检索结果-内蒙古大学图书馆

Dynamic Frame Interpolation in Wavelet Domain

IEEE Transactions on image processing 2023年 32卷 5296-5309页

作者： Kong, Lingtong Jiang, Boyuan Luo, Donghao Chu, Wenqing Tai, Ying Wang, Chengjie Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Department of Automation Shanghai200240 China Tencent Youtu Laboratory Shanghai200233 China Nanjing University School of Intelligence Science and Technology Suzhou215163 China

Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. However, the spatial redundancy when synthesizing the target frame has not been fully explored, that can result in lots of inefficient computation. On the other hand, the computation compression degree in frame interpolation is highly dependent on both texture distribution and scene motion, which demands to understand the spatial-temporal information of each input frame pair for a better compression degree selection. In this work, we propose a novel two-stage frame interpolation framework termed WaveletVFI to address above problems. It first estimates intermediate optical flow with a lightweight motion perception network, and then a wavelet synthesis network uses flow aligned context features to predict multi-scale wavelet coefficients with sparse convolution for efficient target frame reconstruction, where the sparse valid masks that control computation in each scale are determined by a crucial threshold ratio. Instead of setting a fixed value like previous methods, we find that embedding a classifier in the motion perception network to learn a dynamic threshold for each sample can achieve more computation reduction with almost no loss of accuracy. On the common high resolution and animation frame interpolation benchmarks, proposed WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts. © 1992-2012 IEEE.

关键词： Wavelet transforms

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 5

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

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2022

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

ISBN: (纸本)9781665479677

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. © 2022 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

GAN-DIRNet:A Novel Deformable image Registration Approach for Multimodal Histological images

引用

Computers, Materials & Continua 2024年第7期80卷 487-506页

作者： Haiyue Li Jing Xie Jing Ke Ye Yuan Xiaoyong Pan Hongyi Xin Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai200240China Department of Pathology Ruijin HospitalShanghai Jiao Tong UniversitySchool of MedicineShanghai200025China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai200240China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai200240China

Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of *** neural network(CNN)and generative adversarial network(GAN)are pivotal inmedical image ***,existing methods often struggle with severe interference and deformation,as seen in histological images of conditions like Cushing’s *** argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator *** this study,we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image *** begin with,the discriminators of two GANs are embedded as a new dual parallel feature extraction module into the unsupervised registration networks,characterized by implicitly extracting feature descriptors of specific ***,modal feature description layers and registration layers collaborate in unsupervised optimization,facilitating faster convergence and more precise ***,experiments and evaluations were conducted on the registration of the Mixed National institute of Standards and Technology database(MNIST),eight publicly available datasets of histological sections and the Clustering-Registration-Classification-Segmentation(CRCS)dataset on the Cushing’s *** results demonstrate that our proposed GAN-DIRNet method surpasses existing approaches like DIRNet in terms of both registration accuracy and time efficiency,while also exhibiting robustness across different image types.

关键词： Histological images registration deformable registration generative adversarial network cushing’s disease machine learning computer vision

来源：评论

学校读者我要写书评

暂无评论

A Coarse-to-Fine Framework for Head and Neck Tumor Segmentation in CT and PET images 1

引用

2nd 3D Head and Neck Tumor Segmentation in PET/CT Challenge, HECKTOR 2021, held in conjunction with 24th International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2021

作者： An, Chengyang Chen, Huai Wang, Lisheng Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China

ISBN: (数字)9783030982539

ISBN: (纸本)9783030982522

Radiomics analysis can help patients suffered from head and neck (H&N) cancer customize tailoring treatments. It requires a large number of segmentation of the H&N tumor area in PET and CT images. However, the cost of manual segmentation is extremely high. In this paper, we propose a coarse-to-fine framework to segment the H&N tumor automatically in FluoroDeoxyGlucose (FDG)-Positron Emission Tomography (PET) and Computed Tomography (CT) images. Specifically, we trained three 3D-UNets with residual blocks to make coarse stage, fine stage and refined stage predictions respectively. Experiments show that such a training framework can improve the segmentation quality step by step. We evaluated our framework with Dice Similarity Coefficient (DSC) and Hausdorff Distance at 95% (HD95) of 0.7733 and 3.0882 respectively in the task 1 of the HEad and neCK TumOR segmentation and outcome prediction in PET/CT images (HECKTOR2021) Challenge and ranked second. © 2022, Springer Nature Switzerland AG.

关键词： Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Neovascularization Detection in Color Fundus Photography image 23

Deep Learning Based Neovascularization Detection in Color Fu...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Guo, Tianjiao Yang, Jie Yu, Qi Institute of Medical Robotics Institute of Image Processing and Pattern Recognition Department of Automation School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Shanghai General Hospital Shanghai Jiao Tong University School of Medicine Shanghai China National Clinical Research Center for Eye Diseases Shanghai China

ISBN: (纸本)9781450399029

Diabetic retinopathy (DR) has already been one of the leading causes of vision loss. A large number of researches about deep learning-based DR screening using color retinal photography images have been proposed in recent years. However, existing works mainly concentrated on non-proliferative diabetic retinopathy (NPDR) lesions. The exploration of proliferative diabetic retinopathy (PDR) lesion, which is more serious, is still insufficient. In this paper, we explored into one typical PDR lesion named neovascularization (NV). We collected and annotated retinal images from public and private datasets to construct and release a new dataset for NV detection. Three tasks including segmentation, detection, and grading were conducted on our dataset by using a set of state-of-the-art deep learning models. The results show that introducing NV detection can benefit DR grading. However, the segmentation and detection of NV are still challenging and have considerable room for improvement. © 2023 Copyright held by the owner/author(s).

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Remaining-data-free Machine Unlearning by Suppressing Sample Contribution

arXiv

引用

arXiv 2024年

作者： Cheng, Xinwen Huang, Zhehao Zhou, Wenxin He, Zhengbao Yang, Ruikai Wu, Yingwen Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China

Machine unlearning (MU) is to forget data from a well-trained model, which is practically important due to the "right to be forgotten". The unlearned model should approach the retrained model, where the forgetting data are not involved in the training process and hence do not contribute to the retrained model. Considering the forgetting data’s absence during retraining, we think unlearning should withdraw their contribution from the pre-trained model. The challenge is that when tracing the learning process is impractical, how to quantify and detach sample’s contribution to the dynamic learning process using only the pre-trained model. We first theoretically discover that sample’s contribution during the process will reflect in the learned model’s sensitivity to it. We then practically design a novel method, namely MU-Mis (Machine Unlearning by Minimizing input sensitivity), to suppress the contribution of the forgetting data. Experimental results demonstrate that MU-Mis can unlearn effectively and efficiently without utilizing the remaining data. It is the first time that a remaining-data-free method can outperform state-of-the-art (SoTA) unlearning methods that utilize the remaining data. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

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

GRC-Net: Grouping Guided R-band Chromosome recognition Network 24

GRC-Net: Grouping Guided R-band Chromosome Recognition Netwo...

引用

10th International Conference on Computing and Artificial Intelligence, ICCAI 2024

作者： Xia, Chao Liu, Wei Liu, Zhao Jiang Chen, Bing Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Shanghai Institute of Hematology State Key Laboratory of Medical Genomics National Research Center for Translational Medicine at Shanghai Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai China

ISBN: (纸本)9798400717055

Chromosome recognition is a critical and time-consuming process in karyotyping, especially for R-band chromosomes with poor visualization quality. In this paper, we propose an end-to-end grouping guided R-band chromosome recognition method GRC-Net. GRC-Net serves the chromosome recognition task as the main task and takes the chromosome length grouping task and centromere position grouping task as auxiliary tasks. Two auxiliary modules, Chromosome Length Grouping Module (CLGM) and Centromere Position Grouping Model (CPGM), are designed to extract the task-specific feature and refine the feature map of the main task. A large-scale R-band chromosome dataset with 1735 cases was collected. Experiment results on the 423 testing cases show that the proposed GRC-Net gets the highest accuracy of 96.87%, outperforming the baseline by 2.24%. With grouping task-guided feature extraction, GRC-Net reduces approximately 50% of the inter-group misclassification. The proposed GRC-Net can serve as a general framework for incorporating the domain knowledge into the process of feature learning, meanwhile, a powerful tool to assist clinical chromosome karyotyping. © 2024 ACM.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Analysis of Distracted Driving Detection Based on Deep Learning Human Posture 23

Analysis of Distracted Driving Detection Based on Deep Learn...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Li, Yanjun Ling, Xufeng Yang, Jie Shanghai Normal University Tianhua College AI School No. 1661 North Sheng Xin Road China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University 800 Dongchuan Road 200240 China

ISBN: (纸本)9781450399029

Distracted driving is a phenomenon that drivers’ attention points to activities unrelated to normal driving, which leads to the decline of driving operation ability. With the popularity of smart phones, traffic accidents caused by distracted driving are on the rise. Traffic accidents caused by driver’s inattention due to vision deviation or distraction are particularly obvious in rear end collisions. The results of the distracted driving questionnaire show that almost all drivers have experienced distracted driving. In order to detect whether drivers are distracted when driving, this paper proposes a distracted driving analysis based on deep learning of human posture. This method uses the MMDetection framework in depth learning to build a target detection network to achieve target detection, then uses the depth neural network to estimate the geometric transformation features, and uses the stacked hourglass network to accurately predict the state features of drivers in the graph. The experimental results show that the measurement method has good accuracy, fast speed, good robustness and consistency, more accurate extraction of human posture related features, strong generalization ability and certain practical value. © 2023 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of Steel Surface Defect Based on Faster R-CNN and FPN 2021

Detection of Steel Surface Defect Based on Faster R-CNN and ...

引用

7th International Conference on Computing and Artificial Intelligence, ICCAI 2021

作者： Yin, Tianping Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781450389501

With the development of economy, steel has been widely used by human beings in various fields of social life, for example, military products, vehicles, aerospace, high-rise buildings and daily necessities. Therefore, it is very important to get high quality steel in industrial production. Detection of steel surface defect is a vital process in steel quality inspection. Traditional method uses artificial feature to detect steel surface defect, which costs lots of time to get features, and it is not robust in new environment. Therefore, this paper proposes an efficient and accurate method to solve the problem. In this paper, we adopt the faster R-CNN algorithm as baseline to train our own model. The feature pyramid network (FPN) is added to the original network of faster R-CNN, so that the network can combine high-level feature information and low-level feature information, furthermore, we replace the region-of-interest (RoI) pooling module with RoI align to reduce quantization error, which helps the mean average precision (mAP) increase about 0.8%. We use cycle GAN to do data enhancement, which helps our network easily to converge. Another problem is that it is quite common to get extreme aspect ratio in steel surface samples, which makes the detection more difficult, we introduce a method called multi-layer RoI align to solve this problem, which makes the mAP increase about 3.2%. According to our experiment results, the proposed method has a quite good performance on detection of steel surface defect. © 2021 ACM.

关键词： Aspect ratio

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：