检索结果-内蒙古大学图书馆

arXiv 2022年

作者： He, Mengzhe Wang, Yali Wu, Jiaxi Wang, Yiru Li, Hanqing Li, Bo Gan, Weihao Wu, Wei Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China SenseTime Research University of Chinese Academy of Science China Shanghai AI Laboratory Shanghai China Beihang University China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. Our code and model will be available at here. Copyright © 2022, 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

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

Robotic workcell for sole grasping in footwear manufacturing

Robotic workcell for sole grasping in footwear manufacturing

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Guillermo Oliver Pablo Gil Fernando Torres Automatics Robotics and Artificial Vision Lab (AUROVA). Computer Science Research Institute University of Alicante Spain

ISBN: (数字)9781728189567

ISBN: (纸本)9781728189574

The goal of this paper is to present a robotic workcell to automate several tasks of the cementing process in footwear manufacturing. Our cell's main applications are sole digitization of a wide variety of footwear, glue dispensing and sole grasping from conveyor belts. This cell is made up of a manipulator arm endowed with a gripper, a conveyor belt and a 3D scanner. We have integrated all the elements into a ROS simulation environment facilitating control and communication among them, also providing flexibility to support future extensions. We propose a novel method to grasp soles of different shape, size and material, exploiting the particular characteristics of these objects. Our method relies on object contour extraction using concave hulls. We evaluate it on point clouds of 16 digitized real soles in three different scenarios: concave hull, k-NNs extension and PCA correction. While we have tested this workcell in a simulated environment, the presented system's performance is scheduled to be tested on a real setup at INESCOP facilities in the upcoming months.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CertainOdom: Uncertainty Weighted Multi-task Learning Model for LiDAR Odometry Estimation

CertainOdom: Uncertainty Weighted Multi-task Learning Model ...

引用

IEEE International Conference on robotics and Biomimetics

作者： Leyuan Sun Guanqun Ding Yusuke Yoshiyasu Fumio Kanehiro Department of Intelligent and Mechanical Interaction Systems Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan CNRS-AIST Joint Robotics Laboratory (JRL) IRL National Institute of Advanced Industrial Science and Technology (AIST). Digital Architecture Research Center (DARC) National Institute of Advanced Industrial Science and Technology (AIST) Tokyo Japan Computer Vision Research Team Artificial Intelligence Research Center (AIRC) National Institute of Advanced Industrial Science and Technology (AIST) Japan

ISBN: (纸本)9781665481106

As a basic and indispensable module, LiDAR odom-etry estimation is widely used in robotics. In recent years, learning-based modeling approaches for odometry estimation have been validated to be feasible. However, it is necessary to consider security factors as the highest priorities when we apply the learning-based model to certain high-risk real-world scenarios, such as autonomous driving. The odometry uncertainty estimation provides more valuable information for downstream tasks, such as route planning and navigation. In this paper, we propose an end-to-end neural network (namely CertainOdom) to solve odometry and uncertainty estimation tasks by applying multi-task learning. Instead of using the manually-tuned hyper-parameters, we employ the learnable uncertainties to weigh the balance between the error of translation and orientation in the loss function. We evaluate the estimated trajectory and uncertainty on KITTI dataset. We also compare the robustness against the traditional geometry-based methods on our artificially degraded KITTI LiDAR dataset. Extensive experimental results show that our model with uncertainty weighted loss achieves competitive performance in LiDAR odometry estimation. We also explain our uncertainties qualitatively and quantitatively.

关键词： Uncertainty Laser radar Biological system modeling Estimation Multitasking Robustness Trajectory

来源：评论

学校读者我要写书评

暂无评论

Fair Evaluation of Federated Learning Algorithms for Automated Breast Density Classification: The Results of the 2022 ACR-NCI-NVIDIA Federated Learning Challenge

arXiv

引用

arXiv 2024年

作者： Schmidt, Kendall Bearce, Benjamin Chang, Ken Coombs, Laura Farahani, Keyvan Elbatel, Marawan Mouheb, Kaouther Marti, Robert Zhang, Ruipeng Zhang, Yao Wang, Yanfeng Hu, Yaojun Ying, Haochao Xu, Yuyang Testagrose, Conrad Demirer, Mutlu Gupta, Vikash Akünal, Ünal Bujotzek, Markus Maier-Hein, Klaus H. Qin, Yi Li, Xiaomeng Kalpathy-Cramer, Jayashree Roth, Holger R. American College of Radiology United States The Massachusetts General Hospital United States University of Colorado United States National Institutes of Health National Cancer Institute United States Computer Vision and Robotics Institute University of Girona Spain Cooperative Medianet Innovation Center Shanghai Jiao Tong University China Shanghai AI Laboratory China Real Doctor AI Research Centre Zhejiang University China School of Public Health Zhejiang University China College of Computer Science and Technology Zhejiang University China University of North Florida College of Computing Jacksonville United States Mayo Clinic Florida Radiology United States Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Electronic and Computer Engineering Hong Kong University of Science and Technology China NVIDIA United States

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical Schools' Mass General Brigham, University of Colorado, NVIDIA, and the National institutes of Health National Cancer institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location. © 2024, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Navigation Command Matching for vision-based Autonomous Driving

Navigation Command Matching for Vision-based Autonomous Driv...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yuxin Pan Jianru Xue Pengfei Zhang Wanli Ouyang Jianwu Fang Xingyu Chen Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China SenseTime Computer Vision Research Group University of Sydney Australia

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Learning an optimal policy for autonomous driving task to confront with complex environment is a long- studied challenge. Imitative reinforcement learning is accepted as a promising approach to learn a robust driving policy through expert demonstrations and interactions with environments. However, this model utilizes non-smooth rewards, which have a negative impact on matching between navigation commands and trajectory (state-action pairs), and degrade the generalizability of an agent. Smooth rewards are crucial to discriminate actions generated from sub-optimal policy. In this paper, we propose a navigation command matching (NCM) model to address this issue. There are two key components in NCM, 1) a matching measurer produces smooth navigation rewards that measure matching between navigation commands and trajectory; 2) attention-guided agent performs actions given states where salient regions in RGB images (i.e. roadsides, lane markings and dynamic obstacles) are highlighted to amplify their influence on the final model. We obtain navigation rewards and store transitions to replay buffer after an episode, so NCM is able to discriminate actions generated from suboptimal policy. Experiments on CARLA driving benchmark show our proposed NCM outperforms previous state-of-the- art models on various tasks in terms of the percentage of successfully completed episodes. Moreover, our model improves generalizability of the agent and obtains good performance even in unseen scenarios.

关键词： Navigation Task analysis Trajectory Learning (artificial intelligence) Autonomous vehicles Smoothing methods Current measurement

来源：评论

学校读者我要写书评

暂无评论

Collaborative Multi-View Convolutions With Gating For Accurate And Fast Volumetric Medical Image Segmentation

Collaborative Multi-View Convolutions With Gating For Accura...

引用

IEEE International Symposium on Biomedical Imaging

作者： Cheng Li Jin Ye Junjun He Shanshan Wang Lixu Gu Yu Qiao Paul C. Lauterbur Research Center for Biomedical Imaging SIAT CAS Shenzhen China Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab SIAT CAS Shenzhen China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Biomedical Engineering/the Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665412469;9781665429474

Due to their high capacity in capturing 3D spatial information, 3D Fully Convolutional Neural Networks (3D FCNs), especially 3D U-Net, are prevalent for volumetric medical image segmentation. However, 3D convolutions are much more computationally complex than 2D convolutions and thus, are more prone to overfitting. This paper proposes Collaborative Multi-View convolutions (CMV convs) that can keep the model complexity similar to those employing 2D convolutions while capturing the 3D spatial context like 3D convolutions. Specifically, CMV convs simultaneously extract information from three orthogonal views with three parameter-shared 2D convolutions. A Global-Guided Gating mechanism (3G) is further designed that selectively passes information from CMV convs to the next stage. Combined with 3G, a CMV conv become a G-CMV conv that constitutes a plug-and-play module, which can be easily integrated into various 3D CNNs for image segmentation. Extensive experiments utilizing BraTS18 dataset have been conducted. Our method achieves competitive results compared to state-of-the-art methods with over 10× fewer parameters than 3D-UNet.

关键词： Solid modeling Image segmentation Interpolation Three-dimensional displays Computational modeling Biological system modeling Collaboration

来源：评论

学校读者我要写书评

暂无评论

Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network

arXiv

引用

arXiv 2021年

作者： Wan, Jun Xi, Hui Zhou, Jie Lai, Zhihui Pedrycz, Witold Wang, Xu Sun, Hang School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Department of Electrical & Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland College of Computer and Information Technology China Three Gorges University Yichang HuBei China

Current fully-supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under large poses and heavy occlusions for inaccurate facial shape constraints and insufficient labeled training samples. In this paper, we propose a semi-supervised framework, i.e., a Self-Calibrated Pose Attention Network (SCPAN) to achieve more robust and precise facial landmark detection in challenging scenarios. To be specific, a Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial shape constraints by fusing boundary and landmark intensity field information. Moreover, a Self-Calibrated Pose Attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision without label information by introducing a self-calibrated mechanism and a pose attention mask. We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved. The experimental results obtained for challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature. Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration 16th

PIPAL: A Large-Scale Image Quality Assessment Dataset for Pe...

引用

16th European Conference on computer vision, ECCV 2020

作者： Jinjin, Gu Haoming, Cai Haoyu, Chen Xiaoxing, Ye Ren, Jimmy S. Chao, Dong The School of Data Science The Chinese University of Hong Kong Shenzhen China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China SenseTime Research Science Park Hong Kong SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9783030586201

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these 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 methods, which are missing in previous datasets. We collect more than 1.13 million human judgments 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 improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Self-slimmed vision Transformer

arXiv

引用

arXiv 2021年

作者： Zong, Zhuofan Li, Kunchang Song, Guanglu Wang, Yali Qiao, Yu Leng, Biao Liu, Yu School of Computer Science and Engineering Beihang University China SenseTime Research China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Shanghai AI Laboratory China

vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting token-to-token comparison. The previous works focus on dropping insignificant tokens to reduce the computational cost of ViTs. But when the dropping ratio increases, this hard manner will inevitably discard the vital tokens, which limits its efficiency. To solve the issue, we propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation. As a general method of token hard dropping, our TSM softly integrates redundant tokens into fewer informative ones. It can dynamically zoom visual attention without cutting off discriminative token relations in the images, even with a high slimming ratio. Furthermore, we introduce a concise Feature Recalibration Distillation (FRD) framework, wherein we design a reverse version of TSM (RTSM) to recalibrate the unstructured token in a flexible auto-encoder manner. Due to the similar structure between teacher and student, our FRD can effectively leverage structure knowledge for better convergence. Finally, we conduct extensive experiments to evaluate our SiT. It demonstrates that our method can speed up ViTs by 1.7× with negligible accuracy drop, and even speed up ViTs by 3.6× while maintaining 97% of their performance. Surprisingly, by simply arming LV-ViT with our SiT, we achieve new state-of-the-art performance on ImageNet. Code is available at https://***/Sense-X/SiT. © 2021, CC BY.

关键词： Distillation

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：