检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

Image quality assessment for perceptual image restoration: A new dataset, benchmark and metric

arXiv

引用

arXiv 2020年

作者： Gu, Jinjin Cai, Haoming Chen, Haoyu Ye, Xiaoxing Ren, Jimmy S. Dong, Chao School of Electrical and Information Engineering University of Sydney Australia Chinese University of Hong Kong Shenzhen Hong Kong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent perceptual IR algorithms based on generative adversarial networks (GANs) have brought in significant improvement on visual performance, but also pose great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. We present two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) With the focus on beating current benchmarks, are we getting better IR algorithms? To answer the questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing ALgorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based IR algorithms, which are missing in previous datasets. We collect more than 1.13 million human judgements to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we shed light on how to improve the IQA performance on GAN-based distortion. Inspired by the find that the existing IQA methods have an unsatisfactory performance on the GAN-based distortion partially because of their low tolerance to spatial misalignment, we propose to improve the performance of an IQA network on GAN-based distortion by explicitly considering this misalignment. We propose the Space Warping Difference Network, which includes the novel l2 pooling layers and Space Warping Difference layers. Experiments demonstrate the effectiveness of the proposed method. © 2020, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild

arXiv

引用

arXiv 2023年

作者： Sun, Lei Gehrig, Daniel Sakaridis, Christos Gehrig, Mathias Liang, Jingyun Sun, Peng Xu, Zhijie Wang, Kaiwei Van Gool, Luc Scaramuzza, Davide National Research Center for Optical Instrumentation Zhejiang University Hangzhou310027 China Robotics and Perception Group University of Zurich Zurich8050 Switzerland Computer Vision Lab ETH Zurich Zurich8092 Switzerland Centre for Visual and Immersive Computing Huddersfield University HD1 3DH United Kingdom INSAIT Sofia University "St. Kliment Ohridski" Bulgaria

Effective video frame interpolation hinges on the adept handling of motion in the input scene. Prior work acknowledges asynchronous event information for this, but often overlooks whether motion induces blur in the video, limiting its scope to sharp frame interpolation. We instead propose a unified framework for event-based frame interpolation that performs deblurring ad-hoc and thus works both on sharp and blurry input videos. Our model consists in a bidirectional recurrent network that incorporates the temporal dimension of interpolation and fuses information from the input frames and the events adaptively based on their temporal proximity. To enhance the generalization from synthetic data to real event cameras, we integrate self-supervised framework with the proposed model to enhance the generalization on real-world datasets in the wild. At the dataset level, we introduce a novel real-world high-resolution dataset with events and color videos named HighREV, which provides a challenging evaluation setting for the examined task. Extensive experiments show that our network consistently outperforms previous state-of-the-art methods on frame interpolation, single image deblurring, and the joint task of both. Experiments on domain transfer reveal that self-supervised training effectively mitigates the performance degradation observed when transitioning from synthetic data to real-world data. Code and datasets are available at https://***/AHupuJR/REFID. Copyright © 2023, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report

NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report

引用

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

作者： Ancuti, Codruta O. Ancuti, Cosmin Vasluianu, Florin-Alexandru Timofte, Radu Zhou, Han Dong, Wei Liu, Yangyi Chen, Jun Liu, Huan Li, Liangyan Wu, Zijun Dong, Yubo Li, Yuyan Qiu, Tian He, Yu Lu, Yonghong Wu, Yinwei Jiang, Zhenxiang Liu, Songhua Yang, Xingyi Jing, Yongcheng Benjdira, Bilel Ali, Anas M. Koubaa, Anis Yang, Hao-Hsiang Chen, I-Hsiang Chen, Wei-Ting Huang, Zhi-Kai Chen, Yi-Chung Hsieh, Chia-Hsuan Chang, Hua-En Chiang, Yuan-Chun Kuo, Sy-Yen Guo, Yu Gao, Yuan Liu, Ryan Wen Lu, Yuxu Qu, Jingxiang He, Shengfeng Ren, Wenqi Hoang, Trung Zhang, Haichuan Yazdani, Amirsaeed Monga, Vishal Yang, Lehan Wu, Alex Jiahao Mai, Tiancheng Cong, Xiaofeng Yin, Xuemeng Yin, Xuefei Emad, Hazim Abdallah, Ahmed Yasser, Yahya Elshahat, Dalia Elbaz, Esraa Li, Zhan Kuang, Wenqing Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Zhang, Zhao Wei, Yanyan Wang, Junhu Zhao, Suiyi Zheng, Huan Guo, Jin Sun, Yangfan Liu, Tianli Hao, Dejun Jiang, Kui Sarvaiya, Anjali Prajapati, Kalpesh Patra, Ratnadeep Barik, Pragnesh Rathod, Chaitanya Upla, Kishor Raja, Kiran Ramachandra, Raghavendra Busch, Christoph ETcTI Universitatea Politehnica Timisoara Romania ICTEAM UCL Belgium Computer Vision Lab University of Wuerzburg Germany Computer Vision Lab ETH Zurich Switzerland Department of Electrical and Computer Engineering McMaster University Canada Department of Electrical and Computer Engineering University of Alberta Canada McMaster University Canada Xidian University China Research Institute Singapore National University of Singapore Singapore University of Sydney Australia Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh12435 Saudi Arabia Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Wuhan University of Technology China Singapore Management University Singapore Singapore Sun Yat-sen University China Electrical Engineering Department Pennsylvania State University United States The University of Sydney Australia Southeast University China University of California Los Angeles United States Beijing Jiaotong University China Mansoura Univeristy Egypt College of Information Science and Technology Jinan University China Department of Information Technology Uppsala University Sweden Hefei University of Technology China Zhejiang Dahua Technology China Sardar Vallabhbhai National Institute of Technology India Norwegian University of Science and Technology Norway

ISBN: (纸本)9798350302493

This study assesses the outcomes of the NTIRE 2023 Challenge on Non-Homogeneous Dehazing, wherein novel techniques were proposed and evaluated on new image dataset called HD-NH-HAZE. The HD-NH-HAZE dataset contains 50 high resolution pairs of real-life outdoor images featuring nonhomogeneous hazy images and corresponding haze-free images of the same scene. The nonhomogeneous haze was simulated using a professional setup that replicated real-world conditions of hazy scenarios. The competition had 246 participants and 17 teams submitted solutions for the final testing phase. The proposed solutions demonstrated the cutting-edge in image dehazing technology. © 2023 IEEE.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Platform-portable reinforcement learning methods to localize underwater targets

Platform-portable reinforcement learning methods to localize...

引用

OCEANS

作者： Ivan Masmitja Mario Martin Tom O’Reilly Narcis Palomeras Kakani Katija Joan Navarro Institut de Ciències del Mar (ICM) CSIC Barcelona Spain KEMLG Research Group Universitat Politècnica de Catalunya Barcelona Tech. Barcelona Spain Monterey Bay Aquarium Research Institute Moss Landing USA Computer Vision and Robotics Institute Universitat de Girona Girona Spain Bioinspiration Lab Monterey Bay Aquarium Research Institute Moss Landing USA

Subsea residential autonomous systems will reduce the cost and CO 2 footprint of future subsea operations. This concept includes subsea docking stations (SDS) and Autonomous Underwater Vehicles (AUVs). To ensure the AUVs are capable of interfacing with the SDS, a driftless and accurate close-range navigation schema is required. Thus, this paper proposes a visual method for navigation utilizing a defined set of ArUco markers printed on the SDS. To increase the accuracy of the system, the set of ArUco markers is defined to a common frame of reference, introducing more points in the camera frame for a more accurate solution to the Perspective-n-Point problem. This makes the system robust against partial occlusion. The paper has also implemented a modified Line of Sight (LOS) schema for the guidance of the vehicle. The results show stable pose estimates at up to 6 meters above the SDS, and successful autonomous docking of an underwater vehicle. The navigational estimates provided by the system get more stable when the vehicle is closer to the SDS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Attention Using Human-Robot Interaction: Impact of Sensory Preferences of Children with Autism

Joint Attention Using Human-Robot Interaction: Impact of Sen...

引用

IEEE International Symposium on Robot and Human Interactive Communication

作者： Pauline Chevalier Jean-Claude Martin Brice Isableu Christophe Bazile David-Octavian Iacob Adriana Tapus Robotics and Computer Vision Lab U2IS ENSTA ParisTech Université Paris-Saclay 828 bd des Maréchaux 91762 Palaiseau cedex France Cognition Perception Use LIMSI-CNRS Orsay 91403 France CIAMS Univ. Paris-Sud Université Paris-Saclay 91405 Orsay Cedex France Groupement des Associations Partenaires de l'Action Sociale France

ISBN: (纸本)9781509039302

Individuals suffering from Autistic Spectrum Disorder (ASD) have impaired skills in social communication and joint attention. In this paper, we explain how we designed and evaluated a Joint Attention (JA) task for individuals with ASD using the Nao humanoid robot. The interaction was tested in children and teenagers with ASD (N=11). Their proprioceptive and visual integration of cues were first assessed, with the hypothesis that individuals with an overreliance on proprioceptive cues and with a hyporeactivity to visual cues would have more difficulties conducting successful interactions with the robot. We observed that participants with an overreliance on proprioceptive cues and hyporeactivity to visual cues showed different behaviors in responding to joint attention. They followed the prompting of the Nao robot more slowly than individuals with an overreliance on visual cues and a hyporeactivity to proprioceptive cues. Defining such individual profiles prior to the social interaction with a robot and working closely with caregivers could provide promising strategies for designing successful and adapted Human-Robot Interaction (HRI) for individuals with ASD.

关键词： Visualization Robot sensing systems Variable speed drives Medical treatment Games Head Manipulator sensing systems Variable speed drives Visualization MEDICAL TREATMENT heart atrium septum defect Head Robot Human machine interaction autism Joints Joints Medicine Game theory

来源：评论

学校读者我要写书评

暂无评论

SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery

arXiv

引用

arXiv 2023年

作者： Cartucho, João Weld, Alistair Tukra, Samyakh Xu, Haozheng Matsuzaki, Hiroki Ishikawa, Taiyo Kwon, Minjun Jang, Yong Eun Kim, Kwang-Ju Lee, Gwang Bai, Bizhe Kahrs, Lueder Boecking, Lars Allmendinger, Simeon Müller, Leopold Zhang, Yitong Jin, Yueming Bano, Sophia Vasconcelos, Francisco Reiter, Wolfgang Hajek, Jonas Silva, Bruno Lima, Estevão Vilaça, João L. Queirós, Sandro Giannarou, Stamatia The Hamlyn Centre for Robotic Surgery Imperial College London United Kingdom Jmees Japan Daejeon Korea Republic of Ajou University Gyeonggi-do Korea Republic of Medical Computer Vision and Robotics Lab University of Toronto Canada Germany Surgical Robot Vision University College London United Kingdom Company Name RIWOlink GmbH Munich Germany School of Medicine University of Minho Braga Portugal ICVS/3B’s - PT Government Associate Laboratory Braga/Guimarães Portugal 2Ai - School of Technology IPCA Barcelos Portugal

This paper introduces the "SurgT: Surgical Tracking" challenge which was organised in conjunction with the 25th International Conference on Medical Image Computing and computer-Assisted Intervention (MICCAI 2022). There were two purposes for the creation of this challenge: (1) the establishment of the first standardised benchmark for the research community to assess soft-tissue trackers;and (2) to encourage the development of unsupervised deep learning methods, given the lack of annotated data in surgery. A dataset of 157 stereo endoscopic videos from 20 clinical cases, along with stereo camera calibration parameters, have been provided. Participants were assigned the task of developing algorithms to track the movement of soft tissues, represented by bounding boxes, in stereo endoscopic videos. At the end of the challenge, the developed methods were assessed on a previously hidden test subset. This assessment uses benchmarking metrics that were purposely developed for this challenge, to verify the efficacy of unsupervised deep learning algorithms in tracking soft-tissue. The metric used for ranking the methods was the Expected Average Overlap (EAO) score, which measures the average overlap between a tracker’s and the ground truth bounding boxes. Coming first in the challenge was the deep learning submission by ICVS-2Ai with a superior EAO score of 0.617. This method employs ARFlow to estimate unsupervised dense optical flow from cropped images, using photometric and regularization losses. Second, Jmees with an EAO of 0.583, uses deep learning for surgical tool segmentation on top of a non-deep learning baseline method: CSRT. CSRT by itself scores a similar EAO of 0.563. The results from this challenge show that currently, non-deep learning methods are still competitive. The dataset and benchmarking tool created for this challenge have been made publicly available at https://***/. This challenge is expected to contribute to the development of au

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Edge-based algorithm for discontinuity adaptive color image smoothing

引用

Pattern Recognition 2001年第2期34卷 333-342页

作者： Kang, Dong Joong Kweon, In So Signal Processing Lab. Samsung Adv. Institute of Technology P.O. Box 111 Suwon 440-600 Korea Republic of Robotics and Computer Vision Lab. Department of Electrical Engineering Korea Adv. Inst. Sci. and Technol. 207-43 Cheong. Dongdaemoon-Gu Seoul United States Pusan National University Pusan Korea Republic of KAIST Seoul Korea Republic of Seoul National University Seoul Korea Republic of Carnegie Mellon University Pittsburgh PA United States

We present a new scheme to increase the performance of edge-preserving image smoothing algorithm from the parameter tuning of a Markov random field (MRF) function. This method is based on an automatic control of the image-smoothing strength in the MRF function in which the parameter control of the function depends on edge magnitude resulted from discontinuities of image intensity. Without any binary decision for the edge magnitude, direct use of full edge magnitude could improve the performance of discontinuity-preserving image smoothing technique.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Evaluation of dense 3D reconstruction from 2D face images in the wild

arXiv

引用

arXiv 2018年

作者： Feng, Zhen-Hua Huber, Patrik Kittler, Josef Hancock, Peter J.B. Wu, Xiao-Jun Zhao, Qijun Koppen, Paul Rätsch, Matthias Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom Faculty of Natural Sciences University of Stirling StirlingFK9 4LA United Kingdom School of Internet of Things Engineering Jiangnan University Wuxi214122 China Biometrics Research Lab College of Computer Science Sichuan University Chengdu610065 China Image Understanding and Interactive Robotics Reutlingen University Reutlingen72762 Germany

This paper investigates the evaluation of dense 3D face reconstruction from a single 2D image in the wild. To this end, we organise a competition that provides a new benchmark dataset that contains 2000 2D facial images of 135 subjects as well as their 3D ground truth face scans. In contrast to previous competitions or challenges, the aim of this new benchmark dataset is to evaluate the accuracy of a 3D dense face reconstruction algorithm using real, accurate and high-resolution 3D ground truth face scans. In addition to the dataset, we provide a standard protocol as well as a Python script for the evaluation. Last, we report the results obtained by five state-of-the-art 3D face reconstruction systems on the new benchmark dataset. The competition is organised along with the 2018 13th IEEE Conference on Automatic Face & Gesture Recognition. This is an extended version of the original conference submission with two additional 3D face reconstruction systems evaluated on the benchmark. Copyright © 2018, The Authors. All rights reserved.

关键词： Petroleum reservoir evaluation

来源：评论

学校读者我要写书评

暂无评论

Group shift pointwise convolution for volumetric medical image segmentation

arXiv

引用

arXiv 2021年

作者： He, Junjun Ye, Jin Li, Cheng Song, Diping Chen, Wanli Wang, Shanshan Gu, Lixu Qiao, Yu School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Shanghai AI Lab Shanghai China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Chinese University of Hong Kong Hong Kong Peng Cheng Laboratory Guangdong Shenzhen China Pazhou Lab Guangdong Guangzhou China

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models employing 3D convolutions introduce more trainable parameters and are more computationally complex, which may lead easily to model overfitting especially for medical applications with limited available training data. This paper aims to improve the effectiveness and efficiency of 3D convolutions by introducing a novel Group Shift Pointwise Convolution (GSP-Conv). GSP-Conv simplifies 3D convolutions into pointwise ones with 1 × 1 × 1 kernels, which dramatically reduces the number of model parameters and FLOPs (e.g. 27× fewer than 3D convolutions with 3 × 3 × 3 kernels). Naïve pointwise convolutions with limited receptive fields cannot make full use of the spatial image context. To address this problem, we propose a parameter-free operation, Group Shift (GS), which shifts the feature maps along different spatial directions in an elegant way. With GS, pointwise convolutions can access features from different spatial locations, and the limited receptive fields of pointwise convolutions can be compensated. We evaluate the proposed methods on two datasets, PROMISE12 and BraTS18. Results show that our method, with substantially decreased model complexity, achieves comparable or even better performance than models employing 3D convolutions. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：