, Gozde Unal
Abstract: Point clouds are extensively employed in a variety of real-world applications such as robotics, autonomous driving and augmented reality. Despite the recent success of point cloud neural networks, especially for safety-critical tasks, it is essential to also ensure the robustness of the model. A typical way to assess a model's robustness is through adversarial attacks, where test-time examples are generated based on gradients to deceive the model. While many different defense mechanisms are studied in 2D, studies on 3D point clouds have been relatively limited in the academic field. Inspired from PointDP, which denoises the network inputs by diffusion, we propose Point Cloud Layerwise Diffusion (PCLD), a layerwise diffusion based 3D point cloud defense strategy. Unlike PointDP, we propagated the diffusion denoising after each layer to incrementally enhance the results. We apply our defense method to different types of commonly used point cloud models and adversarial attacks to evaluate its robustness. Our experiments demonstrate that the proposed defense method achieved results that are comparable to or surpass those of existing methodologies, establishing robustness through a novel technique. Code is available at https://github.com/batuceng/diffusion-layer-robustness-pc.
URLs: https://github.com/batuceng/diffusion-layer-robustness-pc.
Authors: Jinlu Zhang, Yiyi Zhou, Qiancheng Zheng, Xiaoxiong Du, Gen Luo, Jun Peng, Xiaoshuai Sun, Rongrong Ji
Abstract: Text-to-3D-aware face (T3D Face) generation and manipulation is an emerging research hot spot in machine learning, which still suffers from low efficiency and poor quality. In this paper, we propose an End-to-End Efficient and Effective network for fast and accurate T3D face generation and manipulation, termed $E^3$-FaceNet. Different from existing complex generation paradigms, $E^3$-FaceNet resorts to a direct mapping from text instructions to 3D-aware visual space. We introduce a novel Style Code Enhancer to enhance cross-modal semantic alignment, alongside an innovative Geometric Regularization objective to maintain consistency across multi-view generations. Extensive experiments on three benchmark datasets demonstrate that $E^3$-FaceNet can not only achieve picture-like 3D face generation and manipulation, but also improve inference speed by orders of magnitudes. For instance, compared with Latent3D, $E^3$-FaceNet speeds up the five-view generations by almost 470 times, while still exceeding in generation quality. Our code are released at https://github.com/Aria-Zhangjl/E3-FaceNet.
Authors: Zijian Zhou, Miaojing Shi, Meng Wei, Oluwatosin Alabi, Zijie Yue, Tom Vercauteren
Abstract: Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. Current RRG approaches are still unsatisfactory against clinical standards. This paper introduces a novel RRG method, \textbf{LM-RRG}, that integrates large models (LMs) with clinical quality reinforcement learning to generate accurate and comprehensive chest X-ray radiology reports. Our method first designs a large language model driven feature extractor to analyze and interpret different regions of the chest X-ray image, emphasizing specific regions with medical significance. Next, based on the large model's decoder, we develop a multimodal report generator that leverages multimodal prompts from visual features and textual instruction to produce the radiology report in an auto-regressive way. Finally, to better reflect the clinical significant and insignificant errors that radiologists would normally assign in the report, we introduce a novel clinical quality reinforcement learning strategy. It utilizes the radiology report clinical quality (RadCliQ) metric as a reward function in the learning process. Extensive experiments on the MIMIC-CXR and IU-Xray datasets demonstrate the superiority of our method over the state of the art.
Authors: Adarsh N L, Arun P V, Aravindh N L
Abstract: Research on generative models to produce human-aligned / human-preferred outputs has seen significant recent contributions. Between text and image-generative models, we narrowed our focus to text-based generative models, particularly to produce captions for images that align with human preferences. In this research, we explored a potential method to amplify the performance of the Deep Neural Network Model to generate captions that are preferred by humans. This was achieved by integrating Supervised Learning and Reinforcement Learning with Human Feedback (RLHF) using the Flickr8k dataset. Also, a novel loss function that is capable of optimizing the model based on human feedback is introduced. In this paper, we provide a concise sketch of our approach and results, hoping to contribute to the ongoing advances in the field of human-aligned generative AI models.
Authors: Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu
Abstract: Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency. Our code is available at https://github.com/heheyas/V3D
Authors: Haowei Zhu, Ling Yang, Jun-Hai Yong, Wentao Zhang, Bin Wang
Abstract: The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion technologies aim to automatically augment datasets, unlocking the full potential of deep models. Current data expansion methods encompass image transformation-based and synthesis-based methods. The transformation-based methods introduce only local variations, resulting in poor diversity. While image synthesis-based methods can create entirely new content, significantly enhancing informativeness. However, existing synthesis methods carry the risk of distribution deviations, potentially degrading model performance with out-of-distribution samples. In this paper, we propose DistDiff, an effective data expansion framework based on the distribution-aware diffusion model. DistDiff constructs hierarchical prototypes to approximate the real data distribution, optimizing latent data points within diffusion models with hierarchical energy guidance. We demonstrate its ability to generate distribution-consistent samples, achieving substantial improvements in data expansion tasks. Specifically, without additional training, DistDiff achieves a 30.7% improvement in accuracy across six image datasets compared to the model trained on original datasets and a 9.8% improvement compared to the state-of-the-art diffusion-based method. Our code is available at https://github.com/haoweiz23/DistDiff
Authors: Gabriele Berton, Alex Stoken, Barbara Caputo, Carlo Masone
Abstract: Astronaut photography, spanning six decades of human spaceflight, presents a unique Earth observations dataset with immense value for both scientific research and disaster response. Despite its significance, accurately localizing the geographical extent of these images, crucial for effective utilization, poses substantial challenges. Current manual localization efforts are time-consuming, motivating the need for automated solutions. We propose a novel approach - leveraging image retrieval - to address this challenge efficiently. We introduce innovative training techniques, including Year-Wise Data Augmentation and a Neutral-Aware Multi-Similarity Loss, which contribute to the development of a high-performance model, EarthLoc. We develop six evaluation datasets and perform a comprehensive benchmark comparing EarthLoc to existing methods, showcasing its superior efficiency and accuracy. Our approach marks a significant advancement in automating the localization of astronaut photography, which will help bridge a critical gap in Earth observations data. Code and datasets are available at https://github.com/gmberton/EarthLoc
Authors: Theodore Barfoot, Luis Garcia-Peraza-Herrera, Ben Glocker, Tom Vercauteren
Abstract: Deep neural networks for medical image segmentation often produce overconfident results misaligned with empirical observations. Such miscalibration, challenges their clinical translation. We propose to use marginal L1 average calibration error (mL1-ACE) as a novel auxiliary loss function to improve pixel-wise calibration without compromising segmentation quality. We show that this loss, despite using hard binning, is directly differentiable, bypassing the need for approximate but differentiable surrogate or soft binning approaches. Our work also introduces the concept of dataset reliability histograms which generalises standard reliability diagrams for refined visual assessment of calibration in semantic segmentation aggregated at the dataset level. Using mL1-ACE, we reduce average and maximum calibration error by 45% and 55% respectively, maintaining a Dice score of 87% on the BraTS 2021 dataset. We share our code here: https://github.com/cai4cai/ACE-DLIRIS
Authors: Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, Baobao Chang
Abstract: In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat and Video-LLaVA. We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs, suggesting a need for a sparser approach compared to textual data handling. To this end, we introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency by learning adaptive attention patterns in early layers and pruning visual tokens in subsequent ones. Our evaluations demonstrate FastV's ability to dramatically reduce computational costs (e.g., a 45 reduction in FLOPs for LLaVA-1.5-13B) without sacrificing performance in a wide range of image and video understanding tasks. The computational efficiency and performance trade-off of FastV are highly customizable and pareto-efficient. It can compress the FLOPs of a 13B-parameter model to achieve a lower budget than that of a 7B-parameter model, while still maintaining superior performance. We believe FastV has practical values for deployment of LVLMs in edge devices and commercial models. Code is released at https://github.com/pkunlp-icler/FastV.
Authors: Pengchong Qiao, Lei Shang, Chang Liu, Baigui Sun, Xiangyang Ji, Jie Chen
Abstract: Subject-driven generation has garnered significant interest recently due to its ability to personalize text-to-image generation. Typical works focus on learning the new subject's private attributes. However, an important fact has not been taken seriously that a subject is not an isolated new concept but should be a specialization of a certain category in the pre-trained model. This results in the subject failing to comprehensively inherit the attributes in its category, causing poor attribute-related generations. In this paper, motivated by object-oriented programming, we model the subject as a derived class whose base class is its semantic category. This modeling enables the subject to inherit public attributes from its category while learning its private attributes from the user-provided example. Specifically, we propose a plug-and-play method, Subject-Derived regularization (SuDe). It constructs the base-derived class modeling by constraining the subject-driven generated images to semantically belong to the subject's category. Extensive experiments under three baselines and two backbones on various subjects show that our SuDe enables imaginative attribute-related generations while maintaining subject fidelity. Codes will be open sourced soon at FaceChain (https://github.com/modelscope/facechain).
Authors: Bram Vanherle, Nick Michiels, Frank Van Reeth
Abstract: Data augmentations are useful in closing the sim-to-real domain gap when training on synthetic data. This is because they widen the training data distribution, thus encouraging the model to generalize better to other domains. Many image augmentation techniques exist, parametrized by different settings, such as strength and probability. This leads to a large space of different possible augmentation policies. Some policies work better than others for overcoming the sim-to-real gap for specific datasets, and it is unclear why. This paper presents two different interpretable metrics that can be combined to predict how well a certain augmentation policy will work for a specific sim-to-real setting, focusing on object detection. We validate our metrics by training many models with different augmentation policies and showing a strong correlation with performance on real data. Additionally, we introduce GeneticAugment, a genetic programming method that can leverage these metrics to automatically design an augmentation policy for a specific dataset without needing to train a model.
Authors: Xiaogang Xu, Shu Kong, Tao Hu, Zhe Liu, Hujun Bao
Abstract: Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions. Yet, their potential for low-level tasks such as image restoration remains relatively unexplored. In this paper, we explore such models to enhance image restoration. As off-the-shelf features (OSF) from pre-trained models do not directly serve image restoration, we propose to learn an additional lightweight module called Pre-Train-Guided Refinement Module (PTG-RM) to refine restoration results of a target restoration network with OSF. PTG-RM consists of two components, Pre-Train-Guided Spatial-Varying Enhancement (PTG-SVE), and Pre-Train-Guided Channel-Spatial Attention (PTG-CSA). PTG-SVE enables optimal short- and long-range neural operations, while PTG-CSA enhances spatial-channel attention for restoration-related learning. Extensive experiments demonstrate that PTG-RM, with its compact size ($<$1M parameters), effectively enhances restoration performance of various models across different tasks, including low-light enhancement, deraining, deblurring, and denoising.
Authors: Shu Yang, Yihui Wang, Hao Chen
Abstract: Multiple Instance Learning (MIL) has emerged as a dominant paradigm to extract discriminative feature representations within Whole Slide Images (WSIs) in computational pathology. Despite driving notable progress, existing MIL approaches suffer from limitations in facilitating comprehensive and efficient interactions among instances, as well as challenges related to time-consuming computations and overfitting. In this paper, we incorporate the Selective Scan Space State Sequential Model (Mamba) in Multiple Instance Learning (MIL) for long sequence modeling with linear complexity, termed as MambaMIL. By inheriting the capability of vanilla Mamba, MambaMIL demonstrates the ability to comprehensively understand and perceive long sequences of instances. Furthermore, we propose the Sequence Reordering Mamba (SR-Mamba) aware of the order and distribution of instances, which exploits the inherent valuable information embedded within the long sequences. With the SR-Mamba as the core component, MambaMIL can effectively capture more discriminative features and mitigate the challenges associated with overfitting and high computational overhead. Extensive experiments on two public challenging tasks across nine diverse datasets demonstrate that our proposed framework performs favorably against state-of-the-art MIL methods. The code is released at https://github.com/isyangshu/MambaMIL.
Authors: Chuangchuang Tan, Ping Liu, RenShuai Tao, Huan Liu, Yao Zhao, Baoyuan Wu, Yunchao Wei
Abstract: Recently, the proliferation of increasingly realistic synthetic images generated by various generative adversarial networks has increased the risk of misuse. Consequently, there is a pressing need to develop a generalizable detector for accurately recognizing fake images. The conventional methods rely on generating diverse training sources or large pretrained models. In this work, we show that, on the contrary, the small and training-free filter is sufficient to capture more general artifact representations. Due to its unbias towards both the training and test sources, we define it as Data-Independent Operator (DIO) to achieve appealing improvements on unseen sources. In our framework, handcrafted filters and the randomly-initialized convolutional layer can be used as the training-free artifact representations extractor with excellent results. With the data-independent operator of a popular classifier, such as Resnet50, one could already reach a new state-of-the-art without bells and whistles. We evaluate the effectiveness of the DIO on 33 generation models, even DALLE and Midjourney. Our detector achieves a remarkable improvement of $13.3\%$, establishing a new state-of-the-art performance. The DIO and its extension can serve as strong baselines for future methods. The code is available at \url{https://github.com/chuangchuangtan/Data-Independent-Operator}.
URLs: https://github.com/chuangchuangtan/Data-Independent-Operator
Authors: Souhaib Attaiki, Maks Ovsjanikov
Abstract: We present Shape Non-rigid Kinematics (SNK), a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data. SNK operates on a single pair of shapes, and employs a reconstruction-based strategy using an encoder-decoder architecture, which deforms the source shape to closely match the target shape. During the process, an unsupervised functional map is predicted and converted into a point-to-point map, serving as a supervisory mechanism for the reconstruction. To aid in training, we have designed a new decoder architecture that generates smooth, realistic deformations. SNK demonstrates competitive results on traditional benchmarks, simplifying the shape-matching process without compromising accuracy. Our code can be found online: https://github.com/pvnieo/SNK
Authors: Yufei Xie
Abstract: Human action recognition in videos is a critical task with significant implications for numerous applications, including surveillance, sports analytics, and healthcare. The challenge lies in creating models that are both precise in their recognition capabilities and efficient enough for practical use. This study conducts an in-depth analysis of various deep learning models to address this challenge. Utilizing a subset of the UCF101 Videos dataset, we focus on Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Two-Stream ConvNets. The research reveals that while CNNs effectively capture spatial features and RNNs encode temporal sequences, Two-Stream ConvNets exhibit superior performance by integrating spatial and temporal dimensions. These insights are distilled from the evaluation metrics of accuracy, precision, recall, and F1-score. The results of this study underscore the potential of composite models in achieving robust human action recognition and suggest avenues for future research in optimizing these models for real-world deployment.
Authors: Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Abstract: Contrastive instance discrimination outperforms supervised learning in downstream tasks like image classification and object detection. However, this approach heavily relies on data augmentation during representation learning, which may result in inferior results if not properly implemented. Random cropping followed by resizing is a common form of data augmentation used in contrastive learning, but it can lead to degraded representation learning if the two random crops contain distinct semantic content. To address this issue, this paper introduces LeOCLR (Leveraging Original Images for Contrastive Learning of Visual Representations), a framework that employs a new instance discrimination approach and an adapted loss function that ensures the shared region between positive pairs is semantically correct. The experimental results show that our approach consistently improves representation learning across different datasets compared to baseline models. For example, our approach outperforms MoCo-v2 by 5.1% on ImageNet-1K in linear evaluation and several other methods on transfer learning tasks.
Authors: Shuaikang Shang, Xuejing Kang, Anlong Ming
Abstract: High Dynamic Range (HDR) imaging aims to generate an artifact-free HDR image with realistic details by fusing multi-exposure Low Dynamic Range (LDR) images. Caused by large motion and severe under-/over-exposure among input LDR images, HDR imaging suffers from ghosting artifacts and fusion distortions. To address these critical issues, we propose an HDR Transformer Deformation Convolution (HDRTransDC) network to generate high-quality HDR images, which consists of the Transformer Deformable Convolution Alignment Module (TDCAM) and the Dynamic Weight Fusion Block (DWFB). To solve the ghosting artifacts, the proposed TDCAM extracts long-distance content similar to the reference feature in the entire non-reference features, which can accurately remove misalignment and fill the content occluded by moving objects. For the purpose of eliminating fusion distortions, we propose DWFB to spatially adaptively select useful information across frames to effectively fuse multi-exposed features. Extensive experiments show that our method quantitatively and qualitatively achieves state-of-the-art performance.
Authors: Wenting Chen, Pengyu Wang, Hui Ren, Lichao Sun, Quanzheng Li, Yixuan Yuan, Xiang Li
Abstract: Data scarcity and privacy concerns limit the availability of high-quality medical images for public use, which can be mitigated through medical image synthesis. However, current medical image synthesis methods often struggle to accurately capture the complexity of detailed anatomical structures and pathological conditions. To address these challenges, we propose a novel medical image synthesis model that leverages fine-grained image-text alignment and anatomy-pathology prompts to generate highly detailed and accurate synthetic medical images. Our method integrates advanced natural language processing techniques with image generative modeling, enabling precise alignment between descriptive text prompts and the synthesized images' anatomical and pathological details. The proposed approach consists of two key components: an anatomy-pathology prompting module and a fine-grained alignment-based synthesis module. The anatomy-pathology prompting module automatically generates descriptive prompts for high-quality medical images. To further synthesize high-quality medical images from the generated prompts, the fine-grained alignment-based synthesis module pre-defines a visual codebook for the radiology dataset and performs fine-grained alignment between the codebook and generated prompts to obtain key patches as visual clues, facilitating accurate image synthesis. We validate the superiority of our method through experiments on public chest X-ray datasets and demonstrate that our synthetic images preserve accurate semantic information, making them valuable for various medical applications.
Authors: Christian Wachinger, Dennis Hedderich, Fabian Bongratz
Abstract: Magnetic resonance imaging (MRI) is critical for diagnosing neurodegenerative diseases, yet accurately assessing mild cortical atrophy remains a challenge due to its subtlety. Automated cortex reconstruction, paired with healthy reference ranges, aids in pinpointing pathological atrophy, yet their generalization is limited by biases from image acquisition and processing. We introduce the concept of stochastic cortical self-reconstruction (SCSR) that creates a subject-specific healthy reference by taking MRI-derived thicknesses as input and, therefore, implicitly accounting for potential confounders. SCSR randomly corrupts parts of the cortex and self-reconstructs them from the remaining information. Trained exclusively on healthy individuals, repeated self-reconstruction generates a stochastic reference cortex for assessing deviations from the norm. We present three implementations of this concept: XGBoost applied on parcels, and two autoencoders on vertex level -- one based on a multilayer perceptron and the other using a spherical U-Net. These models were trained on healthy subjects from the UK Biobank and subsequently evaluated across four public Alzheimer's datasets. Finally, we deploy the model on clinical in-house data, where deviation maps' high spatial resolution aids in discriminating between four types of dementia.
Authors: Guosheng Zhao, Xiaofeng Wang, Zheng Zhu, Xinze Chen, Guan Huang, Xiaoyi Bao, Xingang Wang
Abstract: World models have demonstrated superiority in autonomous driving, particularly in the generation of multi-view driving videos. However, significant challenges still exist in generating customized driving videos. In this paper, we propose DriveDreamer-2, which builds upon the framework of DriveDreamer and incorporates a Large Language Model (LLM) to generate user-defined driving videos. Specifically, an LLM interface is initially incorporated to convert a user's query into agent trajectories. Subsequently, a HDMap, adhering to traffic regulations, is generated based on the trajectories. Ultimately, we propose the Unified Multi-View Model to enhance temporal and spatial coherence in the generated driving videos. DriveDreamer-2 is the first world model to generate customized driving videos, it can generate uncommon driving videos (e.g., vehicles abruptly cut in) in a user-friendly manner. Besides, experimental results demonstrate that the generated videos enhance the training of driving perception methods (e.g., 3D detection and tracking). Furthermore, video generation quality of DriveDreamer-2 surpasses other state-of-the-art methods, showcasing FID and FVD scores of 11.2 and 55.7, representing relative improvements of 30% and 50%.
Authors: Chao Zhang, Mohan Li, Ignas Budvytis, Stephan Liwicki
Abstract: Multimodal learning has advanced the performance for many vision-language tasks. However, most existing works in embodied dialog research focus on navigation and leave the localization task understudied. The few existing dialog-based localization approaches assume the availability of entire dialog prior to localizaiton, which is impractical for deployed dialog-based localization. In this paper, we propose DiaLoc, a new dialog-based localization framework which aligns with a real human operator behavior. Specifically, we produce an iterative refinement of location predictions which can visualize current pose believes after each dialog turn. DiaLoc effectively utilizes the multimodal data for multi-shot localization, where a fusion encoder fuses vision and dialog information iteratively. We achieve state-of-the-art results on embodied dialog-based localization task, in single-shot (+7.08% in Acc5@valUnseen) and multi- shot settings (+10.85% in Acc5@valUnseen). DiaLoc narrows the gap between simulation and real-world applications, opening doors for future research on collaborative localization and navigation.
Authors: Zhengyi Luo, Jinkun Cao, Rawal Khirodkar, Alexander Winkler, Kris Kitani, Weipeng Xu
Abstract: We present SimXR, a method for controlling a simulated avatar from information (headset pose and cameras) obtained from AR / VR headsets. Due to the challenging viewpoint of head-mounted cameras, the human body is often clipped out of view, making traditional image-based egocentric pose estimation challenging. On the other hand, headset poses provide valuable information about overall body motion, but lack fine-grained details about the hands and feet. To synergize headset poses with cameras, we control a humanoid to track headset movement while analyzing input images to decide body movement. When body parts are seen, the movements of hands and feet will be guided by the images; when unseen, the laws of physics guide the controller to generate plausible motion. We design an end-to-end method that does not rely on any intermediate representations and learns to directly map from images and headset poses to humanoid control signals. To train our method, we also propose a large-scale synthetic dataset created using camera configurations compatible with a commercially available VR headset (Quest 2) and show promising results on real-world captures. To demonstrate the applicability of our framework, we also test it on an AR headset with a forward-facing camera.
Authors: Sergey KastryulinSkolkovo Institute of Science and Technology, Yandex, Denis ProkopenkoKing's Colledge London, Artem BabenkoYandex, Dmitry V. DylovSkolkovo Institute of Science and Technology, AIRI
Abstract: This paper introduces a new data-driven, non-parametric method for image quality and aesthetics assessment, surpassing existing approaches and requiring no prompt engineering or fine-tuning. We eliminate the need for expressive textual embeddings by proposing efficient image anchors in the data. Through extensive evaluations of 7 state-of-the-art self-supervised models, our method demonstrates superior performance and robustness across various datasets and benchmarks. Notably, it achieves high agreement with human assessments even with limited data and shows high robustness to the nature of data and their pre-processing pipeline. Our contributions offer a streamlined solution for assessment of images while providing insights into the perception of visual information.
Authors: L. E. Hogeweg, R. Gangireddy, D. Brunink, V. J. Kalkman, L. Cornelissen, J. W. Kamminga
Abstract: High-performing out-of-distribution (OOD) detection, both anomaly and novel class, is an important prerequisite for the practical use of classification models. In this paper, we focus on the species recognition task in images concerned with large databases, a large number of fine-grained hierarchical classes, severe class imbalance, and varying image quality. We propose a framework for combining individual OOD measures into one combined OOD (COOD) measure using a supervised model. The individual measures are several existing state-of-the-art measures and several novel OOD measures developed with novel class detection and hierarchical class structure in mind. COOD was extensively evaluated on three large-scale (500k+ images) biodiversity datasets in the context of anomaly and novel class detection. We show that COOD outperforms individual, including state-of-the-art, OOD measures by a large margin in terms of TPR@1% FPR in the majority of experiments, e.g., improving detecting ImageNet images (OOD) from 54.3% to 85.4% for the iNaturalist 2018 dataset. SHAP (feature contribution) analysis shows that different individual OOD measures are essential for various tasks, indicating that multiple OOD measures and combinations are needed to generalize. Additionally, we show that explicitly considering ID images that are incorrectly classified for the original (species) recognition task is important for constructing high-performing OOD detection methods and for practical applicability. The framework can easily be extended or adapted to other tasks and media modalities.
Authors: Pan He, Quanyi Li, Xiaoyong Yuan, Bolei Zhou
Abstract: Traffic signal control (TSC) is crucial for reducing traffic congestion that leads to smoother traffic flow, reduced idling time, and mitigated CO2 emissions. In this study, we explore the computer vision approach for TSC that modulates on-road traffic flows through visual observation. Unlike traditional feature-based approaches, vision-based methods depend much less on heuristics and predefined features, bringing promising potentials for end-to-end learning and optimization of traffic signals. Thus, we introduce a holistic traffic simulation framework called TrafficDojo towards vision-based TSC and its benchmarking by integrating the microscopic traffic flow provided in SUMO into the driving simulator MetaDrive. This proposed framework offers a versatile traffic environment for in-depth analysis and comprehensive evaluation of traffic signal controllers across diverse traffic conditions and scenarios. We establish and compare baseline algorithms including both traditional and Reinforecment Learning (RL) approaches. This work sheds insights into the design and development of vision-based TSC approaches and open up new research opportunities. All the code and baselines will be made publicly available.
Authors: Tiancheng Zhao, Peng Liu, Xuan He, Lu Zhang, Kyusong Lee
Abstract: End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set and open-vocabulary object detection (OVD) tasks through the integration of language modalities. However, their demanding computational requirements have hindered their practical application in real-time object detection (OD) scenarios. In this paper, we scrutinize the limitations of two leading models in the OVDEval benchmark, OmDet and Grounding-DINO, and introduce OmDet-Turbo. This novel transformer-based real-time OVD model features an innovative Efficient Fusion Head (EFH) module designed to alleviate the bottlenecks observed in OmDet and Grounding-DINO. Notably, OmDet-Turbo-Base achieves a 100.2 frames per second (FPS) with TensorRT and language cache techniques applied. Notably, in zero-shot scenarios on COCO and LVIS datasets, OmDet-Turbo achieves performance levels nearly on par with current state-of-the-art supervised models. Furthermore, it establishes new state-of-the-art benchmarks on ODinW and OVDEval, boasting an AP of 30.1 and an NMS-AP of 26.86, respectively. The practicality of OmDet-Turbo in industrial applications is underscored by its exceptional performance on benchmark datasets and superior inference speed, positioning it as a compelling choice for real-time object detection tasks. Code: \url{https://github.com/om-ai-lab/OmDet}
Authors: N K Sagar Reddy, Neeraj Kasera, Avinash Thakur
Abstract: Our research focuses on the analysis and improvement of the Graph-based Relation Inference Transformer (GRIT), which serves as an important benchmark in the field. We conduct a comprehensive ablation study using the PISC-fine dataset, to find and explore improvement in efficiency and performance of GRITv2. Our research has provided a new state-of-the-art relation recognition model on the PISC relation dataset. We introduce several features in the GRIT model and analyse our new benchmarks in two versions: GRITv2-L (large) and GRITv2-S (small). Our proposed GRITv2-L surpasses existing methods on relation recognition and the GRITv2-S is within 2% performance gap of GRITv2-L, which has only 0.0625x the model size and parameters of GRITv2-L. Furthermore, we also address the need for model compression, an area crucial for deploying efficient models on resource-constrained platforms. By applying quantization techniques, we efficiently reduced the GRITv2-S size to 22MB and deployed it on the flagship OnePlus 12 mobile which still surpasses the PISC-fine benchmarks in performance, highlighting the practical viability and improved efficiency of our model on mobile devices.
Authors: Joaquim Comas, Adria Ruiz, Federico Sukno
Abstract: Recent advances in remote heart rate measurement, motivated by data-driven approaches, have notably enhanced accuracy. However, these improvements primarily focus on recovering the rPPG signal, overlooking the implicit challenges of estimating the heart rate (HR) from the derived signal. While many methods employ the Fast Fourier Transform (FFT) for HR estimation, the performance of the FFT is inherently affected by a limited frequency resolution. In contrast, the Chirp-Z Transform (CZT), a generalization form of FFT, can refine the spectrum to the narrow-band range of interest for heart rate, providing improved frequential resolution and, consequently, more accurate estimation. This paper presents the advantages of employing the CZT for remote HR estimation and introduces a novel data-driven adaptive CZT estimator. The objective of our proposed model is to tailor the CZT to match the characteristics of each specific dataset sensor, facilitating a more optimal and accurate estimation of HR from the rPPG signal without compromising generalization across diverse datasets. This is achieved through a Sparse Matrix Optimization (SMO). We validate the effectiveness of our model through exhaustive evaluations on three publicly available datasets UCLA-rPPG, PURE, and UBFC-rPPG employing both intra- and cross-database performance metrics. The results reveal outstanding heart rate estimation capabilities, establishing the proposed approach as a robust and versatile estimator for any rPPG method.
Authors: Muhammad Saif Ullah Khan, Muhammad Ferjad Naeem, Federico Tombari, Luc Van Gool, Didier Stricker, Muhammad Zeshan Afzal
Abstract: We propose FocusCLIP, integrating subject-level guidance--a specialized mechanism for target-specific supervision--into the CLIP framework for improved zero-shot transfer on human-centric tasks. Our novel contributions enhance CLIP on both the vision and text sides. On the vision side, we incorporate ROI heatmaps emulating human visual attention mechanisms to emphasize subject-relevant image regions. On the text side, we introduce human pose descriptions to provide rich contextual information. For human-centric tasks, FocusCLIP is trained with images from the MPII Human Pose dataset. The proposed approach surpassed CLIP by an average of 8.61% across five previously unseen datasets covering three human-centric tasks. FocusCLIP achieved an average accuracy of 33.65% compared to 25.04% by CLIP. We observed a 3.98% improvement in activity recognition, a 14.78% improvement in age classification, and a 7.06% improvement in emotion recognition. Moreover, using our proposed single-shot LLM prompting strategy, we release a high-quality MPII Pose Descriptions dataset to encourage further research in multimodal learning for human-centric tasks. Furthermore, we also demonstrate the effectiveness of our subject-level supervision on non-human-centric tasks. FocusCLIP shows a 2.47% improvement over CLIP in zero-shot bird classification using the CUB dataset. Our findings emphasize the potential of integrating subject-level guidance with general pretraining methods for enhanced downstream performance.
Authors: Jiahui Zhang, Fangneng Zhan, Muyu Xu, Shijian Lu, Eric Xing
Abstract: 3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
Authors: Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu
Abstract: Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized framework based on 3D Gaussian radiance fields, offering real-time and high-quality few-shot novel view synthesis at low costs. Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease. In the Gaussian radiance fields, we find this degradation in scene geometry primarily lined to the positioning of Gaussian primitives and can be mitigated by depth constraint. Consequently, we propose a Hard and Soft Depth Regularization to restore accurate scene geometry under coarse monocular depth supervision while maintaining a fine-grained color appearance. To further refine detailed geometry reshaping, we introduce Global-Local Depth Normalization, enhancing the focus on small local depth changes. Extensive experiments on LLFF, DTU, and Blender datasets demonstrate that DNGaussian outperforms state-of-the-art methods, achieving comparable or better results with significantly reduced memory cost, a $25 \times$ reduction in training time, and over $3000 \times$ faster rendering speed.
Authors: Xinyao Li, Yuke Li, Zhekai Du, Fengling Li, Ke Lu, Jingjing Li
Abstract: Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches, overlooking the nuanced interplay between both modalities. In this work, we introduce a Unified Modality Separation (UniMoS) framework for unsupervised domain adaptation. Leveraging insights from modality gap studies, we craft a nimble modality separation network that distinctly disentangles CLIP's features into language-associated and vision-associated components. Our proposed Modality-Ensemble Training (MET) method fosters the exchange of modality-agnostic information while maintaining modality-specific nuances. We align features across domains using a modality discriminator. Comprehensive evaluations on three benchmarks reveal our approach sets a new state-of-the-art with minimal computational costs. Code: https://github.com/TL-UESTC/UniMoS
Authors: Yuting Zhang, Hao Lu, Xin Liu, Yingcong Chen, Kaishun Wu
Abstract: Remote photoplethysmography (rPPG) is a promising technology that captures physiological signals from face videos, with potential applications in medical health, emotional computing, and biosecurity recognition. The demand for rPPG tasks has expanded from demonstrating good performance on intra-dataset testing to cross-dataset testing (i.e., domain generalization). However, most existing methods have overlooked the prior knowledge of rPPG, resulting in poor generalization ability. In this paper, we propose a novel framework that simultaneously utilizes explicit and implicit prior knowledge in the rPPG task. Specifically, we systematically analyze the causes of noise sources (e.g., different camera, lighting, skin types, and movement) across different domains and incorporate these prior knowledge into the network. Additionally, we leverage a two-branch network to disentangle the physiological feature distribution from noises through implicit label correlation. Our extensive experiments demonstrate that the proposed method not only outperforms state-of-the-art methods on RGB cross-dataset evaluation but also generalizes well from RGB datasets to NIR datasets. The code is available at https://github.com/keke-nice/Greip.
Authors: Tianhao Qi, Shancheng Fang, Yanze Wu, Hongtao Xie, Jiawei Liu, Lang Chen, Qian He, Yongdong Zhang
Abstract: The diffusion-based text-to-image model harbors immense potential in transferring reference style. However, current encoder-based approaches significantly impair the text controllability of text-to-image models while transferring styles. In this paper, we introduce \textit{DEADiff} to address this issue using the following two strategies: 1) a mechanism to decouple the style and semantics of reference images. The decoupled feature representations are first extracted by Q-Formers which are instructed by different text descriptions. Then they are injected into mutually exclusive subsets of cross-attention layers for better disentanglement. 2) A non-reconstructive learning method. The Q-Formers are trained using paired images rather than the identical target, in which the reference image and the ground-truth image are with the same style or semantics. We show that DEADiff attains the best visual stylization results and optimal balance between the text controllability inherent in the text-to-image model and style similarity to the reference image, as demonstrated both quantitatively and qualitatively. Our project page is~\href{https://tianhao-qi.github.io/DEADiff/}{https://tianhao-qi.github.io/DEADiff/}.
URLs: https://tianhao-qi.github.io/DEADiff/, https://tianhao-qi.github.io/DEADiff/
Authors: Jialu Li, Jaemin Cho, Yi-Lin Sung, Jaehong Yoon, Mohit Bansal
Abstract: Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions. However, these T2I generation models often fall short of generating images that precisely match the details of the text inputs, such as incorrect spatial relationship or missing objects. In this paper, we introduce SELMA: Skill-Specific Expert Learning and Merging with Auto-Generated Data, a novel paradigm to improve the faithfulness of T2I models by fine-tuning models on automatically generated, multi-skill image-text datasets, with skill-specific expert learning and merging. First, SELMA leverages an LLM's in-context learning capability to generate multiple datasets of text prompts that can teach different skills, and then generates the images with a T2I model based on the prompts. Next, SELMA adapts the T2I model to the new skills by learning multiple single-skill LoRA (low-rank adaptation) experts followed by expert merging. Our independent expert fine-tuning specializes multiple models for different skills, and expert merging helps build a joint multi-skill T2I model that can generate faithful images given diverse text prompts, while mitigating the knowledge conflict from different datasets. We empirically demonstrate that SELMA significantly improves the semantic alignment and text faithfulness of state-of-the-art T2I diffusion models on multiple benchmarks (+2.1% on TIFA and +6.9% on DSG), human preference metrics (PickScore, ImageReward, and HPS), as well as human evaluation. Moreover, fine-tuning with image-text pairs auto-collected via SELMA shows comparable performance to fine-tuning with ground truth data. Lastly, we show that fine-tuning with images from a weaker T2I model can help improve the generation quality of a stronger T2I model, suggesting promising weak-to-strong generalization in T2I models.
Authors: Siddhant Satyanaik, Aditya Murali, Deepak Alapatt, Xin Wang, Pietro Mascagni, Nicolas Padoy
Abstract: Purpose: Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera setups, and patient demographics. Recently, object-centric learning has emerged as a promising approach for improved surgical scene understanding, capturing and disentangling visual and semantic properties of surgical tools and anatomy to improve downstream task performance. In this work, we conduct a multi-centric performance benchmark of object-centric approaches, focusing on Critical View of Safety assessment in laparoscopic cholecystectomy, then propose an improved approach for unseen domain generalization. Methods: We evaluate four object-centric approaches for domain generalization, establishing baseline performance. Next, leveraging the disentangled nature of object-centric representations, we dissect one of these methods through a series of ablations (e.g. ignoring either visual or semantic features for downstream classification). Finally, based on the results of these ablations, we develop an optimized method specifically tailored for domain generalization, LG-DG, that includes a novel disentanglement loss function. Results: Our optimized approach, LG-DG, achieves an improvement of 9.28% over the best baseline approach. More broadly, we show that object-centric approaches are highly effective for domain generalization thanks to their modular approach to representation learning. Conclusion: We investigate the use of object-centric methods for unseen domain generalization, identify method-agnostic factors critical for performance, and present an optimized approach that substantially outperforms existing methods.
Authors: Ugur Demir, Debesh Jha, Zheyuan Zhang, Elif Keles, Bradley Allen, Aggelos K. Katsaggelos, Ulas Bagci
Abstract: Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions. The recent trend in automated medical image diagnostics leans towards the deployment of Transformer-based architectures, credited to their impressive capabilities. Since the self-attention feature of transformers contributes towards identifying crucial regions during the classification process, they enhance the trustability of the methods. However, the complex intricacies of these attention mechanisms may fall short of effectively pinpointing the regions of interest directly influencing AI decisions. Our research endeavors to innovate a unique attention block that underscores the correlation between 'regions' rather than 'pixels'. To address this challenge, we introduce an innovative system grounded in prototype learning, featuring an advanced self-attention mechanism that goes beyond conventional ad-hoc visual explanation techniques by offering comprehensible visual insights. A combined quantitative and qualitative methodological approach was used to demonstrate the effectiveness of the proposed method on the large-scale NIH chest X-ray dataset. Experimental results showed that our proposed method offers a promising direction for explainability, which can lead to the development of more trustable systems, which can facilitate easier and rapid adoption of such technology into routine clinics. The code is available at www.github.com/NUBagcilab/r2r_proto.
Authors: Haiyang Xu, Yu Lei, Zeyuan Chen, Xiang Zhang, Yue Zhao, Yilin Wang, Zhuowen Tu
Abstract: We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We show the effectiveness of BDM on the 3D shape reconstruction task. Compared to prototypical deep learning data-driven approaches trained on paired (supervised) data-labels (e.g. image-point clouds) datasets, our BDM brings in rich prior information from standalone labels (e.g. point clouds) to improve the bottom-up 3D reconstruction. As opposed to the standard Bayesian frameworks where explicit prior and likelihood are required for the inference, BDM performs seamless information fusion via coupled diffusion processes with learned gradient computation networks. The specialty of our BDM lies in its capability to engage the active and effective information exchange and fusion of the top-down and bottom-up processes where each itself is a diffusion process. We demonstrate state-of-the-art results on both synthetic and real-world benchmarks for 3D shape reconstruction.
Authors: Xiuwei Xu, Chong Xia, Ziwei Wang, Linqing Zhao, Yueqi Duan, Jie Zhou, Jiwen Lu
Abstract: In this paper, we propose a new framework for online 3D scene perception. Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometry as input, which is not applicable in robotic applications where the input data is streaming RGB-D videos rather than a complete 3D scene reconstructed from pre-collected RGB-D videos. To deal with online 3D scene perception tasks where data collection and perception should be performed simultaneously, the model should be able to process 3D scenes frame by frame and make use of the temporal information. To this end, we propose an adapter-based plug-and-play module for the backbone of 3D scene perception model, which constructs memory to cache and aggregate the extracted RGB-D features to empower offline models with temporal learning ability. Specifically, we propose a queued memory mechanism to cache the supporting point cloud and image features. Then we devise aggregation modules which directly perform on the memory and pass temporal information to current frame. We further propose 3D-to-2D adapter to enhance image features with strong global context. Our adapters can be easily inserted into mainstream offline architectures of different tasks and significantly boost their performance on online tasks. Extensive experiments on ScanNet and SceneNN datasets demonstrate our approach achieves leading performance on three 3D scene perception tasks compared with state-of-the-art online methods by simply finetuning existing offline models, without any model and task-specific designs. \href{https://xuxw98.github.io/Online3D/}{Project page}.
Authors: Xuan Ju, Xian Liu, Xintao Wang, Yuxuan Bian, Ying Shan, Qiang Xu
Abstract: Image inpainting, the process of restoring corrupted images, has seen significant advancements with the advent of diffusion models (DMs). Despite these advancements, current DM adaptations for inpainting, which involve modifications to the sampling strategy or the development of inpainting-specific DMs, frequently suffer from semantic inconsistencies and reduced image quality. Addressing these challenges, our work introduces a novel paradigm: the division of masked image features and noisy latent into separate branches. This division dramatically diminishes the model's learning load, facilitating a nuanced incorporation of essential masked image information in a hierarchical fashion. Herein, we present BrushNet, a novel plug-and-play dual-branch model engineered to embed pixel-level masked image features into any pre-trained DM, guaranteeing coherent and enhanced image inpainting outcomes. Additionally, we introduce BrushData and BrushBench to facilitate segmentation-based inpainting training and performance assessment. Our extensive experimental analysis demonstrates BrushNet's superior performance over existing models across seven key metrics, including image quality, mask region preservation, and textual coherence.
Authors: Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, Limin Wang, Yu Qiao
Abstract: Addressing the dual challenges of local redundancy and global dependencies in video understanding, this work innovatively adapts the Mamba to the video domain. The proposed VideoMamba overcomes the limitations of existing 3D convolution neural networks and video transformers. Its linear-complexity operator enables efficient long-term modeling, which is crucial for high-resolution long video understanding. Extensive evaluations reveal VideoMamba's four core abilities: (1) Scalability in the visual domain without extensive dataset pretraining, thanks to a novel self-distillation technique; (2) Sensitivity for recognizing short-term actions even with fine-grained motion differences; (3) Superiority in long-term video understanding, showcasing significant advancements over traditional feature-based models; and (4) Compatibility with other modalities, demonstrating robustness in multi-modal contexts. Through these distinct advantages, VideoMamba sets a new benchmark for video understanding, offering a scalable and efficient solution for comprehensive video understanding. All the code and models are available at https://github.com/OpenGVLab/VideoMamba.
Authors: Wele Gedara Chaminda Bandara, Vishal M. Patel
Abstract: In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts along with data tokens during fine-tuning while keeping the backbone frozen. This approach greatly reduces the number of learnable parameters compared to full tuning. For image-based downstream tasks, normally a couple of learnable prompts achieve results close to those of full tuning. However, videos, which contain more complex spatiotemporal information, require hundreds of tunable prompts to achieve reasonably good results. This reduces the parameter efficiency observed in images and significantly increases latency and the number of floating-point operations (FLOPs) during inference. To tackle these issues, we directly inject the prompts into the keys and values of the non-local attention mechanism within the transformer block. Additionally, we introduce a novel prompt reparameterization technique to make APT more robust against hyperparameter selection. The proposed APT approach greatly reduces the number of FLOPs and latency while achieving a significant performance boost over the existing parameter-efficient tuning methods on UCF101, HMDB51, and SSv2 datasets for action recognition. The code and pre-trained models are available at https://github.com/wgcban/apt
Authors: Peng Qi, Zehong Yan, Wynne Hsu, Mong Li Lee
Abstract: Misinformation is a prevalent societal issue due to its potential high risks. Out-of-context (OOC) misinformation, where authentic images are repurposed with false text, is one of the easiest and most effective ways to mislead audiences. Current methods focus on assessing image-text consistency but lack convincing explanations for their judgments, which is essential for debunking misinformation. While Multimodal Large Language Models (MLLMs) have rich knowledge and innate capability for visual reasoning and explanation generation, they still lack sophistication in understanding and discovering the subtle crossmodal differences. In this paper, we introduce SNIFFER, a novel multimodal large language model specifically engineered for OOC misinformation detection and explanation. SNIFFER employs two-stage instruction tuning on InstructBLIP. The first stage refines the model's concept alignment of generic objects with news-domain entities and the second stage leverages language-only GPT-4 generated OOC-specific instruction data to fine-tune the model's discriminatory powers. Enhanced by external tools and retrieval, SNIFFER not only detects inconsistencies between text and image but also utilizes external knowledge for contextual verification. Our experiments show that SNIFFER surpasses the original MLLM by over 40% and outperforms state-of-the-art methods in detection accuracy. SNIFFER also provides accurate and persuasive explanations as validated by quantitative and human evaluations.
Authors: Shanu Vashishtha, Abhinav Prakash, Lalitesh Morishetti, Kaushiki Nag, Yokila Arora, Sushant Kumar, Kannan Achan
Abstract: Text-to-image models such as stable diffusion have opened a plethora of opportunities for generating art. Recent literature has surveyed the use of text-to-image models for enhancing the work of many creative artists. Many e-commerce platforms employ a manual process to generate the banners, which is time-consuming and has limitations of scalability. In this work, we demonstrate the use of text-to-image models for generating personalized web banners with dynamic content for online shoppers based on their interactions. The novelty in this approach lies in converting users' interaction data to meaningful prompts without human intervention. To this end, we utilize a large language model (LLM) to systematically extract a tuple of attributes from item meta-information. The attributes are then passed to a text-to-image model via prompt engineering to generate images for the banner. Our results show that the proposed approach can create high-quality personalized banners for users.
Authors: Jian Chen, Petra Isenberg, Robert S. Laramee, Tobias Isenberg, Michael Sedlmair, Torsten Moeller, Rui Li
Abstract: We present and discuss the results of a qualitative analysis of visual representations from images. We labeled each image's essential stimuli, the removal of which would render a visualization uninterpretable. As a result, we derive a typology of 10 visualization types of defined groups. We describe the typology derivation process in which we engaged. The resulting typology and image analysis can serve a number of purposes: enabling researchers to study the evolution of the community and its research output over time, facilitating the categorization of visualization images for the purpose of research and teaching, allowing researchers and practitioners to identify visual design styles to further align the quantification of any visual information processor, be that a person or an algorithm observer, and it facilitates a discussion of standardization in visualization. In addition to the visualization typology from images, we provide a dataset of 6,833 tagged images and an online tool that can be used to explore and analyze the large set of labeled images. The tool and data set enable scholars to closely examine the diverse visual designs used and how they are published and communicated in our community. A pre-registration, a free copy of this paper, and all supplemental materials are available via osf.io/dxjwt.
Authors: Farhad Nazari, Navid Mohajer, Darius Nahavandi, Abbas Khosravi
Abstract: Human walking is a complex activity with a high level of cooperation and interaction between different systems in the body. Accurate detection of the phases of the gait in real-time is crucial to control lower-limb assistive devices like exoskeletons and prostheses. There are several ways to detect the walking gait phase, ranging from cameras and depth sensors to the sensors attached to the device itself or the human body. Electromyography (EMG) is one of the input methods that has captured lots of attention due to its precision and time delay between neuromuscular activity and muscle movement. This study proposes a few Machine Learning (ML) based models on lower-limb EMG data for human walking. The proposed models are based on Gaussian Naive Bayes (NB), Decision Tree (DT), Random Forest (RF), Linear Discriminant Analysis (LDA) and Deep Convolutional Neural Networks (DCNN). The traditional ML models are trained on hand-crafted features or their reduced components using Principal Component Analysis (PCA). On the contrary, the DCNN model utilises convolutional layers to extract features from raw data. The results show up to 75% average accuracy for traditional ML models and 79% for Deep Learning (DL) model. The highest achieved accuracy in 50 trials of the training DL model is 89.5%.
Authors: Yifan Wu, Yang Liu, Yue Yang, Michael S. Yao, Wenli Yang, Xuehui Shi, Lihong Yang, Dongjun Li, Yueming Liu, James C. Gee, Xuan Yang, Wenbin Wei, Shi Gu
Abstract: Diagnosing rare diseases presents a common challenge in clinical practice, necessitating the expertise of specialists for accurate identification. The advent of machine learning offers a promising solution, while the development of such technologies is hindered by the scarcity of data on rare conditions and the demand for models that are both interpretable and trustworthy in a clinical context. Interpretable AI, with its capacity for human-readable outputs, can facilitate validation by clinicians and contribute to medical education. In the current work, we focus on choroid neoplasias, the most prevalent form of eye cancer in adults, albeit rare with 5.1 per million. We built the so-far largest dataset consisting of 750 patients, incorporating three distinct imaging modalities collected from 2004 to 2022. Our work introduces a concept-based interpretable model that distinguishes between three types of choroidal tumors, integrating insights from domain experts via radiological reports. Remarkably, this model not only achieves an F1 score of 0.91, rivaling that of black-box models, but also boosts the diagnostic accuracy of junior doctors by 42%. This study highlights the significant potential of interpretable machine learning in improving the diagnosis of rare diseases, laying a groundwork for future breakthroughs in medical AI that could tackle a wider array of complex health scenarios.
Authors: Thien An L. Nguyen
Abstract: Understanding the convergence process of neural networks is one of the most complex and crucial issues in the field of machine learning. Despite the close association of notable successes in this domain with the convergence of artificial neural networks, this concept remains predominantly theoretical. In reality, due to the non-convex nature of the optimization problems that artificial neural networks tackle, very few trained networks actually achieve convergence. To expand recent research efforts on artificial-neural-network convergence, this paper will discuss a different approach based on observations of cohesive-convergence groups emerging during the optimization process of an artificial neural network.
Authors: Qingqing Zhu, Benjamin Hou, Tejas S. Mathai, Pritam Mukherjee, Qiao Jin, Xiuying Chen, Zhizheng Wang, Ruida Cheng, Ronald M. Summers, Zhiyong Lu
Abstract: The volume of CT exams being done in the world has been rising every year, which has led to radiologist burn-out. Large Language Models (LLMs) have the potential to reduce their burden, but their adoption in the clinic depends on radiologist trust, and easy evaluation of generated content. Presently, many automated methods are available to evaluate the reports generated for chest radiographs, but such an approach is not available for CT presently. In this paper, we propose a novel evaluation framework to judge the capabilities of vision-language LLMs in generating accurate summaries of CT-based abnormalities. CT slices containing an abnormality (e.g., lesion) were input to a vision-based LLM (GPT-4V, LLaVA-Med, and RadFM), and it generated a free-text summary of the predicted characteristics of the abnormality. Next, a GPT-4 model decomposed the summary into specific aspects (body part, location, type, and attributes), automatically evaluated the characteristics against the ground-truth, and generated a score for each aspect based on its clinical relevance and factual accuracy. These scores were then contrasted against those obtained from a clinician, and a high correlation ( 85%, p < .001) was observed. Although GPT-4V outperformed other models in our evaluation, it still requires overall improvement. Our evaluation method offers valuable insights into the specific areas that need the most enhancement, guiding future development in this field.
Authors: Mukul Bhutani, Kevin Robinson, Vinodkumar Prabhakaran, Shachi Dave, Sunipa Dev
Abstract: While generative multilingual models are rapidly being deployed, their safety and fairness evaluations are largely limited to resources collected in English. This is especially problematic for evaluations targeting inherently socio-cultural phenomena such as stereotyping, where it is important to build multi-lingual resources that reflect the stereotypes prevalent in respective language communities. However, gathering these resources, at scale, in varied languages and regions pose a significant challenge as it requires broad socio-cultural knowledge and can also be prohibitively expensive. To overcome this critical gap, we employ a recently introduced approach that couples LLM generations for scale with culturally situated validations for reliability, and build SeeGULL Multilingual, a global-scale multilingual dataset of social stereotypes, containing over 25K stereotypes, spanning 20 languages, with human annotations across 23 regions, and demonstrate its utility in identifying gaps in model evaluations. Content warning: Stereotypes shared in this paper can be offensive.
Authors: Mona Ashtari-Majlan, Mohammad Mahdi Dehshibi, David Masip
Abstract: Glaucoma, a leading cause of irreversible blindness, necessitates early detection for accurate and timely intervention to prevent irreversible vision loss. In this study, we present a novel deep learning framework that leverages the diagnostic value of 3D Optical Coherence Tomography (OCT) imaging for automated glaucoma detection. In this framework, we integrate a pre-trained Vision Transformer on retinal data for rich slice-wise feature extraction and a bidirectional Gated Recurrent Unit for capturing inter-slice spatial dependencies. This dual-component approach enables comprehensive analysis of local nuances and global structural integrity, crucial for accurate glaucoma diagnosis. Experimental results on a large dataset demonstrate the superior performance of the proposed method over state-of-the-art ones, achieving an F1-score of 93.58%, Matthews Correlation Coefficient (MCC) of 73.54%, and AUC of 95.24%. The framework's ability to leverage the valuable information in 3D OCT data holds significant potential for enhancing clinical decision support systems and improving patient outcomes in glaucoma management.
Authors: Warren Morningstar, Alex Bijamov, Chris Duvarney, Luke Friedman, Neha Kalibhat, Luyang Liu, Philip Mansfield, Renan Rojas-Gomez, Karan Singhal, Bradley Green, Sushant Prakash
Abstract: We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL). While the recent literature in this space leaves the impression that the pretraining algorithm is of critical importance to performance, understanding its effect is complicated by the difficulty in making objective and direct comparisons between methods. We propose a new framework which unifies many seemingly disparate SSL methods into a single shared template. Using this framework, we identify aspects in which methods differ and observe that in addition to changing the pretraining algorithm, many works also use new data augmentations or more powerful model architectures. We compare several popular SSL methods using our framework and find that many algorithmic additions, such as prediction networks or new losses, have a minor impact on downstream task performance (often less than $1\%$), while enhanced augmentation techniques offer more significant performance improvements ($2-4\%$). Our findings challenge the premise that SSL is being driven primarily by algorithmic improvements, and suggest instead a bitter lesson for SSL: that augmentation diversity and data / model scale are more critical contributors to recent advances in self-supervised learning.
Authors: Wentao Liu, Bowen Liang, Weijin Xu, Tong Tian, Qingsheng Lu, Xipeng Pan, Haoyuan Li, Siyu Tian, Huihua Yang, Ruisheng Su
Abstract: The rigid registration of aortic Digital Subtraction Angiography (DSA) and Computed Tomography Angiography (CTA) can provide 3D anatomical details of the vasculature for the interventional surgical treatment of conditions such as aortic dissection and aortic aneurysms, holding significant value for clinical research. However, the current methods for 2D/3D image registration are dependent on manual annotations or synthetic data, as well as the extraction of landmarks, which is not suitable for cross-modal registration of aortic DSA/CTA. In this paper, we propose an unsupervised method, UDCR, for aortic DSA/CTA rigid registration based on deep reinforcement learning. Leveraging the imaging principles and characteristics of DSA and CTA, we have constructed a cross-dimensional registration environment based on spatial transformations. Specifically, we propose an overlap degree calculation reward function that measures the intensity difference between the foreground and background, aimed at assessing the accuracy of registration between segmentation maps and DSA images. This method is highly flexible, allowing for the loading of pre-trained models to perform registration directly or to seek the optimal spatial transformation parameters through online learning. We manually annotated 61 pairs of aortic DSA/CTA for algorithm evaluation. The results indicate that the proposed UDCR achieved a Mean Absolute Error (MAE) of 2.85 mm in translation and 4.35{\deg} in rotation, showing significant potential for clinical applications.
Authors: Andre Ye
Abstract: Vision is an important metaphor in ethical and political questions of knowledge. The feminist philosopher Donna Haraway points out the ``perverse'' nature of an intrusive, alienating, all-seeing vision (to which we might cry out ``stop looking at me!''), but also encourages us to embrace the embodied nature of sight and its promises for genuinely situated knowledge. Current technologies of machine vision -- surveillance cameras, drones (for war or recreation), iPhone cameras -- are usually construed as instances of the former rather than the latter, and for good reasons. However, although in no way attempting to diminish the real suffering these technologies have brought about in the world, I make the case for understanding technologies of computer vision as material instances of embodied seeing and situated knowing. Furthermore, borrowing from Iris Murdoch's concept of moral vision, I suggest that these technologies direct our labor towards self-reflection in ethically significant ways. My approach draws upon paradigms in computer vision research, phenomenology, and feminist epistemology. Ultimately, this essay is an argument for directing more philosophical attention from merely criticizing technologies of vision as ethically deficient towards embracing them as complex, methodologically and epistemologically important objects.
Authors: Yuhao Bian, Shengjing Tian, Xiuping Liu
Abstract: The widespread deployment of Deep Neural Networks (DNNs) for 3D point cloud processing starkly contrasts with their susceptibility to security breaches, notably backdoor attacks. These attacks hijack DNNs during training, embedding triggers in the data that, once activated, cause the network to make predetermined errors while maintaining normal performance on unaltered data. This vulnerability poses significant risks, especially given the insufficient research on robust defense mechanisms for 3D point cloud networks against such sophisticated threats. Existing attacks either struggle to resist basic point cloud pre-processing methods, or rely on delicate manual design. Exploring simple, effective, imperceptible, and difficult-to-defend triggers in 3D point clouds is still challenging.To address these challenges, we introduce MirrorAttack, a novel effective 3D backdoor attack method, which implants the trigger by simply reconstructing a clean point cloud with an auto-encoder. The data-driven nature of the MirrorAttack obviates the need for complex manual design. Minimizing the reconstruction loss automatically improves imperceptibility. Simultaneously, the reconstruction network endows the trigger with pronounced nonlinearity and sample specificity, rendering traditional preprocessing techniques ineffective in eliminating it. A trigger smoothing module based on spherical harmonic transformation is also attached to regulate the intensity of the attack.Both quantitive and qualitative results verify the effectiveness of our method. We achieve state-of-the-art ASR on different types of victim models with the intervention of defensive techniques. Moreover, the minimal perturbation introduced by our trigger, as assessed by various metrics, attests to the method's stealth, ensuring its imperceptibility.
Authors: Jingyun Xue, Tao Wang, Jun Wang, Kaihao Zhang, Wenhan Luo, Wenqi Ren, Zikun Liu, Hyunhee Park, Xiaochun Cao
Abstract: Under-Display Camera (UDC) is an emerging technology that achieves full-screen display via hiding the camera under the display panel. However, the current implementation of UDC causes serious degradation. The incident light required for camera imaging undergoes attenuation and diffraction when passing through the display panel, leading to various artifacts in UDC imaging. Presently, the prevailing UDC image restoration methods predominantly utilize convolutional neural network architectures, whereas Transformer-based methods have exhibited superior performance in the majority of image restoration tasks. This is attributed to the Transformer's capability to sample global features for the local reconstruction of images, thereby achieving high-quality image restoration. In this paper, we observe that when using the Vision Transformer for UDC degraded image restoration, the global attention samples a large amount of redundant information and noise. Furthermore, compared to the ordinary Transformer employing dense attention, the Transformer utilizing sparse attention can alleviate the adverse impact of redundant information and noise. Building upon this discovery, we propose a Segmentation Guided Sparse Transformer method (SGSFormer) for the task of restoring high-quality images from UDC degraded images. Specifically, we utilize sparse self-attention to filter out redundant information and noise, directing the model's attention to focus on the features more relevant to the degraded regions in need of reconstruction. Moreover, we integrate the instance segmentation map as prior information to guide the sparse self-attention in filtering and focusing on the correct regions.
Authors: Hairong Shi, Songhao Han, Shaofei Huang, Yue Liao, Guanbin Li, Xiangxing Kong, Hua Zhu, Xiaomu Wang, Si Liu
Abstract: Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation data across various medical imaging modalities and equipment, integrating medical knowledge into the Segment Anything Model (SAM) presents promising capability due to its versatility and generalization potential. Recent studies have attempted to enhance SAM with medical expertise by pre-training on large-scale medical segmentation datasets. However, challenges still exist in 3D tumor lesion segmentation owing to tumor complexity and the imbalance in foreground and background regions. Therefore, we introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks, facilitating the generation of more precise segmentation masks. Furthermore, an iterative refinement scheme is implemented in M-SAM to refine the segmentation masks progressively, leading to improved performance. Extensive experiments on seven tumor lesion segmentation datasets indicate that our M-SAM not only achieves high segmentation accuracy but also exhibits robust generalization.
Authors: Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin
Abstract: No-reference image- and video-quality metrics are widely used in video processing benchmarks. The robustness of learning-based metrics under video attacks has not been widely studied. In addition to having success, attacks that can be employed in video processing benchmarks must be fast and imperceptible. This paper introduces an Invisible One-Iteration (IOI) adversarial attack on no reference image and video quality metrics. We compared our method alongside eight prior approaches using image and video datasets via objective and subjective tests. Our method exhibited superior visual quality across various attacked metric architectures while maintaining comparable attack success and speed. We made the code available on GitHub.
Authors: Tiejin Chen, Wenwang Huang, Linsey Pang, Dongsheng Luo, Hua Wei
Abstract: This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated. Through a novel evaluation approach leveraging clustering for efficient assessment of explanation robustness, we demonstrate that enhancing explanation robustness does not necessarily flatten the input loss landscape with respect to explanation loss - contrary to flattened loss landscapes indicating better classification robustness. To deeply investigate this contradiction, a groundbreaking training method designed to adjust the loss landscape with respect to explanation loss is proposed. Through the new training method, we uncover that although such adjustments can impact the robustness of explanations, they do not have an influence on the robustness of classification. These findings not only challenge the prevailing assumption of a strong correlation between the two forms of robustness but also pave new pathways for understanding relationship between loss landscape and explanation loss.
Authors: Jeonghwan Park, Paul Miller, Niall McLaughlin
Abstract: We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white box surrogate models and black box target model. However, the majority of the methods adopting this approach are soft label based to take the full advantage of zeroth order optimisation. Unlike mainstream methods, we propose a new practical setting of hard label based attack with an optimisation process guided by a pretrained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250.
Authors: Rohan Asthana, Joschua Conrad, Youssef Dawoud, Maurits Ortmanns, Vasileios Belagiannis
Abstract: Neural architecture search automates the design of neural network architectures usually by exploring a large and thus complex architecture search space. To advance the architecture search, we present a graph diffusion-based NAS approach that uses discrete conditional graph diffusion processes to generate high-performing neural network architectures. We then propose a multi-conditioned classifier-free guidance approach applied to graph diffusion networks to jointly impose constraints such as high accuracy and low hardware latency. Unlike the related work, our method is completely differentiable and requires only a single model training. In our evaluations, we show promising results on six standard benchmarks, yielding novel and unique architectures at a fast speed, i.e. less than 0.2 seconds per architecture. Furthermore, we demonstrate the generalisability and efficiency of our method through experiments on ImageNet dataset.
Authors: Zhuo Xu, Rui Zhou, Yida Yin, Huidong Gao, Masayoshi Tomizuka, Jiachen Li
Abstract: Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications. However, collecting massive and annotated real-world human datasets has been a laborious task, especially for highly interactive scenarios. On the other hand, algorithmic data generation methods are usually limited by their model capacities, making them unable to offer realistic and diverse data needed by various application users. In this work, we study trajectory-level data generation for multi-human or human-robot interaction scenarios and propose a learning-based automatic trajectory generation model, which we call Multi-Agent TRajectory generation with dIverse conteXts (MATRIX). MATRIX is capable of generating interactive human behaviors in realistic diverse contexts. We achieve this goal by modeling the explicit and interpretable objectives so that MATRIX can generate human motions based on diverse destinations and heterogeneous behaviors. We carried out extensive comparison and ablation studies to illustrate the effectiveness of our approach across various metrics. We also presented experiments that demonstrate the capability of MATRIX to serve as data augmentation for imitation-based motion planning.
Authors: Xiang Li, Soo Min Kwon, Ismail R. Alkhouri, Saiprasad Ravishanka, Qing Qu
Abstract: Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability to model data distributions. To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models. However, the additional gradient steps pose a challenge for real-world practical applications as they incur a large computational overhead, thereby increasing inference time. They also present additional difficulties when using accelerated diffusion model samplers, as the number of data consistency steps is limited by the number of reverse sampling steps. In this work, we propose a novel diffusion-based image restoration solver that addresses these issues by decoupling the reverse process from the data consistency steps. Our method involves alternating between a reconstruction phase to maintain data consistency and a refinement phase that enforces the prior via diffusion purification. Our approach demonstrates versatility, making it highly adaptable for efficient problem-solving in latent space. Additionally, it reduces the necessity for numerous sampling steps through the integration of consistency models. The efficacy of our approach is validated through comprehensive experiments across various image restoration tasks, including image denoising, deblurring, inpainting, and super-resolution.
Authors: Dawei Fan, Yifan Gao, Jiaming Yu, Yanping Chen, Wencheng Li, Chuancong Lin, Kaibin Li, Changcai Yang, Riqing Chen, Lifang Wei
Abstract: Deep learning models have shown promising performance for cell nucleus segmentation in the field of pathology image analysis. However, training a robust model from multiple domains remains a great challenge for cell nucleus segmentation. Additionally, the shortcomings of background noise, highly overlapping between cell nucleus, and blurred edges often lead to poor performance. To address these challenges, we propose a novel framework termed CausalCellSegmenter, which combines Causal Inference Module (CIM) with Diversified Aggregation Convolution (DAC) techniques. The DAC module is designed which incorporates diverse downsampling features through a simple, parameter-free attention module (SimAM), aiming to overcome the problems of false-positive identification and edge blurring. Furthermore, we introduce CIM to leverage sample weighting by directly removing the spurious correlations between features for every input sample and concentrating more on the correlation between features and labels. Extensive experiments on the MoNuSeg-2018 dataset achieves promising results, outperforming other state-of-the-art methods, where the mIoU and DSC scores growing by 3.6% and 2.65%.
Authors: Yuang Wang, Siyeop Yoon, Pengfei Jin, Matthew Tivnan, Zhennong Chen, Rui Hu, Li Zhang, Zhiqiang Chen, Quanzheng Li, Dufan Wu
Abstract: Conditional diffusion models have gained recognition for their effectiveness in image restoration tasks, yet their iterative denoising process, starting from Gaussian noise, often leads to slow inference speeds. As a promising alternative, the Image-to-Image Schr\"odinger Bridge (I2SB) initializes the generative process from corrupted images and integrates training techniques from conditional diffusion models. In this study, we extended the I2SB method by introducing the Implicit Image-to-Image Schrodinger Bridge (I3SB), transitioning its generative process to a non-Markovian process by incorporating corrupted images in each generative step. This enhancement empowers I3SB to generate images with better texture restoration using a small number of generative steps. The proposed method was validated on CT super-resolution and denoising tasks and outperformed existing methods, including the conditional denoising diffusion probabilistic model (cDDPM) and I2SB, in both visual quality and quantitative metrics. These findings underscore the potential of I3SB in improving medical image restoration by providing fast and accurate generative modeling.
Authors: Zhihao Chen, Tao Chen, Chenhui Wang, Chuang Niu, Ge Wang, Hongming Shan
Abstract: While various deep learning methods were proposed for low-dose computed tomography (CT) denoising, they often suffer from over-smoothing, blurring, and lack of explainability. To alleviate these issues, we propose a plug-and-play Language-Engaged Dual-space Alignment loss (LEDA) to optimize low-dose CT denoising models. Our idea is to leverage large language models (LLMs) to align denoised CT and normal dose CT images in both the continuous perceptual space and discrete semantic space, which is the first LLM-based scheme for low-dose CT denoising. LEDA involves two steps: the first is to pretrain an LLM-guided CT autoencoder, which can encode a CT image into continuous high-level features and quantize them into a token space to produce semantic tokens derived from the LLM's vocabulary; and the second is to minimize the discrepancy between the denoised CT images and normal dose CT in terms of both encoded high-level features and quantized token embeddings derived by the LLM-guided CT autoencoder. Extensive experimental results on two public LDCT denoising datasets demonstrate that our LEDA can enhance existing denoising models in terms of quantitative metrics and qualitative evaluation, and also provide explainability through language-level image understanding. Source code is available at https://github.com/hao1635/LEDA.
Authors: Wenfang Ya, Kejing Yin, William K. Cheung, Jia Liu, Jing Qin
Abstract: The combination of electronic health records (EHR) and medical images is crucial for clinicians in making diagnoses and forecasting prognosis. Strategically fusing these two data modalities has great potential to improve the accuracy of machine learning models in clinical prediction tasks. However, the asynchronous and complementary nature of EHR and medical images presents unique challenges. Missing modalities due to clinical and administrative factors are inevitable in practice, and the significance of each data modality varies depending on the patient and the prediction target, resulting in inconsistent predictions and suboptimal model performance. To address these challenges, we propose DrFuse to achieve effective clinical multi-modal fusion. It tackles the missing modality issue by disentangling the features shared across modalities and those unique within each modality. Furthermore, we address the modal inconsistency issue via a disease-wise attention layer that produces the patient- and disease-wise weighting for each modality to make the final prediction. We validate the proposed method using real-world large-scale datasets, MIMIC-IV and MIMIC-CXR. Experimental results show that the proposed method significantly outperforms the state-of-the-art models. Our implementation is publicly available at https://github.com/dorothy-yao/drfuse.
Authors: Peirong Liu, Oula Puonti, Annabel Sorby-Adams, William T. Kimberly, Juan E. Iglesias
Abstract: Remarkable progress has been made by data-driven machine-learning methods in the analysis of MRI scans. However, most existing MRI analysis approaches are crafted for specific MR pulse sequences (MR contrasts) and usually require nearly isotropic acquisitions. This limits their applicability to diverse real-world clinical data, where scans commonly exhibit variations in appearances due to being obtained with varying sequence parameters, resolutions, and orientations -- especially in the presence of pathology. In this paper, we propose PEPSI, the first pathology-enhanced, and pulse-sequence-invariant feature representation learning model for brain MRI. PEPSI is trained entirely on synthetic images with a novel pathology encoding strategy, and enables co-training across datasets with diverse pathologies and missing modalities. Despite variations in pathology appearances across different MR pulse sequences or the quality of acquired images (e.g., resolution, orientation, artifacts, etc), PEPSI produces a high-resolution image of reference contrast (MP-RAGE) that captures anatomy, along with an image specifically highlighting the pathology. Our experiments demonstrate PEPSI's remarkable capability for image synthesis compared with the state-of-the-art, contrast-agnostic synthesis models, as it accurately reconstructs anatomical structures while differentiating between pathology and normal tissue. We further illustrate the efficiency and effectiveness of PEPSI features for downstream pathology segmentations on five public datasets covering white matter hyperintensities and stroke lesions. Code is available at https://github.com/peirong26/PEPSI.
Authors: Demetris Gerogiannis, Anastasios Arsenos, Dimitrios Kollias, Dimitris Nikitopoulos, Stefanos Kollias
Abstract: Computer-aided diagnosis (CAD) systems stand out as potent aids for physicians in identifying the novel Coronavirus Disease 2019 (COVID-19) through medical imaging modalities. In this paper, we showcase the integration and reliable and fast deployment of a state-of-the-art AI system designed to automatically analyze CT images, offering infection probability for the swift detection of COVID-19. The suggested system, comprising both classification and segmentation components, is anticipated to reduce physicians' detection time and enhance the overall efficiency of COVID-19 detection. We successfully surmounted various challenges, such as data discrepancy and anonymisation, testing the time-effectiveness of the model, and data security, enabling reliable and scalable deployment of the system on both cloud and edge environments. Additionally, our AI system assigns a probability of infection to each 3D CT scan and enhances explainability through anchor set similarity, facilitating timely confirmation and segregation of infected patients by physicians.
Authors: Bin Duan, Yuzhang Shang, Dawen Cai, Yan Yan
Abstract: In this paper, we propose an online multi-spectral neuron tracing method with uniquely designed modules, where no offline training are required. Our method is trained online to update our enhanced discriminative correlation filter to conglutinate the tracing process. This distinctive offline-training-free schema differentiates us from other training-dependent tracing approaches like deep learning methods since no annotation is needed for our method. Besides, compared to other tracing methods requiring complicated set-up such as for clustering and graph multi-cut, our approach is much easier to be applied to new images. In fact, it only needs a starting bounding box of the tracing neuron, significantly reducing users' configuration effort. Our extensive experiments show that our training-free and easy-configured methodology allows fast and accurate neuron reconstructions in multi-spectral images.
Authors: Ming Zhang, Ke Chang, Yunfang Wu
Abstract: Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails to learn cross-modal feature alignment, making it hard to achieve cross-modal deep information interaction. This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment, which projects the features derived from different modalities into a unified deep space. On multi-modal sarcasm detection (MMSD) and multi-modal sentiment analysis (MMSA) tasks, the experimental results show that our proposed model significantly outperforms several baselines, and our feature alignment strategy brings obvious performance gain over models with different aggregating methods and models even enriched with knowledge. More importantly, our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks. Our source codes are available at https://github.com/ChangKe123/CLFA.
Authors: Jianhao Xie, Ziang Zhang, Guibo Luo, Yuesheng Zhu
Abstract: Large pre-trained models with their numerous model parameters and extensive training datasets have shown excellent performance in various tasks. Many publicly available medical image datasets do not have a sufficient amount of data so there are few large-scale models in medical imaging. We propose a large-scale Tumor Segmentation Foundation Model (TSFM) with 1.6 billion parameters using Resblock-backbone and Transformer-bottleneck,which has good transfer ability for downstream tasks. To make TSFM exhibit good performance in tumor segmentation, we make full use of the strong spatial correlation between tumors and organs in the medical image, innovatively fuse 7 tumor datasets and 3 multi-organ datasets to build a 3D medical dataset pool, including 2779 cases with totally 300k medical images, whose size currently exceeds many other single publicly available datasets. TSFM is the pre-trained model for medical image segmentation, which also can be transferred to multiple downstream tasks for fine-tuning learning. The average performance of our pre-trained model is 2% higher than that of nnU-Net across various tumor types. In the transfer learning task, TSFM only needs 5% training epochs of nnU-Net to achieve similar performance and can surpass nnU-Net by 2% on average with 10% training epoch. Pre-trained TSFM and its code will be released soon.
Authors: Ziliang Samuel Zhong, Xiang Pan, Qi Lei
Abstract: Multi-source domain adaptation aims to reduce performance degradation when applying machine learning models to unseen domains. A fundamental challenge is devising the optimal strategy for feature selection. Existing literature is somewhat paradoxical: some advocate for learning invariant features from source domains, while others favor more diverse features. To address the challenge, we propose a statistical framework that distinguishes the utilities of features based on the variance of their correlation to label $y$ across domains. Under our framework, we design and analyze a learning procedure consisting of learning approximately shared feature representation from source tasks and fine-tuning it on the target task. Our theoretical analysis necessitates the importance of learning approximately shared features instead of only the strictly invariant features and yields an improved population risk compared to previous results on both source and target tasks, thus partly resolving the paradox mentioned above. Inspired by our theory, we proposed a more practical way to isolate the content (invariant+approximately shared) from environmental features and further consolidate our theoretical findings.
Authors: Yuxiang Lai, Xiaoxi Chen, Angtian Wang, Alan Yuille, Zongwei Zhou
Abstract: AI for cancer detection encounters the bottleneck of data scarcity, annotation difficulty, and low prevalence of early tumors. Tumor synthesis seeks to create artificial tumors in medical images, which can greatly diversify the data and annotations for AI training. However, current tumor synthesis approaches are not applicable across different organs due to their need for specific expertise and design. This paper establishes a set of generic rules to simulate tumor development. Each cell (pixel) is initially assigned a state between zero and ten to represent the tumor population, and a tumor can be developed based on three rules to describe the process of growth, invasion, and death. We apply these three generic rules to simulate tumor development--from pixel to cancer--using cellular automata. We then integrate the tumor state into the original computed tomography (CT) images to generate synthetic tumors across different organs. This tumor synthesis approach allows for sampling tumors at multiple stages and analyzing tumor-organ interaction. Clinically, a reader study involving three expert radiologists reveals that the synthetic tumors and their developing trajectories are convincingly realistic. Technically, we generate tumors at varied stages in 9,262 raw, unlabeled CT images sourced from 68 hospitals worldwide. The performance in segmenting tumors in the liver, pancreas, and kidneys exceeds prevailing literature benchmarks, underlining the immense potential of tumor synthesis, especially for earlier cancer detection. The code and models are available at https://github.com/MrGiovanni/Pixel2Cancer
Authors: Wenchi Ke
Abstract: Osteoporosis is a common skeletal disease that seriously affects patients' quality of life. Traditional osteoporosis diagnosis methods are expensive and complex. The semi-supervised model based on diffusion model and class threshold sinusoidal decay proposed in this paper can automatically diagnose osteoporosis based on patient's imaging data, which has the advantages of convenience, accuracy, and low cost. Unlike previous semi-supervised models, all the unlabeled data used in this paper are generated by the diffusion model. Compared with real unlabeled data, synthetic data generated by the diffusion model show better performance. In addition, this paper proposes a novel pseudo-label threshold adjustment mechanism, Sinusoidal Threshold Decay, which can make the semi-supervised model converge more quickly and improve its performance. Specifically, the method is tested on a dataset including 749 dental panoramic images, and its achieved leading detect performance and produces a 80.10% accuracy.
Authors: Hongguang Pan, Zhuoyi Li, Yunpeng Fu, Xuebin Qin, Jianchen Hu
Abstract: Reconstructing visual stimulus images is a significant task in neural decoding, and up to now, most studies consider the functional magnetic resonance imaging (fMRI) as the signal source. However, the fMRI-based image reconstruction methods are difficult to widely applied because of the complexity and high cost of the acquisition equipments. Considering the advantages of low cost and easy portability of the electroencephalogram (EEG) acquisition equipments, we propose a novel image reconstruction method based on EEG signals in this paper. Firstly, to satisfy the high recognizability of visual stimulus images in fast switching manner, we build a visual stimuli image dataset, and obtain the EEG dataset by a corresponding EEG signals collection experiment. Secondly, the deep visual representation model(DVRM) consisting of a primary encoder and a subordinate decoder is proposed to reconstruct visual stimuli. The encoder is designed based on the residual-in-residual dense blocks to learn the distribution characteristics between EEG signals and visual stimulus images, while the decoder is designed based on the deep neural network to reconstruct the visual stimulus image from the learned deep visual representation. The DVRM can fit the deep and multiview visual features of human natural state and make the reconstructed images more precise. Finally, we evaluate the DVRM in the quality of the generated images on our EEG dataset. The results show that the DVRM have good performance in the task of learning deep visual representation from EEG signals and generating reconstructed images that are realistic and highly resemble the original images.
Authors: Xiting Zhao, S\"oren Schwertfeger
Abstract: Reflective surfaces present a persistent challenge for reliable 3D mapping and perception in robotics and autonomous systems. However, existing reflection datasets and benchmarks remain limited to sparse 2D data. This paper introduces the first large-scale 3D reflection detection dataset containing more than 50,000 aligned samples of multi-return Lidar, RGB images, and 2D/3D semantic labels across diverse indoor environments with various reflections. Textured 3D ground truth meshes enable automatic point cloud labeling to provide precise ground truth annotations. Detailed benchmarks evaluate three Lidar point cloud segmentation methods, as well as current state-of-the-art image segmentation networks for glass and mirror detection. The proposed dataset advances reflection detection by providing a comprehensive testbed with precise global alignment, multi-modal data, and diverse reflective objects and materials. It will drive future research towards reliable reflection detection. The dataset is publicly available at http://3dref.github.io
URLs: http://3dref.github.io
Authors: Dominik Winter, Nicolas Triltsch, Philipp Plewa, Marco Rosati, Thomas Padel, Ross Hill, Markus Schick, Nicolas Brieu
Abstract: The creation of in-silico datasets can expand the utility of existing annotations to new domains with different staining patterns in computational pathology. As such, it has the potential to significantly lower the cost associated with building large and pixel precise datasets needed to train supervised deep learning models. We propose a novel approach for the generation of in-silico immunohistochemistry (IHC) images by disentangling morphology specific IHC stains into separate image channels in immunofluorescence (IF) images. The proposed approach qualitatively and quantitatively outperforms baseline methods as proven by training nucleus segmentation models on the created in-silico datasets.
Authors: Georgios Tsoumplekas, Vladislav Li, Ilias Siniosoglou, Vasileios Argyriou, Sotirios K. Goudos, Ioannis D. Moscholios, Panagiotis Radoglou-Grammatikis, Panagiotis Sarigiannidis
Abstract: In the ever-evolving era of Artificial Intelligence (AI), model performance has constituted a key metric driving innovation, leading to an exponential growth in model size and complexity. However, sustainability and energy efficiency have been critical requirements during deployment in contemporary industrial settings, necessitating the use of data-efficient approaches such as few-shot learning. In this paper, to alleviate the burden of lengthy model training and minimize energy consumption, a finetuning approach to adapt standard object detection models to downstream tasks is examined. Subsequently, a thorough case study and evaluation of the energy demands of the developed models, applied in object detection benchmark datasets from volatile industrial environments is presented. Specifically, different finetuning strategies as well as utilization of ancillary evaluation data during training are examined, and the trade-off between performance and efficiency is highlighted in this low-data regime. Finally, this paper introduces a novel way to quantify this trade-off through a customized Efficiency Factor metric.
Authors: Fatemeh Ahmadi, Mohamad Ebrahim Shiri, Behroz Bidabad, Maral Sedaghat, Pooran Memari
Abstract: Automated feature extraction from MRI brain scans and diagnosis of Alzheimer's disease are ongoing challenges. With advances in 3D imaging technology, 3D data acquisition is becoming more viable and efficient than its 2D counterpart. Rather than using feature-based vectors, in this paper, for the first time, we suggest a pipeline to extract novel covariance-based descriptors from the cortical surface using the Ricci energy optimization. The covariance descriptors are components of the nonlinear manifold of symmetric positive-definite matrices, thus we focus on using the Gaussian radial basis function to apply manifold-based classification to the 3D shape problem. Applying this novel signature to the analysis of abnormal cortical brain morphometry allows for diagnosing Alzheimer's disease. Experimental studies performed on about two hundred 3D MRI brain models, gathered from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate the effectiveness of our descriptors in achieving remarkable classification accuracy.
Authors: Jaewon Jung, Hongsun Jang, Jaeyong Song, Jinho Lee
Abstract: Adversarial robustness of the neural network is a significant concern when it is applied to security-critical domains. In this situation, adversarial distillation is a promising option which aims to distill the robustness of the teacher network to improve the robustness of a small student network. Previous works pretrain the teacher network to make it robust to the adversarial examples aimed at itself. However, the adversarial examples are dependent on the parameters of the target network. The fixed teacher network inevitably degrades its robustness against the unseen transferred adversarial examples which targets the parameters of the student network in the adversarial distillation process. We propose PeerAiD to make a peer network learn the adversarial examples of the student network instead of adversarial examples aimed at itself. PeerAiD is an adversarial distillation that trains the peer network and the student network simultaneously in order to make the peer network specialized for defending the student network. We observe that such peer networks surpass the robustness of pretrained robust teacher network against student-attacked adversarial samples. With this peer network and adversarial distillation, PeerAiD achieves significantly higher robustness of the student network with AutoAttack (AA) accuracy up to 1.66%p and improves the natural accuracy of the student network up to 4.72%p with ResNet-18 and TinyImageNet dataset.
Authors: Siyu Duan, Jun Wang, Qi Su
Abstract: Cultural heritage serves as the enduring record of human thought and history. Despite significant efforts dedicated to the preservation of cultural relics, many ancient artefacts have been ravaged irreversibly by natural deterioration and human actions. Deep learning technology has emerged as a valuable tool for restoring various kinds of cultural heritages, including ancient text restoration. Previous research has approached ancient text restoration from either visual or textual perspectives, often overlooking the potential of synergizing multimodal information. This paper proposes a novel Multimodal Multitask Restoring Model (MMRM) to restore ancient texts, particularly emphasising the ideograph. This model combines context understanding with residual visual information from damaged ancient artefacts, enabling it to predict damaged characters and generate restored images simultaneously. We tested the MMRM model through experiments conducted on both simulated datasets and authentic ancient inscriptions. The results show that the proposed method gives insightful restoration suggestions in both simulation experiments and real-world scenarios. To the best of our knowledge, this work represents the pioneering application of multimodal deep learning in ancient text restoration, which will contribute to the understanding of ancient society and culture in digital humanities fields.
Authors: Jinghan Huang, Qiufeng Chen, Yijun Bian, Pengli Zhu, Nanguang Chen, Moo K. Chung, Anqi Qiu
Abstract: Graph neural networks (GNNs) have proven effective in capturing relationships among nodes in a graph. This study introduces a novel perspective by considering a graph as a simplicial complex, encompassing nodes, edges, triangles, and $k$-simplices, enabling the definition of graph-structured data on any $k$-simplices. Our contribution is the Hodge-Laplacian heterogeneous graph attention network (HL-HGAT), designed to learn heterogeneous signal representations across $k$-simplices. The HL-HGAT incorporates three key components: HL convolutional filters (HL-filters), simplicial projection (SP), and simplicial attention pooling (SAP) operators, applied to $k$-simplices. HL-filters leverage the unique topology of $k$-simplices encoded by the Hodge-Laplacian (HL) operator, operating within the spectral domain of the $k$-th HL operator. To address computation challenges, we introduce a polynomial approximation for HL-filters, exhibiting spatial localization properties. Additionally, we propose a pooling operator to coarsen $k$-simplices, combining features through simplicial attention mechanisms of self-attention and cross-attention via transformers and SP operators, capturing topological interconnections across multiple dimensions of simplices. The HL-HGAT is comprehensively evaluated across diverse graph applications, including NP-hard problems, graph multi-label and classification challenges, and graph regression tasks in logistics, computer vision, biology, chemistry, and neuroscience. The results demonstrate the model's efficacy and versatility in handling a wide range of graph-based scenarios.
Authors: Chaoqun Du, Yulin Wang, Shiji Song, Gao Huang
Abstract: Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably impairs the performance of standard supervised learning algorithms, which are mainly designed for balanced training sets. Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance. However, the performance of supervised contrastive learning is plagued by an inherent challenge: it necessitates sufficiently large batches of training data to construct contrastive pairs that cover all categories, yet this requirement is difficult to meet in the context of class-imbalanced data. To overcome this obstacle, we propose a novel probabilistic contrastive (ProCo) learning algorithm that estimates the data distribution of the samples from each class in the feature space, and samples contrastive pairs accordingly. In fact, estimating the distributions of all classes using features in a small batch, particularly for imbalanced data, is not feasible. Our key idea is to introduce a reasonable and simple assumption that the normalized features in contrastive learning follow a mixture of von Mises-Fisher (vMF) distributions on unit space, which brings two-fold benefits. First, the distribution parameters can be estimated using only the first sample moment, which can be efficiently computed in an online manner across different batches. Second, based on the estimated distribution, the vMF distribution allows us to sample an infinite number of contrastive pairs and derive a closed form of the expected contrastive loss for efficient optimization. Our code is available at https://github.com/LeapLabTHU/ProCo.
Authors: Keshara Weerasinghe, Saahith Janapati, Xueren Ge, Sion Kim, Sneha Iyer, John A. Stankovic, Homa Alemzadeh
Abstract: Emergency Medical Services (EMS) responders often operate under time-sensitive conditions, facing cognitive overload and inherent risks, requiring essential skills in critical thinking and rapid decision-making. This paper presents CognitiveEMS, an end-to-end wearable cognitive assistant system that can act as a collaborative virtual partner engaging in the real-time acquisition and analysis of multimodal data from an emergency scene and interacting with EMS responders through Augmented Reality (AR) smart glasses. CognitiveEMS processes the continuous streams of data in real-time and leverages edge computing to provide assistance in EMS protocol selection and intervention recognition. We address key technical challenges in real-time cognitive assistance by introducing three novel components: (i) a Speech Recognition model that is fine-tuned for real-world medical emergency conversations using simulated EMS audio recordings, augmented with synthetic data generated by large language models (LLMs); (ii) an EMS Protocol Prediction model that combines state-of-the-art (SOTA) tiny language models with EMS domain knowledge using graph-based attention mechanisms; (iii) an EMS Action Recognition module which leverages multimodal audio and video data and protocol predictions to infer the intervention/treatment actions taken by the responders at the incident scene. Our results show that for speech recognition we achieve superior performance compared to SOTA (WER of 0.290 vs. 0.618) on conversational data. Our protocol prediction component also significantly outperforms SOTA (top-3 accuracy of 0.800 vs. 0.200) and the action recognition achieves an accuracy of 0.727, while maintaining an end-to-end latency of 3.78s for protocol prediction on the edge and 0.31s on the server.
Authors: Manxi Lin, Nina Weng, Kamil Mikolaj, Zahra Bashir, Morten Bo S{\o}ndergaard Svendsen, Martin Tolsgaard, Anders Nymark Christensen, Aasa Feragen
Abstract: Shortcut learning is a phenomenon where machine learning models prioritize learning simple, potentially misleading cues from data that do not generalize well beyond the training set. While existing research primarily investigates this in the realm of image classification, this study extends the exploration of shortcut learning into medical image segmentation. We demonstrate that clinical annotations such as calipers, and the combination of zero-padded convolutions and center-cropped training sets in the dataset can inadvertently serve as shortcuts, impacting segmentation accuracy. We identify and evaluate the shortcut learning on two different but common medical image segmentation tasks. In addition, we suggest strategies to mitigate the influence of shortcut learning and improve the generalizability of the segmentation models. By uncovering the presence and implications of shortcuts in medical image segmentation, we provide insights and methodologies for evaluating and overcoming this pervasive challenge and call for attention in the community for shortcuts in segmentation.
Authors: Adarsh N L, Arun P V, Alok Porwal, Malcolm Aranha
Abstract: Data generated by edge devices has the potential to train intelligent autonomous systems across various domains. Despite the emergence of diverse machine learning approaches addressing privacy concerns and utilizing distributed data, security issues persist due to the sensitive storage of data shards in disparate locations. This paper introduces a potentially groundbreaking paradigm for machine learning model training, specifically designed for scenarios with only a single magnetic image and its corresponding label image available. We harness the capabilities of Deep Learning to generate concise yet informative samples, aiming to overcome data scarcity. Through the utilization of deep learning's internal representations, our objective is to efficiently address data scarcity issues and produce meaningful results. This methodology presents a promising avenue for training machine learning models with minimal data.
Authors: Shuai Li, Xiaoguang Ma, Shancheng Jiang, Lu Meng
Abstract: Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC.
Authors: Ibrahim Ethem Hamamci, Sezgin Er, Bjoern Menze
Abstract: Medical imaging plays a crucial role in diagnosis, with radiology reports serving as vital documentation. Automating report generation has emerged as a critical need to alleviate the workload of radiologists. While machine learning has facilitated report generation for 2D medical imaging, extending this to 3D has been unexplored due to computational complexity and data scarcity. We introduce the first method to generate radiology reports for 3D medical imaging, specifically targeting chest CT volumes. Given the absence of comparable methods, we establish a baseline using an advanced 3D vision encoder in medical imaging to demonstrate our method's effectiveness, which leverages a novel auto-regressive causal transformer. Furthermore, recognizing the benefits of leveraging information from previous visits, we augment CT2Rep with a cross-attention-based multi-modal fusion module and hierarchical memory, enabling the incorporation of longitudinal multimodal data. Access our code at: https://github.com/ibrahimethemhamamci/CT2Rep
Authors: Jonathan Heek, Emiel Hoogeboom, Tim Salimans
Abstract: Diffusion models are relatively easy to train but require many steps to generate samples. Consistency models are far more difficult to train, but generate samples in a single step. In this paper we propose Multistep Consistency Models: A unification between Consistency Models (Song et al., 2023) and TRACT (Berthelot et al., 2023) that can interpolate between a consistency model and a diffusion model: a trade-off between sampling speed and sampling quality. Specifically, a 1-step consistency model is a conventional consistency model whereas we show that a $\infty$-step consistency model is a diffusion model. Multistep Consistency Models work really well in practice. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples, while retaining much of the sampling speed benefits. Notable results are 1.4 FID on Imagenet 64 in 8 step and 2.1 FID on Imagenet128 in 8 steps with consistency distillation. We also show that our method scales to a text-to-image diffusion model, generating samples that are very close to the quality of the original model.
Authors: Ibrahim Salihu Yusuf, Mukhtar Opeyemi Yusuf, Kobby Panford-Quainoo, Arnu Pretorius
Abstract: Desert locust swarms present a major threat to agriculture and food security. Addressing this challenge, our study develops an operationally-ready model for predicting locust breeding grounds, which has the potential to enhance early warning systems and targeted control measures. We curated a dataset from the United Nations Food and Agriculture Organization's (UN-FAO) locust observation records and analyzed it using two types of spatio-temporal input features: remotely-sensed environmental and climate data as well as multi-spectral earth observation images. Our approach employed custom deep learning models (three-dimensional and LSTM-based recurrent convolutional networks), along with the geospatial foundational model Prithvi recently released by Jakubik et al., 2023. These models notably outperformed existing baselines, with the Prithvi-based model, fine-tuned on multi-spectral images from NASA's Harmonized Landsat and Sentinel-2 (HLS) dataset, achieving the highest accuracy, F1 and ROC-AUC scores (83.03%, 81.53% and 87.69%, respectively). A significant finding from our research is that multi-spectral earth observation images alone are sufficient for effective locust breeding ground prediction without the need to explicitly incorporate climatic or environmental features.
Authors: Hao Chen, Jindong Wang, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj
Abstract: Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise that may adversely affect the generalization of the model and pose unexpected risks. This paper stands out as the first work to comprehensively understand and analyze the nature of noise in pre-training datasets and then effectively mitigate its impacts on downstream tasks. Specifically, through extensive experiments of fully-supervised and image-text contrastive pre-training on synthetic noisy ImageNet-1K, YFCC15M, and CC12M datasets, we demonstrate that, while slight noise in pre-training can benefit in-domain (ID) performance, where the training and testing data share a similar distribution, it always deteriorates out-of-domain (OOD) performance, where training and testing distributions are significantly different. These observations are agnostic to scales of pre-training datasets, pre-training noise types, model architectures, pre-training objectives, downstream tuning methods, and downstream applications. We empirically ascertain that the reason behind this is that the pre-training noise shapes the feature space differently. We then propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization, which is applicable in both parameter-efficient and black-box tuning manners. We additionally conduct extensive experiments on popular vision and language models, including APIs, which are supervised and self-supervised pre-trained on realistic noisy data for evaluation. Our analysis and results demonstrate the importance of this novel and fundamental research direction, which we term as Noisy Model Learning.
Authors: Yifu Tao, Yash Bhalgat, Lanke Frank Tarimo Fu, Matias Mattamala, Nived Chebrolu, Maurice Fallon
Abstract: We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photo-realistic textures. This system adapts the state-of-the-art neural radiance field (NeRF) representation to also incorporate lidar data which adds strong geometric constraints on the depth and surface normals. We exploit the trajectory from a real-time lidar SLAM system to bootstrap a Structure-from-Motion (SfM) procedure to both significantly reduce the computation time and to provide metric scale which is crucial for lidar depth loss. We use submapping to scale the system to large-scale environments captured over long trajectories. We demonstrate the reconstruction system with data from a multi-camera, lidar sensor suite onboard a legged robot, hand-held while scanning building scenes for 600 metres, and onboard an aerial robot surveying a multi-storey mock disaster site-building. Website: https://ori-drs.github.io/projects/silvr/
Authors: Justin Engelmann, Diana Moukaddem, Lucas Gago, Niall Strang, Miguel O. Bernabeu
Abstract: Purpose: To investigate whether Fractal Dimension (FD)-based oculomics could be used for individual risk prediction by evaluating repeatability and robustness. Methods: We used two datasets: Caledonia, healthy adults imaged multiple times in quick succession for research (26 subjects, 39 eyes, 377 colour fundus images), and GRAPE, glaucoma patients with baseline and follow-up visits (106 subjects, 196 eyes, 392 images). Mean follow-up time was 18.3 months in GRAPE, thus it provides a pessimistic lower-bound as vasculature could change. FD was computed with DART and AutoMorph. Image quality was assessed with QuickQual, but no images were initially excluded. Pearson, Spearman, and Intraclass Correlation (ICC) were used for population-level repeatability. For individual-level repeatability, we introduce measurement noise parameter {\lambda} which is within-eye Standard Deviation (SD) of FD measurements in units of between-eyes SD. Results: In Caledonia, ICC was 0.8153 for DART and 0.5779 for AutoMorph, Pearson/Spearman correlation (first and last image) 0.7857/0.7824 for DART, and 0.3933/0.6253 for AutoMorph. In GRAPE, Pearson/Spearman correlation (first and next visit) was 0.7479/0.7474 for DART, and 0.7109/0.7208 for AutoMorph (all p<0.0001). Median {\lambda} in Caledonia without exclusions was 3.55\% for DART and 12.65\% for AutoMorph, and improved to up to 1.67\% and 6.64\% with quality-based exclusions, respectively. Quality exclusions primarily mitigated large outliers. Worst quality in an eye correlated strongly with {\lambda} (Pearson 0.5350-0.7550, depending on dataset and method, all p<0.0001). Conclusions: Repeatability was sufficient for individual-level predictions in heterogeneous populations. DART performed better on all metrics and might be able to detect small, longitudinal changes, highlighting the potential of robust methods.
Authors: Ganesh Sistu, Isabelle Leang, Sumanth Chennupati, Senthil Yogamani, Ciaran Hughes, Stefan Milz, Samir Rawashdeh
Abstract: Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are typically independently explored and modeled. In this paper, we propose a joint multi-task network design for learning several tasks simultaneously. Our main motivation is the computational efficiency achieved by sharing the expensive initial convolutional layers between all tasks. Indeed, the main bottleneck in automated driving systems is the limited processing power available on deployment hardware. There is also some evidence for other benefits in improving accuracy for some tasks and easing development effort. It also offers scalability to add more tasks leveraging existing features and achieving better generalization. We survey various CNN based solutions for visual perception tasks in automated driving. Then we propose a unified CNN model for the important tasks and discuss several advanced optimization and architecture design techniques to improve the baseline model. The paper is partly review and partly positional with demonstration of several preliminary results promising for future research. We first demonstrate results of multi-stream learning and auxiliary learning which are important ingredients to scale to a large multi-task model. Finally, we implement a two-stream three-task network which performs better in many cases compared to their corresponding single-task models, while maintaining network size.
Authors: Mohammad Rahimzadeh, AmirAli Askari, Soroush Parvin, Elnaz Safi, Mohammad Reza Mohammadi
Abstract: One of the main challenges since the advancement of convolutional neural networks is how to connect the extracted feature map to the final classification layer. VGG models used two sets of fully connected layers for the classification part of their architectures, which significantly increased the number of models' weights. ResNet and the next deep convolutional models used the Global Average Pooling (GAP) layer to compress the feature map and feed it to the classification layer. Although using the GAP layer reduces the computational cost, but also causes losing spatial resolution of the feature map, which results in decreasing learning efficiency. In this paper, we aim to tackle this problem by replacing the GAP layer with a new architecture called Wise-SrNet. It is inspired by the depthwise convolutional idea and is designed for processing spatial resolution while not increasing computational cost. We have evaluated our method using three different datasets: Intel Image Classification Challenge, MIT Indoors Scenes, and a part of the ImageNet dataset. We investigated the implementation of our architecture on several models of the Inception, ResNet, and DenseNet families. Applying our architecture has revealed a significant effect on increasing convergence speed and accuracy. Our Experiments on images with 224*224 resolution increased the Top-1 accuracy between 2% to 8% on different datasets and models. Running our models on 512*512 resolution images of the MIT Indoors Scenes dataset showed a notable result of improving the Top-1 accuracy within 3% to 26%. We will also demonstrate the GAP layer's disadvantage when the input images are large and the number of classes is not few. In this circumstance, our proposed architecture can do a great help in enhancing classification results. The code is shared at https://github.com/mr7495/image-classification-spatial.
URLs: https://github.com/mr7495/image-classification-spatial.
Authors: Maryam Rahnemoonfar, Tashnim Chowdhury, Robin Murphy
Abstract: Recent advancements in computer vision and deep learning techniques have facilitated notable progress in scene understanding, thereby assisting rescue teams in achieving precise damage assessment. In this paper, we present RescueNet, a meticulously curated high-resolution post-disaster dataset that includes detailed classification and semantic segmentation annotations. This dataset aims to facilitate comprehensive scene understanding in the aftermath of natural disasters. RescueNet comprises post-disaster images collected after Hurricane Michael, obtained using Unmanned Aerial Vehicles (UAVs) from multiple impacted regions. The uniqueness of RescueNet lies in its provision of high-resolution post-disaster imagery, accompanied by comprehensive annotations for each image. Unlike existing datasets that offer annotations limited to specific scene elements such as buildings, RescueNet provides pixel-level annotations for all classes, including buildings, roads, pools, trees, and more. Furthermore, we evaluate the utility of the dataset by implementing state-of-the-art segmentation models on RescueNet, demonstrating its value in enhancing existing methodologies for natural disaster damage assessment.
Authors: Ying Xu, Philipp Terh\"orst, Kiran Raja, Marius Pedersen
Abstract: In recent years, image and video manipulations with Deepfake have become a severe concern for security and society. Many detection models and datasets have been proposed to detect Deepfake data reliably. However, there is an increased concern that these models and training databases might be biased and, thus, cause Deepfake detectors to fail. In this work, we investigate factors causing biased detection in public Deepfake datasets by (a) creating large-scale demographic and non-demographic attribute annotations with 47 different attributes for five popular Deepfake datasets and (b) comprehensively analysing attributes resulting in AI-bias of three state-of-the-art Deepfake detection backbone models on these datasets. The analysis shows how various attributes influence a large variety of distinctive attributes (from over 65M labels) on the detection performance which includes demographic (age, gender, ethnicity) and non-demographic (hair, skin, accessories, etc.) attributes. The results examined datasets show limited diversity and, more importantly, show that the utilised Deepfake detection backbone models are strongly affected by investigated attributes making them not fair across attributes. The Deepfake detection backbone methods trained on such imbalanced/biased datasets result in incorrect detection results leading to generalisability, fairness, and security issues. Our findings and annotated datasets will guide future research to evaluate and mitigate bias in Deepfake detection techniques. The annotated datasets and the corresponding code are publicly available.
Authors: Ohad Amosy, Tomer Volk, Eilam Shapira, Eyal Ben-David, Roi Reichart, Gal Chechik
Abstract: We address the challenge of building task-agnostic classifiers using only text descriptions, demonstrating a unified approach to image classification, 3D point cloud classification, and action recognition from scenes. Unlike approaches that learn a fixed representation of the output classes, we generate at inference time a model tailored to a query classification task. To generate task-based zero-shot classifiers, we train a hypernetwork that receives class descriptions and outputs a multi-class model. The hypernetwork is designed to be equivariant with respect to the set of descriptions and the classification layer, thus obeying the symmetries of the problem and improving generalization. Our approach generates non-linear classifiers and can handle rich textual descriptions. We evaluate this approach in a series of zero-shot classification tasks, for image, point-cloud, and action recognition, using a range of text descriptions: From single words to rich descriptions. Our results demonstrate strong improvements over previous approaches, showing that zero-shot learning can be applied with little training data. Furthermore, we conduct an analysis with foundational vision and language models, demonstrating that they struggle to generalize when describing what attributes the class lacks.
Authors: Razvan-George Pasca, Alexey Gavryushin, Muhammad Hamza, Yen-Ling Kuo, Kaichun Mo, Luc Van Gool, Otmar Hilliges, Xi Wang
Abstract: We study object interaction anticipation in egocentric videos. This task requires an understanding of the spatio-temporal context formed by past actions on objects, coined action context. We propose TransFusion, a multimodal transformer-based architecture. It exploits the representational power of language by summarizing the action context. TransFusion leverages pre-trained image captioning and vision-language models to extract the action context from past video frames. This action context together with the next video frame is processed by the multimodal fusion module to forecast the next object interaction. Our model enables more efficient end-to-end learning. The large pre-trained language models add common sense and a generalisation capability. Experiments on Ego4D and EPIC-KITCHENS-100 show the effectiveness of our multimodal fusion model. They also highlight the benefits of using language-based context summaries in a task where vision seems to suffice. Our method outperforms state-of-the-art approaches by 40.4% in relative terms in overall mAP on the Ego4D test set. We validate the effectiveness of TransFusion via experiments on EPIC-KITCHENS-100. Video and code are available at https://eth-ait.github.io/transfusion-proj/.
Authors: Xiao Li, Wei Zhang, Yining Liu, Zhanhao Hu, Bo Zhang, Xiaolin Hu
Abstract: Deep Neural Networks (DNNs) are known to be susceptible to adversarial attacks. Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero-shot adversarial robustness an open question. In this work, we investigate this domain by leveraging the recent advances in large vision-language models, such as CLIP, to introduce zero-shot adversarial robustness to DNNs. We propose LAAT, a Language-driven, Anchor-based Adversarial Training strategy. LAAT utilizes the features of a text encoder for each category as fixed anchors (normalized feature embeddings) for each category, which are then employed for adversarial training. By leveraging the semantic consistency of the text encoders, LAAT aims to enhance the adversarial robustness of the image model on novel categories. However, naively using text encoders leads to poor results. Through analysis, we identified the issue to be the high cosine similarity between text encoders. We then design an expansion algorithm and an alignment cross-entropy loss to alleviate the problem. Our experimental results demonstrated that LAAT significantly improves zero-shot adversarial robustness over state-of-the-art methods. LAAT has the potential to enhance adversarial robustness by large-scale multimodal models, especially when labeled data is unavailable during training.
Authors: Shay Dekel, Yosi Keller, Martin Cadik
Abstract: The estimation of large and extreme image rotation plays a key role in multiple computer vision domains, where the rotated images are related by a limited or a non-overlapping field of view. Contemporary approaches apply convolutional neural networks to compute a 4D correlation volume to estimate the relative rotation between image pairs. In this work, we propose a cross-attention-based approach that utilizes CNN feature maps and a Transformer-Encoder, to compute the cross-attention between the activation maps of the image pairs, which is shown to be an improved equivalent of the 4D correlation volume, used in previous works. In the suggested approach, higher attention scores are associated with image regions that encode visual cues of rotation. Our approach is end-to-end trainable and optimizes a simple regression loss. It is experimentally shown to outperform contemporary state-of-the-art schemes when applied to commonly used image rotation datasets and benchmarks, and establishes a new state-of-the-art accuracy on these datasets. We make our code publicly available.
Authors: Qin Liu, Meng Zheng, Benjamin Planche, Zhongpai Gao, Terrence Chen, Marc Niethammer, Ziyan Wu
Abstract: Automatic medical volume segmentation often lacks clinical accuracy, necessitating further refinement. In this work, we interactively approach medical volume segmentation via two decoupled modules: interaction-to-segmentation and segmentation propagation. Given a medical volume, a user first segments a slice (or several slices) via the interaction module and then propagates the segmentation(s) to the remaining slices. The user may repeat this process multiple times until a sufficiently high volume segmentation quality is achieved. However, due to the lack of human correction during propagation, segmentation errors are prone to accumulate in the intermediate slices and may lead to sub-optimal performance. To alleviate this issue, we propose a simple yet effective cycle consistency loss that regularizes an intermediate segmentation by referencing the accurate segmentation in the starting slice. To this end, we introduce a backward segmentation path that propagates the intermediate segmentation back to the starting slice using the same propagation network. With cycle consistency training, the propagation network is better regularized than in standard forward-only training approaches. Evaluation results on challenging AbdomenCT-1K and OAI-ZIB datasets demonstrate the effectiveness of our method.
Authors: Tiankai Hang, Shuyang Gu, Chen Li, Jianmin Bao, Dong Chen, Han Hu, Xin Geng, Baining Guo
Abstract: Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting optimization directions between timesteps. To address this issue, we treat the diffusion training as a multi-task learning problem, and introduce a simple yet effective approach referred to as Min-SNR-$\gamma$. This method adapts loss weights of timesteps based on clamped signal-to-noise ratios, which effectively balances the conflicts among timesteps. Our results demonstrate a significant improvement in converging speed, 3.4$\times$ faster than previous weighting strategies. It is also more effective, achieving a new record FID score of 2.06 on the ImageNet $256\times256$ benchmark using smaller architectures than that employed in previous state-of-the-art. The code is available at https://github.com/TiankaiHang/Min-SNR-Diffusion-Training.
URLs: https://github.com/TiankaiHang/Min-SNR-Diffusion-Training.
Authors: Arushi Rai, Adriana Kovashka
Abstract: The use of large-scale vision-language datasets is limited for object detection due to the negative impact of label noise on localization. Prior methods have shown how such large-scale datasets can be used for pretraining, which can provide initial signal for localization, but is insufficient without clean bounding-box data for at least some categories. We propose a technique to "vet" labels extracted from noisy captions, and use them for weakly-supervised object detection (WSOD), without any bounding boxes. We analyze and annotate the types of label noise in captions in our Caption Label Noise dataset, and train a classifier that predicts if an extracted label is actually present in the image or not. Our classifier generalizes across dataset boundaries and across categories. We compare the classifier to nine baselines on five datasets, and demonstrate that it can improve WSOD without label vetting by 30% (31.2 to 40.5 mAP when evaluated on PASCAL VOC). See dataset at: https://github.com/arushirai1/CLaNDataset.
Authors: Kunchang Li, Yali Wang, Yizhuo Li, Yi Wang, Yinan He, Limin Wang, Yu Qiao
Abstract: Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-level reconstruction poses convergence difficulties and conflicts with high-level cross-modal alignment. This paper proposes a training-efficient method for temporal-sensitive VFMs that integrates the benefits of existing methods. To increase data efficiency, we mask out most of the low-semantics video tokens, but selectively align the unmasked tokens with IFM, which serves as the UnMasked Teacher (UMT). By providing semantic guidance, our method enables faster convergence and multimodal friendliness. With a progressive pre-training framework, our model can handle various tasks including scene-related, temporal-related, and complex video-language understanding. Using only public sources for pre-training in 6 days on 32 A100 GPUs, our scratch-built ViT-L/16 achieves state-of-the-art performances on various video tasks. The code and models will be released at https://github.com/OpenGVLab/unmasked_teacher.
Authors: Yuanhao Xiong, Long Zhao, Boqing Gong, Ming-Hsuan Yang, Florian Schroff, Ting Liu, Cho-Jui Hsieh, Liangzhe Yuan
Abstract: Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of importance to downstream tasks requiring temporal localization and semantic reasoning. A powerful model is expected to be capable of capturing region-object correspondences and recognizing scene changes in a video clip, reflecting spatial and temporal granularity, respectively. To strengthen model's understanding into such fine-grained details, we propose a simple yet effective video-language modeling framework, S-ViLM, by exploiting the intrinsic structures of these two modalities. It includes two novel designs, inter-clip spatial grounding and intra-clip temporal grouping, to promote learning region-object alignment and temporal-aware features, simultaneously. Comprehensive evaluations demonstrate that S-ViLM performs favorably against existing approaches in learning more expressive representations. Specifically, S-ViLM surpasses the state-of-the-art methods substantially on four representative downstream tasks, covering text-video retrieval, video question answering, video action recognition, and temporal action localization.
Authors: Ntumba Elie Nsampi, Adarsh Djeacoumar, Hans-Peter Seidel, Tobias Ritschel, Thomas Leimk\"uhler
Abstract: Neural fields are evolving towards a general-purpose continuous representation for visual computing. Yet, despite their numerous appealing properties, they are hardly amenable to signal processing. As a remedy, we present a method to perform general continuous convolutions with general continuous signals such as neural fields. Observing that piecewise polynomial kernels reduce to a sparse set of Dirac deltas after repeated differentiation, we leverage convolution identities and train a repeated integral field to efficiently execute large-scale convolutions. We demonstrate our approach on a variety of data modalities and spatially-varying kernels.
Authors: Chen Zhao, Wei-Ling Cai, Zheng Yuan
Abstract: Existing image-to-image (I2I) translation methods achieve state-of-the-art performance by incorporating the patch-wise contrastive learning into Generative Adversarial Networks. However, patch-wise contrastive learning only focuses on the local content similarity but neglects the global structure constraint, which affects the quality of the generated images. In this paper, we propose a new unpaired I2I translation framework based on dual contrastive regularization and spectral normalization, namely SN-DCR. To maintain consistency of the global structure and texture, we design the dual contrastive regularization using different deep feature spaces respectively. In order to improve the global structure information of the generated images, we formulate a semantic contrastive loss to make the global semantic structure of the generated images similar to the real images from the target domain in the semantic feature space. We use Gram Matrices to extract the style of texture from images. Similarly, we design a style contrastive loss to improve the global texture information of the generated images. Moreover, to enhance the stability of the model, we employ the spectral normalized convolutional network in the design of our generator. We conduct comprehensive experiments to evaluate the effectiveness of SN-DCR, and the results prove that our method achieves SOTA in multiple tasks.
Authors: Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi
Abstract: Contrastive Language-Image Pre-training (CLIP) has become the standard for learning cross-modal representations between images and text. Efforts to improve its capabilities typically demand the collection of additional data and retraining with new loss functions. While effective, the added requirements limit their practical use due to the increased resource and time investments needed. In this work, we present HELIP, a cost-effective strategy tailored to enhance the performance of existing CLIP models without the need for training a model from scratch or collecting additional data. Our method allows for effortless integration with existing models' training pipelines, providing an instant boost by training them with selected challenging text-image pairs from their original training datasets. HELIP treats each text-image pair as a single point in the joint vision-language space, identifying those in close proximity as hard pairs. By incorporating the challenging data, pre-trained CLIP models are refined using both the traditional contrastive loss and the newly introduced hard negative margin loss, ensuring the challenging data is fully utilized. On comprehensive benchmarks, HELIP consistently boosts existing models to achieve leading performance. In particular, it improves the zero-shot classification accuracy on ImageNet for SLIP models pre-trained on CC3M, CC12M and YFCC15M datasets. The improvements are 3.05%, 4.47%, and 10.1% respectively, achieved within two epochs of training. In addition, across fine-grained classification datasets, HELIP improves the zero-shot performance of pre-trained CLIP and SLIP by an average of 8.4% and 18.6%, and their linear probe performance by an average of 9.5% and 3.0%.
Authors: Shunxin Wang, Raymond Veldhuis, Christoph Brune, Nicola Strisciuglio
Abstract: The performance of computer vision models are susceptible to unexpected changes in input images, known as common corruptions (e.g. noise, blur, illumination changes, etc.), that can hinder their reliability when deployed in real scenarios. These corruptions are not always considered to test model generalization and robustness. In this survey, we present a comprehensive overview of methods that improve the robustness of computer vision models against common corruptions. We categorize methods into four groups based on the model part and training method addressed: data augmentation, representation learning, knowledge distillation, and network components. We also cover indirect methods for generalization and mitigation of shortcut learning, potentially useful for corruption robustness. We release a unified benchmark framework to compare robustness performance on several datasets, and address the inconsistencies of evaluation in the literature. We provide an experimental overview of the base corruption robustness of popular vision backbones, and show that corruption robustness does not necessarily scale with model size. The very large models (above 100M parameters) gain negligible robustness, considering the increased computational requirements. To achieve generalizable and robust computer vision models, we foresee the need of developing new learning strategies to efficiently exploit limited data and mitigate unwanted or unreliable learning behaviors.
Authors: Feifei Shao, Yawei Luo, Lei Chen, Ping Liu, Wei Yang, Yi Yang, Jun Xiao
Abstract: Contemporary weakly-supervised object localization (WSOL) methods have primarily focused on addressing the challenge of localizing the most discriminative region while largely overlooking the relatively less explored issue of biased activation -- incorrectly spotlighting co-occurring background with the foreground feature. In this paper, we conduct a thorough causal analysis to investigate the origins of biased activation. Based on our analysis, we attribute this phenomenon to the presence of co-occurring background confounders. Building upon this profound insight, we introduce a pioneering paradigm known as Counterfactual Co-occurring Learning (CCL), meticulously engendering counterfactual representations by adeptly disentangling the foreground from the co-occurring background elements. Furthermore, we propose an innovative network architecture known as Counterfactual-CAM. This architecture seamlessly incorporates a perturbation mechanism for counterfactual representations into the vanilla CAM-based model. By training the WSOL model with these perturbed representations, we guide the model to prioritize the consistent foreground content while concurrently reducing the influence of distracting co-occurring backgrounds. To the best of our knowledge, this study represents the initial exploration of this research direction. Our extensive experiments conducted across multiple benchmarks validate the effectiveness of the proposed Counterfactual-CAM in mitigating biased activation.
Authors: Ibrahim Ethem Hamamci, Sezgin Er, Anjany Sekuboyina, Enis Simsar, Alperen Tezcan, Ayse Gulnihan Simsek, Sevval Nil Esirgun, Furkan Almas, Irem Dogan, Muhammed Furkan Dasdelen, Chinmay Prabhakar, Hadrien Reynaud, Sarthak Pati, Christian Bluethgen, Mehmet Kemal Ozdemir, Bjoern Menze
Abstract: GenerateCT, the first approach to generating 3D medical imaging conditioned on free-form medical text prompts, incorporates a text encoder and three key components: a novel causal vision transformer for encoding 3D CT volumes, a text-image transformer for aligning CT and text tokens, and a text-conditional super-resolution diffusion model. Given the absence of directly comparable methods in 3D medical imaging, we established baselines with cutting-edge methods to demonstrate our method's effectiveness. GenerateCT significantly outperforms these methods across all key metrics. Importantly, we explored GenerateCT's clinical applications by evaluating its utility in a multi-abnormality classification task. First, we established a baseline by training a multi-abnormality classifier on our real dataset. To further assess the model's generalization to external datasets and its performance with unseen prompts in a zero-shot scenario, we employed an external dataset to train the classifier, setting an additional benchmark. We conducted two experiments in which we doubled the training datasets by synthesizing an equal number of volumes for each set using GenerateCT. The first experiment demonstrated an 11% improvement in the AP score when training the classifier jointly on real and generated volumes. The second experiment showed a 7% improvement when training on both real and generated volumes based on unseen prompts. Moreover, GenerateCT enables the scaling of synthetic training datasets to arbitrary sizes. As an example, we generated 100,000 3D CT volumes, fivefold the number in our real dataset, and trained the classifier exclusively on these synthetic volumes. Impressively, this classifier surpassed the performance of the one trained on all available real data by a margin of 8%. Lastly, domain experts evaluated the generated volumes, confirming a high degree of alignment with the text prompt.
Authors: Pinxue Guo, Tony Huang, Peiyang He, Xuefeng Liu, Tianjun Xiao, Zhaoyu Chen, Wenqiang Zhang
Abstract: Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect, segment, and track arbitrary object categories in a video, without being constrained to categories seen during training. In this work, we propose an OpenVIS framework called InstFormer that achieves powerful open vocabulary capability through lightweight fine-tuning on a limited-category labeled dataset. Specifically, InstFormer comes in three steps a) Open-world Mask Proposal: we utilize a query-based transformer, which is encouraged to propose all potential object instances, to obtain class-agnostic instance masks; b) Open-vocabulary Instance Representation and Classification: we propose InstCLIP, adapted from pre-trained CLIP with Instance Guidance Attention. InstCLIP generates the instance token capable of representing each open-vocabulary instance. These instance tokens not only enable open-vocabulary classification for multiple instances with a single CLIP forward pass but have also been proven effective for subsequent open-vocabulary instance tracking. c) Rollout Association: we introduce a class-agnostic rollout tracker to predict rollout tokens from the tracking tokens of previous frames to enable open-vocabulary instance association across frames in the video. The experimental results demonstrate the proposed InstFormer achieve state-of-the-art capabilities on a comprehensive OpenVIS evaluation benchmark, while also achieves competitive performance in fully supervised VIS task.
Authors: Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, Ping Luo
Abstract: Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a "painter" for depicting a particular textual concept onto a specified image region at a diffusion timestep. Comprehensive experiments reveal that RAPHAEL outperforms recent cutting-edge models, such as Stable Diffusion, ERNIE-ViLG 2.0, DeepFloyd, and DALL-E 2, in terms of both image quality and aesthetic appeal. Firstly, RAPHAEL exhibits superior performance in switching images across diverse styles, such as Japanese comics, realism, cyberpunk, and ink illustration. Secondly, a single model with three billion parameters, trained on 1,000 A100 GPUs for two months, achieves a state-of-the-art zero-shot FID score of 6.61 on the COCO dataset. Furthermore, RAPHAEL significantly surpasses its counterparts in human evaluation on the ViLG-300 benchmark. We believe that RAPHAEL holds the potential to propel the frontiers of image generation research in both academia and industry, paving the way for future breakthroughs in this rapidly evolving field. More details can be found on a webpage: https://raphael-painter.github.io/.
Authors: Junzhe Zhu, Peiye Zhuang, Sanmi Koyejo
Abstract: The advancements in automatic text-to-3D generation have been remarkable. Most existing methods use pre-trained text-to-image diffusion models to optimize 3D representations like Neural Radiance Fields (NeRFs) via latent-space denoising score matching. Yet, these methods often result in artifacts and inconsistencies across different views due to their suboptimal optimization approaches and limited understanding of 3D geometry. Moreover, the inherent constraints of NeRFs in rendering crisp geometry and stable textures usually lead to a two-stage optimization to attain high-resolution details. This work proposes holistic sampling and smoothing approaches to achieve high-quality text-to-3D generation, all in a single-stage optimization. We compute denoising scores in the text-to-image diffusion model's latent and image spaces. Instead of randomly sampling timesteps (also referred to as noise levels in denoising score matching), we introduce a novel timestep annealing approach that progressively reduces the sampled timestep throughout optimization. To generate high-quality renderings in a single-stage optimization, we propose regularization for the variance of z-coordinates along NeRF rays. To address texture flickering issues in NeRFs, we introduce a kernel smoothing technique that refines importance sampling weights coarse-to-fine, ensuring accurate and thorough sampling in high-density regions. Extensive experiments demonstrate the superiority of our method over previous approaches, enabling the generation of highly detailed and view-consistent 3D assets through a single-stage training process.
Authors: Changcheng Xiao, Qiong Cao, Yujie Zhong, Long Lan, Xiang Zhang, Zhigang Luo, Dacheng Tao
Abstract: Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous appearance and heterogeneous motion remains a challenge. This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT. In this context, we introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor that relies solely on object trajectory information. This predictor comprehensively integrates two levels of granularity in motion features to enhance the modeling of temporal dynamics and facilitate precise future motion prediction for individual objects. Specifically, the proposed approach adopts a self-attention mechanism to capture token-level information and a Dynamic MLP layer to model channel-level features. MotionTrack is a simple, online tracking approach. Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT, characterized by highly complex object motion.
Authors: Yan Luo, Yu Tian, Min Shi, Louis R. Pasquale, Lucy Q. Shen, Nazlee Zebardast, Tobias Elze, Mengyu Wang
Abstract: Fairness (also known as equity interchangeably) in machine learning is important for societal well-being, but limited public datasets hinder its progress. Currently, no dedicated public medical datasets with imaging data for fairness learning are available, though minority groups suffer from more health issues. To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset with both 2D and 3D imaging data and balanced racial groups for glaucoma detection. Glaucoma is the leading cause of irreversible blindness globally with Blacks having doubled glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature importance between different identity groups. Our FIN approach is compared with various the-state-of-the-art fairness learning methods with superior performance in the racial, gender, and ethnicity fairness tasks with 2D and 3D imaging data, which demonstrate the utilities of our dataset Harvard-GF for fairness learning. To facilitate fairness comparisons between different models, we propose an equity-scaled performance measure, which can be flexibly used to compare all kinds of performance metrics in the context of fairness. The dataset and code are publicly accessible via \url{https://ophai.hms.harvard.edu/datasets/harvard-glaucoma-fairness-3300-samples/}.
URLs: https://ophai.hms.harvard.edu/datasets/harvard-glaucoma-fairness-3300-samples/
Authors: Nicolae-Catalin Ristea, Florinel-Alin Croitoru, Radu Tudor Ionescu, Marius Popescu, Fahad Shahbaz Khan, Mubarak Shah
Abstract: We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First, we introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. Second, we integrate a teacher decoder and a student decoder into our architecture, leveraging the discrepancy between the outputs given by the two decoders to improve anomaly detection. Third, we generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames (without anomalies) and the corresponding pixel-level anomaly maps. Our design leads to an efficient and effective model, as demonstrated by the extensive experiments carried out on four benchmarks: Avenue, ShanghaiTech, UBnormal and UCSD Ped2. The empirical results show that our model achieves an excellent trade-off between speed and accuracy, obtaining competitive AUC scores, while processing 1655 FPS. Hence, our model is between 8 and 70 times faster than competing methods. We also conduct an ablation study to justify our design. Our code is freely available at: https://github.com/ristea/aed-mae.
Authors: Rosario Leonardi, Francesco Ragusa, Antonino Furnari, Giovanni Maria Farinella
Abstract: In this paper, we tackle the problem of Egocentric Human-Object Interaction (EHOI) detection in an industrial setting. To overcome the lack of public datasets in this context, we propose a pipeline and a tool for generating synthetic images of EHOIs paired with several annotations and data signals (e.g., depth maps or segmentation masks). Using the proposed pipeline, we present EgoISM-HOI a new multimodal dataset composed of synthetic EHOI images in an industrial environment with rich annotations of hands and objects. To demonstrate the utility and effectiveness of synthetic EHOI data produced by the proposed tool, we designed a new method that predicts and combines different multimodal signals to detect EHOIs in RGB images. Our study shows that exploiting synthetic data to pre-train the proposed method significantly improves performance when tested on real-world data. Moreover, to fully understand the usefulness of our method, we conducted an in-depth analysis in which we compared and highlighted the superiority of the proposed approach over different state-of-the-art class-agnostic methods. To support research in this field, we publicly release the datasets, source code, and pre-trained models at https://iplab.dmi.unict.it/egoism-hoi.
Authors: Shaoshuai Shi, Li Jiang, Dengxin Dai, Bernt Schiele
Abstract: Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions. However, this task is challenging due to the diverse behaviors of traffic participants and complex environmental contexts. In this paper, we propose Motion TRansformer (MTR) frameworks to address these challenges. The initial MTR framework utilizes a transformer encoder-decoder structure with learnable intention queries, enabling efficient and accurate prediction of future trajectories. By customizing intention queries for distinct motion modalities, MTR improves multimodal motion prediction while reducing reliance on dense goal candidates. The framework comprises two essential processes: global intention localization, identifying the agent's intent to enhance overall efficiency, and local movement refinement, adaptively refining predicted trajectories for improved accuracy. Moreover, we introduce an advanced MTR++ framework, extending the capability of MTR to simultaneously predict multimodal motion for multiple agents. MTR++ incorporates symmetric context modeling and mutually-guided intention querying modules to facilitate future behavior interaction among multiple agents, resulting in scene-compliant future trajectories. Extensive experimental results demonstrate that the MTR framework achieves state-of-the-art performance on the highly-competitive motion prediction benchmarks, while the MTR++ framework surpasses its precursor, exhibiting enhanced performance and efficiency in predicting accurate multimodal future trajectories for multiple agents.
Authors: Huixuan Zhang, Xiaojun Wan
Abstract: Hyperbole, or exaggeration, is a common linguistic phenomenon. The detection of hyperbole is an important part of understanding human expression. There have been several studies on hyperbole detection, but most of which focus on text modality only. However, with the development of social media, people can create hyperbolic expressions with various modalities, including text, images, videos, etc. In this paper, we focus on multimodal hyperbole detection. We create a multimodal detection dataset from Weibo (a Chinese social media) and carry out some studies on it. We treat the text and image from a piece of weibo as two modalities and explore the role of text and image for hyperbole detection. Different pre-trained multimodal encoders are also evaluated on this downstream task to show their performance. Besides, since this dataset is constructed from five different topics, we also evaluate the cross-domain performance of different models. These studies can serve as a benchmark and point out the direction of further study on multimodal hyperbole detection.
Authors: Nati Ofir, Jean-Christophe Nebel
Abstract: Multispectral imaging is an important task of image processing and computer vision, which is especially relevant to applications such as dehazing or object detection. With the development of the RGBT (RGB & Thermal) sensor, the problem of visible (RGB) to Near Infrared (NIR) image fusion has become particularly timely. Indeed, while visible images see color, but suffer from noise, haze, and clouds, the NIR channel captures a clearer picture. The proposed approach fuses these two channels by training a Convolutional Neural Network by Self Supervised Learning (SSL) on a single example. For each such pair, RGB and NIR, the network is trained for seconds to deduce the final fusion. The SSL is based on the comparison of the Structure of Similarity and Edge-Preservation losses, where the labels for the SSL are the input channels themselves. This fusion preserves the relevant detail of each spectral channel without relying on a heavy training process. Experiments demonstrate that the proposed approach achieves similar or better qualitative and quantitative multispectral fusion results than other state-of-the-art methods that do not rely on heavy training and/or large datasets.
Authors: Jianqi Chen, Yilan Zhang, Zhengxia Zou, Keyan Chen, Zhenwei Shi
Abstract: We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training expenses and often struggle with generalization to unseen images. To this end, we introduce a fully modularized framework inspired by human behavior. Leveraging the reasoning capabilities of recent foundation models in language and vision, our approach comprises three main stages. Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image. Subsequently, these descriptions guide the foreground harmonization direction of a text-to-image generative model (T2I). We refine text embeddings for enhanced representation of imaging conditions and employ self-attention and edge maps for structure preservation. Following each harmonization iteration, an evaluator determines whether to conclude or modify the harmonization direction. The resulting framework, mirroring human behavior, achieves harmonious results without the need for extensive training. We present compelling visual results across diverse scenes and objects, along with a user study validating the effectiveness of our approach.
Authors: Ranjan Sapkota, Dawood Ahmed, Manoj Karkee
Abstract: This research investigated the role of artificial intelligence (AI), specifically the DALL.E model by OpenAI, in advancing data generation and visualization techniques in agriculture. DALL.E, an advanced AI image generator, works alongside ChatGPT's language processing to transform text descriptions and image clues into realistic visual representations of the content. The study uses both approaches of image generation: text-to-image and image-to-image (variation). Two types of datasets depicting fruit crops environments and crop vs weed environment were generated. These AI-generated images were then compared against ground truth images captured by sensors in real agricultural fields. The comparison was based on Peak Signal-to-Noise Ratio (PSNR) and Feature Similarity Index (FSIM) metrics. For fruit crops, image-to-image generation exhibited a 5.78% increase in average PSNR over text-to-image methods, signifying superior image clarity and quality. However, this method also resulted in a 10.23% decrease in average FSIM, indicating a diminished structural and textural similarity to the original images. Conversely, in crop vs weed scenarios, image-to-image generation showed a 3.77% increase in PSNR, demonstrating enhanced image precision, but experienced a slight 0.76% decrease in FSIM, suggesting a minor reduction in feature similarity. Similar to these measures, human evaluation also showed that images generated using image-to-image-based method were more realistic compared to those generated with text-to-image approach. The results highlighted DALL.E's potential in generating realistic agricultural image datasets and thus accelerating the development and adoption of precision agricultural solutions.
Authors: Linchao He, Hongyu Yan, Mengting Luo, Hongjie Wu, Kunming Luo, Wang Wang, Wenchao Du, Hu Chen, Hongyu Yang, Yi Zhang, Jiancheng Lv
Abstract: Diffusion models have recently been recognised as efficient inverse problem solvers due to their ability to produce high-quality reconstruction results without relying on pairwise data training. Existing diffusion-based solvers utilize Gradient Descent strategy to get a optimal sample solution. However, these solvers only calculate the current gradient and have not utilized any history information of sampling process, thus resulting in unstable optimization progresses and suboptimal solutions. To address this issue, we propose to utilize the history information of the diffusion-based inverse solvers. In this paper, we first prove that, in previous work, using the gradient descent method to optimize the data fidelity term is convergent. Building on this, we introduce the incorporation of historical gradients into this optimization process, termed History Gradient Update (HGU). We also provide theoretical evidence that HGU ensures the convergence of the entire algorithm. It's worth noting that HGU is applicable to both pixel-based and latent-based diffusion model solvers. Experimental results demonstrate that, compared to previous sampling algorithms, sampling algorithms with HGU achieves state-of-the-art results in medical image reconstruction, surpassing even supervised learning methods. Additionally, it achieves competitive results on natural images.
Authors: Pujin Cheng, Li Lin, Junyan Lyu, Yijin Huang, Wenhan Luo, Xiaoying Tang
Abstract: Contrastive learning based vision-language joint pre-training has emerged as a successful representation learning strategy. In this paper, we present a prototype representation learning framework incorporating both global and local alignment between medical images and reports. In contrast to standard global multi-modality alignment methods, we employ a local alignment module for fine-grained representation. Furthermore, a cross-modality conditional reconstruction module is designed to interchange information across modalities in the training phase by reconstructing masked images and reports. For reconstructing long reports, a sentence-wise prototype memory bank is constructed, enabling the network to focus on low-level localized visual and high-level clinical linguistic features. Additionally, a non-auto-regressive generation paradigm is proposed for reconstructing non-sequential reports. Experimental results on five downstream tasks, including supervised classification, zero-shot classification, image-to-text retrieval, semantic segmentation, and object detection, show the proposed method outperforms other state-of-the-art methods across multiple datasets and under different dataset size settings. The code is available at https://github.com/QtacierP/PRIOR.
Authors: Enxin Song, Wenhao Chai, Guanhong Wang, Yucheng Zhang, Haoyang Zhou, Feiyang Wu, Haozhe Chi, Xun Guo, Tian Ye, Yanting Zhang, Yan Lu, Jenq-Neng Hwang, Gaoang Wang
Abstract: Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method.
Authors: Yanyan Li, Ke Chen, Chong Chen, Jianping Zhang
Abstract: Diffeomorphic registration is a widely used technique for finding a smooth and invertible transformation between two coordinate systems, which are measured using template and reference images. The point-wise volume-preserving constraint $\det(\nabla\bm{\varphi}(\bm{x})) =1$ is effective in some cases, but may be too restrictive in others, especially when local deformations are relatively large. This can result in poor matching when enforcing large local deformations. In this paper, we propose a new bi-variant diffeomorphic image registration model that introduces a soft constraint on the Jacobian equation $\det(\nabla\bm{\varphi}(\bm{x})) = f(\bm{x}) > 0$. This allows local deformations to shrink and grow within a flexible range $0<\kappa_{m}<\det(\nabla\bm{\varphi}(\bm{x}))<\kappa_{M}$. The Jacobian determinant of transformation is explicitly controlled by optimizing the relaxation function $f(\bm{x})$. To prevent deformation folding and improve the smoothness of the transformation, a positive constraint is imposed on the optimization of the relaxation function $f(\bm{x})$, and a regularizer is used to ensure the smoothness of $f(\bm{x})$. Furthermore, the positivity constraint ensures that $f(\bm{x})$ is as close to one as possible, which helps to achieve a volume-preserving transformation on average. We also analyze the existence of the minimizer for the variational model and propose a penalty-splitting algorithm with a multilevel strategy to solve this model. Numerical experiments demonstrate the convergence of the proposed algorithm and show that the positivity constraint can effectively control the range of relative volume without compromising the accuracy of the registration. Moreover, the proposed model generates diffeomorphic maps for large local deformations and outperforms several existing registration models in terms of performance.
Authors: Chunming He, Kai Li, Yachao Zhang, Yulun Zhang, Zhenhua Guo, Xiu Li, Martin Danelljan, Fisher Yu
Abstract: Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD detectors still struggle to obtain precise results in some challenging cases. To handle this problem, we draw inspiration from the prey-vs-predator game that leads preys to develop better camouflage and predators to acquire more acute vision systems and develop algorithms from both the prey side and the predator side. On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect. Camouflageator trains the generator and detector in an adversarial way such that the enhanced auxiliary generator helps produce a stronger detector. On the predator side, we introduce a novel COD method, called Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged feature coherence module to excavate the internal coherence of camouflaged objects, striving to obtain more complete segmentation results. Additionally, ICEG proposes a novel edge-guided separated calibration module to remove false predictions to avoid obtaining ambiguous boundaries. Extensive experiments show that ICEG outperforms existing COD detectors and Camouflageator is flexible to improve various COD detectors, including ICEG, which brings state-of-the-art COD performance.
Authors: Zhenhua Xu, Kwan-Yee. K. Wong, Hengshuang Zhao
Abstract: Vectorized high-definition (HD) maps contain detailed information about surrounding road elements, which are crucial for various downstream tasks in modern autonomous vehicles, such as motion planning and vehicle control. Recent works attempt to directly detect the vectorized HD map as a point set prediction task, achieving notable detection performance improvements. However, these methods usually overlook and fail to analyze the important inner-instance correlations between predicted points, impeding further advancements. To address this issue, we investigate the utilization of inner-instance information for vectorized high-definition mapping through transformers, and propose a powerful system named $\textbf{InsMapper}$, which effectively harnesses inner-instance information with three exquisite designs, including hybrid query generation, inner-instance query fusion, and inner-instance feature aggregation. The first two modules can better initialize queries for line detection, while the last one refines predicted line instances. InsMapper is highly adaptable and can be seamlessly modified to align with the most recent HD map detection frameworks. Extensive experimental evaluations are conducted on the challenging NuScenes and Argoverse 2 datasets, where InsMapper surpasses the previous state-of-the-art method, demonstrating its effectiveness and generality. The project page for this work is available at https://tonyxuqaq.github.io/InsMapper/ .
Authors: Xinghong Liu, Yi Zhou, Tao Zhou, Chun-Mei Feng, Ling Shao
Abstract: Universal domain adaptation (UniDA) aims to address domain and category shifts across data sources. Recently, due to more stringent data restrictions, researchers have introduced source-free UniDA (SF-UniDA). SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain. However, existing SF-UniDA methods still require an extensive quantity of labeled source samples to train a source model, resulting in significant labeling costs. To tackle this issue, we present a novel plug-and-play classifier-oriented calibration (COCA) method. COCA, which exploits textual prototypes, is designed for the source models based on few-shot learning with vision-language models (VLMs). It endows the VLM-powered few-shot learners, which are built for closed-set classification, with the unknown-aware ability to distinguish common and unknown classes in the SF-UniDA scenario. Crucially, COCA is a new paradigm to tackle SF-UniDA challenges based on VLMs, which focuses on classifier instead of image encoder optimization. Experiments show that COCA outperforms state-of-the-art UniDA and SF-UniDA models.
Authors: Haiwen Diao, Bo Wan, Ying Zhang, Xu Jia, Huchuan Lu, Long Chen
Abstract: Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on the more valuable memory-efficient characteristic. In this paper, we argue that the scalability, adaptability, and generalizability of state-of-the-art methods are hindered by structural dependency and pertinency on specific pre-trained backbones. To this end, we propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT), to mitigate these weaknesses. Specifically, we facilitate the transfer process via a lightweight and learnable parallel network, which consists of: 1) A parallel interaction module that decouples the sequential connections and processes the intermediate activations detachedly from the pre-trained network. 2) A confidence aggregation module that learns optimal strategies adaptively for integrating cross-layer features. We evaluate UniPT with different backbones (e.g., T5, VSE$\infty$, CLIP4Clip, Clip-ViL, and MDETR) on various vision-and-language and pure NLP tasks. Extensive ablations on 18 datasets have validated that UniPT can not only dramatically reduce memory consumption and outperform the best competitor, but also achieve competitive performance over other plain PETL methods with lower training memory overhead. Our code is publicly available at: https://github.com/Paranioar/UniPT.
Authors: Pengcheng Zhang, Xiao Bai, Jin Zheng, Xin Ning
Abstract: End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for persons earch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search.
Authors: Ahmed Rida Sekkat, Rohit Mohan, Oliver Sawade, Elmar Matthes, Abhinav Valada
Abstract: Unlike humans, who can effortlessly estimate the entirety of objects even when partially occluded, modern computer vision algorithms still find this aspect extremely challenging. Leveraging this amodal perception for autonomous driving remains largely untapped due to the lack of suitable datasets. The curation of these datasets is primarily hindered by significant annotation costs and mitigating annotator subjectivity in accurately labeling occluded regions. To address these limitations, we introduce AmodalSynthDrive, a synthetic multi-task multi-modal amodal perception dataset. The dataset provides multi-view camera images, 3D bounding boxes, LiDAR data, and odometry for 150 driving sequences with over 1M object annotations in diverse traffic, weather, and lighting conditions. AmodalSynthDrive supports multiple amodal scene understanding tasks including the introduced amodal depth estimation for enhanced spatial understanding. We evaluate several baselines for each of these tasks to illustrate the challenges and set up public benchmarking servers. The dataset is available at http://amodalsynthdrive.cs.uni-freiburg.de.
Authors: Shih-Ying Yeh, Yu-Guan Hsieh, Zhidong Gao, Bernard B W Yang, Giyeong Oh, Yanmin Gong
Abstract: Text-to-image generative models have garnered immense attention for their ability to produce high-fidelity images from text prompts. Among these, Stable Diffusion distinguishes itself as a leading open-source model in this fast-growing field. However, the intricacies of fine-tuning these models pose multiple challenges from new methodology integration to systematic evaluation. Addressing these issues, this paper introduces LyCORIS (Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion) [https://github.com/KohakuBlueleaf/LyCORIS], an open-source library that offers a wide selection of fine-tuning methodologies for Stable Diffusion. Furthermore, we present a thorough framework for the systematic assessment of varied fine-tuning techniques. This framework employs a diverse suite of metrics and delves into multiple facets of fine-tuning, including hyperparameter adjustments and the evaluation with different prompt types across various concept categories. Through this comprehensive approach, our work provides essential insights into the nuanced effects of fine-tuning parameters, bridging the gap between state-of-the-art research and practical application.
Authors: Jingqian Wu, Rongtao Xu, Zach Wood-Doughty, Changwei Wang, Shibiao Xu, Edmund Lam
Abstract: Local feature detection and description play an important role in many computer vision tasks, which are designed to detect and describe keypoints in "any scene" and "any downstream task". Data-driven local feature learning methods need to rely on pixel-level correspondence for training, which is challenging to acquire at scale, thus hindering further improvements in performance. In this paper, we propose SAMFeat to introduce SAM (segment anything model), a fundamental model trained on 11 million images, as a teacher to guide local feature learning and thus inspire higher performance on limited datasets. To do so, first, we construct an auxiliary task of Pixel Semantic Relational Distillation (PSRD), which distillates feature relations with category-agnostic semantic information learned by the SAM encoder into a local feature learning network, to improve local feature description using semantic discrimination. Second, we develop a technique called Weakly Supervised Contrastive Learning Based on Semantic Grouping (WSC), which utilizes semantic groupings derived from SAM as weakly supervised signals, to optimize the metric space of local descriptors. Third, we design an Edge Attention Guidance (EAG) to further improve the accuracy of local feature detection and description by prompting the network to pay more attention to the edge region guided by SAM. SAMFeat's performance on various tasks such as image matching on HPatches, and long-term visual localization on Aachen Day-Night showcases its superiority over previous local features. The release code is available at https://github.com/vignywang/SAMFeat.
Authors: Bianca LammIMLA, Offenburg University, Markant Services International GmbH, Janis KeuperIMLA, Offenburg University
Abstract: Entity Matching (EM) defines the task of learning to group objects by transferring semantic concepts from example groups (=entities) to unseen data. Despite the general availability of image data in the context of many EM-problems, most currently available EM-algorithms solely rely on (textual) meta data. In this paper, we introduce the first publicly available large-scale dataset for "visual entity matching", based on a production level use case in the retail domain. Using scanned advertisement leaflets, collected over several years from different European retailers, we provide a total of ~786k manually annotated, high resolution product images containing ~18k different individual retail products which are grouped into ~3k entities. The annotation of these product entities is based on a price comparison task, where each entity forms an equivalence class of comparable products. Following on a first baseline evaluation, we show that the proposed "visual entity matching" constitutes a novel learning problem which can not sufficiently be solved using standard image based classification and retrieval algorithms. Instead, novel approaches which allow to transfer example based visual equivalent classes to new data are needed to address the proposed problem. The aim of this paper is to provide a benchmark for such algorithms. Information about the dataset, evaluation code and download instructions are provided under https://www.retail-786k.org/.
Authors: Jianning Deng, Gabriel Chan, Hantao Zhong, Chris Xiaoxuan Lu
Abstract: This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple alignments on both spatial and feature levels to achieve simultaneous backbone refinement and hallucination generation. Specifically, spatial alignment is proposed to deal with the geometry discrepancy for better instance matching between LiDAR and radar. The feature alignment step further bridges the intrinsic attribute gap between the sensing modalities and stabilizes the training. The trained object detection models can deal with difficult detection cases better, even though only single-modal data is used as the input during the inference stage. Extensive experiments on the View-of-Delft (VoD) dataset show that our proposed method outperforms the state-of-the-art (SOTA) methods for both radar and LiDAR object detection while maintaining competitive efficiency in runtime.
Authors: Max Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, Wenhu Chen
Abstract: Recently, a myriad of conditional image generation and editing models have been developed to serve different downstream tasks, including text-to-image generation, text-guided image editing, subject-driven image generation, control-guided image generation, etc. However, we observe huge inconsistencies in experimental conditions: datasets, inference, and evaluation metrics - render fair comparisons difficult. This paper proposes ImagenHub, which is a one-stop library to standardize the inference and evaluation of all the conditional image generation models. Firstly, we define seven prominent tasks and curate high-quality evaluation datasets for them. Secondly, we built a unified inference pipeline to ensure fair comparison. Thirdly, we design two human evaluation scores, i.e. Semantic Consistency and Perceptual Quality, along with comprehensive guidelines to evaluate generated images. We train expert raters to evaluate the model outputs based on the proposed metrics. Our human evaluation achieves a high inter-worker agreement of Krippendorff's alpha on 76% models with a value higher than 0.4. We comprehensively evaluated a total of around 30 models and observed three key takeaways: (1) the existing models' performance is generally unsatisfying except for Text-guided Image Generation and Subject-driven Image Generation, with 74% models achieving an overall score lower than 0.5. (2) we examined the claims from published papers and found 83% of them hold with a few exceptions. (3) None of the existing automatic metrics has a Spearman's correlation higher than 0.2 except subject-driven image generation. Moving forward, we will continue our efforts to evaluate newly published models and update our leaderboard to keep track of the progress in conditional image generation.
Authors: Utsab Saha, Sawradip Saha, Tahmid Kabir, Shaikh Anowarul Fattah, Mohammad Saquib
Abstract: A person's movement or relative positioning effectively generates raw electrical signals that can be read by computing machines to apply various manipulative techniques for the classification of different human activities. In this paper, a stratified multi-structural approach based on a Residual network ensembled with Residual MobileNet is proposed, termed as FusionActNet. The proposed method involves using carefully designed Residual blocks for classifying the static and dynamic activities separately because they have clear and distinct characteristics that set them apart. These networks are trained independently, resulting in two specialized and highly accurate models. These models excel at recognizing activities within a specific superclass by taking advantage of the unique algorithmic benefits of architectural adjustments. Afterward, these two ResNets are passed through a weighted ensemble-based Residual MobileNet. Subsequently, this ensemble proficiently discriminates between a specific static and a specific dynamic activity, which were previously identified based on their distinct feature characteristics in the earlier stage. The proposed model is evaluated using two publicly accessible datasets; namely, UCI HAR and Motion-Sense. Therein, it successfully handled the highly confusing cases of data overlap. Therefore, the proposed approach achieves a state-of-the-art accuracy of 96.71% and 95.35% in the UCI HAR and Motion-Sense datasets respectively.
Authors: Anas Mahmoud, Mostafa Elhoushi, Amro Abbas, Yu Yang, Newsha Ardalani, Hugh Leather, Ari Morcos
Abstract: Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. This underscores the critical need for dataset pruning, as the quality of these datasets is strongly correlated with the performance of VLMs on downstream tasks. Using CLIPScore from a pretrained model to only train models using highly-aligned samples is one of the most successful methods for pruning. We argue that this approach suffers from multiple limitations including: false positives and negatives due to CLIP's pretraining on noisy labels. We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs. To bridge the gap between the limited diversity of generated captions and the high diversity of alternative text (alt-text), we estimate the semantic textual similarity in the embedding space of a language model pretrained on unlabeled text corpus. Using DataComp, a multimodal dataset filtering benchmark, when evaluating on 38 downstream tasks, our pruning approach, surpasses CLIPScore by 2.6\% and 1.7\% on medium and large scale respectively. In addition, on retrieval tasks, Sieve leads to a significant improvement of 2.7% and 4.5% on medium and large scale respectively.
Authors: Shuai Yang, Yukang Chen, Luozhou Wang, Shu Liu, Yingcong Chen
Abstract: Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains. However, a significant bottleneck is the necessity for whole-network computation during every step of the generative process, leading to high computational overheads. This paper presents a novel framework, Denoising Diffusion Step-aware Models (DDSM), to address this challenge. Unlike conventional approaches, DDSM employs a spectrum of neural networks whose sizes are adapted according to the importance of each generative step, as determined through evolutionary search. This step-wise network variation effectively circumvents redundant computational efforts, particularly in less critical steps, thereby enhancing the efficiency of the diffusion model. Furthermore, the step-aware design can be seamlessly integrated with other efficiency-geared diffusion models such as DDIMs and latent diffusion, thus broadening the scope of computational savings. Empirical evaluations demonstrate that DDSM achieves computational savings of 49% for CIFAR-10, 61% for CelebA-HQ, 59% for LSUN-bedroom, 71% for AFHQ, and 76% for ImageNet, all without compromising the generation quality.
Authors: Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe, Ali Cheraghian, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
Abstract: In knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill `dark knowledge' from teachers, typically exhibit inferior performance compared to feature-based methods. To bridge this gap, we present LumiNet, a novel knowledge distillation algorithm designed to enhance logit-based distillation. We introduce the concept of 'perception', aiming to calibrate logits based on the model's representation capability. This concept addresses overconfidence issues in logit-based distillation method while also introducing a novel method to distill knowledge from the teacher. It reconstructs the logits of a sample/instances by considering relationships with other samples in the batch. LumiNet excels on benchmarks like CIFAR-100, ImageNet, and MSCOCO, outperforming leading feature-based methods, e.g., compared to KD with ResNet18 and MobileNetV2 on ImageNet, it shows improvements of 1.5% and 2.05%, respectively.
Authors: Ashwini Pokle, Matthew J. Muckley, Ricky T. Q. Chen, Brian Karrer
Abstract: Solving inverse problems without any training involves using a pretrained generative model and making appropriate modifications to the generation process to avoid finetuning of the generative model. While recent methods have explored the use of diffusion models, they still require the manual tuning of many hyperparameters for different inverse problems. In this work, we propose a training-free method for solving linear inverse problems by using pretrained flow models, leveraging the simplicity and efficiency of Flow Matching models, using theoretically-justified weighting schemes, and thereby significantly reducing the amount of manual tuning. In particular, we draw inspiration from two main sources: adopting prior gradient correction methods to the flow regime, and a solver scheme based on conditional Optimal Transport paths. As pretrained diffusion models are widely accessible, we also show how to practically adapt diffusion models for our method. Empirically, our approach requires no problem-specific tuning across an extensive suite of noisy linear inverse problems on high-dimensional datasets, ImageNet-64/128 and AFHQ-256, and we observe that our flow-based method for solving inverse problems improves upon closely-related diffusion-based methods in most settings.
Authors: Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu
Abstract: Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data collection/curation costs do not justify the end application. This motivates a vendor-client paradigm, where a vendor trains a large-scale VLM and grants only input-output access to clients on a pay-per-query basis in a black-box setting. The client aims to minimize inference cost by distilling the VLM to a student model using the limited available task-specific data, and further deploying this student model in the downstream application. While naive distillation largely improves the In-Domain (ID) accuracy of the student, it fails to transfer the superior out-of-distribution (OOD) generalization of the VLM teacher using the limited available labeled images. To mitigate this, we propose Vision-Language to Vision - Align, Distill, Predict (VL2V-ADiP), which first aligns the vision and language modalities of the teacher model with the vision modality of a pre-trained student model, and further distills the aligned VLM representations to the student. This maximally retains the pre-trained features of the student, while also incorporating the rich representations of the VLM image encoder and the superior generalization of the text embeddings. The proposed approach achieves state-of-the-art results on the standard Domain Generalization benchmarks in a black-box teacher setting as well as a white-box setting where the weights of the VLM are accessible.
Authors: Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Sijia Liu, Tsung-Yi Ho
Abstract: Visual prompting (VP) is an emerging parameter-efficient fine-tuning approach to adapting pre-trained vision models to solve various downstream image-classification tasks. However, there has hitherto been little systematic study of the design space of VP and no clear benchmark for evaluating its performance. To bridge this gap, we propose AutoVP, an end-to-end expandable framework for automating VP design choices, along with 12 downstream image-classification tasks that can serve as a holistic VP-performance benchmark. Our design space covers 1) the joint optimization of the prompts; 2) the selection of pre-trained models, including image classifiers and text-image encoders; and 3) model output mapping strategies, including nonparametric and trainable label mapping. Our extensive experimental results show that AutoVP outperforms the best-known current VP methods by a substantial margin, having up to 6.7% improvement in accuracy; and attains a maximum performance increase of 27.5% compared to linear-probing (LP) baseline. AutoVP thus makes a two-fold contribution: serving both as an efficient tool for hyperparameter tuning on VP design choices, and as a comprehensive benchmark that can reasonably be expected to accelerate VP's development. The source code is available at https://github.com/IBM/AutoVP.
Authors: Sihan Xu, Ziqiao Ma, Yidong Huang, Honglak Lee, Joyce Chai
Abstract: Diffusion models (DMs) have enabled breakthroughs in image synthesis tasks but lack an intuitive interface for consistent image-to-image (I2I) translation. Various methods have been explored to address this issue, including mask-based methods, attention-based methods, and image-conditioning. However, it remains a critical challenge to enable unpaired I2I translation with pre-trained DMs while maintaining satisfying consistency. This paper introduces Cyclenet, a novel but simple method that incorporates cycle consistency into DMs to regularize image manipulation. We validate Cyclenet on unpaired I2I tasks of different granularities. Besides the scene and object level translation, we additionally contribute a multi-domain I2I translation dataset to study the physical state changes of objects. Our empirical studies show that Cyclenet is superior in translation consistency and quality, and can generate high-quality images for out-of-domain distributions with a simple change of the textual prompt. Cyclenet is a practical framework, which is robust even with very limited training data (around 2k) and requires minimal computational resources (1 GPU) to train. Project homepage: https://cyclenetweb.github.io/
Authors: Andre Ye, Sebastin Santy, Jena D. Hwang, Amy X. Zhang, Ranjay Krishna
Abstract: Computer vision often treats human perception as homogeneous: an implicit assumption that visual stimuli are perceived similarly by everyone. This assumption is reflected in the way researchers collect datasets and train vision models. By contrast, literature in cross-cultural psychology and linguistics has provided evidence that people from different cultural backgrounds observe vastly different concepts even when viewing the same visual stimuli. In this paper, we study how these differences manifest themselves in vision-language datasets and models, using language as a proxy for culture. By comparing textual descriptions generated across 7 languages for the same images, we find significant differences in the semantic content and linguistic expression. When datasets are multilingual as opposed to monolingual, descriptions have higher semantic coverage on average, where coverage is measured using scene graphs, model embeddings, and linguistic taxonomies. For example, multilingual descriptions have on average 29.9% more objects, 24.5% more relations, and 46.0% more attributes than a set of monolingual captions. When prompted to describe images in different languages, popular models (e.g. LLaVA) inherit this bias and describe different parts of the image. Moreover, finetuning models on captions from one language performs best on corresponding test data from that language, while finetuning on multilingual data performs consistently well across all test data compositions. Our work points towards the need to account for and embrace the diversity of human perception in the computer vision community.
Authors: Noa Cohen, Hila Manor, Yuval Bahat, Tomer Michaeli
Abstract: Image restoration problems are typically ill-posed in the sense that each degraded image can be restored in infinitely many valid ways. To accommodate this, many works generate a diverse set of outputs by attempting to randomly sample from the posterior distribution of natural images given the degraded input. Here we argue that this strategy is commonly of limited practical value because of the heavy tail of the posterior distribution. Consider for example inpainting a missing region of the sky in an image. Since there is a high probability that the missing region contains no object but clouds, any set of samples from the posterior would be entirely dominated by (practically identical) completions of sky. However, arguably, presenting users with only one clear sky completion, along with several alternative solutions such as airships, birds, and balloons, would better outline the set of possibilities. In this paper, we initiate the study of meaningfully diverse image restoration. We explore several post-processing approaches that can be combined with any diverse image restoration method to yield semantically meaningful diversity. Moreover, we propose a practical approach for allowing diffusion based image restoration methods to generate meaningfully diverse outputs, while incurring only negligent computational overhead. We conduct extensive user studies to analyze the proposed techniques, and find the strategy of reducing similarity between outputs to be significantly favorable over posterior sampling. Code and examples are available at https://noa-cohen.github.io/MeaningfulDiversityInIR.
Authors: Kai Li, Yupeng Deng, Yunlong Kong, Diyou Liu, Jingbo Chen, Yu Meng, Junxian Ma
Abstract: More accurate extraction of invisible building footprints from very-high-resolution (VHR) aerial images relies on roof segmentation and roof-to-footprint offset extraction. Existing state-of-the-art methods based on instance segmentation suffer from poor generalization when extended to large-scale data production and fail to achieve low-cost human interactive annotation. The latest prompt paradigms inspire us to design a promptable framework for roof and offset extraction, which transforms end-to-end algorithms into promptable methods. Within this framework, we propose a novel Offset-Building Model (OBM). To rigorously evaluate the algorithm's capabilities, we introduce a prompt-based evaluation method, where our model reduces offset errors by 16.6% and improves roof Intersection over Union (IoU) by 10.8% compared to other models. Leveraging the common patterns in predicting offsets, we propose Distance-NMS (DNMS) algorithms, enabling the model to further reduce offset vector loss by 6.5%. To further validate the generalization of models, we tested them using a new dataset with over 7,000 manually annotated instance samples. Our algorithms and dataset are available at https://anonymous.4open.science/r/OBM-B3EC.
Authors: Chengyao Duan, Zhiliu Yang
Abstract: Previous attempts to integrate Neural Radiance Fields (NeRF) into Simultaneous Localization and Mapping (SLAM) framework either rely on the assumption of static scenes or treat dynamic objects as outliers. However, most of real-world scenarios is dynamic. In this paper, we propose a time-varying representation to track and reconstruct the dynamic scenes. Firstly, two processes, tracking process and mapping process, are simultaneously maintained in our system. For tracking process, \red{the entire input images are} uniformly sampled, then progressively trained in a self-supervised paradigm. For mapping process, we leverage motion masks to differentiate dynamic objects and static backgrounds, \red{and we apply distinct sampling strategies for these two types of areas.} Secondly, the parameters optimization for both processes are made up by two stages, the first stage associates time with 3D positions to convert the deformation field to the canonical field. And the second stage associates time with 3D positions in canonical field to obtain colors and Signed Distance Function (SDF). Lastly, we propose a novel key-frame selection strategy based on the overlapping rate. We evaluate our approach on two synthetic datasets and a real-world dataset. And the experiment results validate that our method is more effective when compared to existing state-of-the-art dynamic mapping methods.
Authors: Tianrui Hui, Zihan Ding, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Jiao Dai, Jizhong Han, Si Liu
Abstract: Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a PhraseObject Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.
Authors: Yu Tian, Min Shi, Yan Luo, Ava Kouhana, Tobias Elze, Mengyu Wang
Abstract: Fairness in artificial intelligence models has gained significantly more attention in recent years, especially in the area of medicine, as fairness in medical models is critical to people's well-being and lives. High-quality medical fairness datasets are needed to promote fairness learning research. Existing medical fairness datasets are all for classification tasks, and no fairness datasets are available for medical segmentation, while medical segmentation is an equally important clinical task as classifications, which can provide detailed spatial information on organ abnormalities ready to be assessed by clinicians. In this paper, we propose the first fairness dataset for medical segmentation named Harvard-FairSeg with 10,000 subject samples. In addition, we propose a fair error-bound scaling approach to reweight the loss function with the upper error-bound in each identity group, using the segment anything model (SAM). We anticipate that the segmentation performance equity can be improved by explicitly tackling the hard cases with high training errors in each identity group. To facilitate fair comparisons, we utilize a novel equity-scaled segmentation performance metric to compare segmentation metrics in the context of fairness, such as the equity-scaled Dice coefficient. Through comprehensive experiments, we demonstrate that our fair error-bound scaling approach either has superior or comparable fairness performance to the state-of-the-art fairness learning models. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/datasets/harvard-fairseg10k.
URLs: https://ophai.hms.harvard.edu/datasets/harvard-fairseg10k.
Authors: Ainaz Eftekhar, Kuo-Hao Zeng, Jiafei Duan, Ali Farhadi, Ani Kembhavi, Ranjay Krishna
Abstract: Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this information is often irrelevant to the specific task at hand. This introduces noise within the learning process and distracts the agent's focus from task-relevant visual cues. Inspired by selective attention in humans-the process through which people filter their perception based on their experiences, knowledge, and the task at hand-we introduce a parameter-efficient approach to filter visual stimuli for embodied AI. Our approach induces a task-conditioned bottleneck using a small learnable codebook module. This codebook is trained jointly to optimize task reward and acts as a task-conditioned selective filter over the visual observation. Our experiments showcase state-of-the-art performance for object goal navigation and object displacement across 5 benchmarks, ProcTHOR, ArchitecTHOR, RoboTHOR, AI2-iTHOR, and ManipulaTHOR. The filtered representations produced by the codebook are also able generalize better and converge faster when adapted to other simulation environments such as Habitat. Our qualitative analyses show that agents explore their environments more effectively and their representations retain task-relevant information like target object recognition while ignoring superfluous information about other objects. Code and pretrained models are available at our project website: https://embodied-codebook.github.io.
Authors: Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, Hao Tan
Abstract: We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts a highly scalable transformer-based architecture with 500 million learnable parameters to directly predict a neural radiance field (NeRF) from the input image. We train our model in an end-to-end manner on massive multi-view data containing around 1 million objects, including both synthetic renderings from Objaverse and real captures from MVImgNet. This combination of a high-capacity model and large-scale training data empowers our model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs, including real-world in-the-wild captures and images created by generative models. Video demos and interactable 3D meshes can be found on our LRM project webpage: https://yiconghong.me/LRM.
Authors: Jinjin Xu, Liwu Xu, Yuzhe Yang, Xiang Li, Fanyi Wang, Yanchun Xie, Yi-Jie Huang, Yaqian Li
Abstract: Recent advancements in multi-modal large language models (MLLMs) have led to substantial improvements in visual understanding, primarily driven by sophisticated modality alignment strategies. However, predominant approaches prioritize global or regional comprehension, with less focus on fine-grained, pixel-level tasks. To address this gap, we introduce u-LLaVA, an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. We commence by leveraging an efficient modality alignment approach, harnessing both image and video datasets to bolster the model's foundational understanding across diverse visual contexts. Subsequently, a joint instruction tuning method with task-specific projectors and decoders for end-to-end downstream training is presented. Furthermore, this work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs. The overall framework is simple, effective, and achieves state-of-the-art performance across multiple benchmarks. We also make our model, data, and code publicly accessible at https://github.com/OPPOMKLab/u-LLaVA.
Authors: Yan Di, Chenyangguang Zhang, Chaowei Wang, Ruida Zhang, Guangyao Zhai, Yanyan Li, Bowen Fu, Xiangyang Ji, Shan Gao
Abstract: In this paper, we present ShapeMatcher, a unified self-supervised learning framework for joint shape canonicalization, segmentation, retrieval and deformation. Given a partially-observed object in an arbitrary pose, we first canonicalize the object by extracting point-wise affine-invariant features, disentangling inherent structure of the object with its pose and size. These learned features are then leveraged to predict semantically consistent part segmentation and corresponding part centers. Next, our lightweight retrieval module aggregates the features within each part as its retrieval token and compare all the tokens with source shapes from a pre-established database to identify the most geometrically similar shape. Finally, we deform the retrieved shape in the deformation module to tightly fit the input object by harnessing part center guided neural cage deformation. The key insight of ShapeMaker is the simultaneous training of the four highly-associated processes: canonicalization, segmentation, retrieval, and deformation, leveraging cross-task consistency losses for mutual supervision. Extensive experiments on synthetic datasets PartNet, ComplementMe, and real-world dataset Scan2CAD demonstrate that ShapeMaker surpasses competitors by a large margin.
Authors: Chunming He, Chengyu Fang, Yulun Zhang, Tian Ye, Kai Li, Longxiang Tang, Zhenhua Guo, Xiu Li, Sina Farsiu
Abstract: Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. To tackle these problems, we propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RGformer). To ensure detailed reconstruction and illumination correction, RLDM is empowered to acquire Retinex knowledge and extract reflectance and illumination priors. These priors are subsequently utilized by RGformer to guide the decomposition of image features into their respective reflectance and illumination components. Following this, RGformer further enhances and consolidates the decomposed features, resulting in the production of refined images with consistent content and robustness to handle complex degradation scenarios. Extensive experiments show that Reti-Diff outperforms existing methods on three IDIR tasks, as well as downstream applications. Code will be available at \url{https://github.com/ChunmingHe/Reti-Diff}.
Authors: Zeyu Liu, Tianyi Zhang, Yufang He, Yunlu Feng, Yu Zhao, Guanglei Zhang
Abstract: Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which faces challenges due to the sampling and annotation scarcity in pathological images. The rapid developing generative models shows potential to generate more training samples from recent studies. However, they also struggle in generalization diversity with limited training data, incapable of generating effective samples. Inspired by the pathological transitions between different stages, we propose an adaptive depth-controlled diffusion (ADD) network to generate pathological progressive images for effective data augmentation. This novel approach roots in domain migration, where a hybrid attention strategy guides the bidirectional diffusion, blending local and global attention priorities. With feature measuring, the adaptive depth-controlled strategy ensures the migration and maintains locational similarity in simulating the pathological feature transition. Based on tiny training set (samples less than 500), the ADD yields cross-domain progressive images with corresponding soft-labels. Experiments on two datasets suggest significant improvements in generation diversity, and the effectiveness with generated progressive samples are highlighted in downstream classifications. The code is available at https://github.com/Rowerliu/ADD.
Authors: Youqi Liao, Shuhao Kang, Jianping Li, Yang Liu, Yun Liu, Zhen Dong, Bisheng Yang, Xieyuanli Chen
Abstract: Precise and rapid delineation of sharp boundaries and robust semantics is essential for numerous downstream robotic tasks, such as robot grasping and manipulation, real-time semantic mapping, and online sensor calibration performed on edge computing units. Although boundary detection and semantic segmentation are complementary tasks, most studies focus on lightweight models for semantic segmentation but overlook the critical role of boundary detection. In this work, we introduce Mobile-Seed, a lightweight, dual-task framework tailored for simultaneous semantic segmentation and boundary detection. Our framework features a two-stream encoder, an active fusion decoder (AFD) and a dual-task regularization approach. The encoder is divided into two pathways: one captures category-aware semantic information, while the other discerns boundaries from multi-scale features. The AFD module dynamically adapts the fusion of semantic and boundary information by learning channel-wise relationships, allowing for precise weight assignment of each channel. Furthermore, we introduce a regularization loss to mitigate the conflicts in dual-task learning and deep diversity supervision. Compared to existing methods, the proposed Mobile-Seed offers a lightweight framework to simultaneously improve semantic segmentation performance and accurately locate object boundaries. Experiments on the Cityscapes dataset have shown that Mobile-Seed achieves notable improvement over the state-of-the-art (SOTA) baseline by 2.2 percentage points (pp) in mIoU and 4.2 pp in mF-score, while maintaining an online inference speed of 23.9 frames-per-second (FPS) with 1024x2048 resolution input on an RTX 2080 Ti GPU. Additional experiments on CamVid and PASCAL Context datasets confirm our method's generalizability. Code and additional results are publicly available at https://whu-usi3dv.github.io/Mobile-Seed/.
Authors: Kaiyuan Tang, Chaoli Wang
Abstract: Due to its conceptual simplicity and generality, compressive neural representation has emerged as a promising alternative to traditional compression methods for managing massive volumetric datasets. The current practice of neural compression utilizes a single large multilayer perceptron (MLP) to encode the global volume, incurring slow training and inference. This paper presents an efficient compressive neural representation (ECNR) solution for time-varying data compression, utilizing the Laplacian pyramid for adaptive signal fitting. Following a multiscale structure, we leverage multiple small MLPs at each scale for fitting local content or residual blocks. By assigning similar blocks to the same MLP via size uniformization, we enable balanced parallelization among MLPs to significantly speed up training and inference. Working in concert with the multiscale structure, we tailor a deep compression strategy to compact the resulting model. We show the effectiveness of ECNR with multiple datasets and compare it with state-of-the-art compression methods (mainly SZ3, TTHRESH, and neurcomp). The results position ECNR as a promising solution for volumetric data compression.
Authors: Yaqi Liu, Chao Xia, Song Xiao, Qingxiao Guan, Wenqian Dong, Yifan Zhang, Nenghai Yu
Abstract: Copy-move forgery detection aims at detecting duplicated regions in a suspected forged image, and deep learning based copy-move forgery detection methods are in the ascendant. These deep learning based methods heavily rely on synthetic training data, and the performance will degrade when facing new tasks. In this paper, we propose a Transformer-style copy-move forgery detection network named as CMFDFormer, and provide a novel PCSD (Pooled Cube and Strip Distillation) continual learning framework to help CMFDFormer handle new tasks. CMFDFormer consists of a MiT (Mix Transformer) backbone network and a PHD (Pluggable Hybrid Decoder) mask prediction network. The MiT backbone network is a Transformer-style network which is adopted on the basis of comprehensive analyses with CNN-style and MLP-style backbones. The PHD network is constructed based on self-correlation computation, hierarchical feature integration, a multi-scale cycle fully-connected block and a mask reconstruction block. The PHD network is applicable to feature extractors of different styles for hierarchical multi-scale information extraction, achieving comparable performance. Last but not least, we propose a PCSD continual learning framework to improve the forgery detectability and avoid catastrophic forgetting when handling new tasks. Our continual learning framework restricts intermediate features from the PHD network, and takes advantage of both cube pooling and strip pooling. Extensive experiments on publicly available datasets demonstrate the good performance of CMFDFormer and the effectiveness of the PCSD continual learning framework.
Authors: Luca Eyring, Dominik Klein, Th\'eo Uscidda, Giovanni Palla, Niki Kilbertus, Zeynep Akata, Fabian Theis
Abstract: In optimal transport (OT), a Monge map is known as a mapping that transports a source distribution to a target distribution in the most cost-efficient way. Recently, multiple neural estimators for Monge maps have been developed and applied in diverse unpaired domain translation tasks, e.g. in single-cell biology and computer vision. However, the classic OT framework enforces mass conservation, which makes it prone to outliers and limits its applicability in real-world scenarios. The latter can be particularly harmful in OT domain translation tasks, where the relative position of a sample within a distribution is explicitly taken into account. While unbalanced OT tackles this challenge in the discrete setting, its integration into neural Monge map estimators has received limited attention. We propose a theoretically grounded method to incorporate unbalancedness into any Monge map estimator. We improve existing estimators to model cell trajectories over time and to predict cellular responses to perturbations. Moreover, our approach seamlessly integrates with the OT flow matching (OT-FM) framework. While we show that OT-FM performs competitively in image translation, we further improve performance by incorporating unbalancedness (UOT-FM), which better preserves relevant features. We hence establish UOT-FM as a principled method for unpaired image translation.
Authors: Yichao Cai, Yuhang Liu, Zhen Zhang, Javen Qinfeng Shi
Abstract: Contrastive vision-language models, such as CLIP, have garnered considerable attention for various dowmsteam tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often blend content and style information, which somewhat limits their generalization capabilities under distribution shifts. To address this limitation, we adopt a causal generative perspective for multimodal data and propose contrastive learning with data augmentation to disentangle content features from the original representations. To achieve this, we begins with exploring image augmentation techniques and develop a method to seamlessly integrate them into pre-trained CLIP-like models to extract pure content features. Taking a step further, recognizing the inherent semantic richness and logical structure of text data, we explore the use of text augmentation to isolate latent content from style features. This enables CLIP-like model's encoders to concentrate on latent content information, refining the learned representations by pre-trained CLIP-like models. Our extensive experiments across diverse datasets demonstrate significant improvements in zero-shot and few-shot classification tasks, alongside enhanced robustness to various perturbations. These results underscore the effectiveness of our proposed methods in refining vision-language representations and advancing the state-of-the-art in multimodal learning.
Authors: Bin Xia, Shiyin Wang, Yingfan Tao, Yitong Wang, Jiaya Jia
Abstract: In this paper, we introduce a Multimodal Large Language Model-based Generation Assistant (LLMGA), leveraging the vast reservoir of knowledge and proficiency in reasoning, comprehension, and response inherent in Large Language Models (LLMs) to assist users in image generation and editing. Diverging from existing approaches where Multimodal Large Language Models (MLLMs) generate fixed-size embeddings to control Stable Diffusion (SD), our LLMGA provides a detailed language generation prompt for precise control over SD. This not only augments LLM context understanding but also reduces noise in generation prompts, yields images with more intricate and precise content, and elevates the interpretability of the network. To this end, we curate a comprehensive dataset comprising prompt refinement, similar image generation, inpainting \& outpainting, and instruction-based editing. Moreover, we propose a two-stage training scheme. In the first stage, we train the MLLM to grasp the properties of image generation and editing, enabling it to generate detailed prompts. In the second stage, we optimize SD to align with the MLLM's generation prompts. Additionally, we propose a reference-based restoration network to alleviate texture, brightness, and contrast disparities between generated and preserved regions during inpainting and outpainting. Extensive results show that LLMGA has promising generation and editing capabilities and can enable more flexible and expansive applications in an interactive manner.
Authors: Yushi Huang, Ruihao Gong, Jing Liu, Tianlong Chen, Xianglong Liu
Abstract: The Diffusion model, a prevalent framework for image generation, encounters significant challenges in terms of broad applicability due to its extended inference times and substantial memory requirements. Efficient Post-training Quantization (PTQ) is pivotal for addressing these issues in traditional models. Different from traditional models, diffusion models heavily depend on the time-step $t$ to achieve satisfactory multi-round denoising. Usually, $t$ from the finite set $\{1, \ldots, T\}$ is encoded to a temporal feature by a few modules totally irrespective of the sampling data. However, existing PTQ methods do not optimize these modules separately. They adopt inappropriate reconstruction targets and complex calibration methods, resulting in a severe disturbance of the temporal feature and denoising trajectory, as well as a low compression efficiency. To solve these, we propose a Temporal Feature Maintenance Quantization (TFMQ) framework building upon a Temporal Information Block which is just related to the time-step $t$ and unrelated to the sampling data. Powered by the pioneering block design, we devise temporal information aware reconstruction (TIAR) and finite set calibration (FSC) to align the full-precision temporal features in a limited time. Equipped with the framework, we can maintain the most temporal information and ensure the end-to-end generation quality. Extensive experiments on various datasets and diffusion models prove our state-of-the-art results. Remarkably, our quantization approach, for the first time, achieves model performance nearly on par with the full-precision model under 4-bit weight quantization. Additionally, our method incurs almost no extra computational cost and accelerates quantization time by $2.0 \times$ on LSUN-Bedrooms $256 \times 256$ compared to previous works. Our code is publicly available at https://github.com/ModelTC/TFMQ-DM.
Authors: Peirong Liu, Oula Puonti, Xiaoling Hu, Daniel C. Alexander, Juan E. Iglesias
Abstract: Recent learning-based approaches have made astonishing advances in calibrated medical imaging like computerized tomography (CT), yet they struggle to generalize in uncalibrated modalities -- notably magnetic resonance (MR) imaging, where performance is highly sensitive to the differences in MR contrast, resolution, and orientation. This prevents broad applicability to diverse real-world clinical protocols. We introduce Brain-ID, an anatomical representation learning model for brain imaging. With the proposed "mild-to-severe" intra-subject generation, Brain-ID is robust to the subject-specific brain anatomy regardless of the appearance of acquired images (e.g., contrast, deformation, resolution, artifacts). Trained entirely on synthetic data, Brain-ID readily adapts to various downstream tasks through only one layer. We present new metrics to validate the intra- and inter-subject robustness of Brain-ID features, and evaluate their performance on four downstream applications, covering contrast-independent (anatomy reconstruction/contrast synthesis, brain segmentation), and contrast-dependent (super-resolution, bias field estimation) tasks. Extensive experiments on six public datasets demonstrate that Brain-ID achieves state-of-the-art performance in all tasks on different MRI modalities and CT, and more importantly, preserves its performance on low-resolution and small datasets. Code is available at https://github.com/peirong26/Brain-ID.
Authors: Y. Wang, J. Xu, Y. Zeng, Y. Gong
Abstract: Neural radiance fields (NeRFs) have achieved impressive view synthesis results by learning an implicit volumetric representation from multi-view images. To project the implicit representation into an image, NeRF employs volume rendering that approximates the continuous integrals of rays as an accumulation of the colors and densities of the sampled points. Although this approximation enables efficient rendering, it ignores the direction information in point intervals, resulting in ambiguous features and limited reconstruction quality. In this paper, we propose an anisotropic neural representation learning method that utilizes learnable view-dependent features to improve scene representation and reconstruction. We model the volumetric function as spherical harmonic (SH)-guided anisotropic features, parameterized by multilayer perceptrons, facilitating ambiguity elimination while preserving the rendering efficiency. To achieve robust scene reconstruction without anisotropy overfitting, we regularize the energy of the anisotropic features during training. Our method is flexiable and can be plugged into NeRF-based frameworks. Extensive experiments show that the proposed representation can boost the rendering quality of various NeRFs and achieve state-of-the-art rendering performance on both synthetic and real-world scenes.
Authors: Trong-Thuan Nguyen, Pha Nguyen, Khoa Luu
Abstract: Visual interactivity understanding within visual scenes presents a significant challenge in computer vision. Existing methods focus on complex interactivities while leveraging a simple relationship model. These methods, however, struggle with a diversity of appearance, situation, position, interaction, and relation in videos. This limitation hinders the ability to fully comprehend the interplay within the complex visual dynamics of subjects. In this paper, we delve into interactivities understanding within visual content by deriving scene graph representations from dense interactivities among humans and objects. To achieve this goal, we first present a new dataset containing Appearance-Situation-Position-Interaction-Relation predicates, named ASPIRe, offering an extensive collection of videos marked by a wide range of interactivities. Then, we propose a new approach named Hierarchical Interlacement Graph (HIG), which leverages a unified layer and graph within a hierarchical structure to provide deep insights into scene changes across five distinct tasks. Our approach demonstrates superior performance to other methods through extensive experiments conducted in various scenarios.
Authors: Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda
Abstract: In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availability of training data to mitigate quantization errors, a significant challenge when data availability is scarce or restricted due to privacy or copyright concerns. Addressing this, we introduce GenQ, a novel approach employing an advanced Generative AI model to generate photorealistic, high-resolution synthetic data, overcoming the limitations of traditional methods that struggle to accurately mimic complex objects in extensive datasets like ImageNet. Our methodology is underscored by two robust filtering mechanisms designed to ensure the synthetic data closely aligns with the intrinsic characteristics of the actual training data. In case of limited data availability, the actual data is used to guide the synthetic data generation process, enhancing fidelity through the inversion of learnable token embeddings. Through rigorous experimentation, GenQ establishes new benchmarks in data-free and data-scarce quantization, significantly outperforming existing methods in accuracy and efficiency, thereby setting a new standard for quantization in low data regimes.
Authors: Tongkun Guan, Wei Shen, Xue Yang, Xuehui Wang, Xiaokang Yang
Abstract: Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-scale labeled synthetic data (LSD) for pre-training text detectors. However, a synth-to-real domain gap emerges, further limiting the performance of text detectors. Differently, in this work, we propose FreeReal, a real-domain-aligned pre-training paradigm that enables the complementary strengths of both LSD and unlabeled real data (URD). Specifically, to bridge real and synthetic worlds for pre-training, a glyph-based mixing mechanism (GlyphMix) is tailored for text images.GlyphMix delineates the character structures of synthetic images and embeds them as graffiti-like units onto real images. Without introducing real domain drift, GlyphMix freely yields real-world images with annotations derived from synthetic labels. Furthermore, when given free fine-grained synthetic labels, GlyphMix can effectively bridge the linguistic domain gap stemming from English-dominated LSD to URD in various languages. Without bells and whistles, FreeReal achieves average gains of 1.59\%, 1.97\%, 3.90\%, 3.85\%, and 4.56\% in improving the performance of DPText, FCENet, PSENet, PANet, and DBNet methods, respectively, consistently outperforming previous pre-training methods by a substantial margin across four public datasets. Code will be released soon.
Authors: Haowen Bai, Zixiang Zhao, Jiangshe Zhang, Yichen Wu, Lilun Deng, Yukun Cui, Shuang Xu, Baisong Jiang
Abstract: Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. The significant challenges for deep learning-based image fusion algorithms are the lack of a definitive ground truth as well as the corresponding distance measurement, with current manually given loss functions constrain the flexibility of model and generalizability for unified fusion tasks. To overcome these limitations, we introduce a unified image fusion framework based on meta-learning, named ReFusion, which provides a learning paradigm that obtains the optimal fusion loss for various fusion tasks based on reconstructing the source images. Compared to existing methods, ReFusion employs a parameterized loss function, dynamically adjusted by the training framework according to the specific scenario and task. ReFusion is constituted by three components: a fusion module, a loss proposal module, and a source reconstruction module. To ensure the fusion module maximally preserves the information from the source images, enabling the reconstruction of the source images from the fused image, we adopt a meta-learning strategy to train the loss proposal module using reconstruction loss. The update of the fusion module relies on the fusion loss proposed by the loss proposal module. The alternating updates of the three modules mutually facilitate each other, aiming to propose an appropriate fusion loss for different tasks and yield satisfactory fusion results. Extensive experiments demonstrate that ReFusion is capable of adapting to various tasks, including infrared-visible, medical, multi-focus, and multi-exposure image fusion. The code will be released.
Authors: Jiafeng Mao, Xueting Wang, Kiyoharu Aizawa
Abstract: Text-to-image diffusion models allow users control over the content of generated images. Still, text-to-image generation occasionally leads to generation failure requiring users to generate dozens of images under the same text prompt before they obtain a satisfying result. We formulate the lottery ticket hypothesis in denoising: randomly initialized Gaussian noise images contain special pixel blocks (winning tickets) that naturally tend to be denoised into specific content independently. The generation failure in standard text-to-image synthesis is caused by the gap between optimal and actual spatial distribution of winning tickets in initial noisy images. To this end, we implement semantic-driven initial image construction creating initial noise from known winning tickets for each concept mentioned in the prompt. We conduct a series of experiments that verify the properties of winning tickets and demonstrate their generalizability across images and prompts. Our results show that aggregating winning tickets into the initial noise image effectively induce the model to generate the specified object at the corresponding location.
Authors: Shuzhou Yang, Chong Mou, Jiwen Yu, Yuhan Wang, Xiandong Meng, Jian Zhang
Abstract: Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in GPU memory demand as the number of frames grows, and (2) the inter-frame inconsistency in edited videos. To this end, we propose NVEdit, a novel text-driven video editing framework designed to mitigate memory overhead and improve consistent editing for real-world long videos. Specifically, we construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames in a memory-efficient manner. Next, we update the video field through off-the-shelf Text-to-Image (T2I) models to impart text-driven editing effects. A progressive optimization strategy is developed to preserve original temporal priors. Importantly, both the neural video field and T2I model are adaptable and replaceable, thus inspiring future research. Experiments demonstrate the ability of our approach to edit hundreds of frames with impressive inter-frame consistency. Our project is available at: https://nvedit.github.io/.
Authors: Zhiyuan You, Zheyuan Li, Jinjin Gu, Zhenfei Yin, Tianfan Xue, Chao Dong
Abstract: We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods. DepictQA allows for detailed, language-based, human-like evaluation of image quality by leveraging Multi-modal Large Language Models (MLLMs). Unlike conventional Image Quality Assessment (IQA) methods relying on scores, DepictQA interprets image content and distortions descriptively and comparatively, aligning closely with humans' reasoning process. To build the DepictQA model, we establish a hierarchical task framework, and collect a multi-modal IQA training dataset. To tackle the challenges of limited training data and multi-image processing, we propose to use multi-source training data and specialized image tags. These designs result in a better performance of DepictQA than score-based approaches on multiple benchmarks. Moreover, compared with general MLLMs, DepictQA can generate more accurate reasoning descriptive languages. Our work demonstrates the utility of our full-reference dataset in non-reference applications, and indicates that language-based IQA methods have the potential to be customized for individual preferences.
Authors: Shuailei Ma, Chen-Wei Xie, Ying Wei, Siyang Sun, Jiaqi Fan, Xiaoyi Bao, Yuxin Guo, Yun Zheng
Abstract: Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. However, there is no work that provides a comprehensive explanation for the working mechanism of the multi-modal prompts. In this paper, we conduct a direct analysis of the multi-modal prompts by asking the following questions: $(i)$ How do the learned multi-modal prompts improve the recognition performance? $(ii)$ What do the multi-modal prompts learn? To answer these questions, we begin by isolating the component of the formula where the prompt influences the calculation of self-attention at each layer in two distinct ways, \ie, $(1)$ introducing prompt embeddings makes the $[cls]$ token focus on foreground objects. $(2)$ the prompts learn a bias term during the update of token embeddings, allowing the model to adapt to the target domain. Subsequently, we conduct extensive visualization and statistical experiments on the eleven diverse downstream recognition datasets. From the experiments, we reveal that the learned prompts improve the performance mainly through the second way, which acts as the dataset bias to improve the recognition performance of the pre-trained model on the corresponding dataset. Based on this finding, we propose the bias tuning way and demonstrate that directly incorporating the learnable bias outperforms the learnable prompts in the same parameter settings. In datasets with limited category information, \ie, EuroSAT, bias tuning surpasses prompt tuning by a large margin. With a deeper understanding of the multi-modal prompt, we hope our work can inspire new and solid research in this direction.
Authors: Han Shu, Wenshuo Li, Yehui Tang, Yiman Zhang, Yihao Chen, Houqiang Li, Yunhe Wang, Xinghao Chen
Abstract: Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pretrained SAM and achieved impressive performance on downstream vision tasks. However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the promptable segmentation task and further reduce the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by $2\times$ with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods. Pre-trained models and codes are available at https://github.com/xinghaochen/TinySAM and https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.
URLs: https://github.com/xinghaochen/TinySAM, https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.
Authors: Yunhao Du, Cheng Lei, Zhicheng Zhao, Fei Su
Abstract: Referring multi-object tracking (RMOT) aims to track multiple objects based on input textual descriptions. Previous works realize it by simply integrating an extra textual module into the multi-object tracker. However, they typically need to retrain the entire framework and have difficulties in optimization. In this work, we propose an insertable Knowledge Unification Network, termed iKUN, to enable communication with off-the-shelf trackers in a plug-and-play manner. Concretely, a knowledge unification module (KUM) is designed to adaptively extract visual features based on textual guidance. Meanwhile, to improve the localization accuracy, we present a neural version of Kalman filter (NKF) to dynamically adjust process noise and observation noise based on the current motion status. Moreover, to address the problem of open-set long-tail distribution of textual descriptions, a test-time similarity calibration method is proposed to refine the confidence score with pseudo frequency. Extensive experiments on Refer-KITTI dataset verify the effectiveness of our framework. Finally, to speed up the development of RMOT, we also contribute a more challenging dataset, Refer-Dance, by extending public DanceTrack dataset with motion and dressing descriptions. The codes and dataset are available at https://github.com/dyhBUPT/iKUN.
Authors: Mingrui Li, Yiming Zhou, Guangan Jiang, Tianchen Deng, Yangyang Wang, Hongyu Wang
Abstract: SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in real-world scenarios with dynamic interferences. To address these issues, we introduce DDN-SLAM, the first real-time dense dynamic neural implicit SLAM system integrating semantic features. To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model. To avoid incorrect background removal, we propose a mapping strategy based on sparse point cloud sampling and background restoration. We propose a dynamic semantic loss to eliminate dynamic occlusions. Experimental results demonstrate that DDN-SLAM is capable of robustly tracking and producing high-quality reconstructions in dynamic environments, while appropriately preserving potential dynamic objects. Compared to existing neural implicit SLAM systems, the tracking results on dynamic datasets indicate an average 90% improvement in Average Trajectory Error (ATE) accuracy.
Authors: Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik, Alessandro G Allievi, Senem Velipasalar, Liu Ren
Abstract: Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning. While vision-only autonomous driving methods have recently achieved notable performance, through enhanced scene understanding, several key issues, including lack of reasoning, low generalization performance and long-tail scenarios, still need to be addressed. In this paper, we present VLP, a novel Vision-Language-Planning framework that exploits language models to bridge the gap between linguistic understanding and autonomous driving. VLP enhances autonomous driving systems by strengthening both the source memory foundation and the self-driving car's contextual understanding. VLP achieves state-of-the-art end-to-end planning performance on the challenging NuScenes dataset by achieving 35.9\% and 60.5\% reduction in terms of average L2 error and collision rates, respectively, compared to the previous best method. Moreover, VLP shows improved performance in challenging long-tail scenarios and strong generalization capabilities when faced with new urban environments.
Authors: Lidong Zeng, Zhedong Zheng, Yinwei Wei, Tat-seng Chua
Abstract: This paper delves into the text-guided image editing task, focusing on modifying a reference image according to user-specified textual feedback to embody specific attributes. Despite recent advancements, a persistent challenge remains that the single-round generation often overlooks crucial details, particularly in the realm of fine-grained changes like shoes or sleeves. This issue compounds over multiple rounds of interaction, severely limiting customization quality. In an attempt to address this challenge, we introduce a new self-supervised regularization, \ie, multi-round regularization, which is compatible with existing methods. Specifically, the multi-round regularization encourages the model to maintain consistency across different modification orders. It builds upon the observation that the modification order generally should not affect the final result. Different from traditional one-round generation, the mechanism underpinning the proposed method is the error amplification of initially minor inaccuracies in capturing intricate details. Qualitative and quantitative experiments affirm that the proposed method achieves high-fidelity editing quality, especially the local modification, in both single-round and multiple-round generation, while also showcasing robust generalization to irregular text inputs. The effectiveness of our semantic alignment with textual feedback is further substantiated by the retrieval improvements on FahisonIQ and Fashion200k.
Authors: Christian Cre{\ss}, Walter Zimmer, Nils Purschke, Bach Ngoc Doan, Sven Kirchner, Venkatnarayanan Lakshminarasimhan, Leah Strand, Alois C. Knoll
Abstract: Event-based cameras are predestined for Intelligent Transportation Systems (ITS). They provide very high temporal resolution and dynamic range, which can eliminate motion blur and improve detection performance at night. However, event-based images lack color and texture compared to images from a conventional RGB camera. Considering that, data fusion between event-based and conventional cameras can combine the strengths of both modalities. For this purpose, extrinsic calibration is necessary. To the best of our knowledge, no targetless calibration between event-based and RGB cameras can handle multiple moving objects, nor does data fusion optimized for the domain of roadside ITS exist. Furthermore, synchronized event-based and RGB camera datasets considering roadside perspective are not yet published. To fill these research gaps, based on our previous work, we extended our targetless calibration approach with clustering methods to handle multiple moving objects. Furthermore, we developed an early fusion, simple late fusion, and a novel spatiotemporal late fusion method. Lastly, we published the TUMTraf Event Dataset, which contains more than 4,111 synchronized event-based and RGB images with 50,496 labeled 2D boxes. During our extensive experiments, we verified the effectiveness of our calibration method with multiple moving objects. Furthermore, compared to a single RGB camera, we increased the detection performance of up to +9 % mAP in the day and up to +13 % mAP during the challenging night with our presented event-based sensor fusion methods. The TUMTraf Event Dataset is available at https://innovation-mobility.com/tumtraf-dataset.
Authors: Paulina Tomaszewska, El\.zbieta Sienkiewicz, Mai P. Hoang, Przemys{\l}aw Biecek
Abstract: We propose 'Deep spatial context' (DSCon) method, which serves for investigation of the attention-based vision models using the concept of spatial context. It was inspired by histopathologists, however, the method can be applied to various domains. The DSCon allows for a quantitative measure of the spatial context's role using three Spatial Context Measures: $SCM_{features}$, $SCM_{targets}$, $SCM_{residuals}$ to distinguish whether the spatial context is observable within the features of neighboring regions, their target values (attention scores) or residuals, respectively. It is achieved by integrating spatial regression into the pipeline. The DSCon helps to verify research questions. The experiments reveal that spatial relationships are much bigger in the case of the classification of tumor lesions than normal tissues. Moreover, it turns out that the larger the size of the neighborhood taken into account within spatial regression, the less valuable contextual information is. Furthermore, it is observed that the spatial context measure is the largest when considered within the feature space as opposed to the targets and residuals.
Authors: Ci-Siang Lin, Chien-Yi Wang, Yu-Chiang Frank Wang, Min-Hung Chen
Abstract: Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds. To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories. More specifically, we propose Contrastive Prompt Learning and Prompt-guided Semantic Refinement to learn the prompts that adequately describe and suppress the co-occurring backgrounds associated with each target object category. In this way, SemPLeS can perform better semantic alignment between object regions and the associated class labels, resulting in desired pseudo masks for training the segmentation model. The proposed SemPLeS framework achieves SOTA performance on the standard WSSS benchmarks, PASCAL VOC and MS COCO, and shows compatibility with other WSSS methods. The source codes are provided in the supplementary.
Authors: Leichao Cui, Xiuxian Li, Min Meng, Guangyu Jia
Abstract: The enhancement of 3D object detection is pivotal for precise environmental perception and improved task execution capabilities in autonomous driving. LiDAR point clouds, offering accurate depth information, serve as a crucial information for this purpose. Our study focuses on key challenges in 3D target detection. To tackle the challenge of expanding the receptive field of a 3D convolutional kernel, we introduce the Dynamic Feature Fusion Module (DFFM). This module achieves adaptive expansion of the 3D convolutional kernel's receptive field, balancing the expansion with acceptable computational loads. This innovation reduces operations, expands the receptive field, and allows the model to dynamically adjust to different object requirements. Simultaneously, we identify redundant information in 3D features. Employing the Feature Selection Module (FSM) quantitatively evaluates and eliminates non-important features, achieving the separation of output box fitting and feature extraction. This innovation enables the detector to focus on critical features, resulting in model compression, reduced computational burden, and minimized candidate frame interference. Extensive experiments confirm that both DFFM and FSM not only enhance current benchmarks, particularly in small target detection, but also accelerate network performance. Importantly, these modules exhibit effective complementarity.
Authors: Mingxuan Liu, Subhankar Roy, Wenjing Li, Zhun Zhong, Nicu Sebe, Elisa Ricci
Abstract: Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average layperson does not excel at differentiating species of birds or mushrooms due to subtle differences among the species. A major bottleneck in developing FGVR systems is caused by the need of high-quality paired expert annotations. To circumvent the need of expert knowledge we propose Fine-grained Semantic Category Reasoning (FineR) that internally leverages the world knowledge of large language models (LLMs) as a proxy in order to reason about fine-grained category names. In detail, to bridge the modality gap between images and LLM, we extract part-level visual attributes from images as text and feed that information to a LLM. Based on the visual attributes and its internal world knowledge the LLM reasons about the subordinate-level category names. Our training-free FineR outperforms several state-of-the-art FGVR and language and vision assistant models and shows promise in working in the wild and in new domains where gathering expert annotation is arduous.
Authors: Tao Guo, Yinuo Wang, Shihao Shu, Diansheng Chen, Zhouping Tang, Cai Meng, Xiangzhi Bai
Abstract: Capturing voxel-wise spatial correspondence across distinct modalities is crucial for medical image analysis. However, current registration approaches are not practical enough in terms of registration accuracy and clinical applicability. In this paper, we introduce MambaMorph, a novel multi-modality deformable registration framework. Specifically, MambaMorph utilizes a Mamba-based registration module and a fine-grained, yet simple, feature extractor for efficient long-range correspondence modeling and high-dimensional feature learning, respectively. Additionally, we develop a well-annotated brain MR-CT registration dataset, SR-Reg, to address the scarcity of data in multi-modality registration. To validate MambaMorph's multi-modality registration capabilities, we conduct quantitative experiments on both our SR-Reg dataset and a public T1-T2 dataset. The experimental results on both datasets demonstrate that MambaMorph significantly outperforms the current state-of-the-art learning-based registration methods in terms of registration accuracy. Further study underscores the efficiency of the Mamba-based registration module and the lightweight feature extractor, which achieve notable registration quality while maintaining reasonable computational costs and speeds. We believe that MambaMorph holds significant potential for practical applications in medical image registration. The code for MambaMorph is available at: https://github.com/Guo-Stone/MambaMorph.
Authors: Guang Lin, Chao Li, Jianhai Zhang, Toshihisa Tanaka, Qibin Zhao
Abstract: The deep neural networks are known to be vulnerable to well-designed adversarial attacks. The most successful defense technique based on adversarial training (AT) can achieve optimal robustness against particular attacks but cannot generalize well to unseen attacks. Another effective defense technique based on adversarial purification (AP) can enhance generalization but cannot achieve optimal robustness. Meanwhile, both methods share one common limitation on the degraded standard accuracy. To mitigate these issues, we propose a novel pipeline called Adversarial Training on Purification (AToP), which comprises two components: perturbation destruction by random transforms (RT) and purifier model fine-tuned (FT) by adversarial loss. RT is essential to avoid overlearning to known attacks resulting in the robustness generalization to unseen attacks and FT is essential for the improvement of robustness. To evaluate our method in an efficient and scalable way, we conduct extensive experiments on CIFAR-10, CIFAR-100, and ImageNette to demonstrate that our method achieves state-of-the-art results and exhibits generalization ability against unseen attacks.
Authors: Yiming Huang, Beilei Cui, Long Bai, Ziqi Guo, Mengya Xu, Mobarakol Islam, Hongliang Ren
Abstract: In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes. Neural Radiance Fields (NeRF)-based methods have recently risen to prominence for their exceptional ability to reconstruct scenes but are hampered by slow inference speed, prolonged training, and inconsistent depth estimation. Some previous work utilizes ground truth depth for optimization but is hard to acquire in the surgical domain. To overcome these obstacles, we present Endo-4DGS, a real-time endoscopic dynamic reconstruction approach that utilizes 3D Gaussian Splatting (GS) for 3D representation. Specifically, we propose lightweight MLPs to capture temporal dynamics with Gaussian deformation fields. To obtain a satisfactory Gaussian Initialization, we exploit a powerful depth estimation foundation model, Depth-Anything, to generate pseudo-depth maps as a geometry prior. We additionally propose confidence-guided learning to tackle the ill-pose problems in monocular depth estimation and enhance the depth-guided reconstruction with surface normal constraints and depth regularization. Our approach has been validated on two surgical datasets, where it can effectively render in real-time, compute efficiently, and reconstruct with remarkable accuracy.
Authors: Shibiao Xu, Shunpeng Chen, Rongtao Xu, Changwei Wang, Peng Lu, Li Guo
Abstract: Local feature matching enjoys wide-ranging applications in the realm of computer vision, encompassing domains such as image retrieval, 3D reconstruction, and object recognition. However, challenges persist in improving the accuracy and robustness of matching due to factors like viewpoint and lighting variations. In recent years, the introduction of deep learning models has sparked widespread exploration into local feature matching techniques. The objective of this endeavor is to furnish a comprehensive overview of local feature matching methods. These methods are categorized into two key segments based on the presence of detectors. The Detector-based category encompasses models inclusive of Detect-then-Describe, Joint Detection and Description, Describe-then-Detect, as well as Graph Based techniques. In contrast, the Detector-free category comprises CNN Based, Transformer Based, and Patch Based methods. Our study extends beyond methodological analysis, incorporating evaluations of prevalent datasets and metrics to facilitate a quantitative comparison of state-of-the-art techniques. The paper also explores the practical application of local feature matching in diverse domains such as Structure from Motion, Remote Sensing Image Registration, and Medical Image Registration, underscoring its versatility and significance across various fields. Ultimately, we endeavor to outline the current challenges faced in this domain and furnish future research directions, thereby serving as a reference for researchers involved in local feature matching and its interconnected domains. A comprehensive list of studies in this survey is available at https://github.com/vignywang/Awesome-Local-Feature-Matching .
URLs: https://github.com/vignywang/Awesome-Local-Feature-Matching
Authors: Rozhan Ahmadi, Shohreh Kasaei
Abstract: In recent years, weakly supervised semantic segmentation using image-level labels as supervision has received significant attention in the field of computer vision. Most existing methods have addressed the challenges arising from the lack of spatial information in these labels by focusing on facilitating supervised learning through the generation of pseudo-labels from class activation maps (CAMs). Due to the localized pattern detection of CNNs, CAMs often emphasize only the most discriminative parts of an object, making it challenging to accurately distinguish foreground objects from each other and the background. Recent studies have shown that Vision Transformer (ViT) features, due to their global view, are more effective in capturing the scene layout than CNNs. However, the use of hierarchical ViTs has not been extensively explored in this field. This work explores the use of Swin Transformer by proposing "SWTformer" to enhance the accuracy of the initial seed CAMs by bringing local and global views together. SWTformer-V1 generates class probabilities and CAMs using only the patch tokens as features. SWTformer-V2 incorporates a multi-scale feature fusion mechanism to extract additional information and utilizes a background-aware mechanism to generate more accurate localization maps with improved cross-object discrimination. Based on experiments on the PascalVOC 2012 dataset, SWTformer-V1 achieves a 0.98% mAP higher localization accuracy, outperforming state-of-the-art models. It also yields comparable performance by 0.82% mIoU on average higher than other methods in generating initial localization maps, depending only on the classification network. SWTformer-V2 further improves the accuracy of the generated seed CAMs by 5.32% mIoU, further proving the effectiveness of the local-to-global view provided by the Swin transformer. Code available at: https://github.com/RozhanAhmadi/SWTformer
Authors: Yuzhong Zhao, Yue Liu, Zonghao Guo, Weijia Wu, Chen Gong, Fang Wan, Qixiang Ye
Abstract: Region-level captioning is challenged by the caption degeneration issue, which refers to that pre-trained multimodal models tend to predict the most frequent captions but miss the less frequent ones. In this study, we propose a controllable region-level captioning (ControlCap) approach, which introduces control words to a multimodal model to address the caption degeneration issue. In specific, ControlCap leverages a discriminative module to generate control words within the caption space to partition it to multiple sub-spaces. The multimodal model is constrained to generate captions within a few sub-spaces containing the control words, which increases the opportunity of hitting less frequent captions, alleviating the caption degeneration issue. Furthermore, interactive control words can be given by either a human or an expert model, which enables captioning beyond the training caption space, enhancing the model's generalization ability. Extensive experiments on Visual Genome and RefCOCOg datasets show that ControlCap respectively improves the CIDEr score by 21.6 and 2.2, outperforming the state-of-the-arts by significant margins. Code is available at https://github.com/callsys/ControlCap.
Authors: Haifan Gong, Luoyao Kang, Yitao Wang, Xiang Wan, Haofeng Li
Abstract: In the field of biomedical image analysis, the quest for architectures capable of effectively capturing long-range dependencies is paramount, especially when dealing with 3D image segmentation, classification, and landmark detection. Traditional Convolutional Neural Networks (CNNs) struggle with locality respective field, and Transformers have a heavy computational load when applied to high-dimensional medical images.In this paper, we introduce nnMamba, a novel architecture that integrates the strengths of CNNs and the advanced long-range modeling capabilities of State Space Sequence Models (SSMs). Specifically, we propose the Mamba-In-Convolution with Channel-Spatial Siamese learning (MICCSS) block to model the long-range relationship of the voxels. For the dense prediction and classification tasks, we also design the channel-scaling and channel-sequential learning methods. Extensive experiments on 6 datasets demonstrate nnMamba's superiority over state-of-the-art methods in a suite of challenging tasks, including 3D image segmentation, classification, and landmark detection. nnMamba emerges as a robust solution, offering both the local representation ability of CNNs and the efficient global context processing of SSMs, setting a new standard for long-range dependency modeling in medical image analysis. Code is available at https://github.com/lhaof/nnMamba
Authors: Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov
Abstract: Exemplar-Free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in the first task to learn a high-quality backbone. This is especially challenging for EFCIL since it requires high plasticity, which results in feature drift which is difficult to compensate for in the exemplar-free setting. To address this problem, we propose a simple and effective approach that consolidates feature representations by regularizing drift in directions highly relevant to previous tasks and employs prototypes to reduce task-recency bias. Our method, called Elastic Feature Consolidation (EFC), exploits a tractable second-order approximation of feature drift based on an Empirical Feature Matrix (EFM). The EFM induces a pseudo-metric in feature space which we use to regularize feature drift in important directions and to update Gaussian prototypes used in a novel asymmetric cross entropy loss which effectively balances prototype rehearsal with data from new tasks. Experimental results on CIFAR-100, Tiny-ImageNet, ImageNet-Subset and ImageNet-1K demonstrate that Elastic Feature Consolidation is better able to learn new tasks by maintaining model plasticity and significantly outperform the state-of-the-art.
Authors: Yuxi Wei, Zi Wang, Yifan Lu, Chenxin Xu, Changxing Liu, Hao Zhao, Siheng Chen, Yanfeng Wang
Abstract: Scene simulation in autonomous driving has gained significant attention because of its huge potential for generating customized data. However, existing editable scene simulation approaches face limitations in terms of user interaction efficiency, multi-camera photo-realistic rendering and external digital assets integration. To address these challenges, this paper introduces ChatSim, the first system that enables editable photo-realistic 3D driving scene simulations via natural language commands with external digital assets. To enable editing with high command flexibility,~ChatSim leverages a large language model (LLM) agent collaboration framework. To generate photo-realistic outcomes, ChatSim employs a novel multi-camera neural radiance field method. Furthermore, to unleash the potential of extensive high-quality digital assets, ChatSim employs a novel multi-camera lighting estimation method to achieve scene-consistent assets' rendering. Our experiments on Waymo Open Dataset demonstrate that ChatSim can handle complex language commands and generate corresponding photo-realistic scene videos.
Authors: Xiaoxuan Zhang, Quan Pan, Salvador Garc\'ia
Abstract: Deep learning (DL)-based sea\textendash land clutter classification for sky-wave over-the-horizon-radar (OTHR) has become a novel research topic. In engineering applications, real-time predictions of sea\textendash land clutter with existing distribution discrepancies are crucial. To solve this problem, this article proposes a novel Multisource Semisupervised Adversarial Domain Generalization Network (MSADGN) for cross-scene sea\textendash land clutter classification. MSADGN can extract domain-invariant and domain-specific features from one labeled source domain and multiple unlabeled source domains, and then generalize these features to an arbitrary unseen target domain for real-time prediction of sea\textendash land clutter. Specifically, MSADGN consists of three modules: domain-related pseudolabeling module, domain-invariant module, and domain-specific module. The first module introduces an improved pseudolabel method called domain-related pseudolabel, which is designed to generate reliable pseudolabels to fully exploit unlabeled source domains. The second module utilizes a generative adversarial network (GAN) with a multidiscriminator to extract domain-invariant features, to enhance the model's transferability in the target domain. The third module employs a parallel multiclassifier branch to extract domain-specific features, to enhance the model's discriminability in the target domain. The effectiveness of our method is validated in twelve domain generalizations (DG) scenarios. Meanwhile, we selected 10 state-of-the-art DG methods for comparison. The experimental results demonstrate the superiority of our method.
Authors: Jiaheng Xie, Ruicheng Liang, Yidong Chai, Yang Liu, Daniel Zeng
Abstract: While short-form videos head to reshape the entire social media landscape, experts are exceedingly worried about their depressive impacts on viewers, as evidenced by medical studies. To prevent widespread consequences, platforms are eager to predict these videos' impact on viewers' mental health. Subsequently, they can take intervention measures, such as revising recommendation algorithms and displaying viewer discretion. Nevertheless, applicable predictive methods lack relevance to well-established medical knowledge, which outlines clinically proven external and environmental factors of depression. To account for such medical knowledge, we resort to an emergent methodological discipline, seeded Neural Topic Models (NTMs). However, existing seeded NTMs suffer from the limitations of single-origin topics, unknown topic sources, unclear seed supervision, and suboptimal convergence. To address those challenges, we develop a novel Knowledge-guided Multimodal NTM to predict a short-form video's depressive impact on viewers. Extensive empirical analyses using TikTok and Douyin datasets prove that our method outperforms state-of-the-art benchmarks. Our method also discovers medically relevant topics from videos that are linked to depressive impact. We contribute to IS with a novel video analytics method that is generalizable to other video classification problems. Practically, our method can help platforms understand videos' mental impacts, thus adjusting recommendations and video topic disclosure.
Authors: Jihai Zhang, Xiang Lan, Xiaoye Qu, Yu Cheng, Mengling Feng, Bryan Hooi
Abstract: Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a phenomenon where the trained model captures only a limited portion of the information from the input data while overlooking other potentially valuable content. This issue often leads to indistinguishable representations for visually similar but semantically different inputs, adversely affecting downstream task performance, particularly those requiring rigorous semantic comprehension. To address this challenge, we propose a novel model-agnostic Multistage Contrastive Learning (MCL) framework. Unlike standard contrastive learning which inherently captures one single biased feature distribution, MCL progressively learns previously unlearned features through feature-aware negative sampling at each stage, where the negative samples of an anchor are exclusively selected from the cluster it was assigned to in preceding stages. Meanwhile, MCL preserves the previously well-learned features by cross-stage representation integration, integrating features across all stages to form final representations. Our comprehensive evaluation demonstrates MCL's effectiveness and superiority across both unimodal and multimodal contrastive learning, spanning a range of model architectures from ResNet to Vision Transformers (ViT). Remarkably, in tasks where the original CLIP model has shown limitations, MCL dramatically enhances performance, with improvements up to threefold on specific attributes in the recently proposed MMVP benchmark.
Authors: Xuanhua He, Ke Cao, Keyu Yan, Rui Li, Chengjun Xie, Jie Zhang, Man Zhou
Abstract: Pan-sharpening involves integrating information from low-resolution multi-spectral and high-resolution panchromatic images to generate high-resolution multi-spectral counterparts. While recent advancements in the state space model, particularly the efficient long-range dependency modeling achieved by Mamba, have revolutionized computer vision community, its untapped potential in pan-sharpening motivates our exploration. Our contribution, Pan-Mamba, represents a novel pan-sharpening network that leverages the efficiency of the Mamba model in global information modeling. In Pan-Mamba, we customize two core components: channel swapping Mamba and cross-modal Mamba, strategically designed for efficient cross-modal information exchange and fusion. The former initiates a lightweight cross-modal interaction through the exchange of partial panchromatic and multi-spectral channels, while the latter facilities the information representation capability by exploiting inherent cross-modal relationships. Through extensive experiments across diverse datasets, our proposed approach surpasses state-of-the-art methods, showcasing superior fusion results in pan-sharpening. To the best of our knowledge, this work is the first attempt in exploring the potential of the Mamba model and establishes a new frontier in the pan-sharpening techniques. The source code is available at \url{https://github.com/alexhe101/Pan-Mamba}.
Authors: Li Zhang, Youwei Liang, Ruiyi Zhang, Amirhosein Javadi, Pengtao Xie
Abstract: The Segment Anything Model (SAM), a foundation model pretrained on millions of images and segmentation masks, has significantly advanced semantic segmentation, a fundamental task in computer vision. Despite its strengths, SAM encounters two major challenges. Firstly, it struggles with segmenting specific objects autonomously, as it relies on users to manually input prompts like points or bounding boxes to identify targeted objects. Secondly, SAM faces challenges in excelling at specific downstream tasks, like medical imaging, due to a disparity between the distribution of its pretraining data, which predominantly consists of general-domain images, and the data used in downstream tasks. Current solutions to these problems, which involve finetuning SAM, often lead to overfitting, a notable issue in scenarios with very limited data, like in medical imaging. To overcome these limitations, we introduce BLO-SAM, which finetunes SAM based on bi-level optimization (BLO). Our approach allows for automatic image segmentation without the need for manual prompts, by optimizing a learnable prompt embedding. Furthermore, it significantly reduces the risk of overfitting by training the model's weight parameters and the prompt embedding on two separate subsets of the training dataset, each at a different level of optimization. We apply BLO-SAM to diverse semantic segmentation tasks in general and medical domains. The results demonstrate BLO-SAM's superior performance over various state-of-the-art image semantic segmentation methods.
Authors: Wenzhao Zhao, Steffen Albert, Barbara D. Wichtmann, Angelika Maurer, Ulrike Attenberger, Frank G. Z\"ollner, J\"urgen Hesser
Abstract: Filter-decomposition-based group equivariant convolutional neural networks show promising stability and data efficiency for 3D image feature extraction. However, the existing filter-decomposition-based 3D group equivariant neural networks rely on parameter-sharing designs and are mostly limited to rotation transformation groups, where the chosen spherical harmonic filter bases consider only angular orthogonality. These limitations hamper its application to deep neural network architectures for medical image segmentation. To address these issues, this paper describes a non-parameter-sharing affine group equivariant neural network for 3D medical image segmentation based on an adaptive aggregation of Monte Carlo augmented spherical Fourier Bessel filter bases. The efficiency and flexibility of the adopted non-parameter-sharing strategy enable for the first time an efficient implementation of 3D affine group equivariant convolutional neural networks for volumetric data. The introduced spherical Bessel Fourier filter basis combines both angular and radial orthogonality for better feature extraction. The 3D image segmentation experiments on two abdominal medical image sets, BTCV and the NIH Pancreas datasets, show that the proposed methods excel the state-of-the-art 3D neural networks with high training stability and data efficiency. The code will be available at https://github.com/ZhaoWenzhao/WMCSFB.
Authors: Qunliang Xing, Mai Xu, Shengxi Li, Xin Deng, Meisong Zheng, Huaida Liu, Ying Chen
Abstract: Existing quality enhancement methods for compressed images focus on aligning the enhancement domain with the raw domain to yield realistic images. However, these methods exhibit a pervasive enhancement bias towards the compression domain, inadvertently regarding it as more realistic than the raw domain. This bias makes enhanced images closely resemble their compressed counterparts, thus degrading their perceptual quality. In this paper, we propose a simple yet effective method to mitigate this bias and enhance the quality of compressed images. Our method employs a conditional discriminator with the compressed image as a key condition, and then incorporates a domain-divergence regularization to actively distance the enhancement domain from the compression domain. Through this dual strategy, our method enables the discrimination against the compression domain, and brings the enhancement domain closer to the raw domain. Comprehensive quality evaluations confirm the superiority of our method over other state-of-the-art methods without incurring inference overheads.
Authors: Jin Liu, Bo Wang, Chuanming Wang, Huiyuan Fu, Huadong Ma
Abstract: Capturing videos with wrong exposure usually produces unsatisfactory visual effects. While image exposure correction is a popular topic, the video counterpart is less explored in the literature. Directly applying prior image-based methods to input videos often results in temporal incoherence with low visual quality. Existing research in this area is also limited by the lack of high-quality benchmark datasets. To address these issues, we construct the first real-world paired video dataset, including both underexposure and overexposure dynamic scenes. To achieve spatial alignment, we utilize two DSLR cameras and a beam splitter to simultaneously capture improper and normal exposure videos. In addition, we propose a Video Exposure Correction Network (VECNet) based on Retinex theory, which incorporates a two-stream illumination learning mechanism to enhance the overexposure and underexposure factors, respectively. The estimated multi-frame reflectance and dual-path illumination components are fused at both feature and image levels, leading to visually appealing results. Experimental results demonstrate that the proposed method outperforms existing image exposure correction and underexposed video enhancement methods. The code and dataset will be available soon.
Authors: Deshan Gong, Ningtao Mao, He Wang
Abstract: We propose a new method for cloth digitalization. Deviating from existing methods which learn from data captured under relatively casual settings, we propose to learn from data captured in strictly tested measuring protocols, and find plausible physical parameters of the cloths. However, such data is currently absent, so we first propose a new dataset with accurate cloth measurements. Further, the data size is considerably smaller than the ones in current deep learning, due to the nature of the data capture process. To learn from small data, we propose a new Bayesian differentiable cloth model to estimate the complex material heterogeneity of real cloths. It can provide highly accurate digitalization from very limited data samples. Through exhaustive evaluation and comparison, we show our method is accurate in cloth digitalization, efficient in learning from limited data samples, and general in capturing material variations. Code and data are available https://github.com/realcrane/Bayesian-Differentiable-Physics-for-Cloth-Digitalization
URLs: https://github.com/realcrane/Bayesian-Differentiable-Physics-for-Cloth-Digitalization
Authors: Chao Wu, Xiaobin Chang, Ruixuan Wang
Abstract: Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and achieved substantial improvements.In this paper, a novel two-branch continual learning framework is proposed to further enhance most existing CL methods. Specifically, the main branch can be any existing CL model and the newly introduced side branch is a lightweight convolutional network. The output of each main branch block is modulated by the output of the corresponding side branch block. Such a simple two-branch model can then be easily implemented and learned with the vanilla optimization setting without whistles and bells.Extensive experiments with various settings on multiple image datasets show that the proposed framework yields consistent improvements over state-of-the-art methods.
Authors: Joo Chan Lee, Taejune Kim, Eunbyung Park, Simon S. Woo, Jong Hwan Ko
Abstract: There have been significant advancements in anomaly detection in an unsupervised manner, where only normal images are available for training. Several recent methods aim to detect anomalies based on a memory, comparing or reconstructing the input with directly stored normal features (or trained features with normal images). However, such memory-based approaches operate on a discrete feature space implemented by the nearest neighbor or attention mechanism, suffering from poor generalization or an identity shortcut issue outputting the same as input, respectively. Furthermore, the majority of existing methods are designed to detect single-class anomalies, resulting in unsatisfactory performance when presented with multiple classes of objects. To tackle all of the above challenges, we propose CRAD, a novel anomaly detection method for representing normal features within a "continuous" memory, enabled by transforming spatial features into coordinates and mapping them to continuous grids. Furthermore, we carefully design the grids tailored for anomaly detection, representing both local and global normal features and fusing them effectively. Our extensive experiments demonstrate that CRAD successfully generalizes the normal features and mitigates the identity shortcut, furthermore, CRAD effectively handles diverse classes in a single model thanks to the high-granularity continuous representation. In an evaluation using the MVTec AD dataset, CRAD significantly outperforms the previous state-of-the-art method by reducing 65.0% of the error for multi-class unified anomaly detection. The project page is available at https://tae-mo.github.io/crad/.
Authors: Dimitrios Kollias, Panagiotis Tzirakis, Alan Cowen, Stefanos Zafeiriou, Irene Kotsia, Alice Baird, Chris Gagne, Chunchang Shao, Guanyu Hu
Abstract: This paper describes the 6th Affective Behavior Analysis in-the-wild (ABAW) Competition, which is part of the respective Workshop held in conjunction with IEEE CVPR 2024. The 6th ABAW Competition addresses contemporary challenges in understanding human emotions and behaviors, crucial for the development of human-centered technologies. In more detail, the Competition focuses on affect related benchmarking tasks and comprises of five sub-challenges: i) Valence-Arousal Estimation (the target is to estimate two continuous affect dimensions, valence and arousal), ii) Expression Recognition (the target is to recognise between the mutually exclusive classes of the 7 basic expressions and 'other'), iii) Action Unit Detection (the target is to detect 12 action units), iv) Compound Expression Recognition (the target is to recognise between the 7 mutually exclusive compound expression classes), and v) Emotional Mimicry Intensity Estimation (the target is to estimate six continuous emotion dimensions). In the paper, we present these Challenges, describe their respective datasets and challenge protocols (we outline the evaluation metrics) and present the baseline systems as well as their obtained performance. More information for the Competition can be found in: https://affective-behavior-analysis-in-the-wild.github.io/6th.
URLs: https://affective-behavior-analysis-in-the-wild.github.io/6th.
Authors: Wei Chen, Zichen Miao, Qiang Qiu
Abstract: Efficient fine-tuning methods are critical to address the high computational and parameter complexity while adapting large pre-trained models to downstream tasks. Our study is inspired by prior research that represents each convolution filter as a linear combination of a small set of filter subspace elements, referred to as filter atoms. In this paper, we propose to fine-tune pre-trained models by adjusting only filter atoms, which are responsible for spatial-only convolution, while preserving spatially-invariant channel combination knowledge in atom coefficients. In this way, we bring a new filter subspace view for model tuning. Furthermore, each filter atom can be recursively decomposed as a combination of another set of atoms, which naturally expands the number of tunable parameters in the filter subspace. By only adapting filter atoms constructed by a small number of parameters, while maintaining the rest of model parameters constant, the proposed approach is highly parameter-efficient. It effectively preserves the capabilities of pre-trained models and prevents overfitting to downstream tasks. Extensive experiments show that such a simple scheme surpasses previous tuning baselines for both discriminate and generative tasks.
Authors: Zijin Yin, Kongming Liang, Bing Li, Zhanyu Ma, Jun Guo
Abstract: When deploying segmentation models in practice, it is critical to evaluate their behaviors in varied and complex scenes. Different from the previous evaluation paradigms only in consideration of global attribute variations (e.g. adverse weather), we investigate both local and global attribute variations for robustness evaluation. To achieve this, we construct a mask-preserved attribute editing pipeline to edit visual attributes of real images with precise control of structural information. Therefore, the original segmentation labels can be reused for the edited images. Using our pipeline, we construct a benchmark covering both object and image attributes (e.g. color, material, pattern, style). We evaluate a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models on their robustness to different types of variations. We find that both local and global attribute variations affect segmentation performances, and the sensitivity of models diverges across different variation types. We argue that local attributes have the same importance as global attributes, and should be considered in the robustness evaluation of segmentation models. Code: https://github.com/PRIS-CV/Pascal-EA.
Authors: Yunzhuo Sun, Yifang Xu, Zien Xie, Yukun Shu, Sidan Du
Abstract: Moment retrieval (MR) and highlight detection (HD) aim to identify relevant moments and highlights in video from corresponding natural language query. Large language models (LLMs) have demonstrated proficiency in various computer vision tasks. However, existing methods for MR\&HD have not yet been integrated with LLMs. In this letter, we propose a novel two-stage model that takes the output of LLMs as the input to the second-stage transformer encoder-decoder. First, MiniGPT-4 is employed to generate the detailed description of the video frame and rewrite the query statement, fed into the encoder as new features. Then, semantic similarity is computed between the generated description and the rewritten queries. Finally, continuous high-similarity video frames are converted into span anchors, serving as prior position information for the decoder. Experiments demonstrate that our approach achieves a state-of-the-art result, and by using only span anchors and similarity scores as outputs, positioning accuracy outperforms traditional methods, like Moment-DETR.
Authors: Tong Zheng, Shusaku Sone, Yoshitaka Ushiku, Yuki Oba, Jiaxin Ma
Abstract: This paper presents a Tri-branch Neural Fusion (TNF) approach designed for classifying multimodal medical images and tabular data. It also introduces two solutions to address the challenge of label inconsistency in multimodal classification. Traditional methods in multi-modality medical data classification often rely on single-label approaches, typically merging features from two distinct input modalities. This becomes problematic when features are mutually exclusive or labels differ across modalities, leading to reduced accuracy. To overcome this, our TNF approach implements a tri-branch framework that manages three separate outputs: one for image modality, another for tabular modality, and a third hybrid output that fuses both image and tabular data. The final decision is made through an ensemble method that integrates likelihoods from all three branches. We validate the effectiveness of TNF through extensive experiments, which illustrate its superiority over traditional fusion and ensemble methods in various convolutional neural networks and transformer-based architectures across multiple datasets.
Authors: Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita
Abstract: This paper proposes Group Activity Feature (GAF) learning in which features of multi-person activity are learned as a compact latent vector. Unlike prior work in which the manual annotation of group activities is required for supervised learning, our method learns the GAF through person attribute prediction without group activity annotations. By learning the whole network in an end-to-end manner so that the GAF is required for predicting the person attributes of people in a group, the GAF is trained as the features of multi-person activity. As a person attribute, we propose to use a person's action class and appearance features because the former is easy to annotate due to its simpleness, and the latter requires no manual annotation. In addition, we introduce a location-guided attribute prediction to disentangle the complex GAF for extracting the features of each target person properly. Various experimental results validate that our method outperforms SOTA methods quantitatively and qualitatively on two public datasets. Visualization of our GAF also demonstrates that our method learns the GAF representing fined-grained group activity classes. Code: https://github.com/chihina/GAFL-CVPR2024.
Authors: Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang
Abstract: Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting the potential of prompts as effective distillers for learning from larger teacher models. In this paper, we introduce an unsupervised domain prompt distillation framework, which aims to transfer the knowledge of a larger teacher model to a lightweight target model through prompt-driven imitation using unlabeled domain images. Specifically, our framework consists of two distinct stages. In the initial stage, we pre-train a large CLIP teacher model using domain (few-shot) labels. After pre-training, we leverage the unique decoupled-modality characteristics of CLIP by pre-computing and storing the text features as class vectors only once through the teacher text encoder. In the subsequent stage, the stored class vectors are shared across teacher and student image encoders for calculating the predicted logits. Further, we align the logits of both the teacher and student models via KL divergence, encouraging the student image encoder to generate similar probability distributions to the teacher through the learnable prompts. The proposed prompt distillation process eliminates the reliance on labeled data, enabling the algorithm to leverage a vast amount of unlabeled images within the domain. Finally, the well-trained student image encoders and pre-stored text features (class vectors) are utilized for inference. To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student. Extensive experiments on 11 datasets demonstrate the effectiveness of our method.
Authors: Chun-Peng Chang, Shaoxiang Wang, Alain Pagani, Didier Stricker
Abstract: 3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions. The source code and additional resources for this project are available on GitHub: https://github.com/birdy666/MiKASA-3DVG
Authors: Ruizhuo Song, Beiming Yuan
Abstract: Abstract reasoning problems challenge the perceptual and cognitive abilities of AI algorithms, demanding deeper pattern discernment and inductive reasoning beyond explicit image features. This study introduces PMoC, a tailored probability model for the Bongard-Logo problem, achieving high reasoning accuracy by constructing independent probability models. Additionally, we present Pose-Transformer, an enhanced Transformer-Encoder designed for complex abstract reasoning tasks, including Bongard-Logo, RAVEN, I-RAVEN, and PGM. Pose-Transformer incorporates positional information learning, inspired by capsule networks' pose matrices, enhancing its focus on local positional relationships in image data processing. When integrated with PMoC, it further improves reasoning accuracy. Our approach effectively addresses reasoning difficulties associated with abstract entities' positional changes, outperforming previous models on the OIG, D3$\times$3 subsets of RAVEN, and PGM databases. This research contributes to advancing AI's capabilities in abstract reasoning and cognitive pattern recognition.
Authors: Ruizhuo Song, Beiming Yuan
Abstract: Abstract reasoning problems pose significant challenges to artificial intelligence algorithms, demanding cognitive capabilities beyond those required for perception tasks. This study introduces the Triple-CFN approach to tackle the Bongard-Logo problem, achieving notable reasoning accuracy by implicitly reorganizing the concept space of conflicting instances. Additionally, the Triple-CFN paradigm proves effective for the RPM problem with necessary modifications, yielding competitive results. To further enhance performance on the RPM issue, we develop the Meta Triple-CFN network, which explicitly structures the problem space while maintaining interpretability on progressive patterns. The success of Meta Triple-CFN is attributed to its paradigm of modeling the conceptual space, equivalent to normalizing reasoning information. Based on this ideology, we introduce the Re-space layer, enhancing the performance of both Meta Triple-CFN and Triple-CFN. This paper aims to contribute to advancements in machine intelligence by exploring innovative network designs for addressing abstract reasoning problems, paving the way for further breakthroughs in this domain.
Authors: Ruizhuo Song, Beiming Yuan
Abstract: This paper achieves significant progress in the field of abstract reasoning, particularly in addressing Raven's Progressive Matrices (RPM) and Bongard-Logo problems. We propose the D2C approach, which redefines conceptual boundaries in these domains and bridges the gap between high-level concepts and their low-dimensional representations. Based on this, we further introduce the D3C method that handles Bongard-Logo problems and significantly improves reasoning accuracy by estimating the distribution of image representations and measuring their Sinkhorn distance. To enhance computational efficiency, we introduce the D3C-cos variant, which provides an efficient and accurate solution for RPM problems by constraining distribution distances. Additionally, we present Lico-Net, a network that combines D3C and D3C-cos to achieve state-of-the-art performance in both problem-solving and interpretability. Finally, we extend our approach to D4C, employing adversarial strategies to further refine conceptual boundaries and demonstrate notable improvements for both RPM and Bongard-Logo problems. Overall, our contributions offer a new perspective and practical solutions to the field of abstract reasoning.
Authors: Deepanway Ghosal, Vernon Toh Yan Han, Chia Yew Ken, Soujanya Poria
Abstract: This paper introduces the novel task of multimodal puzzle solving, framed within the context of visual question-answering. We present a new dataset, AlgoPuzzleVQA designed to challenge and evaluate the capabilities of multimodal language models in solving algorithmic puzzles that necessitate both visual understanding, language understanding, and complex algorithmic reasoning. We create the puzzles to encompass a diverse array of mathematical and algorithmic topics such as boolean logic, combinatorics, graph theory, optimization, search, etc., aiming to evaluate the gap between visual data interpretation and algorithmic problem-solving skills. The dataset is generated automatically from code authored by humans. All our puzzles have exact solutions that can be found from the algorithm without tedious human calculations. It ensures that our dataset can be scaled up arbitrarily in terms of reasoning complexity and dataset size. Our investigation reveals that large language models (LLMs) such as GPT4V and Gemini exhibit limited performance in puzzle-solving tasks. We find that their performance is near random in a multi-choice question-answering setup for a significant number of puzzles. The findings emphasize the challenges of integrating visual, language, and algorithmic knowledge for solving complex reasoning problems.
Authors: Yuhu Bai, Jiangning Zhang, Yuhang Dong, Guanzhong Tian, Liang Liu, Yunkang Cao, Yabiao Wang, Chengjie Wang
Abstract: Few-shot anomaly detection (FSAD) is essential in industrial manufacturing. However, existing FSAD methods struggle to effectively leverage a limited number of normal samples, and they may fail to detect and locate inconspicuous anomalies in the spatial domain. We further discover that these subtle anomalies would be more noticeable in the frequency domain. In this paper, we propose a Dual-Path Frequency Discriminators (DFD) network from a frequency perspective to tackle these issues. Specifically, we generate anomalies at both image-level and feature-level. Differential frequency components are extracted by the multi-frequency information construction module and supplied into the fine-grained feature construction module to provide adapted features. We consider anomaly detection as a discriminative classification problem, wherefore the dual-path feature discrimination module is employed to detect and locate the image-level and feature-level anomalies in the feature space. The discriminators aim to learn a joint representation of anomalous features and normal features in the latent space. Extensive experiments conducted on MVTec AD and VisA benchmarks demonstrate that our DFD surpasses current state-of-the-art methods. Source code will be available.
Authors: Ruicong Liu, Takehiko Ohkawa, Mingfang Zhang, Yoichi Sato
Abstract: The pursuit of accurate 3D hand pose estimation stands as a keystone for understanding human activity in the realm of egocentric vision. The majority of existing estimation methods still rely on single-view images as input, leading to potential limitations, e.g., limited field-of-view and ambiguity in depth. To address these problems, adding another camera to better capture the shape of hands is a practical direction. However, existing multi-view hand pose estimation methods suffer from two main drawbacks: 1) Requiring multi-view annotations for training, which are expensive. 2) During testing, the model becomes inapplicable if camera parameters/layout are not the same as those used in training. In this paper, we propose a novel Single-to-Dual-view adaptation (S2DHand) solution that adapts a pre-trained single-view estimator to dual views. Compared with existing multi-view training methods, 1) our adaptation process is unsupervised, eliminating the need for multi-view annotation. 2) Moreover, our method can handle arbitrary dual-view pairs with unknown camera parameters, making the model applicable to diverse camera settings. Specifically, S2DHand is built on certain stereo constraints, including pair-wise cross-view consensus and invariance of transformation between both views. These two stereo constraints are used in a complementary manner to generate pseudo-labels, allowing reliable adaptation. Evaluation results reveal that S2DHand achieves significant improvements on arbitrary camera pairs under both in-dataset and cross-dataset settings, and outperforms existing adaptation methods with leading performance. Project page: https://github.com/MickeyLLG/S2DHand.
Authors: Chaehyeon Song, Jaeho Shin, Myung-Hwan Jeon, Jongwoo Lim, Ayoung Kim
Abstract: In the literature, points and conics have been major features for camera geometric calibration. Although conics are more informative features than points, the loss of the conic property under distortion has critically limited the utility of conic features in camera calibration. Many existing approaches addressed conic-based calibration by ignoring distortion or introducing 3D spherical targets to circumvent this limitation. In this paper, we present a novel formulation for conic-based calibration using moments. Our derivation is based on the mathematical finding that the first moment can be estimated without bias even under distortion. This allows us to track moment changes during projection and distortion, ensuring the preservation of the first moment of the distorted conic. With an unbiased estimator, the circular patterns can be accurately detected at the sub-pixel level and can now be fully exploited for an entire calibration pipeline, resulting in significantly improved calibration. The entire code is readily available from https://github.com/ChaehyeonSong/discocal.
Authors: Edgar Medina, Leyong Loh
Abstract: Human motion prediction is still an open problem, which is extremely important for autonomous driving and safety applications. Although there are great advances in this area, the widely studied topic of adversarial attacks has not been applied to multi-regression models such as GCNs and MLP-based architectures in human motion prediction. This work intends to reduce this gap using extensive quantitative and qualitative experiments in state-of-the-art architectures similar to the initial stages of adversarial attacks in image classification. The results suggest that models are susceptible to attacks even on low levels of perturbation. We also show experiments with 3D transformations that affect the model performance, in particular, we show that most models are sensitive to simple rotations and translations which do not alter joint distances. We conclude that similar to earlier CNN models, motion forecasting tasks are susceptible to small perturbations and simple 3D transformations.
Authors: Yunhao Li, Hao Wang, Xue Ma, Jiali Yao, Shaohua Dong, Heng Fan, Libo Zhang
Abstract: Current multi-object tracking (MOT) aims to predict trajectories of targets (i.e.,"where") in videos. Yet, knowing merely "where" is insufficient in many crucial applications. In comparison, semantic understanding such as fine-grained behaviors, interactions, and overall summarized captions (i.e., "what") from videos, associated with "where", is highly-desired for comprehensive video analysis. Thus motivated, we introduce Semantic Multi-Object Tracking (SMOT), that aims to estimate object trajectories and meanwhile understand semantic details of associated trajectories including instance captions, instance interactions, and overall video captions, integrating "where" and "what" for tracking. In order to foster the exploration of SMOT, we propose BenSMOT, a large-scale Benchmark for Semantic MOT. Specifically, BenSMOT comprises 3,292 videos with 151K frames, covering various scenarios for semantic tracking of humans. BenSMOT provides annotations for the trajectories of targets, along with associated instance captions in natural language, instance interactions, and overall caption for each video sequence. To our best knowledge, BenSMOT is the first publicly available benchmark for SMOT. Besides, to encourage future research, we present a novel tracker named SMOTer, which is specially designed and end-to-end trained for SMOT, showing promising performance. By releasing BenSMOT, we expect to go beyond conventional MOT by predicting "where" and "what" for SMOT, opening up a new direction in tracking for video understanding. Our BenSMOT and SMOTer will be released.
Authors: Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, Sung-eui Yoon
Abstract: Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes. However, existing methods select only informative and relevant views using predefined scores for training and testing phases. This constraint renders the model impractical in real-world scenarios, where the availability of favorable combinations cannot always be ensured. We introduce and validate a view-combination score to indicate the effectiveness of the input view combination. We observe that previous methods output degenerate solutions under arbitrary and unfavorable sets. Building upon this finding, we propose UFORecon, a robust view-combination generalizable surface reconstruction framework. To achieve this, we apply cross-view matching transformers to model interactions between source images and build correlation frustums to capture global correlations. Additionally, we explicitly encode pairwise feature similarities as view-consistent priors. Our proposed framework significantly outperforms previous methods in terms of view-combination generalizability and also in the conventional generalizable protocol trained with favorable view-combinations. The code is available at https://github.com/Youngju-Na/UFORecon.
Authors: Yijiang Li, Sucheng Ren, Weipeng Deng, Yuzhi Xu, Ying Gao, Edith Ngai, Haohan Wang
Abstract: Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains that help models learn an invariant representation from the spurious features. Various domain augmentation have been proposed but largely rely on interpolating existing domains and frequently face difficulties in creating truly "novel" domains. Humans, on the other hand, can easily extrapolate novel domains, thus, an intriguing question arises: How can neural networks extrapolate like humans and achieve OOD generalization? We introduce a novel approach to domain extrapolation that leverages reasoning ability and the extensive knowledge encapsulated within large language models (LLMs) to synthesize entirely new domains. Starting with the class of interest, we query the LLMs to extract relevant knowledge for these novel domains. We then bridge the gap between the text-centric knowledge derived from LLMs and the pixel input space of the model using text-to-image generation techniques. By augmenting the training set of domain generalization datasets with high-fidelity, photo-realistic images of these new domains, we achieve significant improvements over all existing methods, as demonstrated in both single and multi-domain generalization across various benchmarks. With the ability to extrapolate any domains for any class, our method has the potential to learn a generalized model for any task without any data. To illustrate, we put forth a much more difficult setting termed, data-free domain generalization, that aims to learn a generalized model in the absence of any collected data. Our empirical findings support the above argument and our methods exhibit commendable performance in this setting, even surpassing the supervised setting by approximately 1-2\% on datasets such as VLCS.
Authors: Sara Atito, Muhammad Awais, Wenwu Wang, Mark D Plumbley, Josef Kittler
Abstract: Transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships. Constrained by the data hungry nature of transformers and the limited amount of labelled data, most transformer-based models for audio tasks are finetuned from ImageNet pretrained models, despite the huge gap between the domain of natural images and audio. This has motivated the research in self-supervised pretraining of audio transformers, which reduces the dependency on large amounts of labeled data and focuses on extracting concise representations of audio spectrograms. In this paper, we propose \textbf{L}ocal-\textbf{G}lobal \textbf{A}udio \textbf{S}pectrogram v\textbf{I}sion \textbf{T}ransformer, namely ASiT, a novel self-supervised learning framework that captures local and global contextual information by employing group masked model learning and self-distillation. We evaluate our pretrained models on both audio and speech classification tasks, including audio event classification, keyword spotting, and speaker identification. We further conduct comprehensive ablation studies, including evaluations of different pretraining strategies. The proposed ASiT framework significantly boosts the performance on all tasks and sets a new state-of-the-art performance in five audio and speech classification tasks, outperforming recent methods, including the approaches that use additional datasets for pretraining.
Authors: Xiaolei Liu, Ming Yi, Kangyi Ding, Bangzhou Xin, Yixiao Xu, Li Yan, Chao Shen
Abstract: Learning-based systems have been demonstrated to be vulnerable to backdoor attacks, wherein malicious users manipulate model performance by injecting backdoors into the target model and activating them with specific triggers. Previous backdoor attack methods primarily focused on two key metrics: attack success rate and stealthiness. However, these methods often necessitate significant privileges over the target model, such as control over the training process, making them challenging to implement in real-world scenarios. Moreover, the robustness of existing backdoor attacks is not guaranteed, as they prove sensitive to defenses such as image augmentations and model distillation. In this paper, we address these two limitations and introduce RSBA (Robust Statistical Backdoor Attack under Privilege-constrained Scenarios). The key insight of RSBA is that statistical features can naturally divide images into different groups, offering a potential implementation of triggers. This type of trigger is more robust than manually designed ones, as it is widely distributed in normal images. By leveraging these statistical triggers, RSBA enables attackers to conduct black-box attacks by solely poisoning the labels or the images. We empirically and theoretically demonstrate the robustness of RSBA against image augmentations and model distillation. Experimental results show that RSBA achieves a 99.83\% attack success rate in black-box scenarios. Remarkably, it maintains a high success rate even after model distillation, where attackers lack access to the training dataset of the student model (1.39\% success rate for baseline methods on average).
Authors: Micha{\l} Zaj\k{a}c, Tinne Tuytelaars, Gido M. van de Ven
Abstract: Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from excessive forgetting and imbalance of the scores assigned to classes that have not been seen together during training. In this study, we introduce a novel approach, Prediction Error-based Classification (PEC), which differs from traditional discriminative and generative classification paradigms. PEC computes a class score by measuring the prediction error of a model trained to replicate the outputs of a frozen random neural network on data from that class. The method can be interpreted as approximating a classification rule based on Gaussian Process posterior variance. PEC offers several practical advantages, including sample efficiency, ease of tuning, and effectiveness even when data are presented one class at a time. Our empirical results show that PEC performs strongly in single-pass-through-data CIL, outperforming other rehearsal-free baselines in all cases and rehearsal-based methods with moderate replay buffer size in most cases across multiple benchmarks.
Authors: Suraj Srinivas, Sebastian Bordt, Hima Lakkaraju
Abstract: One of the remarkable properties of robust computer vision models is that their input-gradients are often aligned with human perception, referred to in the literature as perceptually-aligned gradients (PAGs). Despite only being trained for classification, PAGs cause robust models to have rudimentary generative capabilities, including image generation, denoising, and in-painting. However, the underlying mechanisms behind these phenomena remain unknown. In this work, we provide a first explanation of PAGs via \emph{off-manifold robustness}, which states that models must be more robust off- the data manifold than they are on-manifold. We first demonstrate theoretically that off-manifold robustness leads input gradients to lie approximately on the data manifold, explaining their perceptual alignment. We then show that Bayes optimal models satisfy off-manifold robustness, and confirm the same empirically for robust models trained via gradient norm regularization, randomized smoothing, and adversarial training with projected gradient descent. Quantifying the perceptual alignment of model gradients via their similarity with the gradients of generative models, we show that off-manifold robustness correlates well with perceptual alignment. Finally, based on the levels of on- and off-manifold robustness, we identify three different regimes of robustness that affect both perceptual alignment and model accuracy: weak robustness, bayes-aligned robustness, and excessive robustness. Code is available at \url{https://github.com/tml-tuebingen/pags}.
Authors: Moule Lin, Weipeng Jing, Chao Li, Andr\'as Jung
Abstract: The building planar graph reconstruction, a.k.a. footprint reconstruction, which lies in the domain of computer vision and geoinformatics, has been long afflicted with the challenge of redundant parameters in conventional convolutional models. Therefore, in this letter, we proposed an advanced and adaptive shift architecture, namely the Switch operator, which incorporates non-exponential growth parameters while retaining analogous functionalities to integrate local feature spatial information, resembling a high-dimensional convolution operation. The Switch operator, cross-channel operation, architecture implements the XOR operation to alternately exchange adjacent or diagonal features, and then blends alternating channels through a 1x1 convolution operation to consolidate information from different channels. The SwitchNN architecture, on the other hand, incorporates a group-based parameter-sharing mechanism inspired by the convolutional neural network process and thereby significantly reducing the number of parameters. We validated our proposed approach through experiments on the SpaceNet corpus, a publicly available dataset annotated with 2,001 buildings across the cities of Los Angeles, Las Vegas, and Paris. Our results demonstrate the effectiveness of this innovative architecture in building planar graph reconstruction from 2D building images.
Authors: Ninad Khargonkar, Sai Haneesh Allu, Yangxiao Lu, Jishnu Jaykumar P, Balakrishnan Prabhakaran, Yu Xiang
Abstract: We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on pick-and-place. Our benchmark uses the YCB objects, a commonly used dataset in the robotics community, to ensure that our results are comparable to other studies. Additionally, the benchmark is designed to be easily reproducible in the real world, making it accessible to researchers and practitioners. We also provide our experimental results and analyzes for model-based and model-free 6D robotic grasping on the benchmark, where representative algorithms are evaluated for object perception, grasping planning, and motion planning. We believe that our benchmark will be a valuable tool for advancing the field of robot manipulation. By providing a standardized evaluation framework, researchers can more easily compare different techniques and algorithms, leading to faster progress in developing robot manipulation methods.
Authors: Weiran Lin, Keane Lucas, Neo Eyal, Lujo Bauer, Michael K. Reiter, Mahmood Sharif
Abstract: Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the true threat cannot be assessed accurately by existing attacks. Specifically, we find that conventional metrics measuring targeted and untargeted robustness do not appropriately reflect a model's ability to withstand attacks from one set of source classes to another set of target classes. To address the shortcomings of existing methods, we formally define a new metric, termed group-based robustness, that complements existing metrics and is better-suited for evaluating model performance in certain attack scenarios. We show empirically that group-based robustness allows us to distinguish between models' vulnerability against specific threat models in situations where traditional robustness metrics do not apply. Moreover, to measure group-based robustness efficiently and accurately, we 1) propose two loss functions and 2) identify three new attack strategies. We show empirically that with comparable success rates, finding evasive samples using our new loss functions saves computation by a factor as large as the number of targeted classes, and finding evasive samples using our new attack strategies saves time by up to 99\% compared to brute-force search methods. Finally, we propose a defense method that increases group-based robustness by up to 3.52$\times$.
Authors: Salome Kazeminia, Carsten Marr, Bastian Rieck
Abstract: In biomedical data analysis, Multiple Instance Learning (MIL) models have emerged as a powerful tool to classify patients' microscopy samples. However, the data-intensive requirement of these models poses a significant challenge in scenarios with scarce data availability, e.g., in rare diseases. We introduce a topological regularization term to MIL to mitigate this challenge. It provides a shape-preserving inductive bias that compels the encoder to maintain the essential geometrical-topological structure of input bags during projection into latent space. This enhances the performance and generalization of the MIL classifier regardless of the aggregation function, particularly for scarce training data. The effectiveness of our method is confirmed through experiments across a range of datasets, showing an average enhancement of 2.8% for MIL benchmarks, 15.3% for synthetic MIL datasets, and 5.5% for real-world biomedical datasets over the current state-of-the-art.
Authors: Bernard Lange, Jiachen Li, Mykel J. Kochenderfer
Abstract: Navigating complex and dynamic environments requires autonomous vehicles (AVs) to reason about both visible and occluded regions. This involves predicting the future motion of observed agents, inferring occluded ones, and modeling their interactions based on vectorized scene representations of the partially observable environment. However, prior work on occlusion inference and trajectory prediction have developed in isolation, with the former based on simplified rasterized methods and the latter assuming full environment observability. We introduce the Scene Informer, a unified approach for predicting both observed agent trajectories and inferring occlusions in a partially observable setting. It uses a transformer to aggregate various input modalities and facilitate selective queries on occlusions that might intersect with the AV's planned path. The framework estimates occupancy probabilities and likely trajectories for occlusions, as well as forecast motion for observed agents. We explore common observability assumptions in both domains and their performance impact. Our approach outperforms existing methods in both occupancy prediction and trajectory prediction in partially observable setting on the Waymo Open Motion Dataset.
Authors: Hao Chen, Jindong Wang, Ankit Shah, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj
Abstract: Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model. This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. More specifically, through extensive experiments of supervised pre-training models on synthetic noisy ImageNet-1K and YFCC15M datasets, we demonstrate that while slight noise in pre-training can benefit in-domain (ID) transfer performance, where the training and testing data share the same distribution, it always deteriorates out-of-domain (OOD) performance, where training and testing data distribution are different. We empirically verify that the reason behind is noise in pre-training shapes the feature space differently. We then propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization on both ID and OOD tasks, considering one may not be able to fully fine-tune or even access the pre-trained models. We conduct practical experiments on popular vision and language models that are pre-trained on noisy data for evaluation of our approach. Our analysis and results show the importance of this interesting and novel research direction, which we term Noisy Model Learning.
Authors: Mathias-Felipe de-Lima-Santos, Isabella Gon\c{c}alves, Marcos G. Quiles, Lucia Mesquita, Wilson Ceron, Maria Clara Couto Lorena
Abstract: In today's digital age, images have emerged as powerful tools for politicians to engage with their voters on social media platforms. Visual content possesses a unique emotional appeal that often leads to increased user engagement. However, research on visual communication remains relatively limited, particularly in the Global South. This study aims to bridge this gap by employing a combination of computational methods and qualitative approach to investigate the visual communication strategies employed in a dataset of 11,263 Instagram posts by 19 Brazilian presidential candidates in 2018 and 2022 national elections. Through two studies, we observed consistent patterns across these candidates on their use of visual political communication. Notably, we identify a prevalence of celebratory and positively toned images. They also exhibit a strong sense of personalization, portraying candidates connected with their voters on a more emotional level. Our research also uncovers unique contextual nuances specific to the Brazilian political landscape. We note a substantial presence of screenshots from news websites and other social media platforms. Furthermore, text-edited images with portrayals emerge as a prominent feature. In light of these results, we engage in a discussion regarding the implications for the broader field of visual political communication. This article serves as a testament to the pivotal role that Instagram has played in shaping the narrative of two fiercely polarized Brazilian elections, casting a revealing light on the ever-evolving dynamics of visual political communication in the digital age. Finally, we propose avenues for future research in the realm of visual political communication.
Authors: Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, Yibing Song
Abstract: We propose InstructDET, a data-centric method for referring object detection (ROD) that localizes target objects based on user instructions. While deriving from referring expressions (REC), the instructions we leverage are greatly diversified to encompass common user intentions related to object detection. For one image, we produce tremendous instructions that refer to every single object and different combinations of multiple objects. Each instruction and its corresponding object bounding boxes (bbxs) constitute one training data pair. In order to encompass common detection expressions, we involve emerging vision-language model (VLM) and large language model (LLM) to generate instructions guided by text prompts and object bbxs, as the generalizations of foundation models are effective to produce human-like expressions (e.g., describing object property, category, and relationship). We name our constructed dataset as InDET. It contains images, bbxs and generalized instructions that are from foundation models. Our InDET is developed from existing REC datasets and object detection datasets, with the expanding potential that any image with object bbxs can be incorporated through using our InstructDET method. By using our InDET dataset, we show that a conventional ROD model surpasses existing methods on standard REC datasets and our InDET test set. Our data-centric method InstructDET, with automatic data expansion by leveraging foundation models, directs a promising field that ROD can be greatly diversified to execute common object detection instructions.
Authors: Zhikang Dong, Bin Chen, Xiulong Liu, Pawel Polak, Peng Zhang
Abstract: Music recommendation for videos attracts growing interest in multi-modal research. However, existing systems focus primarily on content compatibility, often ignoring the users' preferences. Their inability to interact with users for further refinements or to provide explanations leads to a less satisfying experience. We address these issues with MuseChat, a first-of-its-kind dialogue-based recommendation system that personalizes music suggestions for videos. Our system consists of two key functionalities with associated modules: recommendation and reasoning. The recommendation module takes a video along with optional information including previous suggested music and user's preference as inputs and retrieves an appropriate music matching the context. The reasoning module, equipped with the power of Large Language Model (Vicuna-7B) and extended to multi-modal inputs, is able to provide reasonable explanation for the recommended music. To evaluate the effectiveness of MuseChat, we build a large-scale dataset, conversational music recommendation for videos, that simulates a two-turn interaction between a user and a recommender based on accurate music track information. Experiment results show that MuseChat achieves significant improvements over existing video-based music retrieval methods as well as offers strong interpretability and interactability.
Authors: Taehyo Kim, Hai Shu, Qiran Jia, Mony J. de Leon
Abstract: Voxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer's disease FDG-PET image analysis, demonstrate DeepFDR's superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.
Authors: Wei Jiang, Junru Li, Kai Zhang, Li Zhang
Abstract: Existing learned video compression models employ flow net or deformable convolutional networks (DCN) to estimate motion information. However, the limited receptive fields of flow net and DCN inherently direct their attentiveness towards the local contexts. Global contexts, such as large-scale motions and global correlations among frames are ignored, presenting a significant bottleneck for capturing accurate motions. To address this issue, we propose a joint local and global motion compensation module (LGMC) for leaned video coding. More specifically, we adopt flow net for local motion compensation. To capture global context, we employ the cross attention in feature domain for motion compensation. In addition, to avoid the quadratic complexity of vanilla cross attention, we divide the softmax operations in attention into two independent softmax operations, leading to linear complexity. To validate the effectiveness of our proposed LGMC, we integrate it with DCVC-TCM and obtain learned video compression with joint local and global motion compensation (LVC-LGMC). Extensive experiments demonstrate that our LVC-LGMC has significant rate-distortion performance improvements over baseline DCVC-TCM.
Authors: Saeed Vahidian, Mingyu Wang, Jianyang Gu, Vyacheslav Kungurtsev, Wei Jiang, Yiran Chen
Abstract: Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its applications span various domains, including transfer learning, federated learning, and neural architecture search. The most popular methods for constructing the synthetic data rely on matching the convergence properties of training the model with the synthetic dataset and the training dataset. However, targeting the training dataset must be thought of as auxiliary in the same sense that the training set is an approximate substitute for the population distribution, and the latter is the data of interest. Yet despite its popularity, an aspect that remains unexplored is the relationship of DD to its generalization, particularly across uncommon subgroups. That is, how can we ensure that a model trained on the synthetic dataset performs well when faced with samples from regions with low population density? Here, the representativeness and coverage of the dataset become salient over the guaranteed training error at inference. Drawing inspiration from distributionally robust optimization, we introduce an algorithm that combines clustering with the minimization of a risk measure on the loss to conduct DD. We provide a theoretical rationale for our approach and demonstrate its effective generalization and robustness across subgroups through numerical experiments. The source code is available in https://github.com/Mming11/RobustDatasetDistillation.
Authors: Nicholas Konz, Yuwen Chen, Haoyu Dong, Maciej A. Mazurowski
Abstract: Diffusion models have enabled remarkably high-quality medical image generation, yet it is challenging to enforce anatomical constraints in generated images. This hampers many useful applications, including pre-registered image generation, counterfactual scenarios, and others. To this end, we propose a diffusion model-based method that supports anatomically-controllable medical image generation, by following a multi-class anatomical segmentation mask at each sampling step. We additionally introduce a random mask ablation training algorithm to enable conditioning on a selected combination of anatomical constraints while allowing flexibility in other anatomical areas. We compare our model ("Seg-Diff") to existing methods on breast MRI and abdominal/neck-to-pelvis CT datasets with a wide range of anatomical objects. Results show that it reaches a new state-of-the-art in the faithfulness of generated images to input anatomical masks on both datasets, and is on par for general anatomical realism. Finally, our model also enjoys the extra benefit of being able to adjust the anatomical similarity of generated images to real images of choice through interpolation in its latent space.
Authors: Kate Sanders, Nathaniel Weir, Benjamin Van Durme
Abstract: It is challenging to perform question-answering over complex, multimodal content such as television clips. This is in part because current video-language models rely on single-modality reasoning, have lowered performance on long inputs, and lack interpetability. We propose TV-TREES, the first multimodal entailment tree generator. TV-TREES serves as an approach to video understanding that promotes interpretable joint-modality reasoning by producing trees of entailment relationships between simple premises directly entailed by the videos and higher-level conclusions. We then introduce the task of multimodal entailment tree generation to evaluate the reasoning quality of such methods. Our method's experimental results on the challenging TVQA dataset demonstrate intepretable, state-of-the-art zero-shot performance on full video clips, illustrating a best-of-both-worlds contrast to black-box methods.
Authors: Mengfei Ji, Yuchun Chang, Baolin Zhang, Zaid Al-Ars
Abstract: As machine learning (ML) algorithms get deployed in an ever-increasing number of applications, these algorithms need to achieve better trade-offs between high accuracy, high throughput and low latency. This paper introduces NASH, a novel approach that applies neural architecture search to machine learning hardware. Using NASH, hardware designs can achieve not only high throughput and low latency but also superior accuracy performance. We present four versions of the NASH strategy in this paper, all of which show higher accuracy than the original models. The strategy can be applied to various convolutional neural networks, selecting specific model operations among many to guide the training process toward higher accuracy. Experimental results show that applying NASH on ResNet18 or ResNet34 achieves a top 1 accuracy increase of up to 3.1% and a top 5 accuracy increase of up to 2.2% compared to the non-NASH version when tested on the ImageNet data set. We also integrated this approach into the FINN hardware model synthesis tool to automate the application of our approach and the generation of the hardware model. Results show that using FINN can achieve a maximum throughput of 324.5 fps. In addition, NASH models can also result in a better trade-off between accuracy and hardware resource utilization. The accuracy-hardware (HW) Pareto curve shows that the models with the four NASH versions represent the best trade-offs achieving the highest accuracy for a given HW utilization. The code for our implementation is open-source and publicly available on GitHub at https://github.com/MFJI/NASH.
Authors: Dimitrios Kollias, Anastasios Arsenos, Stefanos Kollias
Abstract: The paper presents the DEF-AI-MIA COV19D Competition, which is organized in the framework of the 'Domain adaptation, Explainability, Fairness in AI for Medical Image Analysis (DEF-AI-MIA)' Workshop of the 2024 Computer Vision and Pattern Recognition (CVPR) Conference. The Competition is the 4th in the series, following the first three Competitions held in the framework of ICCV 2021, ECCV 2022 and ICASSP 2023 International Conferences respectively. It includes two Challenges on: i) Covid-19 Detection and ii) Covid-19 Domain Adaptation. The Competition use data from COV19-CT-DB database, which is described in the paper and includes a large number of chest CT scan series. Each chest CT scan series consists of a sequence of 2-D CT slices, the number of which is between 50 and 700. Training, validation and test datasets have been extracted from COV19-CT-DB and provided to the participants in both Challenges. The paper presents the baseline models used in the Challenges and the performance which was obtained respectively.
Authors: Yameng Peng, Andy Song, Haytham M. Fayek, Vic Ciesielski, Xiaojun Chang
Abstract: Training-free metrics (a.k.a. zero-cost proxies) are widely used to avoid resource-intensive neural network training, especially in Neural Architecture Search (NAS). Recent studies show that existing training-free metrics have several limitations, such as limited correlation and poor generalisation across different search spaces and tasks. Hence, we propose Sample-Wise Activation Patterns and its derivative, SWAP-Score, a novel high-performance training-free metric. It measures the expressivity of networks over a batch of input samples. The SWAP-Score is strongly correlated with ground-truth performance across various search spaces and tasks, outperforming 15 existing training-free metrics on NAS-Bench-101/201/301 and TransNAS-Bench-101. The SWAP-Score can be further enhanced by regularisation, which leads to even higher correlations in cell-based search space and enables model size control during the search. For example, Spearman's rank correlation coefficient between regularised SWAP-Score and CIFAR-100 validation accuracies on NAS-Bench-201 networks is 0.90, significantly higher than 0.80 from the second-best metric, NWOT. When integrated with an evolutionary algorithm for NAS, our SWAP-NAS achieves competitive performance on CIFAR-10 and ImageNet in approximately 6 minutes and 9 minutes of GPU time respectively.
Authors: Weibin Liao, Yinghao Zhu, Xinyuan Wang, Chengwei Pan, Yasha Wang, Liantao Ma
Abstract: UNet and its variants have been widely used in medical image segmentation. However, these models, especially those based on Transformer architectures, pose challenges due to their large number of parameters and computational loads, making them unsuitable for mobile health applications. Recently, State Space Models (SSMs), exemplified by Mamba, have emerged as competitive alternatives to CNN and Transformer architectures. Building upon this, we employ Mamba as a lightweight substitute for CNN and Transformer within UNet, aiming at tackling challenges stemming from computational resource limitations in real medical settings. To this end, we introduce the Lightweight Mamba UNet (LightM-UNet) that integrates Mamba and UNet in a lightweight framework. Specifically, LightM-UNet leverages the Residual Vision Mamba Layer in a pure Mamba fashion to extract deep semantic features and model long-range spatial dependencies, with linear computational complexity. Extensive experiments conducted on two real-world 2D/3D datasets demonstrate that LightM-UNet surpasses existing state-of-the-art literature. Notably, when compared to the renowned nnU-Net, LightM-UNet achieves superior segmentation performance while drastically reducing parameter and computation costs by 116x and 21x, respectively. This highlights the potential of Mamba in facilitating model lightweighting. Our code implementation is publicly available at https://github.com/MrBlankness/LightM-UNet.