Authors: Vadim Holodovsky, Masada Tzabari, Yoav Schechner, Alex Frid, Klaus Schilling
Abstract: Platforms such as robots, security cameras, drones and satellites are used in multi-view imaging for three-dimensional (3D) recovery by stereoscopy or tomography. Each camera in the setup has a field of view (FOV). Multi-view analysis requires overlap of the FOVs of all cameras, or a significant subset of them. However, the success of such methods is not guaranteed, because the FOVs may not sufficiently overlap. The reason is that pointing of a camera from a mount or platform has some randomness (noise), due to imprecise platform control, typical to mechanical systems, and particularly moving systems such as satellites. So, success is probabilistic. This paper creates a framework to analyze this aspect. This is critical for setting limitations on the capabilities of imaging systems, such as resolution (pixel footprint), FOV, the size of domains that can be captured, and efficiency. The framework uses the fact that imprecise pointing can be mitigated by self-calibration - provided that there is sufficient overlap between pairs of views and sufficient visual similarity of views. We show an example considering the design of a formation of nanosatellites that seek 3D reconstruction of clouds.
Authors: Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
Abstract: This paper addresses the societal concerns arising from large-scale text-to-image diffusion models for generating potentially harmful or copyrighted content. Existing models rely heavily on internet-crawled data, wherein problematic concepts persist due to incomplete filtration processes. While previous approaches somewhat alleviate the issue, they often rely on text-specified concepts, introducing challenges in accurately capturing nuanced concepts and aligning model knowledge with human understandings. In response, we propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. The proposed framework can be built upon existing techniques for the same purpose, enhancing their alignment with human judgment. By doing so, we simplify the training objective with a self-distillation-based technique, providing a strong baseline for concept removal. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
Authors: Yong-Hyun Park, Sangdoo Yun, Jin-Hwa Kim, Junho Kim, Geonhui Jang, Yonghyun Jeong, Junghyo Jo, Gayoung Lee
Abstract: Recent advancements in text-to-image (T2I) models have greatly benefited from large-scale datasets, but they also pose significant risks due to the potential generation of unsafe content. To mitigate this issue, researchers have developed unlearning techniques to remove the model's ability to generate potentially harmful content. However, these methods are easily bypassed by adversarial attacks, making them unreliable for ensuring the safety of generated images. In this paper, we propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models while preserving their performance on unrelated topics. DUO employs a preference optimization approach using curated paired image data, ensuring that the model learns to remove unsafe visual concepts while retaining unrelated features. Furthermore, we introduce an output-preserving regularization term to maintain the model's generative capabilities on safe content. Extensive experiments demonstrate that DUO can robustly defend against various state-of-the-art red teaming methods without significant performance degradation on unrelated topics, as measured by FID and CLIP scores. Our work contributes to the development of safer and more reliable T2I models, paving the way for their responsible deployment in both closed-source and open-source scenarios.
Authors: Akin Caliskan, Berkay Kicanaoglu, Hyeongwoo Kim
Abstract: We propose PAV, Personalized Head Avatar for the synthesis of human faces under arbitrary viewpoints and facial expressions. PAV introduces a method that learns a dynamic deformable neural radiance field (NeRF), in particular from a collection of monocular talking face videos of the same character under various appearance and shape changes. Unlike existing head NeRF methods that are limited to modeling such input videos on a per-appearance basis, our method allows for learning multi-appearance NeRFs, introducing appearance embedding for each input video via learnable latent neural features attached to the underlying geometry. Furthermore, the proposed appearance-conditioned density formulation facilitates the shape variation of the character, such as facial hair and soft tissues, in the radiance field prediction. To the best of our knowledge, our approach is the first dynamic deformable NeRF framework to model appearance and shape variations in a single unified network for multi-appearances of the same subject. We demonstrate experimentally that PAV outperforms the baseline method in terms of visual rendering quality in our quantitative and qualitative studies on various subjects.
Authors: Bernard Lange, Masha Itkina, Jiachen Li, Mykel J. Kochenderfer
Abstract: Environment prediction frameworks are critical for the safe navigation of autonomous vehicles (AVs) in dynamic settings. LiDAR-generated occupancy grid maps (L-OGMs) offer a robust bird's-eye view for the scene representation, enabling self-supervised joint scene predictions while exhibiting resilience to partial observability and perception detection failures. Prior approaches have focused on deterministic L-OGM prediction architectures within the grid cell space. While these methods have seen some success, they frequently produce unrealistic predictions and fail to capture the stochastic nature of the environment. Additionally, they do not effectively integrate additional sensor modalities present in AVs. Our proposed framework performs stochastic L-OGM prediction in the latent space of a generative architecture and allows for conditioning on RGB cameras, maps, and planned trajectories. We decode predictions using either a single-step decoder, which provides high-quality predictions in real-time, or a diffusion-based batch decoder, which can further refine the decoded frames to address temporal consistency issues and reduce compression losses. Our experiments on the nuScenes and Waymo Open datasets show that all variants of our approach qualitatively and quantitatively outperform prior approaches.
Authors: Yuxuan Bian, Ailing Zeng, Xuan Ju, Xian Liu, Zhaoyang Zhang, Wei Liu, Qiang Xu
Abstract: Whole-body multi-modal motion generation, controlled by text, speech, or music, has numerous applications including video generation and character animation. However, employing a unified model to accomplish various generation tasks with different condition modalities presents two main challenges: motion distribution drifts across different generation scenarios and the complex optimization of mixed conditions with varying granularity. Furthermore, inconsistent motion formats in existing datasets further hinder effective multi-modal motion generation. In this paper, we propose ControlMM, a unified framework to Control whole-body Multi-modal Motion generation in a plug-and-play manner. To effectively learn and transfer motion knowledge across different motion distributions, we propose ControlMM-Attn, for parallel modeling of static and dynamic human topology graphs. To handle conditions with varying granularity, ControlMM employs a coarse-to-fine training strategy, including stage-1 text-to-motion pre-training for semantic generation and stage-2 multi-modal control adaptation for conditions of varying low-level granularity. To address existing benchmarks' varying motion format limitations, we introduce ControlMM-Bench, the first publicly available multi-modal whole-body human motion generation benchmark based on the unified whole-body SMPL-X format. Extensive experiments show that ControlMM achieves state-of-the-art performance across various standard motion generation tasks. Our website is at https://yxbian23.github.io/ControlMM.
Authors: Kerem Merto\u{g}lu, Yusuf \c{S}alk, Server Karahan Sar{\i}kaya, Kaya Turgut, Yasemin Evreneso\u{g}lu, Hakan \c{C}evikalp, \"Omer Nezih Gerek, Helin Duta\u{g}ac{\i}, David Rousseau
Abstract: Creation of new annotated public datasets is crucial in helping advances in 3D computer vision and machine learning meet their full potential for automatic interpretation of 3D plant models. In this paper, we introduce PLANesT-3D; a new annotated dataset of 3D color point clouds of plants. PLANesT-3D is composed of 34 point cloud models representing 34 real plants from three different plant species: \textit{Capsicum annuum}, \textit{Rosa kordana}, and \textit{Ribes rubrum}. Both semantic labels in terms of "leaf" and "stem", and organ instance labels were manually annotated for the full point clouds. As an additional contribution, SP-LSCnet, a novel semantic segmentation method that is a combination of unsupervised superpoint extraction and a 3D point-based deep learning approach is introduced and evaluated on the new dataset. Two existing deep neural network architectures, PointNet++ and RoseSegNet were also tested on the point clouds of PLANesT-3D for semantic segmentation.
Authors: Maisha Binte Rashid, Pablo Rivas
Abstract: Multimodal machine learning models that combine visual and textual data are increasingly being deployed in critical applications, raising significant safety and security concerns due to their vulnerability to adversarial attacks. This paper presents an effective strategy to enhance the robustness of multimodal image captioning models against such attacks. By leveraging the Fast Gradient Sign Method (FGSM) to generate adversarial examples and incorporating adversarial training techniques, we demonstrate improved model robustness on two benchmark datasets: Flickr8k and COCO. Our findings indicate that selectively training only the text decoder of the multimodal architecture shows performance comparable to full adversarial training while offering increased computational efficiency. This targeted approach suggests a balance between robustness and training costs, facilitating the ethical deployment of multimodal AI systems across various domains.
Authors: Ngoc Son Nguyen, Van Son Nguyen, Tung Le
Abstract: Visual Question Answering (VQA) has recently emerged as a potential research domain, captivating the interest of many in the field of artificial intelligence and computer vision. Despite the prevalence of approaches in English, there is a notable lack of systems specifically developed for certain languages, particularly Vietnamese. This study aims to bridge this gap by conducting comprehensive experiments on the Vietnamese Visual Question Answering (ViVQA) dataset, demonstrating the effectiveness of our proposed model. In response to community interest, we have developed a model that enhances image representation capabilities, thereby improving overall performance in the ViVQA system. Specifically, our model integrates the Bootstrapping Language-Image Pre-training with frozen unimodal models (BLIP-2) and the convolutional neural network EfficientNet to extract and process both local and global features from images. This integration leverages the strengths of transformer-based architectures for capturing comprehensive contextual information and convolutional networks for detailed local features. By freezing the parameters of these pre-trained models, we significantly reduce the computational cost and training time, while maintaining high performance. This approach significantly improves image representation and enhances the performance of existing VQA systems. We then leverage a multi-modal fusion module based on a general-purpose multi-modal foundation model (BEiT-3) to fuse the information between visual and textual features. Our experimental findings demonstrate that our model surpasses competing baselines, achieving promising performance. This is particularly evident in its accuracy of $71.04\%$ on the test set of the ViVQA dataset, marking a significant advancement in our research area. The code is available at https://github.com/nngocson2002/ViVQA.
Authors: Jae-Won Yang, Seungbin Hong, Jae-Young Sim
Abstract: Person search is the task to localize a query person in gallery datasets of scene images. Existing methods have been mainly developed to handle a single target dataset only, however diverse datasets are continuously given in practical applications of person search. In such cases, they suffer from the catastrophic knowledge forgetting in the old datasets when trained on new datasets. In this paper, we first introduce a novel problem of lifelong person search (LPS) where the model is incrementally trained on the new datasets while preserving the knowledge learned in the old datasets. We propose an end-to-end LPS framework that facilitates the knowledge distillation to enforce the consistency learning between the old and new models by utilizing the prototype features of the foreground persons as well as the hard background proposals in the old domains. Moreover, we also devise the rehearsal-based instance matching to further improve the discrimination ability in the old domains by using the unlabeled person instances additionally. Experimental results demonstrate that the proposed method achieves significantly superior performance of both the detection and re-identification to preserve the knowledge learned in the old domains compared with the existing methods.
Authors: Ziyu Zhao, Xiaoguang Li, Pingping Cai, Canyu Zhang, Song Wang
Abstract: Implicit representation mapping (IRM) can translate image features to any continuous resolution, showcasing its potent capability for ultra-high-resolution image segmentation refinement. Current IRM-based methods for refining ultra-high-resolution image segmentation often rely on CNN-based encoders to extract image features and apply a Shared Implicit Representation Mapping Function (SIRMF) to convert pixel-wise features into segmented results. Hence, these methods exhibit two crucial limitations. Firstly, the CNN-based encoder may not effectively capture long-distance information, resulting in a lack of global semantic information in the pixel-wise features. Secondly, SIRMF is shared across all samples, which limits its ability to generalize and handle diverse inputs. To address these limitations, we propose a novel approach that leverages the newly proposed Adaptive Implicit Representation Mapping (AIRM) for ultra-high-resolution Image Segmentation. Specifically, the proposed method comprises two components: (1) the Affinity Empowered Encoder (AEE), a robust feature extractor that leverages the benefits of the transformer architecture and semantic affinity to model long-distance features effectively, and (2) the Adaptive Implicit Representation Mapping Function (AIRMF), which adaptively translates pixel-wise features without neglecting the global semantic information, allowing for flexible and precise feature translation. We evaluated our method on the commonly used ultra-high-resolution segmentation refinement datasets, i.e., BIG and PASCAL VOC 2012. The extensive experiments demonstrate that our method outperforms competitors by a large margin. The code is provided in supplementary material.
Authors: Corn\'e Verburg, Alexander Heinlein, Eric C. Cyr
Abstract: The segmentation of ultra-high resolution images poses challenges such as loss of spatial information or computational inefficiency. In this work, a novel approach that combines encoder-decoder architectures with domain decomposition strategies to address these challenges is proposed. Specifically, a domain decomposition-based U-Net (DDU-Net) architecture is introduced, which partitions input images into non-overlapping patches that can be processed independently on separate devices. A communication network is added to facilitate inter-patch information exchange to enhance the understanding of spatial context. Experimental validation is performed on a synthetic dataset that is designed to measure the effectiveness of the communication network. Then, the performance is tested on the DeepGlobe land cover classification dataset as a real-world benchmark data set. The results demonstrate that the approach, which includes inter-patch communication for images divided into $16\times16$ non-overlapping subimages, achieves a $2-3\,\%$ higher intersection over union (IoU) score compared to the same network without inter-patch communication. The performance of the network which includes communication is equivalent to that of a baseline U-Net trained on the full image, showing that our model provides an effective solution for segmenting ultra-high-resolution images while preserving spatial context. The code is available at https://github.com/corne00/HiRes-Seg-CNN.
Authors: Rohini Banerjee, Cecilia G. Morales, Artur Dubrawski
Abstract: Efficient intravascular access in trauma and critical care significantly impacts patient outcomes. However, the availability of skilled medical personnel in austere environments is often limited. Autonomous robotic ultrasound systems can aid in needle insertion for medication delivery and support non-experts in such tasks. Despite advances in autonomous needle insertion, inaccuracies in vessel segmentation predictions pose risks. Understanding the uncertainty of predictive models in ultrasound imaging is crucial for assessing their reliability. We introduce MSU-Net, a novel multistage approach for training an ensemble of U-Nets to yield accurate ultrasound image segmentation maps. We demonstrate substantial improvements, 18.1% over a single Monte Carlo U-Net, enhancing uncertainty evaluations, model transparency, and trustworthiness. By highlighting areas of model certainty, MSU-Net can guide safe needle insertions, empowering non-experts to accomplish such tasks.
Authors: Yuhao Huang, Xin Yang, Han Zhou, Yan Cao, Haoran Dou, Fajin Dong, Dong Ni
Abstract: The Segment Anything Model (SAM) can achieve satisfactory segmentation performance under high-quality box prompts. However, SAM's robustness is compromised by the decline in box quality, limiting its practicality in clinical reality. In this study, we propose a novel Robust Box prompt based SAM (\textbf{RoBox-SAM}) to ensure SAM's segmentation performance under prompts with different qualities. Our contribution is three-fold. First, we propose a prompt refinement module to implicitly perceive the potential targets, and output the offsets to directly transform the low-quality box prompt into a high-quality one. We then provide an online iterative strategy for further prompt refinement. Second, we introduce a prompt enhancement module to automatically generate point prompts to assist the box-promptable segmentation effectively. Last, we build a self-information extractor to encode the prior information from the input image. These features can optimize the image embeddings and attention calculation, thus, the robustness of SAM can be further enhanced. Extensive experiments on the large medical segmentation dataset including 99,299 images, 5 modalities, and 25 organs/targets validated the efficacy of our proposed RoBox-SAM.
Authors: Zhuheng Lu, Ting Wu, Yuewei Dai, Weiqing Li, Zhiyong Su
Abstract: Two forms of imbalances are commonly observed in point cloud semantic segmentation datasets: (1) category imbalances, where certain objects are more prevalent than others; and (2) size imbalances, where certain objects occupy more points than others. Because of this, the majority of categories and large objects are favored in the existing evaluation metrics. This paper suggests fine-grained mIoU and mAcc for a more thorough assessment of point cloud segmentation algorithms in order to address these issues. Richer statistical information is provided for models and datasets by these fine-grained metrics, which also lessen the bias of current semantic segmentation metrics towards large objects. The proposed metrics are used to train and assess various semantic segmentation algorithms on three distinct indoor and outdoor semantic segmentation datasets.
Authors: Peiru Zheng, Yun Zhao, Zhan Gong, Hong Zhu, Shaohua Wu
Abstract: Many fields could benefit from the rapid development of the large language models (LLMs). The end-to-end autonomous driving (e2eAD) is one of the typically fields facing new opportunities as the LLMs have supported more and more modalities. Here, by utilizing vision-language model (VLM), we proposed an e2eAD method called SimpleLLM4AD. In our method, the e2eAD task are divided into four stages, which are perception, prediction, planning, and behavior. Each stage consists of several visual question answering (VQA) pairs and VQA pairs interconnect with each other constructing a graph called Graph VQA (GVQA). By reasoning each VQA pair in the GVQA through VLM stage by stage, our method could achieve e2e driving with language. In our method, vision transformers (ViT) models are employed to process nuScenes visual data, while VLM are utilized to interpret and reason about the information extracted from the visual inputs. In the perception stage, the system identifies and classifies objects from the driving environment. The prediction stage involves forecasting the potential movements of these objects. The planning stage utilizes the gathered information to develop a driving strategy, ensuring the safety and efficiency of the autonomous vehicle. Finally, the behavior stage translates the planned actions into executable commands for the vehicle. Our experiments demonstrate that SimpleLLM4AD achieves competitive performance in complex driving scenarios.
Authors: Lianghao Tan, Shubing Liu, Jing Gao, Xiaoyi Liu, Linyue Chu, Huangqi Jiang
Abstract: With the rapid advancement of deep learning technologies, computer vision has shown immense potential in retail automation. This paper presents a novel self-checkout system for retail based on an improved YOLOv10 network, aimed at enhancing checkout efficiency and reducing labor costs. We propose targeted optimizations to the YOLOv10 model, by incorporating the detection head structure from YOLOv8, which significantly improves product recognition accuracy. Additionally, we develop a post-processing algorithm tailored for self-checkout scenarios, to further enhance the application of system. Experimental results demonstrate that our system outperforms existing methods in both product recognition accuracy and checkout speed. This research not only provides a new technical solution for retail automation but offers valuable insights into optimizing deep learning models for real-world applications.
Authors: Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah
Abstract: Unsupervised domain adaptation (UDA) aims to mitigate the domain shift issue, where the distribution of training (source) data differs from that of testing (target) data. Many models have been developed to tackle this problem, and recently vision transformers (ViTs) have shown promising results. However, the complexity and large number of trainable parameters of ViTs restrict their deployment in practical applications. This underscores the need for an efficient model that not only reduces trainable parameters but also allows for adjustable complexity based on specific needs while delivering comparable performance. To achieve this, in this paper we introduce an Efficient Unsupervised Domain Adaptation (EUDA) framework. EUDA employs the DINOv2, which is a self-supervised ViT, as a feature extractor followed by a simplified bottleneck of fully connected layers to refine features for enhanced domain adaptation. Additionally, EUDA employs the synergistic domain alignment loss (SDAL), which integrates cross-entropy (CE) and maximum mean discrepancy (MMD) losses, to balance adaptation by minimizing classification errors in the source domain while aligning the source and target domain distributions. The experimental results indicate the effectiveness of EUDA in producing comparable results as compared with other state-of-the-art methods in domain adaptation with significantly fewer trainable parameters, between 42% to 99.7% fewer. This showcases the ability to train the model in a resource-limited environment. The code of the model is available at: https://github.com/A-Abedi/EUDA.
Authors: Mieko Ochi, Daisuke Komura, Shumpei Ishikawa
Abstract: Pathology has played a crucial role in the diagnosis and evaluation of patient tissue samples obtained from surgeries and biopsies for many years. The advent of Whole Slide Scanners and the development of deep learning technologies have significantly advanced the field, leading to extensive research and development in pathology AI (Artificial Intelligence). These advancements have contributed to reducing the workload of pathologists and supporting decision-making in treatment plans. Recently, large-scale AI models known as Foundation Models (FMs), which are more accurate and applicable to a wide range of tasks compared to traditional AI, have emerged, and expanded their application scope in the healthcare field. Numerous FMs have been developed in pathology, and there are reported cases of their application in various tasks, such as disease diagnosis, rare cancer diagnosis, patient survival prognosis prediction, biomarker expression prediction, and the scoring of immunohistochemical expression intensity. However, several challenges remain for the clinical application of FMs, which healthcare professionals, as users, must be aware of. Research is ongoing to address these challenges. In the future, it is expected that the development of Generalist Medical AI, which integrates pathology FMs with FMs from other medical domains, will progress, leading to the effective utilization of AI in real clinical settings to promote precision and personalized medicine.
Authors: Shiyuan Chen, Jiaxin Zhang, Ruohong Mei, Yingfeng Cai, Haoran Yin, Tao Chen, Wei Sui, Cong Yang
Abstract: The recent development of online static map element (a.k.a. HD map) construction algorithms has raised a vast demand for data with ground truth annotations. However, available public datasets currently cannot provide high-quality training data regarding consistency and accuracy. For instance, the manual labelled (low efficiency) nuScenes still contains misalignment and inconsistency between the HD maps and images (e.g., around 8.03 pixels reprojection error on average). To this end, we present CAMAv2: a vision-centric approach for Consistent and Accurate Map Annotation. Without LiDAR inputs, our proposed framework can still generate high-quality 3D annotations of static map elements. Specifically, the annotation can achieve high reprojection accuracy across all surrounding cameras and is spatial-temporal consistent across the whole sequence. We apply our proposed framework to the popular nuScenes dataset to provide efficient and highly accurate annotations. Compared with the original nuScenes static map element, our CAMAv2 annotations achieve lower reprojection errors (e.g., 4.96 vs. 8.03 pixels). Models trained with annotations from CAMAv2 also achieve lower reprojection errors (e.g., 5.62 vs. 8.43 pixels).
Authors: Can Wang, Hongliang Zhong, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao
Abstract: Automatic furniture layout is long desired for convenient interior design. Leveraging the remarkable visual reasoning capabilities of multimodal large language models (MLLMs), recent methods address layout generation in a static manner, lacking the feedback-driven refinement essential for interactive user engagement. We introduce Chat2Layout, a novel interactive furniture layout generation system that extends the functionality of MLLMs into the realm of interactive layout design. To achieve this, we establish a unified vision-question paradigm for in-context learning, enabling seamless communication with MLLMs to steer their behavior without altering model weights. Within this framework, we present a novel training-free visual prompting mechanism. This involves a visual-text prompting technique that assist MLLMs in reasoning about plausible layout plans, followed by an Offline-to-Online search (O2O-Search) method, which automatically identifies the minimal set of informative references to provide exemplars for visual-text prompting. By employing an agent system with MLLMs as the core controller, we enable bidirectional interaction. The agent not only comprehends the 3D environment and user requirements through linguistic and visual perception but also plans tasks and reasons about actions to generate and arrange furniture within the virtual space. Furthermore, the agent iteratively updates based on visual feedback from execution results. Experimental results demonstrate that our approach facilitates language-interactive generation and arrangement for diverse and complex 3D furniture.
Authors: Jiangyi Wang, Zhongyao Cheng, Na Zhao, Jun Cheng, Xulei Yang
Abstract: Point cloud analysis is challenging due to its unique characteristics of unorderness, sparsity and irregularity. Prior works attempt to capture local relationships by convolution operations or attention mechanisms, exploiting geometric information from coordinates implicitly. These methods, however, are insufficient to describe the explicit local geometry, e.g., curvature and orientation. In this paper, we propose On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module. This is inspired by Point Feature Histogram (PFH) from computer vision community. However, the utilization of vanilla PFH encounters great difficulties when applied to large datasets and dense point clouds, as it demands considerable time for feature generation. In contrast, we introduce the Local Reference Constructor module, which approximates the local coordinate systems based on triangle sets. Owing to this, our OPFR only requires extra 1.56ms for inference (65x faster than vanilla PFH) and 0.012M more parameters, and it can serve as a versatile plug-and-play module for various backbones, particularly MLP-based and Transformer-based backbones examined in this study. Additionally, we introduce the novel Hierarchical Sampling module aimed at enhancing the quality of triangle sets, thereby ensuring robustness of the obtained geometric features. Our proposed method improves overall accuracy (OA) on ModelNet40 from 90.7% to 94.5% (+3.8%) for classification, and OA on S3DIS Area-5 from 86.4% to 90.0% (+3.6%) for semantic segmentation, respectively, building upon PointNet++ backbone. When integrated with Point Transformer backbone, we achieve state-of-the-art results on both tasks: 94.8% OA on ModelNet40 and 91.7% OA on S3DIS Area-5.
Authors: Pieter M. Blok, Federico Magistri, Cyrill Stachniss, Haozhou Wang, James Burridge, Wei Guo
Abstract: Potato yield is an important metric for farmers to further optimize their cultivation practices. Potato yield can be estimated on a harvester using an RGB-D camera that can estimate the three-dimensional (3D) volume of individual potato tubers. A challenge, however, is that the 3D shape derived from RGB-D images is only partially completed, underestimating the actual volume. To address this issue, we developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images. CoRe++ is a deep learning network that consists of a convolutional encoder and a decoder. The encoder compresses RGB-D images into latent vectors that are used by the decoder to complete the 3D shape using the deep signed distance field network (DeepSDF). To evaluate our CoRe++ network, we collected partial and complete 3D point clouds of 339 potato tubers on an operational harvester in Japan. On the 1425 RGB-D images in the test set (representing 51 unique potato tubers), our network achieved a completion accuracy of 2.8 mm on average. For volumetric estimation, the root mean squared error (RMSE) was 22.6 ml, and this was better than the RMSE of the linear regression (31.1 ml) and the base model (36.9 ml). We found that the RMSE can be further reduced to 18.2 ml when performing the 3D shape completion in the center of the RGB-D image. With an average 3D shape completion time of 10 milliseconds per tuber, we can conclude that CoRe++ is both fast and accurate enough to be implemented on an operational harvester for high-throughput potato yield estimation. Our code, network weights and dataset are publicly available at https://github.com/UTokyo-FieldPhenomics-Lab/corepp.git.
URLs: https://github.com/UTokyo-FieldPhenomics-Lab/corepp.git.
Authors: Zilong Zhang, Chang Niu, Zhibin Zhao, Xingwu Zhang, Xuefeng Chen
Abstract: Vision-based industrial inspection (VII) aims to locate defects quickly and accurately. Supervised learning under a close-set setting and industrial anomaly detection, as two common paradigms in VII, face different problems in practical applications. The former is that various and sufficient defects are difficult to obtain, while the latter is that specific defects cannot be located. To solve these problems, in this paper, we focus on the few-shot semantic segmentation (FSS) method, which can locate unseen defects conditioned on a few annotations without retraining. Compared to common objects in natural images, the defects in VII are small. This brings two problems to current FSS methods: 1 distortion of target semantics and 2 many false positives for backgrounds. To alleviate these problems, we propose a small object few-shot segmentation (SOFS) model. The key idea for alleviating 1 is to avoid the resizing of the original image and correctly indicate the intensity of target semantics. SOFS achieves this idea via the non-resizing procedure and the prototype intensity downsampling of support annotations. To alleviate 2, we design an abnormal prior map in SOFS to guide the model to reduce false positives and propose a mixed normal Dice loss to preferentially prevent the model from predicting false positives. SOFS can achieve FSS and few-shot anomaly detection determined by support masks. Diverse experiments substantiate the superior performance of SOFS. Code is available at https://github.com/zhangzilongc/SOFS.
Authors: Xilei Zhu, Liu Yang, Huiyu Duan, Xiongkuo Min, Guangtao Zhai, Patrick Le Callet
Abstract: With the development of eXtended Reality (XR), head-mounted shooting and display technology have experienced significant advancement and gained considerable attention. Egocentric spatial images and videos are emerging as a compelling form of stereoscopic XR content. Different from traditional 2D images, egocentric spatial images present challenges for perceptual quality assessment due to their special shooting, processing methods, and stereoscopic characteristics. However, the corresponding image quality assessment (IQA) research for egocentric spatial images is still lacking. In this paper, we establish the Egocentric Spatial Images Quality Assessment Database (ESIQAD), the first IQA database dedicated for egocentric spatial images as far as we know. Our ESIQAD includes 500 egocentric spatial images, containing 400 images captured with the Apple Vision Pro and 100 images generated via an iPhone's "Spatial Camera" app. The corresponding mean opinion scores (MOSs) are collected under three viewing modes, including 2D display, 3D-window display, and 3D-immersive display. Furthermore, based on our database, we conduct a benchmark experiment and evaluate the performance of 22 state-of-the-art IQA models under three different viewing modes. We hope this research can facilitate future IQA research on egocentric spatial images. The database is available at https://github.com/IntMeGroup/ESIQA.
Authors: Danfeng Guo, Demetri Terzopoulos
Abstract: Large Vision-Language Models (LVLMs) have achieved significant success in recent years, and they have been extended to the medical domain. Although demonstrating satisfactory performance on medical Visual Question Answering (VQA) tasks, Medical LVLMs (MLVLMs) suffer from the hallucination problem, which makes them fail to diagnose complex pathologies. Moreover, they readily fail to learn minority pathologies due to imbalanced training data. We propose two prompting strategies for MLVLMs that reduce hallucination and improve VQA performance. In the first strategy, we provide a detailed explanation of the queried pathology. In the second strategy, we fine-tune a cheap, weak learner to achieve high performance on a specific metric, and textually provide its judgment to the MLVLM. Tested on the MIMIC-CXR-JPG and Chexpert datasets, our methods significantly improve the diagnostic F1 score, with the highest increase being 0.27. We also demonstrate that our prompting strategies can be extended to general LVLM domains. Based on POPE metrics, it effectively suppresses the false negative predictions of existing LVLMs and improves Recall by approximately 0.07.
Authors: Pei-Kai Huang, Tzu-Hsien Chen, Ya-Ting Chan, Kuan-Wen Chen, Chiou-Ting Hsu
Abstract: Remote Photoplethysmography (rPPG) aims to measure physiological signals and Heart Rate (HR) from facial videos. Recent unsupervised rPPG estimation methods have shown promising potential in estimating rPPG signals from facial regions without relying on ground truth rPPG signals. However, these methods seem oblivious to interference existing in rPPG signals and still result in unsatisfactory performance. In this paper, we propose a novel De-interfered and Descriptive rPPG Estimation Network (DD-rPPGNet) to eliminate the interference within rPPG features for learning genuine rPPG signals. First, we investigate the characteristics of local spatial-temporal similarities of interference and design a novel unsupervised model to estimate the interference. Next, we propose an unsupervised de-interfered method to learn genuine rPPG signals with two stages. In the first stage, we estimate the initial rPPG signals by contrastive learning from both the training data and their augmented counterparts. In the second stage, we use the estimated interference features to derive de-interfered rPPG features and encourage the rPPG signals to be distinct from the interference. In addition, we propose an effective descriptive rPPG feature learning by developing a strong 3D Learnable Descriptive Convolution (3DLDC) to capture the subtle chrominance changes for enhancing rPPG estimation. Extensive experiments conducted on five rPPG benchmark datasets demonstrate that the proposed DD-rPPGNet outperforms previous unsupervised rPPG estimation methods and achieves competitive performances with state-of-the-art supervised rPPG methods.
Authors: Zhichao Zhang, Xinyue Li, Wei Sun, Jun Jia, Xiongkuo Min, Zicheng Zhang, Chunyi Li, Zijian Chen, Puyi Wang, Zhongpeng Ji, Fengyu Sun, Shangling Jui, Guangtao Zhai
Abstract: In recent years, artificial intelligence (AI) driven video generation has garnered significant attention due to advancements in stable diffusion and large language model techniques. Thus, there is a great demand for accurate video quality assessment (VQA) models to measure the perceptual quality of AI-generated content (AIGC) videos as well as optimize video generation techniques. However, assessing the quality of AIGC videos is quite challenging due to the highly complex distortions they exhibit (e.g., unnatural action, irrational objects, etc.). Therefore, in this paper, we try to systemically investigate the AIGC-VQA problem from both subjective and objective quality assessment perspectives. For the subjective perspective, we construct a Large-scale Generated Vdeo Quality assessment (LGVQ) dataset, consisting of 2,808 AIGC videos generated by 6 video generation models using 468 carefully selected text prompts. Unlike previous subjective VQA experiments, we evaluate the perceptual quality of AIGC videos from three dimensions: spatial quality, temporal quality, and text-to-video alignment, which hold utmost importance for current video generation techniques. For the objective perspective, we establish a benchmark for evaluating existing quality assessment metrics on the LGVQ dataset, which reveals that current metrics perform poorly on the LGVQ dataset. Thus, we propose a Unify Generated Video Quality assessment (UGVQ) model to comprehensively and accurately evaluate the quality of AIGC videos across three aspects using a unified model, which uses visual, textual and motion features of video and corresponding prompt, and integrates key features to enhance feature expression. We hope that our benchmark can promote the development of quality evaluation metrics for AIGC videos. The LGVQ dataset and the UGVQ metric will be publicly released.
Authors: Yuhang Ming, Minyang Xu, Xingrui Yang, Weicai Ye, Weihan Wang, Yong Peng, Weichen Dai, Wanzeng Kong
Abstract: Visual place recognition (VPR) is an essential component of many autonomous and augmented/virtual reality systems. It enables the systems to robustly localize themselves in large-scale environments. Existing VPR methods demonstrate attractive performance at the cost of heavy pre-training and limited generalizability. When deployed in unseen environments, these methods exhibit significant performance drops. Targeting this issue, we present VIPeR, a novel approach for visual incremental place recognition with the ability to adapt to new environments while retaining the performance of previous environments. We first introduce an adaptive mining strategy that balances the performance within a single environment and the generalizability across multiple environments. Then, to prevent catastrophic forgetting in lifelong learning, we draw inspiration from human memory systems and design a novel memory bank for our VIPeR. Our memory bank contains a sensory memory, a working memory and a long-term memory, with the first two focusing on the current environment and the last one for all previously visited environments. Additionally, we propose a probabilistic knowledge distillation to explicitly safeguard the previously learned knowledge. We evaluate our proposed VIPeR on three large-scale datasets, namely Oxford Robotcar, Nordland, and TartanAir. For comparison, we first set a baseline performance with naive finetuning. Then, several more recent lifelong learning methods are compared. Our VIPeR achieves better performance in almost all aspects with the biggest improvement of 13.65% in average performance.
Authors: Chenfan Qu, Yiwu Zhong, Fengjun Guo, Lianwen Jin
Abstract: The rapid advancements of generative AI have fueled the potential of generative text image editing while simultaneously escalating the threat of misinformation spreading. However, existing forensics methods struggle to detect unseen forgery types that they have not been trained on, leaving the development of a model capable of generalized detection of tampered scene text as an unresolved issue. To tackle this, we propose a novel task: open-set tampered scene text detection, which evaluates forensics models on their ability to identify both seen and previously unseen forgery types. We have curated a comprehensive, high-quality dataset, featuring the texts tampered by eight text editing models, to thoroughly assess the open-set generalization capabilities. Further, we introduce a novel and effective pre-training paradigm that subtly alters the texture of selected texts within an image and trains the model to identify these regions. This approach not only mitigates the scarcity of high-quality training data but also enhances models' fine-grained perception and open-set generalization abilities. Additionally, we present DAF, a novel framework that improves open-set generalization by distinguishing between the features of authentic and tampered text, rather than focusing solely on the tampered text's features. Our extensive experiments validate the remarkable efficacy of our methods. For example, our zero-shot performance can even beat the previous state-of-the-art full-shot model by a large margin. Our dataset and code will be open-source.
Authors: Antonia Bieringer, Olaf Wysocki, Sebastian Tuttas, Ludwig Hoegner, Christoph Holst
Abstract: Numerous navigation applications rely on data from global navigation satellite systems (GNSS), even though their accuracy is compromised in urban areas, posing a significant challenge, particularly for precise autonomous car localization. Extensive research has focused on enhancing localization accuracy by integrating various sensor types to address this issue. This paper introduces a novel approach for car localization, leveraging image features that correspond with highly detailed semantic 3D building models. The core concept involves augmenting positioning accuracy by incorporating prior geometric and semantic knowledge into calculations. The work assesses outcomes using Level of Detail 2 (LoD2) and Level of Detail 3 (LoD3) models, analyzing whether facade-enriched models yield superior accuracy. This comprehensive analysis encompasses diverse methods, including off-the-shelf feature matching and deep learning, facilitating thorough discussion. Our experiments corroborate that LoD3 enables detecting up to 69\% more features than using LoD2 models. We believe that this study will contribute to the research of enhancing positioning accuracy in GNSS-denied urban canyons. It also shows a practical application of under-explored LoD3 building models on map-based car positioning.
Authors: Jingwei Zhu, Olaf Wysocki, Christoph Holst, Thomas H. Kolbe
Abstract: Thermal point clouds integrate thermal radiation and laser point clouds effectively. However, the semantic information for the interpretation of building thermal point clouds can hardly be precisely inferred. Transferring the semantics encapsulated in 3D building models at LoD3 has a potential to fill this gap. In this work, we propose a workflow enriching thermal point clouds with the geo-position and semantics of LoD3 building models, which utilizes features of both modalities: The proposed method can automatically co-register the point clouds from different sources and enrich the thermal point cloud in facade-detailed semantics. The enriched thermal point cloud supports thermal analysis and can facilitate the development of currently scarce deep learning models operating directly on thermal point clouds.
Authors: Lijun Zhang, Wei Suo, Peng Wang, Yanning Zhang
Abstract: Human-object interactions (HOI) detection aims at capturing human-object pairs in images and corresponding actions. It is an important step toward high-level visual reasoning and scene understanding. However, due to the natural bias from the real world, existing methods mostly struggle with rare human-object pairs and lead to sub-optimal results. Recently, with the development of the generative model, a straightforward approach is to construct a more balanced dataset based on a group of supplementary samples. Unfortunately, there is a significant domain gap between the generated data and the original data, and simply merging the generated images into the original dataset cannot significantly boost the performance. To alleviate the above problem, we present a novel model-agnostic framework called \textbf{C}ontext-\textbf{E}nhanced \textbf{F}eature \textbf{A}lignment (CEFA) module, which can effectively align the generated data with the original data at the feature level and bridge the domain gap. Specifically, CEFA consists of a feature alignment module and a context enhancement module. On one hand, considering the crucial role of human-object pairs information in HOI tasks, the feature alignment module aligns the human-object pairs by aggregating instance information. On the other hand, to mitigate the issue of losing important context information caused by the traditional discriminator-style alignment method, we employ a context-enhanced image reconstruction module to improve the model's learning ability of contextual cues. Extensive experiments have shown that our method can serve as a plug-and-play module to improve the detection performance of HOI models on rare categories\footnote{https://github.com/LijunZhang01/CEFA}.
Authors: Jinho Jeong, Jinwoo Kim, Younghyun Jo, Seon Joo Kim
Abstract: In recent times, the need for effective super-resolution (SR) techniques has surged, especially for large-scale images ranging 2K to 8K resolutions. For DNN-based SISR, decomposing images into overlapping patches is typically necessary due to computational constraints. In such patch-decomposing scheme, one can allocate computational resources differently based on each patch's difficulty to further improve efficiency while maintaining SR performance. However, this approach has a limitation: computational resources is uniformly allocated within a patch, leading to lower efficiency when the patch contain pixels with varying levels of restoration difficulty. To address the issue, we propose the Pixel-level Classifier for Single Image Super-Resolution (PCSR), a novel method designed to distribute computational resources adaptively at the pixel level. A PCSR model comprises a backbone, a pixel-level classifier, and a set of pixel-level upsamplers with varying capacities. The pixel-level classifier assigns each pixel to an appropriate upsampler based on its restoration difficulty, thereby optimizing computational resource usage. Our method allows for performance and computational cost balance during inference without re-training. Our experiments demonstrate PCSR's advantage over existing patch-distributing methods in PSNR-FLOP trade-offs across different backbone models and benchmarks. The code is available at https://github.com/3587jjh/PCSR.
Authors: Sudhir Yarram, Junsong Yuan
Abstract: Video extrapolation in space and time (VEST) enables viewers to forecast a 3D scene into the future and view it from novel viewpoints. Recent methods propose to learn an entangled representation, aiming to model layered scene geometry, motion forecasting and novel view synthesis together, while assuming simplified affine motion and homography-based warping at each scene layer, leading to inaccurate video extrapolation. Instead of entangled scene representation and rendering, our approach chooses to disentangle scene geometry from scene motion, via lifting the 2D scene to 3D point clouds, which enables high quality rendering of future videos from novel views. To model future 3D scene motion, we propose a disentangled two-stage approach that initially forecasts ego-motion and subsequently the residual motion of dynamic objects (e.g., cars, people). This approach ensures more precise motion predictions by reducing inaccuracies from entanglement of ego-motion with dynamic object motion, where better ego-motion forecasting could significantly enhance the visual outcomes. Extensive experimental analysis on two urban scene datasets demonstrate superior performance of our proposed method in comparison to strong baselines.
Authors: Alexandra Kapp, Edith Hoffmann, Esther Weigmann, Helena Mihaljevi\'c
Abstract: Road unevenness significantly impacts the safety and comfort of various traffic participants, especially vulnerable road users such as cyclists and wheelchair users. This paper introduces StreetSurfaceVis, a novel dataset comprising 9,122 street-level images collected from a crowdsourcing platform and manually annotated by road surface type and quality. The dataset is intended to train models for comprehensive surface assessments of road networks. Existing open datasets are constrained by limited geospatial coverage and camera setups, typically excluding cycleways and footways. By crafting a heterogeneous dataset, we aim to fill this gap and enable robust models that maintain high accuracy across diverse image sources. However, the frequency distribution of road surface types and qualities is highly imbalanced. We address the challenge of ensuring sufficient images per class while reducing manual annotation by proposing a sampling strategy that incorporates various external label prediction resources. More precisely, we estimate the impact of (1) enriching the image data with OpenStreetMap tags, (2) iterative training and application of a custom surface type classification model, (3) amplifying underrepresented classes through prompt-based classification with GPT-4o or similarity search using image embeddings. We show that utilizing a combination of these strategies effectively reduces manual annotation workload while ensuring sufficient class representation.
Authors: Kuo Wang, Lechao Cheng, Weikai Chen, Pingping Zhang, Liang Lin, Fan Zhou, Guanbin Li
Abstract: Learning from pseudo-labels that generated with VLMs~(Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies. However, due to the domain gap between VLM and vision-detection tasks, pseudo-labels produced by the VLMs are prone to be noisy, while the training design of the detector further amplifies the bias. In this work, we investigate the root cause of VLMs' biased prediction under the OVD context. Our observations lead to a simple yet effective paradigm, coded MarvelOVD, that generates significantly better training targets and optimizes the learning procedure in an online manner by marrying the capability of the detector with the vision-language model. Our key insight is that the detector itself can act as a strong auxiliary guidance to accommodate VLM's inability of understanding both the ``background'' and the context of a proposal within the image. Based on it, we greatly purify the noisy pseudo-labels via Online Mining and propose Adaptive Reweighting to effectively suppress the biased training boxes that are not well aligned with the target object. In addition, we also identify a neglected ``base-novel-conflict'' problem and introduce stratified label assignments to prevent it. Extensive experiments on COCO and LVIS datasets demonstrate that our method outperforms the other state-of-the-arts by significant margins. Codes are available at https://github.com/wkfdb/MarvelOVD
Authors: Mengtian Kang, Yansong Hu, Shuo Gao, Yuanyuan Liu, Hongbei Meng, Xuemeng Li, Xuhang Chen, Hubin Zhao, Jing Fu, Guohua Hu, Wei Wang, Yanning Dai, Arokia Nathan, Peter Smielewski, Ningli Wang, Shiming Li
Abstract: Childhood myopia constitutes a significant global health concern. It exhibits an escalating prevalence and has the potential to evolve into severe, irreversible conditions that detrimentally impact familial well-being and create substantial economic costs. Contemporary research underscores the importance of precisely predicting myopia progression to enable timely and effective interventions, thereby averting severe visual impairment in children. Such predictions predominantly rely on subjective clinical assessments, which are inherently biased and resource-intensive, thus hindering their widespread application. In this study, we introduce a novel, high-accuracy method for quantitatively predicting the myopic trajectory and myopia risk in children using only fundus images and baseline refraction data. This approach was validated through a six-year longitudinal study of 3,408 children in Henan, utilizing 16,211 fundus images and corresponding refractive data. Our method based on deep learning demonstrated predictive accuracy with an error margin of 0.311D per year and AUC scores of 0.944 and 0.995 for forecasting the risks of developing myopia and high myopia, respectively. These findings confirm the utility of our model in supporting early intervention strategies and in significantly reducing healthcare costs, particularly by obviating the need for additional metadata and repeated consultations. Furthermore, our method was designed to rely only on fundus images and refractive error data, without the need for meta data or multiple inquiries from doctors, strongly reducing the associated medical costs and facilitating large-scale screening. Our model can even provide good predictions based on only a single time measurement. Consequently, the proposed method is an important means to reduce medical inequities caused by economic disparities.
Authors: Dengsheng Chen, Jie Hu, Xiaoming Wei, Enhua Wu
Abstract: Incorporating a temporal dimension into pretrained image diffusion models for video generation is a prevalent approach. However, this method is computationally demanding and necessitates large-scale video datasets. More critically, the heterogeneity between image and video datasets often results in catastrophic forgetting of the image expertise. Recent attempts to directly extract video snippets from image diffusion models have somewhat mitigated these problems. Nevertheless, these methods can only generate brief video clips with simple movements and fail to capture fine-grained motion or non-grid deformation. In this paper, we propose a novel Zero-Shot video Sampling algorithm, denoted as $\mathcal{ZS}^2$, capable of directly sampling high-quality video clips from existing image synthesis methods, such as Stable Diffusion, without any training or optimization. Specifically, $\mathcal{ZS}^2$ utilizes the dependency noise model and temporal momentum attention to ensure content consistency and animation coherence, respectively. This ability enables it to excel in related tasks, such as conditional and context-specialized video generation and instruction-guided video editing. Experimental results demonstrate that $\mathcal{ZS}^2$ achieves state-of-the-art performance in zero-shot video generation, occasionally outperforming recent supervised methods. Homepage: \url{https://densechen.github.io/zss/}.
Authors: Zhe Liu, Xiliang Zhu, Tong Han, Yuhao Huang, Jian Wang, Lian Liu, Fang Wang, Dong Ni, Zhongshan Gou, Xin Yang
Abstract: Mitral regurgitation (MR) is a serious heart valve disease. Early and accurate diagnosis of MR via ultrasound video is critical for timely clinical decision-making and surgical intervention. However, manual MR diagnosis heavily relies on the operator's experience, which may cause misdiagnosis and inter-observer variability. Since MR data is limited and has large intra-class variability, we propose an unsupervised out-of-distribution (OOD) detection method to identify MR rather than building a deep classifier. To our knowledge, we are the first to explore OOD in MR ultrasound videos. Our method consists of a feature extractor, a feature reconstruction model, and a residual accumulation amplification algorithm. The feature extractor obtains features from the video clips and feeds them into the feature reconstruction model to restore the original features. The residual accumulation amplification algorithm then iteratively performs noise feature reconstruction, amplifying the reconstructed error of OOD features. This algorithm is straightforward yet efficient and can seamlessly integrate as a plug-and-play component in reconstruction-based OOD detection methods. We validated the proposed method on a large ultrasound dataset containing 893 non-MR and 267 MR videos. Experimental results show that our OOD detection method can effectively identify MR samples.
Authors: Jawad Haidar, Marc Mouawad, Imad Elhajj, Daniel Asmar
Abstract: Instance segmentation is an advanced form of image segmentation which, beyond traditional segmentation, requires identifying individual instances of repeating objects in a scene. Mask R-CNN is the most common architecture for instance segmentation, and improvements to this architecture include steps such as benefiting from bounding box refinements, adding semantics, or backbone enhancements. In all the proposed variations to date, the problem of competing kernels (each class aims to maximize its own accuracy) persists when models try to synchronously learn numerous classes. In this paper, we propose mitigating this problem by replacing mask prediction with a Switch-Split block that processes refined ROIs, classifies them, and assigns them to specialized mask predictors. We name the method MaskUno and test it on various models from the literature, which are then trained on multiple classes using the benchmark COCO dataset. An increase in the mean Average Precision (mAP) of 2.03% was observed for the high-performing DetectoRS when trained on 80 classes. MaskUno proved to enhance the mAP of instance segmentation models regardless of the number and typ
Authors: Zichen Zhang, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang
Abstract: First-person hand-object interaction anticipation aims to predict the interaction process over a forthcoming period based on current scenes and prompts. This capability is crucial for embodied intelligence and human-robot collaboration. The complete interaction process involves both pre-contact interaction intention (i.e., hand motion trends and interaction hotspots) and post-contact interaction manipulation (i.e., manipulation trajectories and hand poses with contact). Existing research typically anticipates only interaction intention while neglecting manipulation, resulting in incomplete predictions and an increased likelihood of intention errors due to the lack of manipulation constraints. To address this, we propose a novel model, PEAR (Phrase-Based Hand-Object Interaction Anticipation), which jointly anticipates interaction intention and manipulation. To handle uncertainties in the interaction process, we employ a twofold approach. Firstly, we perform cross-alignment of verbs, nouns, and images to reduce the diversity of hand movement patterns and object functional attributes, thereby mitigating intention uncertainty. Secondly, we establish bidirectional constraints between intention and manipulation using dynamic integration and residual connections, ensuring consistency among elements and thus overcoming manipulation uncertainty. To rigorously evaluate the performance of the proposed model, we collect a new task-relevant dataset, EGO-HOIP, with comprehensive annotations. Extensive experimental results demonstrate the superiority of our method.
Authors: Miao Cao, Lishun Wang, Huan Wang, Xin Yuan
Abstract: Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art (SOTA) deep learning-based algorithms have achieved impressive performance, yet with heavy computational workload. Network quantization is a promising way to reduce computational cost. However, a direct low-bit quantization will bring large performance drop. To address this challenge, in this paper, we propose a simple low-bit quantization framework (dubbed Q-SCI) for the end-to-end deep learning-based video SCI reconstruction methods which usually consist of a feature extraction, feature enhancement, and video reconstruction module. Specifically, we first design a high-quality feature extraction module and a precise video reconstruction module to extract and propagate high-quality features in the low-bit quantized model. In addition, to alleviate the information distortion of the Transformer branch in the quantized feature enhancement module, we introduce a shift operation on the query and key distributions to further bridge the performance gap. Comprehensive experimental results manifest that our Q-SCI framework can achieve superior performance, e.g., 4-bit quantized EfficientSCI-S derived by our Q-SCI framework can theoretically accelerate the real-valued EfficientSCI-S by 7.8X with only 2.3% performance gap on the simulation testing datasets. Code is available at https://github.com/mcao92/QuantizedSCI.
Authors: Joaquim Comas, Antonia Alomar, Adria Ruiz, Federico Sukno
Abstract: In recent years, deep learning methods have shown impressive results for camera-based remote physiological signal estimation, clearly surpassing traditional methods. However, the performance and generalization ability of Deep Neural Networks heavily depends on rich training data truly representing different factors of variation encountered in real applications. Unfortunately, many current remote photoplethysmography (rPPG) datasets lack diversity, particularly in darker skin tones, leading to biased performance of existing rPPG approaches. To mitigate this bias, we introduce PhysFlow, a novel method for augmenting skin diversity in remote heart rate estimation using conditional normalizing flows. PhysFlow adopts end-to-end training optimization, enabling simultaneous training of supervised rPPG approaches on both original and generated data. Additionally, we condition our model using CIELAB color space skin features directly extracted from the facial videos without the need for skin-tone labels. We validate PhysFlow on publicly available datasets, UCLA-rPPG and MMPD, demonstrating reduced heart rate error, particularly in dark skin tones. Furthermore, we demonstrate its versatility and adaptability across different data-driven rPPG methods.
Authors: Jingyao Wang, Emmanuel Bergeret, Issam Falih
Abstract: Human Activity Recognition (HAR) is a field of study that focuses on identifying and classifying human activities. Skeleton-based Human Activity Recognition has received much attention in recent years, where Graph Convolutional Network (GCN) based method is widely used and has achieved remarkable results. However, the representation of skeleton data and the issue of over-smoothing in GCN still need to be studied. 1). Compared to central nodes, edge nodes can only aggregate limited neighbor information, and different edge nodes of the human body are always structurally related. However, the information from edge nodes is crucial for fine-grained activity recognition. 2). The Graph Convolutional Network suffers from a significant over-smoothing issue, causing nodes to become increasingly similar as the number of network layers increases. Based on these two ideas, we propose a two-stream graph convolution method called Spatial-Structural GCN (SpSt-GCN). Spatial GCN performs information aggregation based on the topological structure of the human body, and structural GCN performs differentiation based on the similarity of edge node sequences. The spatial connection is fixed, and the human skeleton naturally maintains this topology regardless of the actions performed by humans. However, the structural connection is dynamic and depends on the type of movement the human body is performing. Based on this idea, we also propose an entirely data-driven structural connection, which greatly increases flexibility. We evaluate our method on two large-scale datasets, i.e., NTU RGB+D and NTU RGB+D 120. The proposed method achieves good results while being efficient.
Authors: Mingrui Wu, Xinyue Cai, Jiayi Ji, Jiale Li, Oucheng Huang, Gen Luo, Hao Fei, Xiaoshuai Sun, Rongrong Ji
Abstract: In this work, we propose a training-free method to inject visual referring into Multimodal Large Language Models (MLLMs) through learnable visual token optimization. We observe the relationship between text prompt tokens and visual tokens in MLLMs, where attention layers model the connection between them. Our approach involves adjusting visual tokens from the MLP output during inference, controlling which text prompt tokens attend to which visual tokens. We optimize a learnable visual token based on an energy function, enhancing the strength of referential regions in the attention map. This enables detailed region description and reasoning without the need for substantial training costs or model retraining. Our method offers a promising direction for integrating referential abilities into MLLMs. Our method support referring with box, mask, scribble and point. The results demonstrate that our method exhibits controllability and interpretability.
Authors: Francesco Laiti, Benedetta Liberatori, Thomas De Min, Elisa Ricci
Abstract: The rapid advancement of generative models has significantly enhanced the realism and customization of digital content creation. The increasing power of these tools, coupled with their ease of access, fuels the creation of photorealistic fake content, termed deepfakes, that raises substantial concerns about their potential misuse. In response, there has been notable progress in developing detection mechanisms to identify content produced by these advanced systems. However, existing methods often struggle to adapt to the continuously evolving landscape of deepfake generation. This paper introduces Prompt2Guard, a novel solution for exemplar-free continual deepfake detection of images, that leverages Vision-Language Models (VLMs) and domain-specific multimodal prompts. Compared to previous VLM-based approaches that are either bounded by prompt selection accuracy or necessitate multiple forward passes, we leverage a prediction ensembling technique with read-only prompts. Read-only prompts do not interact with VLMs internal representation, mitigating the need for multiple forward passes. Thus, we enhance efficiency and accuracy in detecting generated content. Additionally, our method exploits a text-prompt conditioning tailored to deepfake detection, which we demonstrate is beneficial in our setting. We evaluate Prompt2Guard on CDDB-Hard, a continual deepfake detection benchmark composed of five deepfake detection datasets spanning multiple domains and generators, achieving a new state-of-the-art. Additionally, our results underscore the effectiveness of our approach in addressing the challenges posed by continual deepfake detection, paving the way for more robust and adaptable solutions in deepfake detection.
Authors: Kit M. Bransby, Woo-jin Cho Kim, Jorge Oliveira, Alex Thorley, Arian Beqiri, Alberto Gomez, Agisilaos Chartsias
Abstract: Building an echocardiography view classifier that maintains performance in real-life cases requires diverse multi-site data, and frequent updates with newly available data to mitigate model drift. Simply fine-tuning on new datasets results in "catastrophic forgetting", and cannot adapt to variations of view labels between sites. Alternatively, collecting all data on a single server and re-training may not be feasible as data sharing agreements may restrict image transfer, or datasets may only become available at different times. Furthermore, time and cost associated with re-training grows with every new dataset. We propose a class-incremental learning method which learns an expert network for each dataset, and combines all expert networks with a score fusion model. The influence of ``unqualified experts'' is minimised by weighting each contribution with a learnt in-distribution score. These weights promote transparency as the contribution of each expert is known during inference. Instead of using the original images, we use learned features from each dataset, which are easier to share and raise fewer licensing and privacy concerns. We validate our work on six datasets from multiple sites, demonstrating significant reductions in training time while improving view classification performance.
Authors: Antoine P. Sanner, Nils F. Grauhan, Marc A. Brockmann, Ahmed E. Othman, Anirban Mukhopadhyay
Abstract: Patients with Intracranial Hemorrhage (ICH) face a potentially life-threatening condition, and patient-centered individualized treatment remains challenging due to possible clinical complications. Deep-Learning-based methods can efficiently analyze the routinely acquired head CTs to support the clinical decision-making. The majority of early work focuses on the detection and segmentation of ICH, but do not model the complex relations between ICH and adjacent brain structures. In this work, we design a tailored object detection method for ICH, which we unite with segmentation-grounded Scene Graph Generation (SGG) methods to learn a holistic representation of the clinical cerebral scene. To the best of our knowledge, this is the first application of SGG for 3D voxel images. We evaluate our method on two head-CT datasets and demonstrate that our model can recall up to 74% of clinically relevant relations. This work lays the foundation towards SGG for 3D voxel data. The generated Scene Graphs can already provide insights for the clinician, but are also valuable for all downstream tasks as a compact and interpretable representation.
Authors: Xiaofei Zhang, Yining Li, Jinping Wang, Xiangyi Qin, Ying Shen, Zhengping Fan, Xiaojun Tan
Abstract: Perception systems of autonomous vehicles are susceptible to occlusion, especially when examined from a vehicle-centric perspective. Such occlusion can lead to overlooked object detections, e.g., larger vehicles such as trucks or buses may create blind spots where cyclists or pedestrians could be obscured, accentuating the safety concerns associated with such perception system limitations. To mitigate these challenges, the vehicle-to-everything (V2X) paradigm suggests employing an infrastructure-side perception system (IPS) to complement autonomous vehicles with a broader perceptual scope. Nevertheless, the scarcity of real-world 3D infrastructure-side datasets constrains the advancement of V2X technologies. To bridge these gaps, this paper introduces a new 3D infrastructure-side collaborative perception dataset, abbreviated as inscope. Notably, InScope is the first dataset dedicated to addressing occlusion challenges by strategically deploying multiple-position Light Detection and Ranging (LiDAR) systems on the infrastructure side. Specifically, InScope encapsulates a 20-day capture duration with 303 tracking trajectories and 187,787 3D bounding boxes annotated by experts. Through analysis of benchmarks, four different benchmarks are presented for open traffic scenarios, including collaborative 3D object detection, multisource data fusion, data domain transfer, and 3D multiobject tracking tasks. Additionally, a new metric is designed to quantify the impact of occlusion, facilitating the evaluation of detection degradation ratios among various algorithms. The Experimental findings showcase the enhanced performance of leveraging InScope to assist in detecting and tracking 3D multiobjects in real-world scenarios, particularly in tracking obscured, small, and distant objects. The dataset and benchmarks are available at https://github.com/xf-zh/InScope.
Authors: Zhiqiang Shen, Peng Cao, Junming Su, Jinzhu Yang, Osmar R. Zaiane
Abstract: Mix-up is a key technique for consistency regularization-based semi-supervised learning methods, generating strong-perturbed samples for strong-weak pseudo-supervision. Existing mix-up operations are performed either randomly or with predefined rules, such as replacing low-confidence patches with high-confidence ones. The former lacks control over the perturbation degree, leading to overfitting on randomly perturbed samples, while the latter tends to generate images with trivial perturbations, both of which limit the effectiveness of consistency learning. This paper aims to answer the following question: How can image mix-up perturbation be adaptively performed during training? To this end, we propose an Adaptive Mix algorithm (AdaMix) for image mix-up in a self-paced learning manner. Given that, in general, a model's performance gradually improves during training, AdaMix is equipped with a self-paced curriculum that, in the initial training stage, provides relatively simple perturbed samples and then gradually increases the difficulty of perturbed images by adaptively controlling the perturbation degree based on the model's learning state estimated by a self-paced regularize. We develop three frameworks with our AdaMix, i.e., AdaMix-ST, AdaMix-MT, and AdaMix-CT, for semi-supervised medical image segmentation. Extensive experiments on three public datasets, including both 2D and 3D modalities, show that the proposed frameworks are capable of achieving superior performance. For example, compared with the state-of-the-art, AdaMix-CT achieves relative improvements of 2.62% in Dice and 48.25% in average surface distance on the ACDC dataset with 10% labeled data. The results demonstrate that mix-up operations with dynamically adjusted perturbation strength based on the segmentation model's state can significantly enhance the effectiveness of consistency regularization.
Authors: Lv Tang, Bo Li
Abstract: The Segment Anything Model (SAM), introduced by Meta AI Research as a generic object segmentation model, quickly garnered widespread attention and significantly influenced the academic community. To extend its application to video, Meta further develops Segment Anything Model 2 (SAM2), a unified model capable of both video and image segmentation. SAM2 shows notable improvements over its predecessor in terms of applicable domains, promptable segmentation accuracy, and running speed. However, this report reveals a decline in SAM2's ability to perceive different objects in images without prompts in its auto mode, compared to SAM. Specifically, we employ the challenging task of camouflaged object detection to assess this performance decrease, hoping to inspire further exploration of the SAM model family by researchers. The results of this paper are provided in \url{https://github.com/luckybird1994/SAMCOD}.
Authors: JongWoo Kim, Bryan Wong, YoungSin Ko, MunYong Yi
Abstract: Current histopathology research has primarily focused on using whole-slide images (WSIs) produced by scanners with weakly-supervised multiple instance learning (MIL). However, WSIs are costly, memory-intensive, and require extensive analysis time. As an alternative, microscopy-based analysis offers cost and memory efficiency, though microscopy images face issues with unknown absolute positions and redundant images due to multiple captures from the subjective perspectives of pathologists. To this end, we introduce MicroMIL, a weakly-supervised MIL framework specifically built to address these challenges by dynamically clustering images using deep cluster embedding (DCE) and Gumbel Softmax for representative image extraction. Graph edges are then constructed from the upper triangular similarity matrix, with nodes connected to their most similar neighbors, and a graph neural network (GNN) is utilized to capture local and diverse areas of contextual information. Unlike existing graph-based MIL methods designed for WSIs that require absolute positions, MicroMIL efficiently handles the graph edges without this need. Extensive evaluations on real-world colon cancer (Seegene) and public BreakHis datasets demonstrate that MicroMIL outperforms state-of-the-art (SOTA) methods, offering a robust and efficient solution for patient diagnosis using microscopy images. The code is available at https://anonymous.4open.science/r/MicroMIL-6C7C
Authors: Yan Yang, Liyuan Pan, Dongxu Li, Liu Liu
Abstract: This paper studies zero-shot object recognition using event camera data. Guided by CLIP, which is pre-trained on RGB images, existing approaches achieve zero-shot object recognition by maximizing embedding similarities between event data encoded by an event encoder and RGB images encoded by the CLIP image encoder. Alternatively, several methods learn RGB frame reconstructions from event data for the CLIP image encoder. However, these approaches often result in suboptimal zero-shot performance. This study develops an event encoder without relying on additional reconstruction networks. We theoretically analyze the performance bottlenecks of previous approaches: global similarity-based objective (i.e., maximizing the embedding similarities) cause semantic misalignments between the learned event embedding space and the CLIP text embedding space due to the degree of freedom. To mitigate the issue, we explore a scalar-wise regularization strategy. Furthermore, to scale up the number of events and RGB data pairs for training, we also propose a pipeline for synthesizing event data from static RGB images. Experimentally, our data synthesis strategy exhibits an attractive scaling property, and our method achieves superior zero-shot object recognition performance on extensive standard benchmark datasets, even compared with past supervised learning approaches. For example, we achieve 47.84% zero-shot accuracy on the N-ImageNet dataset.
Authors: Jianxin Huang, Jiahang Li, Ning Jia, Yuxiang Sun, Chengju Liu, Qijun Chen, Rui Fan
Abstract: Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and fuses these features through attention mechanisms, demonstrating compelling efficacy in RGB-Normal road scene parsing. However, its performance significantly deteriorates when handling other types/sources of data or performing more universal, all-category scene parsing tasks. To overcome these limitations, this study introduces RoadFormer+, an efficient, robust, and adaptable model capable of effectively fusing RGB-X data, where ``X'', represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. Specifically, we propose a novel hybrid feature decoupling encoder to extract heterogeneous features and decouple them into global and local components. These decoupled features are then fused through a dual-branch multi-scale heterogeneous feature fusion block, which employs parallel Transformer attentions and convolutional neural network modules to merge multi-scale features across different scales and receptive fields. The fused features are subsequently fed into a decoder to generate the final semantic predictions. Notably, our proposed RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union on the Cityscapes, MFNet, FMB, and ZJU datasets. Moreover, it reduces the number of learnable parameters by 65\% compared to RoadFormer. Our source code will be publicly available at mias.group/RoadFormerPlus.
Authors: Yash Zambre, Ekdev Rajkitkul, Akshatha Mohan, Joshua Peeples
Abstract: Object detection plays a crucial role in the field of computer vision by autonomously identifying and locating objects of interest. The You Only Look Once (YOLO) model is an effective single-shot detector. However, YOLO faces challenges in cluttered or partially occluded scenes and can struggle with small, low-contrast objects. We propose a new method that integrates spatial transformer networks (STNs) into YOLO to improve performance. The proposed STN-YOLO aims to enhance the model's effectiveness by focusing on important areas of the image and improving the spatial invariance of the model before the detection process. Our proposed method improved object detection performance both qualitatively and quantitatively. We explore the impact of different localization networks within the STN module as well as the robustness of the model across different spatial transformations. We apply the STN-YOLO on benchmark datasets for Agricultural object detection as well as a new dataset from a state-of-the-art plant phenotyping greenhouse facility. Our code and dataset are publicly available.
Authors: Anurag Das, Xinting Hu, Li Jiang, Bernt Schiele
Abstract: Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image features from CLIP, resulting in class ambiguities along boundaries. Moreover, the global scene representations in CLIP text embeddings do not directly correlate with the local and detailed pixel-level features, making meaningful alignment more difficult. To address these limitations, we introduce MTA-CLIP, a novel framework employing mask-level vision-language alignment. Specifically, we first propose Mask-Text Decoder that enhances the mask representations using rich textual data with the CLIP language model. Subsequently, it aligns mask representations with text embeddings using Mask-to-Text Contrastive Learning. Furthermore, we introduce MaskText Prompt Learning, utilizing multiple context-specific prompts for text embeddings to capture diverse class representations across masks. Overall, MTA-CLIP achieves state-of-the-art, surpassing prior works by an average of 2.8% and 1.3% on on standard benchmark datasets, ADE20k and Cityscapes, respectively.
Authors: Aswini Kumar Patra, Ankit Varshney, Lingaraj Sahoo
Abstract: Early detection of drought stress is critical for taking timely measures for reducing crop loss before the drought impact becomes irreversible. The subtle phenotypical and physiological changes in response to drought stress are captured by non-invasive imaging techniques and these imaging data serve as valuable resource for machine learning methods to identify drought stress. While convolutional neural networks (CNNs) are in wide use, vision transformers (ViTs) present a promising alternative in capturing long-range dependencies and intricate spatial relationships, thereby enhancing the detection of subtle indicators of drought stress. We propose an explainable deep learning pipeline that leverages the power of ViTs for drought stress detection in potato crops using aerial imagery. We applied two distinct approaches: a synergistic combination of ViT and support vector machine (SVM), where ViT extracts intricate spatial features from aerial images, and SVM classifies the crops as stressed or healthy and an end-to-end approach using a dedicated classification layer within ViT to directly detect drought stress. Our key findings explain the ViT model's decision-making process by visualizing attention maps. These maps highlight the specific spatial features within the aerial images that the ViT model focuses as the drought stress signature. Our findings demonstrate that the proposed methods not only achieve high accuracy in drought stress identification but also shedding light on the diverse subtle plant features associated with drought stress. This offers a robust and interpretable solution for drought stress monitoring for farmers to undertake informed decisions for improved crop management.
Authors: Krishan Agyakari Raja Babu, Rachana Sathish, Mrunal Pattanaik, Rahul Venkataramani
Abstract: Synthetic data is becoming increasingly integral in data-scarce fields such as medical imaging, serving as a substitute for real data. However, its inherent statistical characteristics can significantly impact downstream tasks, potentially compromising deployment performance. In this study, we empirically investigate this issue and uncover a critical phenomenon: downstream neural networks often exploit spurious distinctions between real and synthetic data when there is a strong correlation between the data source and the task label. This exploitation manifests as \textit{simplicity bias}, where models overly rely on superficial features rather than genuine task-related complexities. Through principled experiments, we demonstrate that the source of data (real vs.\ synthetic) can introduce spurious correlating factors leading to poor performance during deployment when the correlation is absent. We first demonstrate this vulnerability on a digit classification task, where the model spuriously utilizes the source of data instead of the digit to provide an inference. We provide further evidence of this phenomenon in a medical imaging problem related to cardiac view classification in echocardiograms, particularly distinguishing between 2-chamber and 4-chamber views. Given the increasing role of utilizing synthetic datasets, we hope that our experiments serve as effective guidelines for the utilization of synthetic datasets in model training.
Authors: Gyeongsik Moon, Takaaki Shiratori, Shunsuke Saito
Abstract: Facial expression and hand motions are necessary to express our emotions and interact with the world. Nevertheless, most of the 3D human avatars modeled from a casually captured video only support body motions without facial expressions and hand motions.In this work, we present ExAvatar, an expressive whole-body 3D human avatar learned from a short monocular video. We design ExAvatar as a combination of the whole-body parametric mesh model (SMPL-X) and 3D Gaussian Splatting (3DGS). The main challenges are 1) a limited diversity of facial expressions and poses in the video and 2) the absence of 3D observations, such as 3D scans and RGBD images. The limited diversity in the video makes animations with novel facial expressions and poses non-trivial. In addition, the absence of 3D observations could cause significant ambiguity in human parts that are not observed in the video, which can result in noticeable artifacts under novel motions. To address them, we introduce our hybrid representation of the mesh and 3D Gaussians. Our hybrid representation treats each 3D Gaussian as a vertex on the surface with pre-defined connectivity information (i.e., triangle faces) between them following the mesh topology of SMPL-X. It makes our ExAvatar animatable with novel facial expressions by driven by the facial expression space of SMPL-X. In addition, by using connectivity-based regularizers, we significantly reduce artifacts in novel facial expressions and poses.
Authors: Jichuan Zhang, Wei Li, Shuang Cheng, Ya-Li Li, Shengjin Wang
Abstract: Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic forgetting. Prior methodologies mainly tackle the forgetting issue through knowledge distillation and exemplar replay, ignoring the conflict between limited model capacity and increasing knowledge. In this paper, we explore \textit{dynamic object queries} for incremental object detection built on Transformer architecture. We propose the \textbf{Dy}namic object \textbf{Q}uery-based \textbf{DE}tection \textbf{TR}ansformer (DyQ-DETR), which incrementally expands the model representation ability to achieve stability-plasticity tradeoff. First, a new set of learnable object queries are fed into the decoder to represent new classes. These new object queries are aggregated with those from previous phases to adapt both old and new knowledge well. Second, we propose the isolated bipartite matching for object queries in different phases, based on disentangled self-attention. The interaction among the object queries at different phases is eliminated to reduce inter-class confusion. Thanks to the separate supervision and computation over object queries, we further present the risk-balanced partial calibration for effective exemplar replay. Extensive experiments demonstrate that DyQ-DETR significantly surpasses the state-of-the-art methods, with limited parameter overhead. Code will be made publicly available.
Authors: Barun Das, Conor Anderson, Tania Villavicencio, Johanna Lantz, Jenny Foster, Theresa Hamlin, Ali Bahrami Rad, Gari D. Clifford, Hyeokhyen Kwon
Abstract: Rapid identification and accurate documentation of interfering and high-risk behaviors in ASD, such as aggression, self-injury, disruption, and restricted repetitive behaviors, are important in daily classroom environments for tracking intervention effectiveness and allocating appropriate resources to manage care needs. However, having a staff dedicated solely to observing is costly and uncommon in most educational settings. Recently, multiple research studies have explored developing automated, continuous, and objective tools using machine learning models to quantify behaviors in ASD. However, the majority of the work was conducted under a controlled environment and has not been validated for real-world conditions. In this work, we demonstrate that the latest advances in video-based group activity recognition techniques can quantify behaviors in ASD in real-world activities in classroom environments while preserving privacy. Our explainable model could detect the episode of problem behaviors with a 77% F1-score and capture distinctive behavior features in different types of behaviors in ASD. To the best of our knowledge, this is the first work that shows the promise of objectively quantifying behaviors in ASD in a real-world environment, which is an important step toward the development of a practical tool that can ease the burden of data collection for classroom staff.
Authors: Shiwen Zhang
Abstract: The test-time finetuning text-guided image editing method, Forgedit, is capable of tackling general and complex image editing problems given only the input image itself and the target text prompt. During finetuning stage, using the same set of finetuning hyper-paramters every time for every given image, Forgedit remembers and understands the input image in 30 seconds. During editing stage, the workflow of Forgedit might seem complicated. However, in fact, the editing process of Forgedit is not more complex than previous SOTA Imagic, yet completely solves the overfitting problem of Imagic. In this paper, we will elaborate the workflow of Forgedit editing stage with examples. We will show how to tune the hyper-parameters in an efficient way to obtain ideal editing results.
Authors: Zhenghao Zhang, Junchao Liao, Menghao Li, Long Qin, Weizhi Wang
Abstract: Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with controllable motion remains an area of limited exploration. This paper introduces Tora, the first trajectory-oriented DiT framework that integrates textual, visual, and trajectory conditions concurrently for video generation. Specifically, Tora consists of a Trajectory Extractor~(TE), a Spatial-Temporal DiT, and a Motion-guidance Fuser~(MGF). The TE encodes arbitrary trajectories into hierarchical spacetime motion patches with a 3D video compression network. The MGF integrates the motion patches into the DiT blocks to generate consistent videos following trajectories. Our design aligns seamlessly with DiT's scalability, allowing precise control of video content's dynamics with diverse durations, aspect ratios, and resolutions. Extensive experiments demonstrate Tora's excellence in achieving high motion fidelity, while also meticulously simulating the movement of the physical world. Page can be found at https://ali-videoai.github.io/tora_video.
Authors: Yuxin Wen, Yuchen Liu, Chen Chen, Lingjuan Lyu
Abstract: Recent breakthroughs in diffusion models have exhibited exceptional image-generation capabilities. However, studies show that some outputs are merely replications of training data. Such replications present potential legal challenges for model owners, especially when the generated content contains proprietary information. In this work, we introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions. Our proposed method seamlessly integrates without disrupting sampling algorithms, and delivers high accuracy even at the first generation step, with a single generation per prompt. Building on our detection strategy, we unveil an explainable approach that shows the contribution of individual words or tokens to memorization. This offers an interactive medium for users to adjust their prompts. Moreover, we propose two strategies i.e., to mitigate memorization by leveraging the magnitude of text-conditional predictions, either through minimization during inference or filtering during training. These proposed strategies effectively counteract memorization while maintaining high-generation quality. Code is available at https://github.com/YuxinWenRick/diffusion_memorization.
URLs: https://github.com/YuxinWenRick/diffusion_memorization.
Authors: Pengjie Zhang, Lin Zhu, Lizhi Wang, Hua Huang
Abstract: As an emerging vision sensor, the event camera has gained popularity in various vision tasks such as optical flow estimation, stereo matching, and depth estimation due to its high-speed, sparse, and asynchronous event streams. Unlike traditional approaches that use specialized architectures for each specific task, we propose a unified framework, EventMatch, that reformulates these tasks as an event-based dense correspondence matching problem, allowing them to be solved with a single model by directly comparing feature similarities. By utilizing a shared feature similarities module, which integrates knowledge from other event flows via temporal or spatial interactions, and distinct task heads, our network can concurrently perform optical flow estimation from temporal inputs (e.g., two segments of event streams in the temporal domain) and stereo matching from spatial inputs (e.g., two segments of event streams from different viewpoints in the spatial domain). Moreover, we further demonstrate that our unified model inherently supports cross-task transfer since the architecture and parameters are shared across tasks. Without the need for retraining on each task, our model can effectively handle both optical flow and disparity estimation simultaneously. The experiment conducted on the DSEC benchmark demonstrates that our model exhibits superior performance in both optical flow and disparity estimation tasks, outperforming existing state-of-the-art methods. Our unified approach not only advances event-based models but also opens new possibilities for cross-task transfer and inter-task fusion in both spatial and temporal dimensions. Our code will be available later.
Authors: Mothilal Asokan, Joseph Geo Benjamin, Mohammad Yaqub, Karthik Nandakumar
Abstract: Adapting foundation models for medical image analysis requires finetuning them on a considerable amount of data because of extreme distribution shifts between natural (source) data used for pretraining and medical (target) data. However, collecting task-specific medical data for such finetuning at a central location raises many privacy concerns. Although Federated learning (FL) provides an effective means for training on private decentralized data, communication costs in federating large foundation models can quickly become a significant bottleneck, impacting the solution's scalability. In this work, we address this problem of efficient communication while ensuring effective learning in FL by combining the strengths of Parameter-Efficient Fine-tuning (PEFT) with FL. Specifically, we study plug-and-play Low-Rank Adapters (LoRA) in a federated manner to adapt the Segment Anything Model (SAM) for 3D medical image segmentation. Unlike prior works that utilize LoRA and finetune the entire decoder, we critically analyze the contribution of each granular component of SAM on finetuning performance. Thus, we identify specific layers to be federated that are very efficient in terms of communication cost while producing on-par accuracy. Our experiments show that retaining the parameters of the SAM model (including most of the decoder) in their original state during adaptation is beneficial because fine-tuning on small datasets tends to distort the inherent capabilities of the underlying foundation model. On Fed-KiTS, our approach decreases communication cost (~48x) compared to full fine-tuning while increasing performance (~6% Dice score) in 3D segmentation tasks. Our approach performs similar to SAMed while achieving ~2.8x reduction in communication and parameters to be finetuned. We further validate our approach with experiments on Fed-IXI and Prostate MRI datasets.
Authors: Kevin Qinghong Lin, Pengchuan Zhang, Difei Gao, Xide Xia, Joya Chen, Ziteng Gao, Jinheng Xie, Xuhong Xiao, Mike Zheng Shou
Abstract: Narrative videos, such as movies, pose significant challenges in video understanding due to their rich contexts (characters, dialogues, storylines) and diverse demands (identify who, relationship, and reason). In this paper, we introduce MovieSeq, a multimodal language model developed to address the wide range of challenges in understanding video contexts. Our core idea is to represent videos as interleaved multimodal sequences (including images, plots, videos, and subtitles), either by linking external knowledge databases or using offline models (such as whisper for subtitles). Through instruction-tuning, this approach empowers the language model to interact with videos using interleaved multimodal instructions. For example, instead of solely relying on video as input, we jointly provide character photos alongside their names and dialogues, allowing the model to associate these elements and generate more comprehensive responses. To demonstrate its effectiveness, we validate MovieSeq's performance on six datasets (LVU, MAD, Movienet, CMD, TVC, MovieQA) across five settings (video classification, audio description, video-text retrieval, video captioning, and video question-answering). The code will be public at https://github.com/showlab/MovieSeq.
Authors: Shi Liu, Kecheng Zheng, Wei Chen
Abstract: Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder and language model may led to LLMs assuming a predominant role in multi-modal comprehension. This imbalance in LVLMs may result in the instances of hallucinatory. Concretely, LVLMs may generate consistent descriptions with or without visual input, indicating that certain outputs are influenced solely by context text. We refer to this phenomenon as "text inertia." To counteract this issue, we introduce a training-free algorithm to find an equilibrium point between image comprehension and language inference. Specifically, we adaptively involve adjusting and amplifying the attention weights assigned to image tokens, thereby granting greater prominence to visual elements. Meanwhile, we subtract the logits of multi-modal inputs from ones of pure text input, which can help LVLMs be not biased towards LLMs. By enhancing images tokens and reducing the stubborn output of LLM, we can let LVLM pay more attention to images, towards alleviating text inertia and reducing the hallucination in LVLMs. Our extensive experiments shows that this method substantially reduces the frequency of hallucinatory outputs in various LVLMs in terms of different metrics. Project page is available at https://lalbj.github.io/projects/PAI/.
Authors: Hongtao Wu, Yijun Yang, Huihui Xu, Weiming Wang, Jinni Zhou, Lei Zhu
Abstract: The outdoor vision systems are frequently contaminated by rain streaks and raindrops, which significantly degenerate the performance of visual tasks and multimedia applications. The nature of videos exhibits redundant temporal cues for rain removal with higher stability. Traditional video deraining methods heavily rely on optical flow estimation and kernel-based manners, which have a limited receptive field. Yet, transformer architectures, while enabling long-term dependencies, bring about a significant increase in computational complexity. Recently, the linear-complexity operator of the state space models (SSMs) has contrarily facilitated efficient long-term temporal modeling, which is crucial for rain streaks and raindrops removal in videos. Unexpectedly, its uni-dimensional sequential process on videos destroys the local correlations across the spatio-temporal dimension by distancing adjacent pixels. To address this, we present an improved SSMs-based video deraining network (RainMamba) with a novel Hilbert scanning mechanism to better capture sequence-level local information. We also introduce a difference-guided dynamic contrastive locality learning strategy to enhance the patch-level self-similarity learning ability of the proposed network. Extensive experiments on four synthesized video deraining datasets and real-world rainy videos demonstrate the superiority of our network in the removal of rain streaks and raindrops.
Authors: Mihir Chauhan, Abhishek Satbhai, Mohammad Abuzar Hashemi, Mir Basheer Ali, Bina Ramamurthy, Mingchen Gao, Siwei Lyu, Sargur Srihari
Abstract: Handwriting Verification is a critical in document forensics. Deep learning based approaches often face skepticism from forensic document examiners due to their lack of explainability and reliance on extensive training data and handcrafted features. This paper explores using Vision Language Models (VLMs), such as OpenAI's GPT-4o and Google's PaliGemma, to address these challenges. By leveraging their Visual Question Answering capabilities and 0-shot Chain-of-Thought (CoT) reasoning, our goal is to provide clear, human-understandable explanations for model decisions. Our experiments on the CEDAR handwriting dataset demonstrate that VLMs offer enhanced interpretability, reduce the need for large training datasets, and adapt better to diverse handwriting styles. However, results show that the CNN-based ResNet-18 architecture outperforms the 0-shot CoT prompt engineering approach with GPT-4o (Accuracy: 70%) and supervised fine-tuned PaliGemma (Accuracy: 71%), achieving an accuracy of 84% on the CEDAR AND dataset. These findings highlight the potential of VLMs in generating human-interpretable decisions while underscoring the need for further advancements to match the performance of specialized deep learning models.
Authors: Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang, Yifei Ming, Yueqian Lin, Qing Yu, Go Irie, Shafiq Joty, Yixuan Li, Hai Li, Ziwei Liu, Toshihiko Yamasaki, Kiyoharu Aizawa
Abstract: Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other problems are closely related to OOD detection, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD). To unify these problems, a generalized OOD detection framework was proposed, taxonomically categorizing these five problems. However, Vision Language Models (VLMs) such as CLIP have significantly changed the paradigm and blurred the boundaries between these fields, again confusing researchers. In this survey, we first present a generalized OOD detection v2, encapsulating the evolution of AD, ND, OSR, OOD detection, and OD in the VLM era. Our framework reveals that, with some field inactivity and integration, the demanding challenges have become OOD detection and AD. In addition, we also highlight the significant shift in the definition, problem settings, and benchmarks; we thus feature a comprehensive review of the methodology for OOD detection, including the discussion over other related tasks to clarify their relationship to OOD detection. Finally, we explore the advancements in the emerging Large Vision Language Model (LVLM) era, such as GPT-4V. We conclude this survey with open challenges and future directions.
Authors: Jielong Tang, Zhenxing Wang, Ziyang Gong, Jianxing Yu, Shuang Wang, Jian Yin
Abstract: Grounded Multimodal Named Entity Recognition (GMNER) is an emerging information extraction (IE) task, aiming to simultaneously extract entity spans, types, and entity-matched bounding box groundings in images from given sentence-image pairs data. Recent unified methods employing machine reading comprehension (MRC-based) frameworks or sequence generation-based models face challenges in understanding the relationships of multimodal entities. MRC-based frameworks, utilizing human-designed queries, struggle to model intra-entity connections. Meanwhile, sequence generation-based outputs excessively rely on inter-entity dependencies due to pre-defined decoding order. To tackle these, we propose a novel unified framework named Multi-grained Query-guided Set Prediction Network (MQSPN) to learn appropriate relationships at intra-entity and inter-entity levels. Specifically, MQSPN consists of a Multi-grained Query Set (MQS) and a Multimodal Set Prediction Network (MSP). MQS combines specific type-grained and learnable entity-grained queries to adaptively strengthen intra-entity connections by explicitly aligning visual regions with textual spans. Based on solid intra-entity modeling, MSP reformulates GMNER as a set prediction, enabling the parallel prediction of multimodal entities in a non-autoregressive manner, eliminating redundant dependencies from preceding sequences, and guiding models to establish appropriate inter-entity relationships from a global matching perspective. Additionally, to boost better alignment of two-level relationships, we also incorporate a Query-guided Fusion Net (QFNet) to work as a glue network between MQS and MSP. Extensive experiments demonstrate that our approach achieves state-of-the-art performances in widely used benchmarks. Notably, our method improves 2.83% F1 in the difficult fine-grained GMNER benchmark.
Authors: Tiago Novello, Diana Aldana, Luiz Velho
Abstract: This work investigates the structure and representation capacity of $sinusoidal$ MLPs, which have recently shown promising results in encoding low-dimensional signals. This success can be attributed to its smoothness and high representation capacity. The first allows the use of the network's derivatives during training, enabling regularization. However, defining the architecture and initializing its parameters to achieve a desired capacity remains an empirical task. This work provides theoretical and experimental results justifying the capacity property of sinusoidal MLPs and offers control mechanisms for their initialization and training. We approach this from a Fourier series perspective and link the training with the model's spectrum. Our analysis is based on a $harmonic$ expansion of the sinusoidal MLP, which says that the composition of sinusoidal layers produces a large number of new frequencies expressed as integer linear combinations of the input frequencies (weights of the input layer). We use this novel $identity$ to initialize the input neurons which work as a sampling in the signal spectrum. We also note that each hidden neuron produces the same frequencies with amplitudes completely determined by the hidden weights. Finally, we give an upper bound for these amplitudes, which results in a $bounding$ scheme for the network's spectrum during training.
Authors: Mayanka Chandrashekar, Ian Goethert, Md Inzamam Ul Haque, Benjamin McMahon, Sayera Dhaubhadel, Kathryn Knight, Joseph Erdos, Donna Reagan, Caroline Taylor, Peter Kuzmak, John Michael Gaziano, Eileen McAllister, Lauren Costa, Yuk-Lam Ho, Kelly Cho, Suzanne Tamang, Samah Fodeh-Jarad, Olga S. Ovchinnikova, Amy C. Justice, Jacob Hinkle, Ioana Danciu
Abstract: Objectives: This study aims to assess the impact of domain shift on chest X-ray classification accuracy and to analyze the influence of ground truth label quality and demographic factors such as age group, sex, and study year. Materials and Methods: We used a DenseNet121 model pretrained MIMIC-CXR dataset for deep learning-based multilabel classification using ground truth labels from radiology reports extracted using the CheXpert and CheXbert Labeler. We compared the performance of the 14 chest X-ray labels on the MIMIC-CXR and Veterans Healthcare Administration chest X-ray dataset (VA-CXR). The VA-CXR dataset comprises over 259k chest X-ray images spanning between the years 2010 and 2022. Results: The validation of ground truth and the assessment of multi-label classification performance across various NLP extraction tools revealed that the VA-CXR dataset exhibited lower disagreement rates than the MIMIC-CXR datasets. Additionally, there were notable differences in AUC scores between models utilizing CheXpert and CheXbert. When evaluating multi-label classification performance across different datasets, minimal domain shift was observed in unseen datasets, except for the label "Enlarged Cardiomediastinum." The study year's subgroup analyses exhibited the most significant variations in multi-label classification model performance. These findings underscore the importance of considering domain shifts in chest X-ray classification tasks, particularly concerning study years. Conclusion: Our study reveals the significant impact of domain shift and demographic factors on chest X-ray classification, emphasizing the need for improved transfer learning and equitable model development. Addressing these challenges is crucial for advancing medical imaging and enhancing patient care.
Authors: Jack He, Jianxing Zhao, Andrew Bai, Cho-Jui Hsieh
Abstract: In the rapidly evolving landscape of artificial intelligence, generative models such as Generative Adversarial Networks (GANs) and Diffusion Models have become cornerstone technologies, driving innovation in diverse fields from art creation to healthcare. Despite their potential, these models face the significant challenge of data memorization, which poses risks to privacy and the integrity of generated content. Among various metrics of memorization detection, our study delves into the memorization scores calculated from encoder layer embeddings, which involves measuring distances between samples in the embedding spaces. Particularly, we find that the memorization scores calculated from layer embeddings of Vision Transformers (ViTs) show an notable trend - the latter (deeper) the layer, the less the memorization measured. It has been found that the memorization scores from the early layers' embeddings are more sensitive to low-level memorization (e.g. colors and simple patterns for an image), while those from the latter layers are more sensitive to high-level memorization (e.g. semantic meaning of an image). We also observe that, for a specific model architecture, its degree of memorization on different levels of information is unique. It can be viewed as an inherent property of the architecture. Building upon this insight, we introduce a unique fingerprinting methodology. This method capitalizes on the unique distributions of the memorization score across different layers of ViTs, providing a novel approach to identifying models involved in generating deepfakes and malicious content. Our approach demonstrates a marked 30% enhancement in identification accuracy over existing baseline methods, offering a more effective tool for combating digital misinformation.
Authors: Nick Lemke, Camila Gonz\'alez, Anirban Mukhopadhyay, Martin Mundt
Abstract: Medical image distributions shift constantly due to changes in patient population and discrepancies in image acquisition. These distribution changes result in performance deterioration; deterioration that continual learning aims to alleviate. However, only adaptation with data rehearsal strategies yields practically desirable performance for medical image segmentation. Such rehearsal violates patient privacy and, as most continual learning approaches, overlooks unexpected changes from out-of-distribution instances. To transcend both of these challenges, we introduce a distribution-aware replay strategy that mitigates forgetting through auto-encoding of features, while simultaneously leveraging the learned distribution of features to detect model failure. We provide empirical corroboration on hippocampus and prostate MRI segmentation.
Authors: C. A. Mart\'inez-Mej\'ia, J. Solano, J. Breier, D. Bucko, X. Hou
Abstract: Machine Learning using neural networks has received prominent attention recently because of its success in solving a wide variety of computational tasks, in particular in the field of computer vision. However, several works have drawn attention to potential security risks involved with the training and implementation of such networks. In this work, we introduce DeepBaR, a novel approach that implants backdoors on neural networks by faulting their behavior at training, especially during fine-tuning. Our technique aims to generate adversarial samples by optimizing a custom loss function that mimics the implanted backdoors while adding an almost non-visible trigger in the image. We attack three popular convolutional neural network architectures and show that DeepBaR attacks have a success rate of up to 98.30\%. Furthermore, DeepBaR does not significantly affect the accuracy of the attacked networks after deployment when non-malicious inputs are given. Remarkably, DeepBaR allows attackers to choose an input that looks similar to a given class, from a human perspective, but that will be classified as belonging to an arbitrary target class.
Authors: Aaron Ge, Monjoy Saha, Maire A. Duggan, Petra Lenz, Mustapha Abubakar, Montserrat Garc\'ia-Closas, Jeya Balasubramanian, Jonas S. Almeida, Praphulla MS Bhawsar
Abstract: Background: Tissue Microarrays (TMAs) significantly increase analytical efficiency in histopathology and large-scale epidemiologic studies by allowing multiple tissue cores to be scanned on a single slide. The individual cores can be digitally extracted and then linked to metadata for analysis in a process known as de-arraying. However, TMAs often contain core misalignments and artifacts due to assembly errors, which can adversely affect the reliability of the extracted cores during the de-arraying process. Moreover, conventional approaches for TMA de-arraying rely on desktop solutions.Therefore, a robust yet flexible de-arraying method is crucial to account for these inaccuracies and ensure effective downstream analyses. Results: We developed TMA-Grid, an in-browser, zero-footprint, interactive web application for TMA de-arraying. This web application integrates a convolutional neural network for precise tissue segmentation and a grid estimation algorithm to match each identified core to its expected location. The application emphasizes interactivity, allowing users to easily adjust segmentation and gridding results. Operating entirely in the web-browser, TMA-Grid eliminates the need for downloads or installations and ensures data privacy. Adhering to FAIR principles (Findable, Accessible, Interoperable, and Reusable), the application and its components are designed for seamless integration into TMA research workflows. Conclusions: TMA-Grid provides a robust, user-friendly solution for TMA dearraying on the web. As an open, freely accessible platform, it lays the foundation for collaborative analyses of TMAs and similar histopathology imaging data. Availability: Web application: https://episphere.github.io/tma-grid Code: https://github.com/episphere/tma-grid Tutorial: https://youtu.be/miajqyw4BVk
URLs: https://episphere.github.io/tma-grid, https://github.com/episphere/tma-grid, https://youtu.be/miajqyw4BVk
Authors: Hamidreza Kasaei, Mohammadreza Kasaei
Abstract: Imitation Learning (IL) has emerged as a powerful approach in robotics, allowing robots to acquire new skills by mimicking human actions. Despite its potential, the data collection process for IL remains a significant challenge due to the logistical difficulties and high costs associated with obtaining high-quality demonstrations. To address these issues, we propose a low-cost visual teleoperation system for bimanual manipulation tasks, called VITAL. Our approach leverages affordable hardware and visual processing techniques to collect demonstrations, which are then augmented to create extensive training datasets for imitation learning. We enhance the generalizability and robustness of the learned policies by utilizing both real and simulated environments and human-in-the-loop corrections. We evaluated our method through several rounds of experiments in simulated and real-robot settings, focusing on tasks of varying complexity, including bottle collecting, stacking objects, and hammering. Our experimental results validate the effectiveness of our approach in learning robust robot policies from simulated data, significantly improved by human-in-the-loop corrections and real-world data integration. Additionally, we demonstrate the framework's capability to generalize to new tasks, such as setting a drink tray, showcasing its adaptability and potential for handling a wide range of real-world bimanual manipulation tasks. A video of the experiments can be found at: https://youtu.be/YeVAMRqRe64?si=R179xDlEGc7nPu8i
Authors: Mohammad Tariqul Islam, Jason W. Fleischer
Abstract: The success of machine learning algorithms heavily relies on the quality of samples and the accuracy of their corresponding labels. However, building and maintaining large, high-quality datasets is an enormous task. This is especially true for biomedical data and for meta-sets that are compiled from smaller ones, as variations in image quality, labeling, reports, and archiving can lead to errors, inconsistencies, and repeated samples. Here, we show that the uniform manifold approximation and projection (UMAP) algorithm can find these anomalies essentially by forming independent clusters that are distinct from the main (good) data but similar to other points with the same error type. As a representative example, we apply UMAP to discover outliers in the publicly available ChestX-ray14, CheXpert, and MURA datasets. While the results are archival and retrospective and focus on radiological images, the graph-based methods work for any data type and will prove equally beneficial for curation at the time of dataset creation.
Authors: Dongwon Son, Sanghyeon Son, Jaehyung Kim, Beomjoon Kim
Abstract: We present DEF-oriCORN, a framework for language-directed manipulation tasks. By leveraging a novel object-based scene representation and diffusion-model-based state estimation algorithm, our framework enables efficient and robust manipulation planning in response to verbal commands, even in tightly packed environments with sparse camera views without any demonstrations. Unlike traditional representations, our representation affords efficient collision checking and language grounding. Compared to state-of-the-art baselines, our framework achieves superior estimation and motion planning performance from sparse RGB images and zero-shot generalizes to real-world scenarios with diverse materials, including transparent and reflective objects, despite being trained exclusively in simulation. Our code for data generation, training, inference, and pre-trained weights are publicly available at: https://sites.google.com/view/def-oricorn/home.
Authors: Idowu Paul Okuwobi, Zexuan Ji, Wen Fan, Songtao Yuan, Loza Bekalo, Qiang Chen
Abstract: The presence of hyperreflective foci (HFs) is related to retinal disease progression, and the quantity has proven to be a prognostic factor of visual and anatomical outcome in various retinal diseases. However, lack of efficient quantitative tools for evaluating the HFs has deprived ophthalmologist of assessing the volume of HFs. For this reason, we propose an automated quantification algorithm to segment and quantify HFs in spectral domain optical coherence tomography (SD-OCT). The proposed algorithm consists of two parallel processes namely: region of interest (ROI) generation and HFs estimation. To generate the ROI, we use morphological reconstruction to obtain the reconstructed image and histogram constructed for data distributions and clustering. In parallel, we estimate the HFs by extracting the extremal regions from the connected regions obtained from a component tree. Finally, both the ROI and the HFs estimation process are merged to obtain the segmented HFs. The proposed algorithm was tested on 40 3D SD-OCT volumes from 40 patients diagnosed with non-proliferative diabetic retinopathy (NPDR), proliferative diabetic retinopathy (PDR), and diabetic macular edema (DME). The average dice similarity coefficient (DSC) and correlation coefficient (r) are 69.70%, 0.99 for NPDR, 70.31%, 0.99 for PDR, and 71.30%, 0.99 for DME, respectively. The proposed algorithm can provide ophthalmologist with good HFs quantitative information, such as volume, size, and location of the HFs.
Authors: Wei Zhang, Weiming Zeng, Hongyu Chen, Jie Liu, Hongjie Yan, Kaile Zhang, Ran Tao, Wai Ting Siok, Nizhuan Wang
Abstract: Accurate diagnosis of depression is crucial for timely implementation of optimal treatments, preventing complications and reducing the risk of suicide. Traditional methods rely on self-report questionnaires and clinical assessment, lacking objective biomarkers. Combining fMRI with artificial intelligence can enhance depression diagnosis by integrating neuroimaging indicators. However, the specificity of fMRI acquisition for depression often results in unbalanced and small datasets, challenging the sensitivity and accuracy of classification models. In this study, we propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating CNN and RNN to capture both temporal and spatial features of brain activity. STANet comprises the following steps:(1) Aggregate spatio-temporal information via ICA. (2) Utilize multi-scale deep convolution to capture detailed features. (3) Balance data using the SMOTE to generate new samples for minority classes. (4) Employ the AFGRU classifier, which combines Fourier transformation with GRU, to capture long-term dependencies, with an adaptive weight assignment mechanism to enhance model generalization. The experimental results demonstrate that STANet achieves superior depression diagnostic performance with 82.38% accuracy and a 90.72% AUC. The STFA module enhances classification by capturing deeper features at multiple scales. The AFGRU classifier, with adaptive weights and stacked GRU, attains higher accuracy and AUC. SMOTE outperforms other oversampling methods. Additionally, spatio-temporal aggregated features achieve better performance compared to using only temporal or spatial features. STANet outperforms traditional or deep learning classifiers, and functional connectivity-based classifiers, as demonstrated by ten-fold cross-validation.
Authors: Lin Teng, Zihao Zhao, Jiawei Huang, Zehong Cao, Runqi Meng, Feng Shi, Dinggang Shen
Abstract: Automatic and accurate segmentation of brain MR images throughout the human lifespan into tissue and structure is crucial for understanding brain development and diagnosing diseases. However, challenges arise from the intricate variations in brain appearance due to rapid early brain development, aging, and disorders, compounded by the limited availability of manually-labeled datasets. In response, we present a two-step segmentation framework employing Knowledge-Guided Prompt Learning (KGPL) for brain MRI. Specifically, we first pre-train segmentation models on large-scale datasets with sub-optimal labels, followed by the incorporation of knowledge-driven embeddings learned from image-text alignment into the models. The introduction of knowledge-wise prompts captures semantic relationships between anatomical variability and biological processes, enabling models to learn structural feature embeddings across diverse age groups. Experimental findings demonstrate the superiority and robustness of our proposed method, particularly noticeable when employing Swin UNETR as the backbone. Our approach achieves average DSC values of 95.17% and 94.19% for brain tissue and structure segmentation, respectively. Our code is available at https://github.com/TL9792/KGPL.
Authors: Adrian Celaya, Evan Lim, Rachel Glenn, Brayden Mi, Alex Balsells, Tucker Netherton, Caroline Chung, Beatrice Riviere, David Fuentes
Abstract: Medical imaging segmentation is a highly active area of research, with deep learning-based methods achieving state-of-the-art results in several benchmarks. However, the lack of standardized tools for training, testing, and evaluating new methods makes the comparison of methods difficult. To address this, we introduce the Medical Imaging Segmentation Toolkit (MIST), a simple, modular, and end-to-end medical imaging segmentation framework designed to facilitate consistent training, testing, and evaluation of deep learning-based medical imaging segmentation methods. MIST standardizes data analysis, preprocessing, and evaluation pipelines, accommodating multiple architectures and loss functions. This standardization ensures reproducible and fair comparisons across different methods. We detail MIST's data format requirements, pipelines, and auxiliary features and demonstrate its efficacy using the BraTS Adult Glioma Post-Treatment Challenge dataset. Our results highlight MIST's ability to produce accurate segmentation masks and its scalability across multiple GPUs, showcasing its potential as a powerful tool for future medical imaging research and development.
Authors: Eran Bamani Beeri, Eden Nissinman, Avishai Sintov
Abstract: This paper presents a novel approach for ultra-range gesture recognition, addressing Human-Robot Interaction (HRI) challenges over extended distances. By leveraging human gestures in video data, we propose the Temporal-Spatiotemporal Fusion Network (TSFN) model that surpasses the limitations of current methods, enabling robots to understand gestures from long distances. With applications in service robots, search and rescue operations, and drone-based interactions, our approach enhances HRI in expansive environments. Experimental validation demonstrates significant advancements in gesture recognition accuracy, particularly in prolonged gesture sequences.
Authors: Wenhua Wu, Kun Hu, Wenxi Yue, Wei Li, Milena Simic, Changyang Li, Wei Xiang, Zhiyong Wang
Abstract: Knee osteoarthritis (KOA), a common form of arthritis that causes physical disability, has become increasingly prevalent in society. Employing computer-aided techniques to automatically assess the severity and progression of KOA can greatly benefit KOA treatment and disease management. Particularly, the advancement of X-ray technology in KOA demonstrates its potential for this purpose. Yet, existing X-ray prognosis research generally yields a singular progression severity grade, overlooking the potential visual changes for understanding and explaining the progression outcome. Therefore, in this study, a novel generative model is proposed, namely Identity-Consistent Radiographic Diffusion Network (IC-RDN), for multifaceted KOA prognosis encompassing a predicted future knee X-ray scan conditioned on the baseline scan. Specifically, an identity prior module for the diffusion and a downstream generation-guided progression prediction module are introduced. Compared to conventional image-to-image generative models, identity priors regularize and guide the diffusion to focus more on the clinical nuances of the prognosis based on a contrastive learning strategy. The progression prediction module utilizes both forecasted and baseline knee scans, and a more comprehensive formulation of KOA severity progression grading is expected. Extensive experiments on a widely used public dataset, OAI, demonstrate the effectiveness of the proposed method.
Authors: Andreas Birk
Abstract: We introduce SmileyNet, a novel neural network with psychic abilities. It is inspired by the fact that a positive mood can lead to improved cognitive capabilities including classification tasks. The network is hence presented in a first phase with smileys and an encouraging loss function is defined to bias it into a good mood. SmileyNet is then used to forecast the flipping of a coin based on an established method of Tasseology, namely by reading tea leaves. Training and testing in this second phase are done with a high-fidelity simulation based on real-world pixels sampled from a professional tea-reading cup. SmileyNet has an amazing accuracy of 72% to correctly predict the flip of a coin. Resnet-34, respectively YOLOv5 achieve only 49%, respectively 53%. It is then shown how multiple SmileyNets can be combined to win the lottery.
Authors: Fuzheng Zhao, Yu Bai
Abstract: This study aims to design and implement a laughter recognition system based on multimodal fusion and deep learning, leveraging image and audio processing technologies to achieve accurate laughter recognition and emotion analysis. First, the system loads video files and uses the OpenCV library to extract facial information while employing the Librosa library to process audio features such as MFCC. Then, multimodal fusion techniques are used to integrate image and audio features, followed by training and prediction using deep learning models. Evaluation results indicate that the model achieved 80% accuracy, precision, and recall on the test dataset, with an F1 score of 80%, demonstrating robust performance and the ability to handle real-world data variability. This study not only verifies the effectiveness of multimodal fusion methods in laughter recognition but also highlights their potential applications in affective computing and human-computer interaction. Future work will focus on further optimizing feature extraction and model architecture to improve recognition accuracy and expand application scenarios, promoting the development of laughter recognition technology in fields such as mental health monitoring and educational activity evaluation
Authors: Yimeng Geng, Gaofeng Meng, Mingcong Chen, Guanglin Cao, Mingyang Zhao, Jianbo Zhao, Hongbin Liu
Abstract: Accurate identification of arteries and veins in ultrasound images is crucial for vascular examinations and interventions in robotics-assisted surgeries. However, current methods for ultrasound vessel segmentation face challenges in distinguishing between arteries and veins due to their morphological similarities. To address this challenge, this study introduces a novel force sensing guided segmentation approach to enhance artery-vein segmentation accuracy by leveraging their distinct deformability. Our proposed method utilizes force magnitude to identify key frames with the most significant vascular deformation in a sequence of ultrasound images. These key frames are then integrated with the current frame through attention mechanisms, with weights assigned in accordance with force magnitude. Our proposed force sensing guided framework can be seamlessly integrated into various segmentation networks and achieves significant performance improvements in multiple U-shaped networks such as U-Net, Swin-unet and Transunet. Furthermore, we contribute the first multimodal ultrasound artery-vein segmentation dataset, Mus-V, which encompasses both force and image data simultaneously. The dataset comprises 3114 ultrasound images of carotid and femoral vessels extracted from 105 videos, with corresponding force data recorded by the force sensor mounted on the US probe. Our code and dataset will be publicly available.
Authors: Haodong Hong, Sen Wang, Zi Huang, Qi Wu, Jiajun Liu
Abstract: Real-world navigation often involves dealing with unexpected obstructions such as closed doors, moved objects, and unpredictable entities. However, mainstream Vision-and-Language Navigation (VLN) tasks typically assume instructions perfectly align with the fixed and predefined navigation graphs without any obstructions. This assumption overlooks potential discrepancies in actual navigation graphs and given instructions, which can cause major failures for both indoor and outdoor agents. To address this issue, we integrate diverse obstructions into the R2R dataset by modifying both the navigation graphs and visual observations, introducing an innovative dataset and task, R2R with UNexpected Obstructions (R2R-UNO). R2R-UNO contains various types and numbers of path obstructions to generate instruction-reality mismatches for VLN research. Experiments on R2R-UNO reveal that state-of-the-art VLN methods inevitably encounter significant challenges when facing such mismatches, indicating that they rigidly follow instructions rather than navigate adaptively. Therefore, we propose a novel method called ObVLN (Obstructed VLN), which includes a curriculum training strategy and virtual graph construction to help agents effectively adapt to obstructed environments. Empirical results show that ObVLN not only maintains robust performance in unobstructed scenarios but also achieves a substantial performance advantage with unexpected obstructions.
Authors: Junxuan Yu, Rusi Chen, Yongsong Zhou, Yanlin Chen, Yaofei Duan, Yuhao Huang, Han Zhou, Tan Tao, Xin Yang, Dong Ni
Abstract: Echocardiography video is a primary modality for diagnosing heart diseases, but the limited data poses challenges for both clinical teaching and machine learning training. Recently, video generative models have emerged as a promising strategy to alleviate this issue. However, previous methods often relied on holistic conditions during generation, hindering the flexible movement control over specific cardiac structures. In this context, we propose an explainable and controllable method for echocardiography video generation, taking an initial frame and a motion curve as guidance. Our contributions are three-fold. First, we extract motion information from each heart substructure to construct motion curves, enabling the diffusion model to synthesize customized echocardiography videos by modifying these curves. Second, we propose the structure-to-motion alignment module, which can map semantic features onto motion curves across cardiac structures. Third, The position-aware attention mechanism is designed to enhance video consistency utilizing Gaussian masks with structural position information. Extensive experiments on three echocardiography datasets show that our method outperforms others regarding fidelity and consistency. The full code will be released at https://github.com/mlmi-2024-72/ECM.
Authors: I. M. Chernenkiy, Y. A. Drach, S. R. Mustakimova, V. V. Kazantseva, N. A. Ushakov, S. K. Efetov, M. V. Feldsherov
Abstract: Colorectal cancer is the third-most common cancer in the Western Hemisphere. The segmentation of colorectal and colorectal cancer by computed tomography is an urgent problem in medicine. Indeed, a system capable of solving this problem will enable the detection of colorectal cancer at early stages of the disease, facilitate the search for pathology by the radiologist, and significantly accelerate the process of diagnosing the disease. However, scientific publications on medical image processing mostly use closed, non-public data. This paper presents an extension of the Medical Decathlon dataset with colorectal markups in order to improve the quality of segmentation algorithms. An experienced radiologist validated the data, categorized it into subsets by quality, and published it in the public domain. Based on the obtained results, we trained neural network models of the UNet architecture with 5-part cross-validation and achieved a Dice metric quality of $0.6988 \pm 0.3$. The published markups will improve the quality of colorectal cancer detection and simplify the radiologist's job for study description.
Authors: Shoujin Huang, Guanxiong Luo, Yuwan Wang, Kexin Yang, Lingyan Zhang, Jingzhe Liu, Hua Guo, Min Wang, Mengye Lyu
Abstract: Simultaneous multislice (SMS) imaging is a powerful technique for accelerating magnetic resonance imaging (MRI) acquisitions. However, SMS reconstruction remains challenging due to the complex signal interactions between and within the excited slices. This study presents a robust SMS MRI reconstruction method using deep generative priors. Starting from Gaussian noise, we leverage denoising diffusion probabilistic models (DDPM) to gradually recover the individual slices through reverse diffusion iterations while imposing data consistency from the measured k-space under readout concatenation framework. The posterior sampling procedure is designed such that the DDPM training can be performed on single-slice images without special adjustments for SMS tasks. Additionally, our method integrates a low-frequency enhancement (LFE) module to address a practical issue that SMS-accelerated fast spin echo (FSE) and echo-planar imaging (EPI) sequences cannot easily embed autocalibration signals. Extensive experiments demonstrate that our approach consistently outperforms existing methods and generalizes well to unseen datasets. The code is available at https://github.com/Solor-pikachu/ROGER after the review process.
Authors: Hermione Warr, Yasin Ibrahim, Daniel R. McGowan, Konstantinos Kamnitsas
Abstract: Automation of medical image interpretation could alleviate bottlenecks in diagnostic workflows, and has become of particular interest in recent years due to advancements in natural language processing. Great strides have been made towards automated radiology report generation via AI, yet ensuring clinical accuracy in generated reports is a significant challenge, hindering deployment of such methods in clinical practice. In this work we propose a quality control framework for assessing the reliability of AI-generated radiology reports with respect to semantics of diagnostic importance using modular auxiliary auditing components (AC). Evaluating our pipeline on the MIMIC-CXR dataset, our findings show that incorporating ACs in the form of disease-classifiers can enable auditing that identifies more reliable reports, resulting in higher F1 scores compared to unfiltered generated reports. Additionally, leveraging the confidence of the AC labels further improves the audit's effectiveness.
Authors: Sina Ghorbani Kolahi, Seyed Kamal Chaharsooghi, Toktam Khatibi, Afshin Bozorgpour, Reza Azad, Moein Heidari, Ilker Hacihaliloglu, Dorit Merhof
Abstract: Medical image segmentation involves identifying and separating object instances in a medical image to delineate various tissues and structures, a task complicated by the significant variations in size, shape, and density of these features. Convolutional neural networks (CNNs) have traditionally been used for this task but have limitations in capturing long-range dependencies. Transformers, equipped with self-attention mechanisms, aim to address this problem. However, in medical image segmentation it is beneficial to merge both local and global features to effectively integrate feature maps across various scales, capturing both detailed features and broader semantic elements for dealing with variations in structures. In this paper, we introduce MSA2Net, a new deep segmentation framework featuring an expedient design of skip-connections. These connections facilitate feature fusion by dynamically weighting and combining coarse-grained encoder features with fine-grained decoder feature maps. Specifically, we propose a Multi-Scale Adaptive Spatial Attention Gate (MASAG), which dynamically adjusts the receptive field (Local and Global contextual information) to ensure that spatially relevant features are selectively highlighted while minimizing background distractions. Extensive evaluations involving dermatology, and radiological datasets demonstrate that our MSA2Net outperforms state-of-the-art (SOTA) works or matches their performance. The source code is publicly available at https://github.com/xmindflow/MSA-2Net.
Authors: Joseph Geo Benjamin, Mothilal Asokan, Amna Alhosani, Hussain Alasmawi, Werner Gerhard Diehl, Leanne Bricker, Karthik Nandakumar, Mohammad Yaqub
Abstract: Self-supervised learning (SSL) methods are popular since they can address situations with limited annotated data by directly utilising the underlying data distribution. However, the adoption of such methods is not explored enough in ultrasound (US) imaging, especially for fetal assessment. We investigate the potential of dual-encoder SSL in utilizing unlabelled US video data to improve the performance of challenging downstream Standard Fetal Cardiac Planes (SFCP) classification using limited labelled 2D US images. We study 7 SSL approaches based on reconstruction, contrastive loss, distillation, and information theory and evaluate them extensively on a large private US dataset. Our observations and findings are consolidated from more than 500 downstream training experiments under different settings. Our primary observation shows that for SSL training, the variance of the dataset is more crucial than its size because it allows the model to learn generalisable representations, which improve the performance of downstream tasks. Overall, the BarlowTwins method shows robust performance, irrespective of the training settings and data variations, when used as an initialisation for downstream tasks. Notably, full fine-tuning with 1% of labelled data outperforms ImageNet initialisation by 12% in F1-score and outperforms other SSL initialisations by at least 4% in F1-score, thus making it a promising candidate for transfer learning from US video to image data.
Authors: Zhibin Duan, Tiansheng Wen, Yifei Wang, Chen Zhu, Bo Chen, Mingyuan Zhou
Abstract: Factor analysis, often regarded as a Bayesian variant of matrix factorization, offers superior capabilities in capturing uncertainty, modeling complex dependencies, and ensuring robustness. As the deep learning era arrives, factor analysis is receiving less and less attention due to their limited expressive ability. On the contrary, contrastive learning has emerged as a potent technique with demonstrated efficacy in unsupervised representational learning. While the two methods are different paradigms, recent theoretical analysis has revealed the mathematical equivalence between contrastive learning and matrix factorization, providing a potential possibility for factor analysis combined with contrastive learning. Motivated by the interconnectedness of contrastive learning, matrix factorization, and factor analysis, this paper introduces a novel Contrastive Factor Analysis framework, aiming to leverage factor analysis's advantageous properties within the realm of contrastive learning. To further leverage the interpretability properties of non-negative factor analysis, which can learn disentangled representations, contrastive factor analysis is extended to a non-negative version. Finally, extensive experimental validation showcases the efficacy of the proposed contrastive (non-negative) factor analysis methodology across multiple key properties, including expressiveness, robustness, interpretability, and accurate uncertainty estimation.
Authors: Abhimanyu Dubey (Jack), Abhinav Jauhri (Jack), Abhinav Pandey (Jack), Abhishek Kadian (Jack), Ahmad Al-Dahle (Jack), Aiesha Letman (Jack), Akhil Mathur (Jack), Alan Schelten (Jack), Amy Yang (Jack), Angela Fan (Jack), Anirudh Goyal (Jack), Anthony Hartshorn (Jack), Aobo Yang (Jack), Archi Mitra (Jack), Archie Sravankumar (Jack), Artem Korenev (Jack), Arthur Hinsvark (Jack), Arun Rao (Jack), Aston Zhang (Jack), Aurelien Rodriguez (Jack), Austen Gregerson (Jack), Ava Spataru (Jack), Baptiste Roziere (Jack), Bethany Biron (Jack), Binh Tang (Jack), Bobbie Chern (Jack), Charlotte Caucheteux (Jack), Chaya Nayak (Jack), Chloe Bi (Jack), Chris Marra (Jack), Chris McConnell (Jack), Christian Keller (Jack), Christophe Touret (Jack), Chunyang Wu (Jack), Corinne Wong (Jack), Cristian Canton Ferrer (Jack), Cyrus Nikolaidis (Jack), Damien Allonsius (Jack), Daniel Song (Jack), Danielle Pintz (Jack), Danny Livshits (Jack), David Esiobu (Jack), Dhruv Choudhary (Jack), Dhruv Mahajan (Jack), Diego Garcia-Olano (Jack), Diego Perino (Jack), Dieuwke Hupkes (Jack), Egor Lakomkin (Jack), Ehab AlBadawy (Jack), Elina Lobanova (Jack), Emily Dinan (Jack), Eric Michael Smith (Jack), Filip Radenovic (Jack), Frank Zhang (Jack), Gabriel Synnaeve (Jack), Gabrielle Lee (Jack), Georgia Lewis Anderson (Jack), Graeme Nail (Jack), Gregoire Mialon (Jack), Guan Pang (Jack), Guillem Cucurell (Jack), Hailey Nguyen (Jack), Hannah Korevaar (Jack), Hu Xu (Jack), Hugo Touvron (Jack), Iliyan Zarov (Jack), Imanol Arrieta Ibarra (Jack), Isabel Kloumann (Jack), Ishan Misra (Jack), Ivan Evtimov (Jack), Jade Copet (Jack), Jaewon Lee (Jack), Jan Geffert (Jack), Jana Vranes (Jack), Jason Park (Jack), Jay Mahadeokar (Jack), Jeet Shah (Jack), Jelmer van der Linde (Jack), Jennifer Billock (Jack), Jenny Hong (Jack), Jenya Lee (Jack), Jeremy Fu (Jack), Jianfeng Chi (Jack), Jianyu Huang (Jack), Jiawen Liu (Jack), Jie Wang (Jack), Jiecao Yu (Jack), Joanna Bitton (Jack), Joe Spisak (Jack), Jongsoo Park (Jack), Joseph Rocca (Jack), Joshua Johnstun (Jack), Joshua Saxe (Jack), Junteng Jia (Jack), Kalyan Vasuden Alwala (Jack), Kartikeya Upasani (Jack), Kate Plawiak (Jack), Ke Li (Jack), Kenneth Heafield (Jack), Kevin Stone (Jack), Khalid El-Arini (Jack), Krithika Iyer (Jack), Kshitiz Malik (Jack), Kuenley Chiu (Jack), Kunal Bhalla (Jack), Lauren Rantala-Yeary (Jack), Laurens van der Maaten (Jack), Lawrence Chen (Jack), Liang Tan (Jack), Liz Jenkins (Jack), Louis Martin (Jack), Lovish Madaan (Jack), Lubo Malo (Jack), Lukas Blecher (Jack), Lukas Landzaat (Jack), Luke de Oliveira (Jack), Madeline Muzzi (Jack), Mahesh Pasupuleti (Jack), Mannat Singh (Jack), Manohar Paluri (Jack), Marcin Kardas (Jack), Mathew Oldham (Jack), Mathieu Rita (Jack), Maya Pavlova (Jack), Melanie Kambadur (Jack), Mike Lewis (Jack), Min Si (Jack), Mitesh Kumar Singh (Jack), Mona Hassan (Jack), Naman Goyal (Jack), Narjes Torabi (Jack), Nikolay Bashlykov (Jack), Nikolay Bogoychev (Jack), Niladri Chatterji (Jack), Olivier Duchenne (Jack), Onur \c{C}elebi (Jack), Patrick Alrassy (Jack), Pengchuan Zhang (Jack), Pengwei Li (Jack), Petar Vasic (Jack), Peter Weng (Jack), Prajjwal Bhargava (Jack), Pratik Dubal (Jack), Praveen Krishnan (Jack), Punit Singh Koura (Jack), Puxin Xu (Jack), Qing He (Jack), Qingxiao Dong (Jack), Ragavan Srinivasan (Jack), Raj Ganapathy (Jack), Ramon Calderer (Jack), Ricardo Silveira Cabral (Jack), Robert Stojnic (Jack), Roberta Raileanu (Jack), Rohit Girdhar (Jack), Rohit Patel (Jack), Romain Sauvestre (Jack), Ronnie Polidoro (Jack), Roshan Sumbaly (Jack), Ross Taylor (Jack), Ruan Silva (Jack), Rui Hou (Jack), Rui Wang (Jack), Saghar Hosseini (Jack), Sahana Chennabasappa (Jack), Sanjay Singh (Jack), Sean Bell (Jack), Seohyun Sonia Kim (Jack), Sergey Edunov (Jack), Shaoliang Nie (Jack), Sharan Narang (Jack), Sharath Raparthy (Jack), Sheng Shen (Jack), Shengye Wan (Jack), Shruti Bhosale (Jack), Shun Zhang (Jack), Simon Vandenhende (Jack), Soumya Batra (Jack), Spencer Whitman (Jack), Sten Sootla (Jack), Stephane Collot (Jack), Suchin Gururangan (Jack), Sydney Borodinsky (Jack), Tamar Herman (Jack), Tara Fowler (Jack), Tarek Sheasha (Jack), Thomas Georgiou (Jack), Thomas Scialom (Jack), Tobias Speckbacher (Jack), Todor Mihaylov (Jack), Tong Xiao (Jack), Ujjwal Karn (Jack), Vedanuj Goswami (Jack), Vibhor Gupta (Jack), Vignesh Ramanathan (Jack), Viktor Kerkez (Jack), Vincent Gonguet (Jack), Virginie Do (Jack), Vish Vogeti (Jack), Vladan Petrovic (Jack), Weiwei Chu (Jack), Wenhan Xiong (Jack), Wenyin Fu (Jack), Whitney Meers (Jack), Xavier Martinet (Jack), Xiaodong Wang (Jack), Xiaoqing Ellen Tan (Jack), Xinfeng Xie (Jack), Xuchao Jia (Jack), Xuewei Wang (Jack), Yaelle Goldschlag (Jack), Yashesh Gaur (Jack), Yasmine Babaei (Jack), Yi Wen (Jack), Yiwen Song (Jack), Yuchen Zhang (Jack), Yue Li (Jack), Yuning Mao (Jack), Zacharie Delpierre Coudert (Jack), Zheng Yan (Jack), Zhengxing Chen (Jack), Zoe Papakipos (Jack), Aaditya Singh (Jack), Aaron Grattafiori (Jack), Abha Jain (Jack), Adam Kelsey (Jack), Adam Shajnfeld (Jack), Adithya Gangidi (Jack), Adolfo Victoria (Jack), Ahuva Goldstand (Jack), Ajay Menon (Jack), Ajay Sharma (Jack), Alex Boesenberg (Jack), Alex Vaughan (Jack), Alexei Baevski (Jack), Allie Feinstein (Jack), Amanda Kallet (Jack), Amit Sangani (Jack), Anam Yunus (Jack), Andrei Lupu (Jack), Andres Alvarado (Jack), Andrew Caples (Jack), Andrew Gu (Jack), Andrew Ho (Jack), Andrew Poulton (Jack), Andrew Ryan (Jack), Ankit Ramchandani (Jack), Annie Franco (Jack), Aparajita Saraf (Jack), Arkabandhu Chowdhury (Jack), Ashley Gabriel (Jack), Ashwin Bharambe (Jack), Assaf Eisenman (Jack), Azadeh Yazdan (Jack), Beau James (Jack), Ben Maurer (Jack), Benjamin Leonhardi (Jack), Bernie Huang (Jack), Beth Loyd (Jack), Beto De Paola (Jack), Bhargavi Paranjape (Jack), Bing Liu (Jack), Bo Wu (Jack), Boyu Ni (Jack), Braden Hancock (Jack), Bram Wasti (Jack), Brandon Spence (Jack), Brani Stojkovic (Jack), Brian Gamido (Jack), Britt Montalvo (Jack), Carl Parker (Jack), Carly Burton (Jack), Catalina Mejia (Jack), Changhan Wang (Jack), Changkyu Kim (Jack), Chao Zhou (Jack), Chester Hu (Jack), Ching-Hsiang Chu (Jack), Chris Cai (Jack), Chris Tindal (Jack), Christoph Feichtenhofer (Jack), Damon Civin (Jack), Dana Beaty (Jack), Daniel Kreymer (Jack), Daniel Li (Jack), Danny Wyatt (Jack), David Adkins (Jack), David Xu (Jack), Davide Testuggine (Jack), Delia David (Jack), Devi Parikh (Jack), Diana Liskovich (Jack), Didem Foss (Jack), Dingkang Wang (Jack), Duc Le (Jack), Dustin Holland (Jack), Edward Dowling (Jack), Eissa Jamil (Jack), Elaine Montgomery (Jack), Eleonora Presani (Jack), Emily Hahn (Jack), Emily Wood (Jack), Erik Brinkman (Jack), Esteban Arcaute (Jack), Evan Dunbar (Jack), Evan Smothers (Jack), Fei Sun (Jack), Felix Kreuk (Jack), Feng Tian (Jack), Firat Ozgenel (Jack), Francesco Caggioni (Jack), Francisco Guzm\'an (Jack), Frank Kanayet (Jack), Frank Seide (Jack), Gabriela Medina Florez (Jack), Gabriella Schwarz (Jack), Gada Badeer (Jack), Georgia Swee (Jack), Gil Halpern (Jack), Govind Thattai (Jack), Grant Herman (Jack), Grigory Sizov (Jack), Guangyi (Jack), Zhang (Sid), Guna Lakshminarayanan (Sid), Hamid Shojanazeri (Sid), Han Zou (Sid), Hannah Wang (Sid), Hanwen Zha (Sid), Haroun Habeeb (Sid), Harrison Rudolph (Sid), Helen Suk (Sid), Henry Aspegren (Sid), Hunter Goldman (Sid), Igor Molybog (Sid), Igor Tufanov (Sid), Irina-Elena Veliche (Sid), Itai Gat (Sid), Jake Weissman (Sid), James Geboski (Sid), James Kohli (Sid), Japhet Asher (Sid), Jean-Baptiste Gaya (Sid), Jeff Marcus (Sid), Jeff Tang (Sid), Jennifer Chan (Sid), Jenny Zhen (Sid), Jeremy Reizenstein (Sid), Jeremy Teboul (Sid), Jessica Zhong (Sid), Jian Jin (Sid), Jingyi Yang (Sid), Joe Cummings (Sid), Jon Carvill (Sid), Jon Shepard (Sid), Jonathan McPhie (Sid), Jonathan Torres (Sid), Josh Ginsburg (Sid), Junjie Wang (Sid), Kai Wu (Sid), Kam Hou U (Sid), Karan Saxena (Sid), Karthik Prasad (Sid), Kartikay Khandelwal (Sid), Katayoun Zand (Sid), Kathy Matosich (Sid), Kaushik Veeraraghavan (Sid), Kelly Michelena (Sid), Keqian Li (Sid), Kun Huang (Sid), Kunal Chawla (Sid), Kushal Lakhotia (Sid), Kyle Huang (Sid), Lailin Chen (Sid), Lakshya Garg (Sid), Lavender A (Sid), Leandro Silva (Sid), Lee Bell (Sid), Lei Zhang (Sid), Liangpeng Guo (Sid), Licheng Yu (Sid), Liron Moshkovich (Sid), Luca Wehrstedt (Sid), Madian Khabsa (Sid), Manav Avalani (Sid), Manish Bhatt (Sid), Maria Tsimpoukelli (Sid), Martynas Mankus (Sid), Matan Hasson (Sid), Matthew Lennie (Sid), Matthias Reso (Sid), Maxim Groshev (Sid), Maxim Naumov (Sid), Maya Lathi (Sid), Meghan Keneally (Sid), Michael L. Seltzer (Sid), Michal Valko (Sid), Michelle Restrepo (Sid), Mihir Patel (Sid), Mik Vyatskov (Sid), Mikayel Samvelyan (Sid), Mike Clark (Sid), Mike Macey (Sid), Mike Wang (Sid), Miquel Jubert Hermoso (Sid), Mo Metanat (Sid), Mohammad Rastegari (Sid), Munish Bansal (Sid), Nandhini Santhanam (Sid), Natascha Parks (Sid), Natasha White (Sid), Navyata Bawa (Sid), Nayan Singhal (Sid), Nick Egebo (Sid), Nicolas Usunier (Sid), Nikolay Pavlovich Laptev (Sid), Ning Dong (Sid), Ning Zhang (Sid), Norman Cheng (Sid), Oleg Chernoguz (Sid), Olivia Hart (Sid), Omkar Salpekar (Sid), Ozlem Kalinli (Sid), Parkin Kent (Sid), Parth Parekh (Sid), Paul Saab (Sid), Pavan Balaji (Sid), Pedro Rittner (Sid), Philip Bontrager (Sid), Pierre Roux (Sid), Piotr Dollar (Sid), Polina Zvyagina (Sid), Prashant Ratanchandani (Sid), Pritish Yuvraj (Sid), Qian Liang (Sid), Rachad Alao (Sid), Rachel Rodriguez (Sid), Rafi Ayub (Sid), Raghotham Murthy (Sid), Raghu Nayani (Sid), Rahul Mitra (Sid), Raymond Li (Sid), Rebekkah Hogan (Sid), Robin Battey (Sid), Rocky Wang (Sid), Rohan Maheswari (Sid), Russ Howes (Sid), Ruty Rinott (Sid), Sai Jayesh Bondu (Sid), Samyak Datta (Sid), Sara Chugh (Sid), Sara Hunt (Sid), Sargun Dhillon (Sid), Sasha Sidorov (Sid), Satadru Pan (Sid), Saurabh Verma (Sid), Seiji Yamamoto (Sid), Sharadh Ramaswamy (Sid), Shaun Lindsay (Sid), Shaun Lindsay (Sid), Sheng Feng (Sid), Shenghao Lin (Sid), Shengxin Cindy Zha (Sid), Shiva Shankar (Sid), Shuqiang Zhang (Sid), Shuqiang Zhang (Sid), Sinong Wang (Sid), Sneha Agarwal (Sid), Soji Sajuyigbe (Sid), Soumith Chintala (Sid), Stephanie Max (Sid), Stephen Chen (Sid), Steve Kehoe (Sid), Steve Satterfield (Sid), Sudarshan Govindaprasad (Sid), Sumit Gupta (Sid), Sungmin Cho (Sid), Sunny Virk (Sid), Suraj Subramanian (Sid), Sy Choudhury (Sid), Sydney Goldman (Sid), Tal Remez (Sid), Tamar Glaser (Sid), Tamara Best (Sid), Thilo Kohler (Sid), Thomas Robinson (Sid), Tianhe Li (Sid), Tianjun Zhang (Sid), Tim Matthews (Sid), Timothy Chou (Sid), Tzook Shaked (Sid), Varun Vontimitta (Sid), Victoria Ajayi (Sid), Victoria Montanez (Sid), Vijai Mohan (Sid), Vinay Satish Kumar (Sid), Vishal Mangla (Sid), Vlad Ionescu (Sid), Vlad Poenaru (Sid), Vlad Tiberiu Mihailescu (Sid), Vladimir Ivanov (Sid), Wei Li (Sid), Wenchen Wang (Sid), Wenwen Jiang (Sid), Wes Bouaziz (Sid), Will Constable (Sid), Xiaocheng Tang (Sid), Xiaofang Wang (Sid), Xiaojian Wu (Sid), Xiaolan Wang (Sid), Xide Xia (Sid), Xilun Wu (Sid), Xinbo Gao (Sid), Yanjun Chen (Sid), Ye Hu (Sid), Ye Jia (Sid), Ye Qi (Sid), Yenda Li (Sid), Yilin Zhang (Sid), Ying Zhang (Sid), Yossi Adi (Sid), Youngjin Nam (Sid), Yu (Sid), Wang, Yuchen Hao, Yundi Qian, Yuzi He, Zach Rait, Zachary DeVito, Zef Rosnbrick, Zhaoduo Wen, Zhenyu Yang, Zhiwei Zhao
Abstract: Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.
Authors: Chengpeng Chen, Zichao Guo, Haien Zeng, Pengfei Xiong, Jian Dong
Abstract: Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) architecture design. Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers. Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible. To address this, this paper provides a new perspective to realize feature reuse implicitly and more efficiently instead of concatenation. A novel hardware-efficient RepGhost module is proposed for implicit feature reuse via reparameterization, instead of using concatenation operator. Based on the RepGhost module, we develop our efficient RepGhost bottleneck and RepGhostNet. Experiments on ImageNet and COCO benchmarks demonstrate that our RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices. Specially, our RepGhostNet surpasses GhostNet 0.5x by 2.5% Top-1 accuracy on ImageNet dataset with less parameters and comparable latency on an ARM-based mobile device. Code and model weights are available at https://github.com/ChengpengChen/RepGhost.
Authors: Dominik Narnhofer, Andreas Habring, Martin Holler, Thomas Pock
Abstract: In this work, a method for obtaining pixel-wise error bounds in Bayesian regularization of inverse imaging problems is introduced. The proposed method employs estimates of the posterior variance together with techniques from conformal prediction in order to obtain coverage guarantees for the error bounds, without making any assumption on the underlying data distribution. It is generally applicable to Bayesian regularization approaches, independent, e.g., of the concrete choice of the prior. Furthermore, the coverage guarantees can also be obtained in case only approximate sampling from the posterior is possible. With this in particular, the proposed framework is able to incorporate any learned prior in a black-box manner. Guaranteed coverage without assumptions on the underlying distributions is only achievable since the magnitude of the error bounds is, in general, unknown in advance. Nevertheless, experiments with multiple regularization approaches presented in the paper confirm that in practice, the obtained error bounds are rather tight. For realizing the numerical experiments, also a novel primal-dual Langevin algorithm for sampling from non-smooth distributions is introduced in this work.
Authors: Craig Iaboni, Thomas Kelly, Pramod Abichandani
Abstract: This paper presents an open-source aerial neuromorphic dataset that captures pedestrians and vehicles moving in an urban environment. The dataset, titled NU-AIR, features 70.75 minutes of event footage acquired with a 640 x 480 resolution neuromorphic sensor mounted on a quadrotor operating in an urban environment. Crowds of pedestrians, different types of vehicles, and street scenes featuring busy urban environments are captured at different elevations and illumination conditions. Manual bounding box annotations of vehicles and pedestrians contained in the recordings are provided at a frequency of 30 Hz, yielding 93,204 labels in total. Evaluation of the dataset's fidelity is performed through comprehensive ablation study for three Spiking Neural Networks (SNNs) and training ten Deep Neural Networks (DNNs) to validate the quality and reliability of both the dataset and corresponding annotations. All data and Python code to voxelize the data and subsequently train SNNs/DNNs has been open-sourced.
Authors: Mu Chen, Zhedong Zheng, Yi Yang
Abstract: Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting the pixels. Such vanilla methods are usually sub-optimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, it is worth noting that several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to generate the pseudo depth. Extensive experiments show that our proposed methods, even with pseudo depth, achieve competitive performance on two widely-used bench-marks, i.e. 77.7 mIoU on GTA to Cityscapes and 69.3 mIoU on Synthia to Cityscapes.
Authors: Meng Chu, Zhedong Zheng, Wei Ji, Tingyu Wang, Tat-Seng Chua
Abstract: Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this pressing need, we introduce GeoText-1652, a new natural language-guided geo-localization benchmark. This dataset is systematically constructed through an interactive human-computer process leveraging Large Language Model (LLM) driven annotation techniques in conjunction with pre-trained vision models. GeoText-1652 extends the established University-1652 image dataset with spatial-aware text annotations, thereby establishing one-to-one correspondences between image, text, and bounding box elements. We further introduce a new optimization objective to leverage fine-grained spatial associations, called blending spatial matching, for region-level spatial relation matching. Extensive experiments reveal that our approach maintains a competitive recall rate comparing other prevailing cross-modality methods. This underscores the promising potential of our approach in elevating drone control and navigation through the seamless integration of natural language commands in real-world scenarios.
Authors: Zitong Zhan, Dasong Gao, Yun-Jou Lin, Youjie Xia, Chen Wang
Abstract: Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature correspondence learning is still limited by the lack of accurate per-pixel correspondence labels. To overcome this difficulty, we introduce a new self-supervised scheme, imperative learning (IL), for training feature correspondence. It enables correspondence learning on arbitrary uninterrupted videos without any camera pose or depth labels, heralding a new era for self-supervised correspondence learning. Specifically, we formulated the problem of correspondence learning as a bilevel optimization, which takes the reprojection error from bundle adjustment as a supervisory signal for the model. To avoid large memory and computation overhead, we leverage the stationary point to effectively back-propagate the implicit gradients through bundle adjustment. Through extensive experiments, we demonstrate superior performance on tasks including feature matching and pose estimation, in which we obtained an average of 30% accuracy gain over the state-of-the-art matching models. This preprint corresponds to the Accepted Manuscript in European Conference on Computer Vision (ECCV) 2024.
Authors: Yuru Jia, Lukas Hoyer, Shengyu Huang, Tianfu Wang, Luc Van Gool, Konrad Schindler, Anton Obukhov
Abstract: Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content, specialize to user data through few-shot fine-tuning, and condition their output on other modalities, such as semantic maps. However, are they usable as large-scale data generators, e.g., to improve tasks in the perception stack, like semantic segmentation? We investigate this question in the context of autonomous driving, and answer it with a resounding "yes". We propose an efficient data generation pipeline termed DGInStyle. First, we examine the problem of specializing a pretrained LDM to semantically-controlled generation within a narrow domain. Second, we propose a Style Swap technique to endow the rich generative prior with the learned semantic control. Third, we design a Multi-resolution Latent Fusion technique to overcome the bias of LDMs towards dominant objects. Using DGInStyle, we generate a diverse dataset of street scenes, train a domain-agnostic semantic segmentation model on it, and evaluate the model on multiple popular autonomous driving datasets. Our approach consistently increases the performance of several domain generalization methods compared to the previous state-of-the-art methods. The source code and the generated dataset are available at https://dginstyle.github.io.
Authors: Philipp Schr\"oppel, Christopher Wewer, Jan Eric Lenssen, Eddy Ilg, Thomas Brox
Abstract: Controllable generation of 3D assets is important for many practical applications like content creation in movies, games and engineering, as well as in AR/VR. Recently, diffusion models have shown remarkable results in generation quality of 3D objects. However, none of the existing models enable disentangled generation to control the shape and appearance separately. For the first time, we present a suitable representation for 3D diffusion models to enable such disentanglement by introducing a hybrid point cloud and neural radiance field approach. We model a diffusion process over point positions jointly with a high-dimensional feature space for a local density and radiance decoder. While the point positions represent the coarse shape of the object, the point features allow modeling the geometry and appearance details. This disentanglement enables us to sample both independently and therefore to control both separately. Our approach sets a new state of the art in generation compared to previous disentanglement-capable methods by reduced FID scores of 30-90% and is on-par with other non disentanglement-capable state-of-the art methods.
Authors: Wanwen Chen, Adam Schmidt, Eitan Prisman, Septimiu E Salcudean
Abstract: Finding point-level correspondences is a fundamental problem in ultrasound (US), since it can enable US landmark tracking for intraoperative image guidance in different surgeries, including head and neck. Most existing US tracking methods, e.g., those based on optical flow or feature matching, were initially designed for RGB images before being applied to US. Therefore domain shift can impact their performance. Training could be supervised by ground-truth correspondences, but these are expensive to acquire in US. To solve these problems, we propose a self-supervised pixel-level tracking model called PIPsUS. Our model can track an arbitrary number of points in one forward pass and exploits temporal information by considering multiple, instead of just consecutive, frames. We developed a new self-supervised training strategy that utilizes a long-term point-tracking model trained for RGB images as a teacher to guide the model to learn realistic motions and use data augmentation to enforce tracking from US appearance. We evaluate our method on neck and oral US and echocardiography, showing higher point tracking accuracy when compared with fast normalized cross-correlation and tuned optical flow. Code will be available once the paper is accepted.
Authors: Can Liu, Jin Wang, and Yipeng Zhou, Yachao Yuan, Quanzheng Sheng, Kejie Lu
Abstract: Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth training data such as images based on model gradients. However, reconstructing high-resolution images by existing GIAs faces two challenges: inferior accuracy and slow-convergence, especially when duplicating labels exist in the training batch. To address these challenges, we present an Accurate and Fast-convergent Gradient Inversion attack algorithm, called AFGI, with two components: Label Recovery Block (LRB) which can accurately restore duplicating labels of private images based on exposed gradients; VME Regularization Term, which includes the total variance of reconstructed images, the discrepancy between three-channel means and edges, between values from exposed gradients and reconstructed images, respectively. The AFGI can be regarded as a white-box attack strategy to reconstruct images by leveraging labels recovered by LRB. In particular, AFGI is efficient that accurately reconstruct ground-truth images when users' training batch size is up to 48. Our experimental results manifest that AFGI can diminish 85% time costs while achieving superb inversion quality in the ImageNet dataset. At last, our study unveils the shortcomings of FL in privacy-preservation, prompting the development of more advanced countermeasure strategies.
Authors: Shen Zheng, Anurag Ghosh, Srinivasa G. Narasimhan
Abstract: Driving is challenging in conditions like night, rain, and snow. The lack of good labeled datasets has hampered progress in scene understanding under such conditions. Unsupervised domain adaptation (UDA) using large labeled clear-day datasets is a promising research direction in such cases. Current UDA methods, however, treat all image pixels uniformly, leading to over-reliance on the dominant scene backgrounds (e.g., roads, sky, sidewalks) that appear dramatically different across domains. As a result, they struggle to learn effective features of smaller and often sparse foreground objects (e.g., people, vehicles, signs). In this work, we improve UDA training by using in-place image warping to focus on salient object regions. Our insight is that while backgrounds vary significantly across domains (e.g., snowy night vs. clear day), object appearances vary to a lesser extent. Therefore, we design instance-level saliency guidance to adaptively oversample object regions, which reduces adverse effects from background context and enhances backbone feature learning. We then unwarp the better learned features while adapting from source to target. Our approach improves adaptation across geographies, lighting, and weather conditions, and is agnostic to the task (segmentation, detection), domain adaptation algorithm, saliency guidance, and underlying model architecture. Result highlights include +6.1 mAP50 for BDD100K Clear $\rightarrow$ DENSE Foggy, +3.7 mAP50 for BDD100K Day $\rightarrow$ Night, +3.0 mAP50 for BDD100K Clear $\rightarrow$ Rainy, and +6.3 mIoU for Cityscapes $\rightarrow$ ACDC. Our method adds minimal training memory and incurs no additional inference latency. Please see Appendix for more results and analysis.
Authors: Poulami Sinhamahapatra, Suprosanna Shit, Anjany Sekuboyina, Malek Husseini, David Schinz, Nicolas Lenhart, Joern Menze, Jan Kirschke, Karsten Roscher, Stephan Guennemann
Abstract: Vertebral fracture grading classifies the severity of vertebral fractures, which is a challenging task in medical imaging and has recently attracted Deep Learning (DL) models. Only a few works attempted to make such models human-interpretable despite the need for transparency and trustworthiness in critical use cases like DL-assisted medical diagnosis. Moreover, such models either rely on post-hoc methods or additional annotations. In this work, we propose a novel interpretable-by-design method, ProtoVerse, to find relevant sub-parts of vertebral fractures (prototypes) that reliably explain the model's decision in a human-understandable way. Specifically, we introduce a novel diversity-promoting loss to mitigate prototype repetitions in small datasets with intricate semantics. We have experimented with the VerSe'19 dataset and outperformed the existing prototype-based method. Further, our model provides superior interpretability against the post-hoc method. Importantly, expert radiologists validated the visual interpretability of our results, showing clinical applicability.
Authors: Michael Deutges, Ario Sadafi, Nassir Navab, Carsten Marr
Abstract: Diagnosis of hematological malignancies depends on accurate identification of white blood cells in peripheral blood smears. Deep learning techniques are emerging as a viable solution to scale and optimize this process by automatic cell classification. However, these techniques face several challenges such as limited generalizability, sensitivity to domain shifts, and lack of explainability. Here, we introduce a novel approach for white blood cell classification based on neural cellular automata (NCA). We test our approach on three datasets of white blood cell images and show that we achieve competitive performance compared to conventional methods. Our NCA-based method is significantly smaller in terms of parameters and exhibits robustness to domain shifts. Furthermore, the architecture is inherently explainable, providing insights into the decision process for each classification, which helps to understand and validate model predictions. Our results demonstrate that NCA can be used for image classification, and that they address key challenges of conventional methods, indicating a high potential for applicability in clinical practice.
Authors: Aswini Kumar Patra, Lingaraj Sahoo
Abstract: Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants under water deficit. Sensor based imaging data serves as a rich source of information for machine learning and deep learning algorithms, facilitating further analysis aimed at identifying drought stress. While these approaches yield favorable results, real-time field applications requires algorithms specifically designed for the complexities of natural agricultural conditions. Our work proposes a novel deep learning framework for classifying drought stress in potato crops captured by UAVs in natural settings. The novelty lies in the synergistic combination of a pre-trained network with carefully designed custom layers. This architecture leverages feature extraction capabilities of the pre-trained network while the custom layers enable targeted dimensionality reduction and enhanced regularization, ultimately leading to improved performance. A key innovation of our work involves the integration of Gradient-Class Activation Mapping (Grad-CAM), an explainability technique. Grad-CAM sheds light on the internal workings of the deep learning model, typically referred to as a black box. By visualizing the focus areas of the model within the images, Grad-CAM fosters interpretability and builds trust in the decision-making process of the model. Our proposed framework achieves superior performance, particularly with the DenseNet121 pre-trained network, reaching a precision of 97% to identify the stressed class with an overall accuracy of 91%. Comparative analysis of existing state-of-the-art object detection algorithms reveals the superiority of our approach in significantly higher precision and accuracy.
Authors: Samia Shafique, Shu Kong, Charless Fowlkes
Abstract: Shoeprints are a common type of evidence found at crime scenes and are used regularly in forensic investigations. However, existing methods cannot effectively employ deep learning techniques to match noisy and occluded crime-scene shoeprints to a shoe database due to a lack of training data. Moreover, all existing methods match crime-scene shoeprints to clean reference prints, yet our analysis shows matching to more informative tread depth maps yields better retrieval results. The matching task is further complicated by the necessity to identify similarities only in corresponding regions (heels, toes, etc) of prints and shoe treads. To overcome these challenges, we leverage shoe tread images from online retailers and utilize an off-the-shelf predictor to estimate depth maps and clean prints. Our method, named CriSp, matches crime-scene shoeprints to tread depth maps by training on this data. CriSp incorporates data augmentation to simulate crime-scene shoeprints, an encoder to learn spatially-aware features, and a masking module to ensure only visible regions of crime-scene prints affect retrieval results. To validate our approach, we introduce two validation sets by reprocessing existing datasets of crime-scene shoeprints and establish a benchmarking protocol for comparison. On this benchmark, CriSp significantly outperforms state-of-the-art methods in both automated shoeprint matching and image retrieval tailored to this task.
Authors: Lingbo Huang, Yushi Chen, Xin He
Abstract: Recently, deep learning models have achieved excellent performance in hyperspectral image (HSI) classification. Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the long-range dependencies of spatial-spectral features in HSI. However, Transformer has the problem of quadratic computational complexity due to the self-attention mechanism, which is heavier than other models and thus has limited adoption in HSI processing. Fortunately, the recently emerging state space model-based Mamba shows great computational efficiency while achieving the modeling power of Transformers. Therefore, in this paper, we make a preliminary attempt to apply the Mamba to HSI classification, leading to the proposed spectral-spatial Mamba (SS-Mamba). Specifically, the proposed SS-Mamba mainly consists of spectral-spatial token generation module and several stacked spectral-spatial Mamba blocks. Firstly, the token generation module converts any given HSI cube to spatial and spectral tokens as sequences. And then these tokens are sent to stacked spectral-spatial mamba blocks (SS-MB). Each SS-MB block consists of two basic mamba blocks and a spectral-spatial feature enhancement module. The spatial and spectral tokens are processed separately by the two basic mamba blocks, respectively. Besides, the feature enhancement module modulates spatial and spectral tokens using HSI sample's center region information. In this way, the spectral and spatial tokens cooperate with each other and achieve information fusion within each block. The experimental results conducted on widely used HSI datasets reveal that the proposed model achieves competitive results compared with the state-of-the-art methods. The Mamba-based method opens a new window for HSI classification.
Authors: Yihong Sun, Bharath Hariharan
Abstract: Embodied agents must detect and localize objects of interest, e.g. traffic participants for self-driving cars. Supervision in the form of bounding boxes for this task is extremely expensive. As such, prior work has looked at unsupervised instance detection and segmentation, but in the absence of annotated boxes, it is unclear how pixels must be grouped into objects and which objects are of interest. This results in over-/under-segmentation and irrelevant objects. Inspired by human visual system and practical applications, we posit that the key missing cue for unsupervised detection is motion: objects of interest are typically mobile objects that frequently move and their motions can specify separate instances. In this paper, we propose MOD-UV, a Mobile Object Detector learned from Unlabeled Videos only. We begin with instance pseudo-labels derived from motion segmentation, but introduce a novel training paradigm to progressively discover small objects and static-but-mobile objects that are missed by motion segmentation. As a result, though only learned from unlabeled videos, MOD-UV can detect and segment mobile objects from a single static image. Empirically, we achieve state-of-the-art performance in unsupervised mobile object detection on Waymo Open, nuScenes, and KITTI Datasets without using any external data or supervised models. Code is available at https://github.com/YihongSun/MOD-UV.
Authors: Trung Dang, Huy Hoang Nguyen, Aleksei Tiulpin
Abstract: One of the primary challenges in brain tumor segmentation arises from the uncertainty of voxels close to tumor boundaries. However, the conventional process of generating ground truth segmentation masks fails to treat such uncertainties properly. Those "hard labels" with 0s and 1s conceptually influenced the majority of prior studies on brain image segmentation. As a result, tumor segmentation is often solved through voxel classification. In this work, we instead view this problem as a voxel-level regression, where the ground truth represents a certainty mapping from any pixel to the border of the tumor. We propose a novel ground truth label transformation, which is based on a signed geodesic transform, to capture the uncertainty in brain tumors' vicinity. We combine this idea with a Focal-like regression L1-loss that enables effective regression learning in high-dimensional output space by appropriately weighting voxels according to their difficulty. We thoroughly conduct an experimental evaluation to validate the components of our proposed method, compare it to a diverse array of state-of-the-art segmentation models, and show that it is architecture-agnostic. The code of our method is made publicly available (\url{https://github.com/Oulu-IMEDS/SiNGR/}).
Authors: Rishab Parthasarathy, Zachary Ankner, Aaron Gokaslan
Abstract: A recent frontier in computer vision has been the task of 3D video generation, which consists of generating a time-varying 3D representation of a scene. To generate dynamic 3D scenes, current methods explicitly model 3D temporal dynamics by jointly optimizing for consistency across both time and views of the scene. In this paper, we instead investigate whether it is necessary to explicitly enforce multiview consistency over time, as current approaches do, or if it is sufficient for a model to generate 3D representations of each timestep independently. We hence propose a model, Vid3D, that leverages 2D video diffusion to generate 3D videos by first generating a 2D "seed" of the video's temporal dynamics and then independently generating a 3D representation for each timestep in the seed video. We evaluate Vid3D against two state-of-the-art 3D video generation methods and find that Vid3D is achieves comparable results despite not explicitly modeling 3D temporal dynamics. We further ablate how the quality of Vid3D depends on the number of views generated per frame. While we observe some degradation with fewer views, performance degradation remains minor. Our results thus suggest that 3D temporal knowledge may not be necessary to generate high-quality dynamic 3D scenes, potentially enabling simpler generative algorithms for this task.
Authors: Anas Awadalla, Le Xue, Oscar Lo, Manli Shu, Hannah Lee, Etash Kumar Guha, Matt Jordan, Sheng Shen, Mohamed Awadalla, Silvio Savarese, Caiming Xiong, Ran Xu, Yejin Choi, Ludwig Schmidt
Abstract: Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs). Despite the rapid progression of open-source LMMs, there remains a pronounced scarcity of large-scale, diverse open-source multimodal interleaved datasets. In response, we introduce MINT-1T, the most extensive and diverse open-source Multimodal INTerleaved dataset to date. MINT-1T comprises one trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. As scaling multimodal interleaved datasets requires substantial engineering effort, sharing the data curation process and releasing the dataset greatly benefits the community. Our experiments show that LMMs trained on MINT-1T rival the performance of models trained on the previous leading dataset, OBELICS. Our data and code will be released at https://github.com/mlfoundations/MINT-1T.
Authors: William Stevens, Vishal Urs, Karthik Selvaraj, Gabriel Torres, Gaurish Lakhanpal
Abstract: With the increasing prevalence of autonomous vehicles, it is essential for computer vision algorithms to accurately assess road features in real-time. This study explores the LaneSegNet architecture, a new approach to lane topology prediction which integrates topological information with lane-line data to provide a more contextual understanding of road environments. The LaneSegNet architecture includes a feature extractor, lane encoder, lane decoder, and prediction head, leveraging components from ResNet-50, BEVFormer, and various attention mechanisms. We experimented with optimizations to the LaneSegNet architecture through feature extractor modification and transformer encoder-decoder stack modification. We found that modifying the encoder and decoder stacks offered an interesting tradeoff between training time and prediction accuracy, with certain combinations showing promising results. Our implementation, trained on a single NVIDIA Tesla A100 GPU, found that a 2:4 ratio reduced training time by 22.3% with only a 7.1% drop in mean average precision, while a 4:8 ratio increased training time by only 11.1% but improved mean average precision by a significant 23.7%. These results indicate that strategic hyperparameter tuning can yield substantial improvements depending on the resources of the user. This study provides valuable insights for optimizing LaneSegNet according to available computation power, making it more accessible for users with limited resources and increasing the capabilities for users with more powerful resources.
Authors: Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, Bing Qin
Abstract: Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated hallucinations could influence the LVLMs' subsequent generation. Thus, we raise a question: When presented with a query relevant to the previously generated hallucination, will LVLMs be misled and respond incorrectly, even though the ground visual information exists? To answer this, we propose a framework called MMHalSnowball to evaluate LVLMs' behaviors when encountering generated hallucinations, where LVLMs are required to answer specific visual questions within a curated hallucinatory conversation. Crucially, our experiment shows that the performance of open-source LVLMs drops by at least $31\%$, indicating that LVLMs are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions. We term this phenomenon Multimodal Hallucination Snowballing. To mitigate this, we further propose a training-free method called Residual Visual Decoding, where we revise the output distribution of LVLMs with the one derived from the residual visual input, providing models with direct access to the visual information. Experiments show that our method can mitigate more than $24\%$ of the snowballed multimodal hallucination while maintaining capabilities.
Authors: Xianrui Luo, Huiqiang Sun, Juewen Peng, Zhiguo Cao
Abstract: Dynamic Neural Radiance Field (NeRF) from monocular videos has recently been explored for space-time novel view synthesis and achieved excellent results. However, defocus blur caused by depth variation often occurs in video capture, compromising the quality of dynamic reconstruction because the lack of sharp details interferes with modeling temporal consistency between input views. To tackle this issue, we propose D2RF, the first dynamic NeRF method designed to restore sharp novel views from defocused monocular videos. We introduce layered Depth-of-Field (DoF) volume rendering to model the defocus blur and reconstruct a sharp NeRF supervised by defocused views. The blur model is inspired by the connection between DoF rendering and volume rendering. The opacity in volume rendering aligns with the layer visibility in DoF rendering. To execute the blurring, we modify the layered blur kernel to the ray-based kernel and employ an optimized sparse kernel to gather the input rays efficiently and render the optimized rays with our layered DoF volume rendering. We synthesize a dataset with defocused dynamic scenes for our task, and extensive experiments on our dataset show that our method outperforms existing approaches in synthesizing all-in-focus novel views from defocus blur while maintaining spatial-temporal consistency in the scene.
Authors: Byeonghyun Pak, Byeongju Woo, Sunghwan Kim, Dae-hwan Kim, Hoseong Kim
Abstract: In this paper, we introduce a method to tackle Domain Generalized Semantic Segmentation (DGSS) by utilizing domain-invariant semantic knowledge from text embeddings of vision-language models. We employ the text embeddings as object queries within a transformer-based segmentation framework (textual object queries). These queries are regarded as a domain-invariant basis for pixel grouping in DGSS. To leverage the power of textual object queries, we introduce a novel framework named the textual query-driven mask transformer (tqdm). Our tqdm aims to (1) generate textual object queries that maximally encode domain-invariant semantics and (2) enhance the semantic clarity of dense visual features. Additionally, we suggest three regularization losses to improve the efficacy of tqdm by aligning between visual and textual features. By utilizing our method, the model can comprehend inherent semantic information for classes of interest, enabling it to generalize to extreme domains (e.g., sketch style). Our tqdm achieves 68.9 mIoU on GTA5$\rightarrow$Cityscapes, outperforming the prior state-of-the-art method by 2.5 mIoU. The project page is available at https://byeonghyunpak.github.io/tqdm.
Authors: Xiao Liu, Xiaoliu Guan, Yu Wu, Jiaxu Miao
Abstract: Diffusion models, known for their tremendous ability to generate novel and high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy risks. Recent approaches for memory mitigation either only focused on the text modality problem in cross-modal generation tasks or utilized data augmentation strategies. In this paper, we propose a novel training framework for diffusion models from the perspective of visual modality, which is more generic and fundamental for mitigating memorization. To facilitate forgetting of stored information in diffusion model parameters, we propose an iterative ensemble training strategy by splitting the data into multiple shards for training multiple models and intermittently aggregating these model parameters. Moreover, practical analysis of losses illustrates that the training loss for easily memorable images tends to be obviously lower. Thus, we propose an anti-gradient control method to exclude the sample with a lower loss value from the current mini-batch to avoid memorizing. Extensive experiments and analysis on four datasets are conducted to illustrate the effectiveness of our method, and results show that our method successfully reduces memory capacity while even improving the performance slightly. Moreover, to save the computing cost, we successfully apply our method to fine-tune the well-trained diffusion models by limited epochs, demonstrating the applicability of our method. Code is available in https://github.com/liuxiao-guan/IET_AGC.
Authors: Yuyan Chen, Songzhou Yan, Zhihong Zhu, Zhixu Li, Yanghua Xiao
Abstract: Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines. While advances have been made in natural language processing, real-world humor often thrives in a multi-modal context, encapsulated distinctively by memes. This paper poses a particular emphasis on the impact of multi-images on meme captioning. After that, we introduce the \textsc{XMeCap} framework, a novel approach that adopts supervised fine-tuning and reinforcement learning based on an innovative reward model, which factors in both global and local similarities between visuals and text. Our results, benchmarked against contemporary models, manifest a marked improvement in caption generation for both single-image and multi-image memes, as well as different meme categories. \textsc{XMeCap} achieves an average evaluation score of 75.85 for single-image memes and 66.32 for multi-image memes, outperforming the best baseline by 3.71\% and 4.82\%, respectively. This research not only establishes a new frontier in meme-related studies but also underscores the potential of machines in understanding and generating humor in a multi-modal setting.
Authors: Nhat Le, Khoa Do, Xuan Bui, Tuong Do, Erman Tjiputra, Quang D. Tran, Anh Nguyen
Abstract: Generating group dance motion from the music is a challenging task with several industrial applications. Although several methods have been proposed to tackle this problem, most of them prioritize optimizing the fidelity in dancing movement, constrained by predetermined dancer counts in datasets. This limitation impedes adaptability to real-world applications. Our study addresses the scalability problem in group choreography while preserving naturalness and synchronization. In particular, we propose a phase-based variational generative model for group dance generation on learning a generative manifold. Our method achieves high-fidelity group dance motion and enables the generation with an unlimited number of dancers while consuming only a minimal and constant amount of memory. The intensive experiments on two public datasets show that our proposed method outperforms recent state-of-the-art approaches by a large margin and is scalable to a great number of dancers beyond the training data.
Authors: Pascal Spiegler, Amirhossein Rasoulian, Yiming Xiao
Abstract: Intracranial hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis to improve treatment outcomes and patient survival rates. Recent advancements in supervised deep learning have greatly improved the analysis of medical images, but often rely on extensive datasets with high-quality annotations, which are costly, time-consuming, and require medical expertise to prepare. To mitigate the need for large amounts of expert-prepared segmentation data, we have developed a novel weakly supervised ICH segmentation method that utilizes the YOLO object detection model and an uncertainty-rectified Segment Anything Model (SAM). In addition, we have proposed a novel point prompt generator for this model to further improve segmentation results with YOLO-predicted bounding box prompts. Our approach achieved a high accuracy of 0.933 and an AUC of 0.796 in ICH detection, along with a mean Dice score of 0.629 for ICH segmentation, outperforming existing weakly supervised and popular supervised (UNet and Swin-UNETR) approaches. Overall, the proposed method provides a robust and accurate alternative to the more commonly used supervised techniques for ICH quantification without requiring refined segmentation ground truths during model training.
Authors: Chaofan Huo, Ye Shi, Jingya Wang
Abstract: Learning the prior knowledge of the 3D human-object spatial relation is crucial for reconstructing human-object interaction from images and understanding how humans interact with objects in 3D space. Previous works learn this prior from datasets collected in controlled environments, but due to the diversity of domains, they struggle to generalize to real-world scenarios. To overcome this limitation, we present a 2D-supervised method that learns the 3D human-object spatial relation prior purely from 2D images in the wild. Our method utilizes a flow-based neural network to learn the prior distribution of the 2D human-object keypoint layout and viewports for each image in the dataset. The effectiveness of the prior learned from 2D images is demonstrated on the human-object reconstruction task by applying the prior to tune the relative pose between the human and the object during the post-optimization stage. To validate and benchmark our method on in-the-wild images, we collect the WildHOI dataset from the YouTube website, which consists of various interactions with 8 objects in real-world scenarios. We conduct the experiments on the indoor BEHAVE dataset and the outdoor WildHOI dataset. The results show that our method achieves almost comparable performance with fully 3D supervised methods on the BEHAVE dataset, even if we have only utilized the 2D layout information, and outperforms previous methods in terms of generality and interaction diversity on in-the-wild images.
Authors: Changli Wu, Yihang Liu, Jiayi Ji, Yiwei Ma, Haowei Wang, Gen Luo, Henghui Ding, Xiaoshuai Sun, Rongrong Ji
Abstract: 3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-object segmentation tasks into simpler, individual segmentations. MDIN comprises two fundamental components: Text-driven Sparse Queries (TSQ) and Multi-object Decoupling Optimization (MDO). TSQ generates sparse point cloud features distributed over key targets as the initialization for queries. Meanwhile, MDO is tasked with assigning each target in multi-object scenarios to different queries while maintaining their semantic consistency. To adapt to this new task, we build a new dataset, namely Multi3DRes. Our comprehensive evaluations on this dataset demonstrate substantial enhancements over existing models, thus charting a new path for intricate multi-object 3D scene comprehension. The benchmark and code are available at https://github.com/sosppxo/MDIN.
Authors: Tina Dorosti, Manuel Schultheiss, Philipp Schmette, Jule Heuchert, Johannes Thalhammer, Florian Schaff, Thorsten Sellerer, Rafael Schick, Kirsten Taphorn, Korbinian Mechlem, Lorenz Birnbacher, Franz Pfeiffer, Daniela Pfeiffer
Abstract: Purpose: We aimed to estimate the total lung volume (TLV) from real and synthetic frontal X-ray radiographs on a pixel level using lung thickness maps generated by a U-Net. Methods: 5,959 thorax X-ray computed tomography (CT) scans were retrieved from two publicly available datasets of the lung nodule analysis 2016 (n=656) and the RSNA pulmonary embolism detection challenge 2020 (n=5,303). Additionally, thorax CT scans from 72 subjects (33 healthy: 20 men, mean age [range] = 62.4 [34, 80]; 39 suffering from chronic obstructive pulmonary disease: 25 men, mean age [range] = 69.0 [47, 91]) were retrospectively selected (10.2018-12.2019) from our in-house dataset such that for each subject, a frontal chest X-ray radiograph no older than seven days was available. All CT scans and their corresponding lung segmentation were forward projected using a simulated X-ray spectrum to generate synthetic radiographs and lung thickness maps, respectively. A U-Net model was trained and tested on synthetic radiographs from the public datasets to predict lung thickness maps and consequently estimate TLV. Model performance was further assessed by evaluating the TLV estimations for the in-house synthetic and real radiograph pairs using Pearson correlation coefficient (r) and significance testing. Results: Strong correlations were measured between the predicted and CT-derived ground truth TLV values for test data from synthetic ($n_{Public}$=1,191, r=0.987, P < 0.001; $n_{In-house}$=72, r=0.973, P < 0.001) and real radiographs (n=72, r=0.908, P < 0.001). Conclusion: TLV from U-Net-generated pixel-level lung thickness maps were successfully estimated for synthetic and real radiographs.
Authors: Ying Yuan, Haichuan Che, Yuzhe Qin, Binghao Huang, Zhao-Heng Yin, Kang-Won Lee, Yi Wu, Soo-Chul Lim, Xiaolong Wang
Abstract: Executing contact-rich manipulation tasks necessitates the fusion of tactile and visual feedback. However, the distinct nature of these modalities poses significant challenges. In this paper, we introduce a system that leverages visual and tactile sensory inputs to enable dexterous in-hand manipulation. Specifically, we propose Robot Synesthesia, a novel point cloud-based tactile representation inspired by human tactile-visual synesthesia. This approach allows for the simultaneous and seamless integration of both sensory inputs, offering richer spatial information and facilitating better reasoning about robot actions. The method, trained in a simulated environment and then deployed to a real robot, is applicable to various in-hand object rotation tasks. Comprehensive ablations are performed on how the integration of vision and touch can improve reinforcement learning and Sim2Real performance. Our project page is available at https://yingyuan0414.github.io/visuotactile/ .
Authors: Chunlin Li, Hanrui Fan, Xiaorui Huang, Ruofan Liang, Sankeerth Durvasula, Nandita Vijaykumar
Abstract: We present a framework, DISORF, to enable online 3D reconstruction and visualization of scenes captured by resource-constrained mobile robots and edge devices. To address the limited computing capabilities of edge devices and potentially limited network availability, we design a framework that efficiently distributes computation between the edge device and the remote server. We leverage on-device SLAM systems to generate posed keyframes and transmit them to remote servers that can perform high-quality 3D reconstruction and visualization at runtime by leveraging recent advances in neural 3D methods. We identify a key challenge with online training where naive image sampling strategies can lead to significant degradation in rendering quality. We propose a novel shifted exponential frame sampling method that addresses this challenge for online training. We demonstrate the effectiveness of our framework in enabling high-quality real-time reconstruction and visualization of unknown scenes as they are captured and streamed from cameras in mobile robots and edge devices.
Authors: Shoujin Huang, Guanxiong Luo, Xi Wang, Ziran Chen, Yuwan Wang, Huaishui Yang, Pheng-Ann Heng, Lingyan Zhang, Mengye Lyu
Abstract: In general, diffusion model-based MRI reconstruction methods incrementally remove artificially added noise while imposing data consistency to reconstruct the underlying images. However, real-world MRI acquisitions already contain inherent noise due to thermal fluctuations. This phenomenon is particularly notable when using ultra-fast, high-resolution imaging sequences for advanced research, or using low-field systems favored by low- and middle-income countries. These common scenarios can lead to sub-optimal performance or complete failure of existing diffusion model-based reconstruction techniques. Specifically, as the artificially added noise is gradually removed, the inherent MRI noise becomes increasingly pronounced, making the actual noise level inconsistent with the predefined denoising schedule and consequently inaccurate image reconstruction. To tackle this problem, we propose a posterior sampling strategy with a novel NoIse Level Adaptive Data Consistency (Nila-DC) operation. Extensive experiments are conducted on two public datasets and an in-house clinical dataset with field strength ranging from 0.3T to 3T, showing that our method surpasses the state-of-the-art MRI reconstruction methods, and is highly robust against various noise levels. The code for Nila is available at https://github.com/Solor-pikachu/Nila.
Authors: Deepa Krishnaswamy, B\'alint Kov\'acs, Stefan Denner, Steve Pieper, David Clunie, Christopher P. Bridge, Tina Kapur, Klaus H. Maier-Hein, Andrey Fedorov
Abstract: With the wealth of medical image data, efficient curation is essential. Assigning the sequence type to magnetic resonance images is necessary for scientific studies and artificial intelligence-based analysis. However, incomplete or missing metadata prevents effective automation. We therefore propose a deep-learning method for classification of prostate cancer scanning sequences based on a combination of image data and DICOM metadata. We demonstrate superior results compared to metadata or image data alone, and make our code publicly available at https://github.com/deepakri201/DICOMScanClassification.
URLs: https://github.com/deepakri201/DICOMScanClassification.
Authors: Lixing Tan, Shuang Song, Kangneng Zhou, Chengbo Duan, Lanying Wang, Huayang Ren, Linlin Liu, Wei Zhang, Ruoxiu Xiao
Abstract: X-ray images play a vital role in the intraoperative processes due to their high resolution and fast imaging speed and greatly promote the subsequent segmentation, registration and reconstruction. However, over-dosed X-rays superimpose potential risks to human health to some extent. Data-driven algorithms from volume scans to X-ray images are restricted by the scarcity of paired X-ray and volume data. Existing methods are mainly realized by modelling the whole X-ray imaging procedure. In this study, we propose a learning-based approach termed CT2X-GAN to synthesize the X-ray images in an end-to-end manner using the content and style disentanglement from three different image domains. Our method decouples the anatomical structure information from CT scans and style information from unpaired real X-ray images/ digital reconstructed radiography (DRR) images via a series of decoupling encoders. Additionally, we introduce a novel consistency regularization term to improve the stylistic resemblance between synthesized X-ray images and real X-ray images. Meanwhile, we also impose a supervised process by computing the similarity of computed real DRR and synthesized DRR images. We further develop a pose attention module to fully strengthen the comprehensive information in the decoupled content code from CT scans, facilitating high-quality multi-view image synthesis in the lower 2D space. Extensive experiments were conducted on the publicly available CTSpine1K dataset and achieved 97.8350, 0.0842 and 3.0938 in terms of FID, KID and defined user-scored X-ray similarity, respectively. In comparison with 3D-aware methods ($\pi$-GAN, EG3D), CT2X-GAN is superior in improving the synthesis quality and realistic to the real X-ray images.
Authors: Markus Grotz, Mohit Shridhar, Tamim Asfour, Dieter Fox
Abstract: Bimanual manipulation is challenging due to precise spatial and temporal coordination required between two arms. While there exist several real-world bimanual systems, there is a lack of simulated benchmarks with a large task diversity for systematically studying bimanual capabilities across a wide range of tabletop tasks. This paper addresses the gap by extending RLBench to bimanual manipulation. We open-source our code and benchmark comprising 13 new tasks with 23 unique task variations, each requiring a high degree of coordination and adaptability. To kickstart the benchmark, we extended several state-of-the art methods to bimanual manipulation and also present a language-conditioned behavioral cloning agent -- PerAct2, which enables the learning and execution of bimanual 6-DoF manipulation tasks. Our novel network architecture efficiently integrates language processing with action prediction, allowing robots to understand and perform complex bimanual tasks in response to user-specified goals. Project website with code is available at: http://bimanual.github.io
Authors: Qi Zhang, Zhihao Lin, Arnoud Visser
Abstract: The ICRA conference is celebrating its $40^{th}$ anniversary in Rotterdam in September 2024, with as highlight the Happy Birthday ICRA Party at the iconic Holland America Line Cruise Terminal. One month later the IROS conference will take place, which will include the Earth Rover Challenge. In this challenge open-world autonomous navigation models are studied truly open-world settings. As part of the Earth Rover Challenge several real-world navigation sets in several cities world-wide, like Auckland, Australia and Wuhan, China. The only dataset recorded in the Netherlands is the small village Oudewater. The proposal is to record a dataset with the robot used in the Earth Rover Challenge in Rotterdam, in front of the Holland America Line Cruise Terminal, before the festivities of the Happy Birthday ICRA Party start. See: https://github.com/SlamMate/vSLAM-on-FrodoBots-2K
Authors: Zhiwen Yang, Hui Zhang, Dan Zhao, Bingzheng Wei, Yan Xu
Abstract: Transformers have revolutionized medical image restoration, but the quadratic complexity still poses limitations for their application to high-resolution medical images. The recent advent of RWKV in the NLP field has attracted much attention as it can process long sequences efficiently. To leverage its advanced design, we propose Restore-RWKV, the first RWKV-based model for medical image restoration. Since the original RWKV model is designed for 1D sequences, we make two necessary modifications for modeling spatial relations in 2D images. First, we present a recurrent WKV (Re-WKV) attention mechanism that captures global dependencies with linear computational complexity. Re-WKV incorporates bidirectional attention as basic for a global receptive field and recurrent attention to effectively model 2D dependencies from various scan directions. Second, we develop an omnidirectional token shift (Omni-Shift) layer that enhances local dependencies by shifting tokens from all directions and across a wide context range. These adaptations make the proposed Restore-RWKV an efficient and effective model for medical image restoration. Extensive experiments demonstrate that Restore-RWKV achieves superior performance across various medical image restoration tasks, including MRI image super-resolution, CT image denoising, PET image synthesis, and all-in-one medical image restoration. Code is available at: \href{https://github.com/Yaziwel/Restore-RWKV.git}{https://github.com/Yaziwel/Restore-RWKV}.
URLs: https://github.com/Yaziwel/Restore-RWKV.git, https://github.com/Yaziwel/Restore-RWKV
Authors: Luca Tirel, Ali Mohamed Ali, Hashim A. Hashim
Abstract: This paper introduces a novel approach to image denoising that leverages the advantages of Generative Adversarial Networks (GANs). Specifically, we propose a model that combines elements of the Pix2Pix model and the Wasserstein GAN (WGAN) with Gradient Penalty (WGAN-GP). This hybrid framework seeks to capitalize on the denoising capabilities of conditional GANs, as demonstrated in the Pix2Pix model, while mitigating the need for an exhaustive search for optimal hyperparameters that could potentially ruin the stability of the learning process. In the proposed method, the GAN's generator is employed to produce denoised images, harnessing the power of a conditional GAN for noise reduction. Simultaneously, the implementation of the Lipschitz continuity constraint during updates, as featured in WGAN-GP, aids in reducing susceptibility to mode collapse. This innovative design allows the proposed model to benefit from the strong points of both Pix2Pix and WGAN-GP, generating superior denoising results while ensuring training stability. Drawing on previous work on image-to-image translation and GAN stabilization techniques, the proposed research highlights the potential of GANs as a general-purpose solution for denoising. The paper details the development and testing of this model, showcasing its effectiveness through numerical experiments. The dataset was created by adding synthetic noise to clean images. Numerical results based on real-world dataset validation underscore the efficacy of this approach in image-denoising tasks, exhibiting significant enhancements over traditional techniques. Notably, the proposed model demonstrates strong generalization capabilities, performing effectively even when trained with synthetic noise.
Authors: Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang
Abstract: Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution. Knowledge utilization delves into the mechanism of memorization, comprehension and application, and creation. Knowledge evolution focuses on the dynamic progression of knowledge within individual and group LLMs. Moreover, we discuss what knowledge LLMs have learned, the reasons for the fragility of parametric knowledge, and the potential dark knowledge (hypothesis) that will be challenging to address. We hope this work can help understand knowledge in LLMs and provide insights for future research.
Authors: Ammar Ahmed, Abdul Manaf
Abstract: Wrist fractures are highly prevalent among children and can significantly impact their daily activities, such as attending school, participating in sports, and performing basic self-care tasks. If not treated properly, these fractures can result in chronic pain, reduced wrist functionality, and other long-term complications. Recently, advancements in object detection have shown promise in enhancing fracture detection, with systems achieving accuracy comparable to, or even surpassing, that of human radiologists. The YOLO series, in particular, has demonstrated notable success in this domain. This study is the first to provide a thorough evaluation of various YOLOv10 variants to assess their performance in detecting pediatric wrist fractures using the GRAZPEDWRI-DX dataset. It investigates how changes in model complexity, scaling the architecture, and implementing a dual-label assignment strategy can enhance detection performance. Experimental results indicate that our trained model achieved mean average precision (mAP@50-95) of 51.9\% surpassing the current YOLOv9 benchmark of 43.3\% on this dataset. This represents an improvement of 8.6\%. The implementation code is publicly available at https://github.com/ammarlodhi255/YOLOv10-Fracture-Detection
URLs: https://github.com/ammarlodhi255/YOLOv10-Fracture-Detection
Authors: Jian Wang, Razieh Faghihpirayesh, Polina Golland, Ali Gholipour
Abstract: In this paper, we introduce SpaER, a pioneering method for fetal motion tracking that leverages equivariant filters and self-attention mechanisms to effectively learn spatio-temporal representations. Different from conventional approaches that statically estimate fetal brain motions from pairs of images, our method dynamically tracks the rigid movement patterns of the fetal head across temporal and spatial dimensions. Specifically, we first develop an equivariant neural network that efficiently learns rigid motion sequences through low-dimensional spatial representations of images. Subsequently, we learn spatio-temporal representations by incorporating time encoding and self-attention neural network layers. This approach allows for the capture of long-term dependencies of fetal brain motion and addresses alignment errors due to contrast changes and severe motion artifacts. Our model also provides a geometric deformation estimation that properly addresses image distortions among all time frames. To the best of our knowledge, our approach is the first to learn spatial-temporal representations via deep neural networks for fetal motion tracking without data augmentation. We validated our model using real fetal echo-planar images with simulated and real motions. Our method carries significant potential value in accurately measuring, tracking, and correcting fetal motion in fetal MRI sequences.