Student Loss: Towards the Probability Assumption in Inaccurate Supervision-Reference-Cited by-同舟云学术

Student Loss: Towards the Probability Assumption in Inaccurate Supervision

Published:2024-06 Issue:6 Volume:46 Page:4460-4475
ISSN:0162-8828
Container-title:IEEE Transactions on Pattern Analysis and Machine Intelligence
language:
Short-container-title:IEEE Trans. Pattern Anal. Mach. Intell.

Author:

Zhang Shuo¹^ORCID,Li Jian-Qing²^ORCID,Fujita Hamido³^ORCID,Li Yu-Wen²^ORCID,Wang Deng-Bao⁴^ORCID,Zhu Ting-Ting⁵^ORCID,Zhang Min-Ling⁴^ORCID,Liu Cheng-Yu²^ORCID

Affiliation:

1. School of Instrument Science and Engineering, the State Key Laboratory of Digital Medical Engineering, the School of Biological Science and Medical Engineering, Southeast University, Nanjing, China

2. State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China

3. Malaysia-Japan International Institute of Technology (MJIIT), Universiti Teknologi, Kuala Lumpur, Malaysia

4. School of Computer Science and Engineering, Southeast University, Nanjing, China

5. Department of Engineering Science, University of Oxford, Oxford, U.K.

Funder

National Natural Science Foundation of China

Royal Society

National Key Research and Development Program of China

Natural Science Foundation of Jiangsu Province

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/34/10522060/10412669.pdf?arnumber=10412669

Reference68 articles.

1. Pervasive label errors in test sets destabilize machine learning benchmarks;Northcutt,2021

2. A brief introduction to weakly supervised learning

3. Webly Supervised Learning of Convolutional Networks

4. Training convolutional networks with noisy labels;Sukhbaatar

5. Dropout: A simple way to prevent neural networks from overfitting;Srivastava;J. Mach. Learn. Res.,2014