检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

Tackling Noisy labels with Network Parameter Additive Decomposition

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Incrementally Zero-Shot Detection by an Extreme Value Analyzer

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

SSRN

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

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：

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv3 Network for PCB Defect Detection

An Improved YOLOv3 Network for PCB Defect Detection

引用

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

来源：评论

学校读者我要写书评

暂无评论

Online Container Scheduling for Low-Latency IoT Services in Edge Cluster Upgrade: A Reinforcement Learning Approach

Online Container Scheduling for Low-Latency IoT Services in ...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Hanshuai Cui Zhiqing Tang Jiong Lou Weijia Jia Institute of Artificial Intelligence and Future Networks Beijing Normal University Zhuhai China School of Artificial Intelligence Beijing Normal University Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai China

In Mobile Edge Computing (MEC), Internet of Things (IoT) devices offload computationally-intensive tasks to edge nodes, where they are executed within containers, reducing the reliance on centralized cloud infrastructure. Frequent up-grades are essential to maintain the efficient and secure operation of edge clusters. However, traditional cloud cluster upgrade strategies are ill-suited for edge clusters due to their geographically distributed nature and resource limitations. Therefore, it is crucial to properly schedule containers and upgrade edge clusters to minimize the impact on running tasks. In this paper, we propose a low-latency container scheduling algorithm for edge cluster upgrades. Specifically: 1) We formulate the online container scheduling problem for edge cluster upgrade to minimize the total task latency. 2) We propose a policy gradient-based reinforcement learning algorithm to address this problem, considering the unique characteristics of MEC. 3) Experimental results demonstrate that our algorithm reduces total task latency by approximately 27% compared to baseline algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incremental Feature Selection for Dynamic Incomplete data Using Sub-Tolerance Relation

SSRN

引用

SSRN 2023年

作者： Zhao, Jie Ling, Yun Huang, Faliang Wang, Jiahai See-To, Eric Wing kuen 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

TRS theory is widely used for feature selection with incomplete data. However, the traditional positive region-based measure ignores uncertainty, resulting in redundant features and poor classification accuracy. In addition, the computation of the positive region incurs significant time and space costs. To address these limitations, we extend the tolerance class to a Subrelation Tolerance Class (STC) by decomposing the tolerance relation into two subrelations. STC transforms feature selection into a two-stage certainty measurement by partitioning the universe into certainty and uncertainty regions. By progressively filtering out certain regions, the computational space is reduced. Furthermore, we propose a new significance measure that incorporates both certain and uncertain information. This measure effectively reduces redundant features, resulting in improved computational efficiency and classification accuracy. Using STC and our measure, we develop an incremental feature selection algorithm for dealing with incomplete streaming data, which is validated through extensive experiments and comparisons. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

arXiv

引用

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Toward a comprehensive hypothesis of oxygen-evolution reaction in the presence of iron and gold

引用

Journal of Energy Chemistry 2024年第2期89卷 172-183,I0005页

作者： Negah Hashemi Jafar Hussain Shah Cejun Hu Subhajit Nandy Pavlo Aleshkevych Sumbal Farid Keun Hwa Chae Wei Xie Taifeng Liu Junhu Wang Mohammad Mahdi Najafpour Department of Chemistry Institute for Advanced Studies in Basic Sciences(IASBS)Zanjan 45137-66731Iran Center for Advanced Mössbauer Spectroscopy Mössbauer Effect Data CenterDalian Institute of Chemical PhysicsChinese Academy of SciencesDalian 116023LiaoningChina Key Lab of Advanced Energy Materials Chemistry(Ministry of Education) Renewable Energy Conversion and Storage CenterCollege of ChemistryNankai UniversityTianjin 300071China Advanced Analysis Center Korea Institute of Science and TechnologySeoul 02792Republic of Korea Institute of Physics Polish Academy of SciencesWarsaw 02-668Poland National and Local Joint Engineering Research Center for Applied Technology of Hybrid Nanomaterials Henan UniversityKaifeng 475004HenanChina Center of Climate Change and Global Warming Institute for Advanced Studies in Basic Sciences(IASBS)Zanjan 45137-66731Iran Research Center for Basic Sciences&Modern Technologies(RBST) Institute for Advanced Studies in Basic Sciences(IASBS)Zanjan 45137-66731Iran

This study investigates the effects of Fe on the oxygen-evolution reaction(OER)in the presence of *** distinct areas of OER were identified:the first associated with Fe sites at low overpotential(~330 mV),and the second with Au sites at high overpotential(~870 mV).Various factors such as surface Fe concentration,electrochemical method,scan rate,potential range,concentration,method of adding K_(2)Fe O_(4),nature of Fe,and temperature were varied to observe diverse behaviors during OER for Fe O_(x)H_(y)/*** amounts of Fe ions had a significant impact on OER,reaching a saturation point where the activity did not increase *** electronic interaction between Fe and Au ions was indicated by X-ray photoelectron spectroscopy(XPS)and electron paramagnetic resonance(EPR)*** situ visible spectroscopy confirmed the formation of Fe O_(4)^(2-)during *** situ Mossbauer and surfaceenhanced Raman spectroscopy(SERS)analyses suggest the involvement of Fe-based species as intermediates during the rate-determining step of OER.A lattice OER mechanism based on Fe O_(x)H_(y)was proposed for operation at low *** functional theory(DFT)calculations revealed that Fe oxide,Fe-oxide clusters,and Fe doping on the Au foil exhibited different activities and stabilities during *** study provides insights into the interplay between Fe and Au in OER,advancing the understanding of OER mechanisms and offering implications for the design of efficient electrocatalytic systems.

关键词： DFT calculation Fe/Au electrocatalysis Mechanism Oxygen evolution Water oxidation

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：