检索结果-内蒙古大学图书馆

High throughput event filtering: The interpolation-based DIF algorithm hardware architecture

学校读者我要写书评

暂无评论

Microprocessors and Microsystems 2025年

作者： Marcin Kowalczyk Tomasz Kryjak Embedded Vision Systems Group Department of Automatic Control and Robotics Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Krakow Poland

In recent years, there has been rapid development in the field of event vision. It manifests itself both on the technical side, as better and better event sensors are available, and on the algorithmic side, as more and more applications of this technology are proposed and scientific papers are published. However, the data stream from these sensors typically contains a significant amount of noise, which varies depending on factors such as the degree of illumination in the observed scene or the temperature of the sensor. We propose a hardware architecture of the Distance-based Interpolation with Frequency Weights(DIF) filter and implement it on an FPGA chip. To evaluate the algorithm and compare it with other solutions, we have prepared a new high-resolution event dataset, which we are also releasing to the community. Our architecture achieved a throughput of 403.39 million events per second (MEPS) for a sensor resolution of 1280 × 720 and 428.45 MEPS for a resolution of 640 × 480. The averagevalues of the Area Under the Receiver Operating Characteristic (AUROC) index ranged from 0.844 to 0.999, depending on the dataset, which is comparable to the state-of-the-art filtering solutions, but with much higher throughput and better operation over a wide range of noise levels.

关键词： Dataset Denoising DVS FPGA High-throughput

Few-Shot Medical Image Segmentation with High-Fidelity Prototypes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Song Yan, Shaxu Qi, Xiaozhi Gao, Jianxin Ye, Mao Zhang, Jianwei Zhu, Xiatian IMI Group School of Health Sciences and Engineering University of Shanghai for Science and Technology Shanghai China TAMS Group Department of Informatics Universität Hamburg Hamburg Germany School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Surrey Institute for People-Centred Artificial Intelligence Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are limited to the imaging scenarios with considerably distinct objects and not highly complex background, e.g., natural images. This makes such models suboptimal for medical imaging with both conditions invalid. To address this problem, we propose a novel Detail Self-refined Prototype Network (DSPNet) to constructing high-fidelity prototypes representing the object foreground and the background more comprehensively. Specifically, to construct global semantics while maintaining the captured detail semantics, we learn the foreground prototypes by modelling the multi-modal structures with clustering and then fusing each in a channel-wise manner. Considering that the background often has no apparent semantic relation in the spatial dimensions, we integrate channel-specific structural information under sparse channel-aware regulation. Extensive experiments on three challenging medical image benchmarks show the superiority of DSPNet over previous state-of-the-art methods. The code and data are available at https://***/tntek/DSPNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Baumann, Alexander Ayala, Leonardo Seidlitz, Silvia Sellner, Jan Studier-Fischer, Alexander Özdemir, Berkin Maier-Hein, Lena Ilic, Slobodan Siemens AG Munich Germany Heidelberg Germany Medical Faculty Faculty of Mathematics and Computer Science Heidelberg University Germany NCT Heidelberg Germany HIDSS4Health Heidelberg Germany Department of Urology and Urosurgery University Medical Center Mannheim Germany Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Germany Division of Intelligent Systems and Robotics in Urology DKFZ Heidelberg Germany DKFZ Hector Cancer Institute University Medical Center Mannheim Germany

Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding, and is already established as a critical modality in remote sensing. However, variability in channel dimensionality and captured wavelengths among spectral cameras impede the development of AI-driven methodologies, leading to camera-specific models with limited generalizability and inadequate cross-camera applicability. To address this bottleneck, we introduce CARL, a model for Camera-Agnostic Representation Learning across RGB, multispectral, and hyperspectral imaging modalities. To enable the conversion of a spectral image with any channel dimensionality to a camera-agnostic embedding, we introduce wavelength positional encoding and a self-attention-cross-attention mechanism to compress spectral information into learned query representations. Spectral-spatial pre-training is achieved with a novel spectral self-supervised JEPA-inspired strategy tailored to CARL. Large-scale experiments across the domains of medical imaging, autonomous driving, and satellite imaging demonstrate our model’s unique robustness to spectral heterogeneity, outperforming on datasets with simulated and real-world cross-camera spectral variations. The scalability and versatility of the proposed approach position our model as a backbone for future spectral foundation models. © 2025, CC BY.

关键词： Image coding

Extracting Semantic Knowledge from GANs with Unsupervised Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Jianjin Zhang, Zhaoxiang Hu, Xiaolin The School of Mathematics and Computer Science Panzhihua University The Department of Computer Science and Technology Tsinghua University China The Insitute of Automation Chinese Academy of Sciences The Centre for Artificial Intelligence and Robotics Hong Kong Innovation and Science Insitute Chinese Academy of Sciences Hong Kong The Department of Computer Science and Technology Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems THU-Bosch JCML Center THBI IDG/McGovern Institute for Brain Research BNRist Tsinghua University Beijing China Beijing China

Recently, unsupervised learning has made impressive progress on various tasks. Despite the dominance of discriminative models, increasing attention is drawn to representations learned by generative models and in particular, Generative Adversarial Networks (GANs). Previous works on the interpretation of GANs reveal that GANs encode semantics in feature maps in a linearly separable form. In this work, we further find that GAN’s features can be well clustered with the linear separability assumption. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN’s features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects, e.g., car, portrait, animals, and so on. With KLiSH, we can sample images from GANs along with their segmentation masks and synthesize paired image-segmentation datasets. Using the synthesized datasets, we enable two downstream applications. First, we train semantic segmentation networks on these datasets and test them on real images, realizing unsupervised semantic segmentation. Second, we train image-to-image translation networks on the synthesized datasets, enabling semantic-conditional image synthesis without human annotations. © 2022, CC BY-SA.

关键词： Unsupervised learning

NTIRE 2023 Image Shadow Removal Challenge Report

学校读者我要写书评

暂无评论

NTIRE 2023 Image Shadow Removal Challenge Report

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Vasluianu, Florin-Alexandru Seizinger, Tim Timofte, Radu Cui, Shuhao Huang, Junshi Tian, Shuman Fan, Mingyuan Zhang, Jiaqi Zhu, Li Wei, Xiaoming Wei, Xiaolin Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Dong, Xiaoyi Zhang, Xi Sheryl Li, Chenghua Leng, Cong Yeo, Woon-Ha Oh, Wang-Taek Lee, Yeo-Reum Ryu, Han-Cheol Luo, Jinting Jiang, Chengzhi Han, Mingyan Wu, Qi Lin, Wenjie Yu, Lei Li, Xinpeng Jiang, Ting Fan, Haoqiang Liu, Shuaicheng Xu, Shuning Song, Binbin Chen, Xiangyu Zhang, Shile Zhou, Jiantao Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Wang, Bo Ren, Jiahuan Luo, Yan Kondo, Yuki Miyata, Riku Yasue, Fuma Naruki, Taito Ukita, Norimichi Chang, Hua-En Yang, Hao-Hsiang Chen, Yi-Chung Chiang, Yuan-Chun Huang, Zhi-Kai Chen, Wei-Ting Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Xianwei, Li Fu, Huiyuan Liu, Chunlin Ma, Huadong Fu, Binglan He, Huiming Wang, Mengjia She, Wenxuan Liu, Yu Nathan, Sabari Kansal, Priya Zhang, Zhongjian Yang, Huabin Wang, Yan Zhang, Yanru Phutke, Shruti S. Kulkarni, Ashutosh Khan, Md Raqib Murala, Subrahmanyam Vipparthi, Santosh Kumar Ye, Heng Liu, Zixi Yang, Xingyi Liu, Songhua Wu, Yinwei Jing, Yongcheng Yu, Qianhao Zheng, Naishan Huang, Jie Long, Yuhang Yao, Mingde Zhao, Feng Zhao, Bowen Ye, Nan Shen, Ning Cao, Yanpeng Xiong, Tong Xia, Weiran Li, Dingwen Xia, Shuchen Computer Vision Lab Ifi Caidas University of Würzburg Germany Computer Vision Lab Eth Zürich Switzerland Meituan Group China Department of Information Technology Uppsala University Sweden Institute of Automation Chinese Academy of Sciences Beijing China Nanjing China Maicro Nanjing China Department of Artificial Intelligence Convergence Sahmyook University Seoul Korea Republic of Megvii Technology China University of Electronic Science and Technology of China China University of Macau China China Toyota Technological Institute Japan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Beijing University of Post and Teleconmunication Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education China Couger Inc. Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Punjab Rupnagar India Research Institute Singapore National University of Singapore Singapore Research Institute Singapore University of Sydney Australia Brain-Inspired Vision Laboratory Information Science and Technology Institution University of Science and Technology of China China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China South China University of Technology China

ISBN: (纸本)9798350302493

This work reviews the results of the NTIRE 2023 Challenge on Image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs of real shadow free and shadow affected images, captured in a controlled environment. The data was captured in a white-box setup, using professional equipment for lights and data acquisition sensors. The challenge had a number of 144 participants registered, out of which 19 teams were compared in the final ranking. The proposed solutions extend the work on shadow removal, improving over the performance level describing state-of-the-art methods. © 2023 IEEE.

关键词： Data acquisition

Calibrated and partially calibrated semi-generalized homographies

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bhayani, Snehal Sattler, Torsten Barath, Daniel Beliansky, Patrik Heikkilä, Janne Kukelova, Zuzana Center for Machine Vision and Signal Analysis University of Oulu Finland Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Computer Vision and Geometry Group Department of Computer Science ETH Zürich Faculty of Mathematics and Physics Charles University Prague Czech Republic Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague

In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera. The proposed solvers use five 2D-2D image point correspondences induced by a scene plane. One group of solvers assumes the perspective camera to be fully calibrated, while the other estimates the unknown focal length together with the absolute pose parameters. This setup is particularly important in structurefrom-motion and visual localization pipelines, where a new camera is localized in each step with respect to a set of known cameras and 2D-3D correspondences might not be available. Thanks to a clever parametrization and the elimination ideal method, our solvers only need to solve a univariate polynomial of degree five or three, respectively a system of polynomial equations in two variables. All proposed solvers are stable and efficient as demonstrated by a number of synthetic and real-world experiments. Copyright © 2021, The Authors. All rights reserved.

关键词： Cameras

ARMCHAIR: integrated inverse reinforcement learning and model predictive control for human-robot collaboration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Caregnato-Neto, Angelo Siebert, Luciano Cavalcante Zgonnikov, Arkady de Albuquerque Maximo, Marcos Ricardo Omena Afonso, Rubens Junqueira Magalhães Electronic Engineering Division Instituto Tecnológico de Aeronáutica São José dos Campos São Paulo Brazil Computer Science Division Instituto Tecnológico de Aeronáutica São José dos Campos São Paulo Brazil Intelligent Systems Department Interactive Intelligence Group Delft University of Technology Delft Netherlands Department of Cognitive Robotics Delft University of Technology Delft Netherlands

One of the key issues in human-robot collaboration is the development of computational models that allow robots to predict and adapt to human behavior. Much progress has been achieved in developing such models, as well as control techniques that address the autonomy problems of motion planning and decision-making in robotics. However, the integration of computational models of human behavior with such control techniques still poses a major challenge, resulting in a bottleneck for efficient collaborative human-robot teams. In this context, we present a novel architecture for human-robot collaboration: Adaptive Robot Motion for Collaboration with Humans using Adversarial Inverse Reinforcement learning (ARMCHAIR). Our solution leverages adversarial inverse reinforcement learning and model predictive control to compute optimal trajectories and decisions for a mobile multi-robot system that collaborates with a human in an exploration task. During the mission, ARMCHAIR operates without human intervention, autonomously identifying the necessity to support and acting accordingly. Our approach also explicitly addresses the network connectivity requirement of the human-robot team. Extensive simulation-based evaluations demonstrate that ARMCHAIR allows a group of robots to safely support a simulated human in an exploration scenario, preventing collisions and network disconnections, and improving the overall performance of the task. © 2024, CC BY-SA.

关键词： Model predictive control

Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Song, Siyang Shao, Zilong Jaiswal, Shashank Shen, Linlin Valstar, Michel Gunes, Hatice Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Computer Vision Institute Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Computer Vision Lab University of Nottingham Nottingham United Kingdom

This paper proposes to recognise the true (self-reported) personality from the learned simulation of the target subject’s cognition. This approach builds on two following findings in cognitive science: (i) human cognition partially determines expressed behaviour and is directly linked to true personality traits;and (ii) in dyadic interactions individuals’ nonverbal behaviours are influenced by their conversational partner’s behaviours. In this context, we hypothesise that during a dyadic interaction, a target subject’s facial reactions are driven by two main factors, i.e. their internal (person-specific) cognitive process, and the externalised nonverbal behaviours of their conversational partner. Consequently, we propose to represent the target subject’s (defined as the listener) person-specific cognition in the form of a person-specific CNN architecture that has unique architectural parameters and depth, which takes audio-visual non-verbal cues displayed by the conversational partner (defined as the speaker) as input, and is able to reproduce the target subject’s facial reactions. Each person-specific CNN is explored by the Neural Architecture Search (NAS) and a novel adaptive loss function, which is then represented as a graph representation for recognising the target subject’s true personality. Experimental results not only show that the produced graph representations are well associated with target subjects’ personality traits in both human-human and human-machine interaction scenarios, and outperform the existing approaches with significant advantages, but also demonstrate that the proposed novel strategies such as adaptive loss, and the end-to-end vertices/edges feature learning, help the proposed approach in learning more reliable personality representations. Building on our earlier version of this work, this paper further proposes: (i) assigning a unique depth for each CNN;(ii) a novel end-to-end graph vertex feature learning strategy;(iii) a transformer-bas

关键词： Cognitive systems

No One Left Behind: Real-World Federated Class-Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dong, Jiahua Li, Hongliu Cong, Yang Sun, Gan Zhang, Yulun Van Gool, Luc The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China The University of Chinese Academy of Sciences Beijing100049 China The Department of Civil and Environmental Engineering Hong Kong Polytechnic University Hong Kong The College of Automation Science and Engineering South China University of Technology Guangzhou510640 China The Computer Vision Lab ETH Zürich Zürich8092 Switzerland

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://***/JiahuaDong/LGA. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation