Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
Author:
Affiliation:
1. Xidian University
2. The University of Sydney,TML Lab
3. Hong Kong Baptist University
4. RIKEN
5. Chongqing University of Posts and Telecommunications
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
Australian Research Council
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09878933.pdf?arnumber=9878933
Reference55 articles.
1. Joint Optimization Framework for Learning with Noisy Labels
2. Learning SVMs from Sloppily Labeled Data
3. Training deep neural networks on noisy labels with bootstrapping;reed;ArXiv Preprint,2014
4. Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach
5. Loss factorization, weakly supervised learning and label noise robustness;patrini;International Conference on Machine Learning,0
Cited by 26 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Unsupervised domain adaptation with weak source domain labels via bidirectional subdomain alignment;Neural Networks;2024-10
2. Noise‐robust neural networks for medical image segmentation by dual‐strategy sample selection;Concurrency and Computation: Practice and Experience;2024-08-26
3. Tackling Instance-Dependent Label Noise with Class Rebalance and Geometric Regularization;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24
4. A survey of label-noise deep learning for medical image analysis;Medical Image Analysis;2024-07
5. Confidence Calibration of a Medical Imaging Classification System That is Robust to Label Noise;IEEE Transactions on Medical Imaging;2024-06
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3