检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Huang, Zhehao Li, Tao Yuan, Chenhe Wu, Yingwen Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Department of Automation Shanghai Jiao Tong University China

Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting. Inter-class imbalance during training has been identified as a major cause of forgetting, leading to model prediction bias towards recently learned classes. In this paper, we theoretically analyze that inter-class imbalance is entirely attributed to imbalanced class-priors, and the function learned from intra-class intrinsic distributions is the optimal classifier that minimizes the class-balanced error. To that end, we present that a simple adjustment of model logits during training can effectively resist prior class bias and pursue the corresponding optimum. Our proposed method, Logit Adjusted Softmax, can mitigate the impact of inter-class imbalance not only in class-incremental but also in realistic scenarios that sum up class and domain incremental learning, with little additional computational cost. We evaluate our approach on various benchmarks and demonstrate significant performance improvements compared to prior arts. For example, our approach improves the best baseline by 4.6% on CIFAR10. Codes are available at https://***/K1nght/online_CL_logit_adjusted_softmax. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Anatomy recognition in CT images of head and neck region via precision atlases

Anatomy recognition in CT images of head and neck region via...

引用

Medical Imaging 2021: image processing

作者： Li, Jieyu Udupa, Jayaram K. Tong, Yubing Odhner, Dewey Torigian, Drew A. Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University China Medical Image Processing Group Department of Radiology University of Pennsylvania United States

ISBN: (纸本)9781510640214

Multi-atlas segmentation methods will benefit from atlases covering the complete spectrum of population patterns, while the difficulties in generating such large enough datasets and the computation burden required in the segmentation procedure reduce its practicality in clinical application. In this work, we start from a viewpoint that different parts of the target object can be recognized by different atlases and propose a precision atlas selection strategy. By comparing regional similarity between target image and atlases, precision atlases are ranked and selected by the frequency of regional best match, which have no need to be globally similar to the target subject at either image-level or object-level, largely increasing the implicit patterns contained in the atlas set. In the proposed anatomy recognition method, atlas building is first achieved by all-totemplate registration, where the minimum spanning tree (MST) strategy is used to select a registration template from a subset of radiologically near-normal images. Then, a two-stage recognition process is conducted: in rough recognition, sub-image level similarity is calculated between the test image and each image of the whole atlas set, and only the atlas with the highest similarity contributes to the recognition map regionally;in refined recognition, the atlases with the highest frequencies of best match are selected as the precision atlases and are utilized to further increase the accuracy of boundary matching. The proposed method is demonstrated on 298 computed tomography (CT) images and 9 organs in the Head and Neck (HN) body region. Experimental results illustrate that our method is effective for organs with different segmentation challenge and samples with different image quality, where remarkable improvement in boundary interpretation is made by refined recognition and most objects achieve a localization error within 2 voxels. © 2021 SPIE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Person Search Method for Video Surveillance 22

An Unsupervised Person Search Method for Video Surveillance

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Feng, Deying Yang, Jie Wei, Yanxia Xiao, Hairong Zhang, Laigang School of Mechanical and Automotive Engineering Liaocheng University China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Liaocheng University China

ISBN: (纸本)9781450396110

We propose an unsupervised person search method for video surveillance. This method considers both the spatial features of persons within each frame and the temporal relationship of the same person among different frames. Thus, the spatial features are extracted by region convolutional neural network, and the temporal relationship is organized by gate recurrent unit. The spatio-temporal features are generated by the following average pooling layer and indexed by locality sensitive hashing. A surveillance video database is constructed to evaluate the proposed method, and the experimental results demonstrate that our method improves the search accuracy by utilizing the spatio-temporal features. © 2022 ACM.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Gait Planning and Motion Control Based on Vrep Simulation for Quadruped Robot 5

Gait Planning and Motion Control Based on Vrep Simulation fo...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Zhou, Linqi Chen, Zhihua Liu, Jun Liu, Zhi Chen, Yumeng Zhang, Liting Nanchang Hangkong University Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Moe Key Lab of Nondestructive Testing Technology Nanchang330063 China Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing100081 China

ISBN: (纸本)9798350307320

Gait planning of quadruped robots plays an important role in achieving less walking, including dynamic and static gait. In this article, a static and dynamic gait control method based on center of gravity stability margin is proposed. Firstly, the robot model and kinematics modeling are introduced. Secondly, the robot's foot static and dynamic gait were planned and the foot trajectory was designed. Finally, two types of gait of the robot were simulated using Vrep simulation software, and the differences in stability and speed between the coordinated gait with speed and stability in the static and dynamic gait of a 12 degree of freedom robot were analyzed, verifying the effectiveness of the gait control method proposed in this paper. © 2023 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Progressive Motion Context Refine Network for Efficient Video Frame Interpolation

arXiv

引用

arXiv 2022年

作者： Kong, Lingtong Liu, Jinfeng Yang, Jie The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China

Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation. However, above cascaded architecture can lead to large model size and inference delay, hindering them from mobile and real-time applications. To solve this problem, we propose a novel Progressive Motion Context Refine Network (PMCRNet) to predict motion fields and image context jointly for higher efficiency. Different from others that directly synthesize target frame from deep feature, we explore to simplify frame interpolation task by borrowing existing texture from adjacent input frames, which means that decoder in each pyramid level of our PMCRNet only needs to update easier intermediate optical flow, occlusion merge mask and image residual. Moreover, we introduce a new annealed multi-scale reconstruction loss to better guide the learning process of this efficient PMCRNet. Experiments on multiple benchmarks show that proposed approaches not only achieve favorable quantitative and qualitative results but also reduces current model size and running time significantly. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

A Branch-sensitive 3D Convolutional Neural Networks for Airway Segmentation

A Branch-sensitive 3D Convolutional Neural Networks for Airw...

引用

IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC)

作者： Yingjie Zhao Yusheng Liu Lisheng Wang Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781665479691

CT scans are an exceptional tool for quantitative airway analysis. Due to the complex voxel connectivity and branch structure of the airway, precise and fine segmentation results are difficult to accomplish. We propose a fully automated and end-to-end approach for airway segmentation and branch detection in chest CT based on U-Net architecture. We introduce the SE Normalization as a module for feature calibration and the hard region adaptation loss function based on cross entropy (HRA_CE) for dynamically maintaining class balance throughout the training period. We present a brand-new metric Branch DSC designed exclusively to assess the branch structure. We validate the suggested method on a dataset of 46 airway samples, and the experimental findings demonstrate that our proposed method significantly improves branch detection and segmentation continuity.

关键词： Training Measurement Three-dimensional displays Automation Computed tomography Atmospheric modeling Entropy

来源：评论

学校读者我要写书评

暂无评论

Learning with Explicit Shape Priors for Medical image Segmentation

arXiv

引用

arXiv 2023年

作者： You, Xin He, Junjun Yang, Jie Gu, Yun The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Shanghai AI Laboratory Shanghai200240 China

Medical image segmentation is a fundamental task for medical image analysis and surgical planning. In recent years, UNet-based networks have prevailed in the field of medical image segmentation. However, convolution-neural networks (CNNs) suffer from limited receptive fields, which fail to model the long-range dependency of organs or tumors. Besides, these models are heavily dependent on the training of the final segmentation head. And existing methods can not well address these two limitations at the same time. Hence, in our work, we proposed a novel shape prior module (SPM), which can explicitly introduce shape priors to promote the segmentation performance of UNet-based models. The explicit shape priors consist of global and local shape priors. The former with coarse shape representations provides networks with capabilities to model global contexts. The latter with finer shape information serves as additional guidance to boost the segmentation performance, which relieves the heavy dependence on the learnable prototype in the segmentation head. To evaluate the effectiveness of SPM, we conduct experiments on three challenging public datasets. And our proposed model achieves state-of-the-art performance. Furthermore, SPM shows an outstanding generalization ability on classic CNNs and recent Transformer-based backbones, which can serve as a plug- and-play structure for the segmentation task of different datasets. Source codes are available at https://***/AlexYouXin/Explicit-Shape-Priors Copyright © 2023, The Authors. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Follicular Unit Registration Based on Binocular Stereo Vision for Hair Transplantation Surgery Robot

Follicular Unit Registration Based on Binocular Stereo Visio...

引用

Data Science and Information Technology (DSIT), International Conference on

作者： Weiduo Wang Jinfeng Liu Jie Yang Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China

In this paper, we focus on the follicular unit registration problem for hair transplantation surgery robots based on binocular stereo vision system. The follicular units in both images are detected with YOLO V5 network. Because of the dull and similar pattern of the follicular units, previous regular methods which are pixel-based are reported with misalignment and poor accuracy. To solve this problem, we propose the context shape to describe the feature of the follicular unit. The distribution of units surrounding the target unit is estimated as the context shape. Then, Otsu’s method is used to segment hairs and Hungarian algorithm is used to match the hairs in the matched follicular unit. Then, the hairs are projected to 3D coordinate system and reconstructed. The experiments on the generated hair dataset demonstrate that the proposed method achieves both high accuracy and speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Achievement Degree Evaluation Method of Operating System Course Targets under the Background of Engineering Education Accreditation 3

Achievement Degree Evaluation Method of Operating System Cou...

引用

3rd IEEE International Conference on Computer Science and Educational Informatization, CSEI 2021

作者： Zhang, Fan Zhang, Xinhong Henan University School of Computer and Information Engineering Kaifeng China Institute of Image Processing and Pattern Recognition Henan University Kaifeng China

ISBN: (纸本)9781728184739

Engineering education accreditation emphasizes the cultivation of students' ability to solve complex engineering problems, including the cultivation of students' ability to analyze, design and develop solutions, research, application of modern tools and other qualities related to non-technical factors to solve complex engineering problems. Operating system course is the core course of computer science and technology major in colleges and universities. The understanding and mastery of operating system course directly affects students' computer professional level. In view of the new requirements of new engineering construction and engineering education accreditation for major curriculum construction and personnel training, as well as the current characteristics of software engineering and personnel training, this paper, based on the core concept of OBE and complex engineering problems of engineering education accreditation, evaluates the achievement of operating system curriculum requirements under the background of engineering education accreditation. This paper analyzes the effectiveness and puts forward a new method of major curriculum construction and evaluation to meet the requirements of new engineering construction and engineering education accreditation. © 2021 IEEE.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

Diffusion representation for asymmetric kernels via magnetic transform 23

Diffusion representation for asymmetric kernels via magnetic...

引用

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Mingzhen He Fan He Ruikai Yang Xiaolin Huang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Department of Electrical Engineering (ESAT-STADIUS) KU Leuven Leuven Belgium

As a nonlinear dimension reduction technique, the diffusion map (DM) has been widely used. In DM, kernels play an important role for capturing the nonlinear relationship of data. However, only symmetric kernels can be used now, which prevents the use of DM in directed graphs, trophic networks, and other real-world scenarios where the intrinsic and extrinsic geometries in data are asymmetric. A promising technique is the magnetic transform which converts an asymmetric matrix to a Hermitian one. However, we are facing essential problems, including how diffusion distance could be preserved and how divergence could be avoided during diffusion process. Via theoretical proof, we successfully establish a diffusion representation framework with the magnetic transform, named MagDM. The effectiveness and robustness for dealing data endowed with asymmetric proximity are demonstrated on three synthetic datasets and two trophic networks.

关键词：

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：