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

Average Weight Optimization RBPF Method for Target Tracking in Multi-Sensor Observations

引用

Chinese Journal of Electronics 2023年第2期22卷 401-404页

作者： Xianxing Liu Zhentao Hu Jie Li Institute of Image Processing and Pattern Recognition Henan University Kaifeng China

The reasonable design of particle filter framework in multi-sensor observation system is the key to expand the application domain of sampling nonlinear filters. Aiming at the effective realization of particle filter for multi-sensor target tracking problem, a novel average weight optimization Rao-Blackwellised particle filtering algorithm is proposed. Combining with the kinetic equation of target state evolution, RBPF is used as the basic estimator of algorithm realization. For the rational utilization from multi-sensor observations and the reduction of the adverse influence from random observations noise in measuring process of particles weight, the average weight optimization strategy is used to improve the reliability and stability of particle weight variance. In addition, we give the concrete flow of RBPF in average weight optimization strategy. Finally, the theoretical analysis and experimental results show the feasibility and efficiency of the proposed algorithm.

关键词： Weight measurement Technological innovation Target tracking Redundancy Filtering algorithms Reliability theory Particle filters

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

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

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

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

A matching-score-based template reconstruction attack

A matching-score-based template reconstruction attack

引用

2024 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2024

作者： Liao, Fengxiang Leng, Lu Guo, Guodong Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315000 China

ISBN: (纸本)9781510689275

Biometric systems, even with high accuracies, commonly suffer from various attacks. In practical applications, some systems directly display the matching scores, or attackers can obtain the matching scores. This paper proposes a novel matching-score-based template reconstruction attack, which reveals that matching scores can leak the spatial neighborhood range of the attacked template, resulting in some potential security and privacy risks. The dissimilarity (matching score) between two real-number templates is measured by the Euclidean distance. A small number of match scores can be obtained by matching the attacked template with a few randomly selected or generated fake templates. An equation set can be established based on the formulae of the matching scores. However, it is difficult to directly solve the quadratic equation set. We skillfully simplify the quadratic equation set into a linear equation set, which obviously reduces the complexity, especially for large-size templates. This novel attack can be extended to other algorithms, and used to evaluate the security and privacy of the related algorithms. © 2025 SPIE.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Inferior Alveolar Nerve Segmentation in CBCT images Using Connectivity-Based Selective Re-training

Inferior Alveolar Nerve Segmentation in CBCT Images Using C...

引用

2nd International ToothFairy2: Multi-Structure Segmentation in CBCT Volumes, ToothFairy 2024, 3D Teeth Landmarks Detection Challenge, 3DTeethLand 2024, Semi-supervised Teeth Segmentation, STS 2024 held in conjunction with the 27th International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Liu, Yusheng Xin, Rui Yang, Tao Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031889769

Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications to prevent irreversible damage to the nerve during the procedure. The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset comprising both sparse and partially dense labels, with the goal of improving the accuracy of automatic IAN segmentation. In this work, in order to avoid the negative impact brought by sparse labeling, we transform the mixed supervised problem into a semi-supervised problem. Inspired by self-training via pseudo labeling, we propose a selective re-training framework based on IAN connectivity. Our method is quantitatively evaluated on the ToothFairy verification cases, achieving the dice similarity coefficient (DSC) of 0.7956, and 95% hausdorff distance (HD95) of 4.4905, and wining the champion in the competition. Code is available at https://***/GaryNico517/SSL-IAN-Retraining. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Semi-supervised nnU-Net Model for Automated Tooth Segmentation in Panoramic X-Ray images

A Two-Stage Semi-supervised nnU-Net Model for Automated Too...

引用

作者： Ji, Changkai Liu, Yusheng He, Lanshan Jiang, Yuxian Huang, Chuanyi Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031889769

Automatic tooth segmentation in 2D panoramic X-ray images is crucial for various applications. Task 1 of the MICCAI STS 2024 Challenge aims to advance automated tooth segmentation techniques by providing datasets comprising labeled and unlabeled panoramic X-ray images. This paper addresses the challenge of limited labeled data by framing the problem as a semi-supervised learning task. We propose a two-stage deep learning model based on nnU-Net. The method first performs quadrant segmentation using one nnU-Net, followed by fine tooth segmentation using another nnU-Net within each quadrant. To effectively utilize unlabeled data, we implement a selective stability-based retraining strategy to generate reliable pseudo-labels. We further enhance model performance through post-processing methods such as connected domain analysis. Quantitative evaluation on the STS 2024 validation set demonstrates that our method achieves strong performance across several metrics (Dice_instance = 79.82%, Dice_image = 94.02%). In the competition’s validation phase, the method was awarded second place, validating its efficacy in automated dental segmentation of panoramic X-ray images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Semi-supervised nnU-Net Framework for Tooth Segmentation in CBCT images

Two-Stage Semi-supervised nnU-Net Framework for Tooth Segme...

引用

ISBN: (纸本)9783031889769

Automated tooth segmentation in Cone-Beam Computed Tomography (CBCT) images is crucial for various dental applications, including treatment planning and computer-assisted dental prosthesis design. The MICCAI STS 2024 Challenge Task 2 aims to enhance automated tooth segmentation by providing a dataset comprising both labeled and unlabeled CBCT images. This paper addresses the challenge of limited labeled data by reformulating the problem as a semi-supervised learning task. We propose a two-stage deep learning model based on nnU-Net. Our approach initially employs a low-resolution nnU-Net for quadrant segmentation, followed by a full-resolution nnU-Net for fine tooth segmentation within each quadrant. To efficiently utilize unlabeled data, we implement a selective stability-based retraining strategy to generate reliable pseudo-labels. Our method is quantitatively evaluated on the STS 2024 validation set, achieving good performance across various metrics (Dice_instance = 90.74%, Dice_image = 97.70%). The proposed approach achieved one of the highest rankings in the competition’s validation phase, demonstrating its efficacy in automatically segmenting teeth from CBCT images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semi-supervised learning

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：