检索结果-内蒙古大学图书馆

A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Han, Xiaoxiang Liu, Yiman Shang, Jiang Li, Qingli Chen, Jiangang Hu, Menghan Zhang, Qi Zhang, Yuqi Wang, Yan School of Communication and Information Engineering Shanghai University Shanghai China Lab Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Department of Pediatric Cardiology Shanghai Children’s Medical Center School of Medicine Shanghai Jiao Tong University Shanghai China Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China

Segmenting internal structure from echocardiography is essential for the diagnosis and treatment of various heart diseases. Semi-supervised learning shows its ability in alleviating annotations scarcity. While existing semi-supervised methods have been successful in image segmentation across various medical imaging modalities, few have attempted to design methods specifically addressing the challenges posed by the poor contrast, blurred edge details and noise of echocardiography. These characteristics pose challenges to the generation of high-quality pseudo-labels in semi-supervised segmentation based on Mean Teacher. Inspired by human reflection on erroneous practices, we devise an error reflection strategy for echocardiography semi-supervised segmentation architecture. The process triggers the model to reflect on inaccuracies in unlabeled image segmentation, thereby enhancing the robustness of pseudo-label generation. Specifically, the strategy is divided into two steps. The first step is called reconstruction reflection. The network is tasked with reconstructing authentic proxy images from the semantic masks of unlabeled images and their auxiliary sketches, while maximizing the structural similarity between the original inputs and the proxies. The second step is called guidance correction. Reconstruction error maps decouple unreliable segmentation regions. Then, reliable data that are more likely to occur near high-density areas are leveraged to guide the optimization of unreliable data potentially located around decision boundaries. Additionally, we introduce an effective data augmentation strategy, termed as multi-scale mixing up strategy, to minimize the empirical distribution gap between labeled and unlabeled images and perceive diverse scales of cardiac anatomical structures. Extensive experiments on a public echocardiography dataset CAMUS, and a private clinical echocardiography dataset demonstrate the competitiveness of the proposed method. Copyright © 202

关键词： Medical imaging

SOLVING CONTINUAL OFFLINE RL THROUGH SELECTIVE WEIGHTS ACTIVATION ON ALIGNED SPACES

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jifeng Huang, Sili Shen, Li Yang, Zhejian Hu, Shengchao Tang, Shisong Chen, Hechang Chang, Yi Tao, Dacheng Sun, Lichao School of Artificial Intelligence Jilin University China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Shenzhen International Graduate School Tsinghua University China College of Computing and Data Science Nanyang Technological University Singapore Computer Science and Engineering Lehigh University United States

Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. However, most research only focuses on limited continual task settings where the tasks have the same observation and action space, which deviates from the realistic demands of training agents in various environments. In view of this, we propose Vector-Quantized Continual Diffuser, named VQ-CD, to break the barrier of different spaces between various tasks. Specifically, our method contains two complementary sections, where the quantization spaces alignment provides a unified basis for the selective weights activation. In the quantized spaces alignment, we leverage vector quantization to align the different state and action spaces of various tasks, facilitating continual training in the same space. Then, we propose to leverage a unified diffusion model attached by the inverse dynamic model to master all tasks by selectively activating different weights according to the task-related sparse masks. Finally, we conduct extensive experiments on 15 continual learning (CL) tasks, including conventional CL task settings (identical state and action spaces) and general CL task settings (various state and action spaces). Compared with 16 baselines, our method reaches the SOTA performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Vector quantization

Elastic-plastic time-history analysis of steel-tube stiff-frame arch bridge without inner filling concrete 3

学校读者我要写书评

暂无评论

Elastic-plastic time-history analysis of steel-tube stiff-fr...

2020 3rd International Symposium on Traffic Transportation and Civil Architecture, ISTTCA 2020

作者： Zhang, Ben Li, Li Su, Wenming School of Civil Engineering Chongqing Jiaotong University Chongqing400074 China China Railway Bridge Science Research Institute Ltd. Wuhan430034 China State Key Laborary for Health and Safety of Bridge Structures Wuhan430034 China Shandong Hi-Speed Engineering Testing Co. Ltd Jinan250000 China Key Lab. for Bridge Struct. Big Data Perf. Diagn. and Treatm. Improvement of Transp. Industry Jinan250000 China

Based on a case study of a typical arch bridge with hollow steel tube and stiffness frame located in the high intensity region of western China, this paper adopts the onlinear time- history method to analyze the structural response of the overall bridge elastic-plastic model under seismic action. Under the force of Wolong wave in Wenchuan Earthquake, the main load-bearing members of the structure have a good seismic performance. Only part of the columns on the main arch ring enter the plastic hinge state for energy dissipation, and the lower columns have a more obvious energy dissipation effect than the higher ones. The result indicates that the design idea of structure which is similar to that of strong column and weak beam in ductility design, has the characteristics of "strong arch and weak beam"and can therefore improve the ability of structure to resist collapse under earthquake action. © Published under licence by IOP Publishing Ltd.

关键词： Energy dissipation

Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Yuhao Chang, Ao Dou, Haoran Tao, Xing Zhou, Xinrui Cao, Yan Huang, Ruobing Frangi, Alejandro F. Bao, Lingyun Yang, Xin Ni, Dong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Lab Shenzhen University Shenzhen China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen China School of Computing University of Leeds Leeds United Kingdom Shenzhen RayShape Medical Technology Co. Ltd Shenzhen China Division of Informatics Imaging and Data Science School of Health Sciences University of Manchester Manchester United Kingdom Department of Computer Science School of Engineering University of Manchester Manchester United Kingdom Department of Electrical Engineering Department of Cardiovascular Sciences KU Leuven Belgium Alan Turing Institute London United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom Department of Ultrasound Affiliated Hangzhou First People’s Hospital School of Medicine Westlake University China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: 1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. 2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents’ erasing process precisely, thereby avoiding both under- and over-segmentation. 3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

Tackling Noisy labels with Network Parameter Additive Decomposition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Jingyi Xia, Xiaobo Lan, Long Wu, Xinghao Yu, Jun Yang, Wenjing Han, Bo Liu, Tongliang The Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha410073 China The Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering University of Sydney DarlingtonNSW2008 Australia The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Department of Automation University of Science and Technology of China Hefei230026 China The Department of Computer Science Hong Kong Baptist University Hong Kong

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot distinguish the memorization of clean data and mislabeled data, resulting in the network still inevitably overfitting mislabeled data in the early training stage. In this paper, to decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, we perform additive decomposition on network parameters. Namely, all parameters are additively decomposed into two groups, i.e. , parameters w are decomposed as w = σ + γ. Afterward, the parameters σ are considered to memorize clean data, while the parameters γ are considered to memorize mislabeled data. Benefiting from the memorization effect, the updates of the parameters σ are encouraged to fully memorize clean data in early training, and then discouraged with the increase of training epochs to reduce interference of mislabeled data. The updates of the parameters γ are the opposite. In testing, only the parameters σ are employed to enhance generalization. Extensive experiments on both simulated and real-world benchmarks confirm the superior performance of our method. The implementation is available at: https://***/wangjingyi9924/TNLPAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Incrementally Zero-Shot Detection by an Extreme Value Analyzer

学校读者我要写书评

暂无评论

Incrementally Zero-Shot Detection by an Extreme Value Analyz...

International Conference on Pattern Recognition

作者： Sixiao Zheng Yanwei Fu Yanxi Hou Academy for Engineering & Technology Fudan University Shanghai Engineering Research Center of AI& Robotics Engineering Research Center of AI & Robotics Ministry of Education School of Data Science MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University School of Data Science Fudan University

Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes. This paper introduces a novel and challenging task of Incrementally Zero-Shot Detection (IZSD), a practical strategy for both zero-shot learning and class-incremental learning in real-world object detection. An innovative end-to-end model - IZSD-EVer was proposed to tackle this task that requires incrementally detecting new classes and detecting the classes that have never been seen. Specifically, we propose a novel extreme value analyzer to detect objects from old seen, new seen, and unseen classes, simultaneously. Additionally and technically, we propose two innovative losses, i.e., background-foreground mean squared error loss alleviating the extreme imbalance of the background and foreground of images, and projection distance loss aligning the visual space and semantic spaces of old seen classes. Experiments demonstrate the efficacy of our model in detecting objects from both the seen and unseen classes, outperforming the alternative models on Pascal VOC and MSCOCO datasets.

关键词： Analytical models Visualization Semantics Object detection Pattern recognition Task analysis

Consistency Approximation: Incremental Feature Selection Based on Fuzzy Rough Set Theory

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhao, Jie Wu, Daiyang Wu, JiaXin Ye, Wenhao Huang, Faliang Wang, Jiahai See-To, Wing-Kuen Eric Department of Data Science and Business Intelligence Guangdong University of Technology Guangzhou China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong

Fuzzy Rough Set Theory (FRST)-based feature selection has been widely used as a preprocessing step to handle dynamic and large datasets. However, large-scale or high-dimensional datasets remain intractable for FRST-based feature selection approaches due to high space complexity and unsatisfactory classification performance. To overcome these challenges, we propose a Consistency Approximation (CA)-based framework for incremental feature selection. By exploring CA, we introduce a novel significance measure and a tri-accelerator. The CA-based significance measure provides a mechanism for each sample in the universe to keep members with different class labels within its fuzzy neighbourhood as far as possible, while keeping members with the same label as close as possible. Furthermore, our tri-accelerator reduces the search space and decreases the computational space with a theoretical lower bound. The experimental results demonstrate the superiority of our proposed algorithm compared to state-of-the-art methods on efficiency and classification accuracy, especially for large-scale and high-dimensional datasets. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

Divide and contrast: source-free domain adaptation via adaptive contrastive learning 22

学校读者我要写书评

暂无评论

Divide and contrast: source-free domain adaptation via adapt...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Ziyi Zhang Weikai Chen Hui Cheng Zhen Li Siyuan Li Liang Lin Guanbin Li National Key Laboratory of Novel Software Technology Nanjing University Nanjing China Tencent America School of Computer Science and Engineering Sun Yat-sen University Guangzhou China The Chinese University of Hong Kong Shenzhen China and Shenzhen Research Institute of Big Data Shenzhen China AI Lab School of Engineering Westlake University Hangzhou China

ISBN: (纸本)9781713871088

We investigate a practical domain adaptation task, called source-free unsupervised domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages the feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks - the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from the source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the sourcelike domain with the target-specific samples using a memory-based maximum mean discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches.

关键词：

An Improved YOLOv3 Network for PCB Defect Detection

学校读者我要写书评

暂无评论

An Improved YOLOv3 Network for PCB Defect Detection

Chinese Automation Congress (CAC)

作者： Guifang Shao Yuyun Zheng Tiejun Li Jianyi Wu Jincai Luo Fengqiang Gao Jianqi Ma Tundong Liu Xiamen Key Lab. of Big Data Intelligent Analysis and Decision Xiamen University Xiamen China School of Aerospace Engineering Xiamen University Xiamen China School of Information Engineering Jimei University Xiamen China

ISBN: (纸本)9781665426480

Different defects with various features and shapes may appeared in one printed circuit board (PCB), making a great challenge for defect detection. To deal with the contradiction between the speed and accuracy of current deep learning networks, we put forward a MobileNet-YOLOv3 network for PCB defect detection. The MobileNet is introduced to replace the backbone network Darknet-53 of YOLOv3, so as to obtain a lightweight network. Meanwhile, the feature pyramid network (FPN) of YOLOv3 is improved by channel reorganization and downsampling to obtain higher accuracy. Experiments on public data set images with 6 types of defects are conducted, comparative results reveal that the proposed MobileNet-YOLOv3 can achieve higher accuracy than YOLOv3 and YOLOv3-Tiny. According to the frames per second factor compared with YOLOv3-Tiny and YOLOv3, the proposed network is faster than YOLOv3.

关键词： Deep learning Automation Shape Printed circuits Human-robot interaction Feature extraction