Improving Medical Images Classification With Label Noise Using Dual-Uncertainty Estimation-Reference-Cited by-同舟云学术

Improving Medical Images Classification With Label Noise Using Dual-Uncertainty Estimation

Author:

Ju Lie¹^ORCID,Wang Xin²^ORCID,Wang Lin³^ORCID,Mahapatra Dwarikanath⁴^ORCID,Zhao Xin²,Zhou Quan⁵^ORCID,Liu Tongliang¹^ORCID,Ge Zongyuan¹^ORCID

Affiliation:

1. Faculty of Engineering, Monash University, Melbourne, VIC, Australia

2. Airdoc, Beijing, China

3. Monash Medical AI Group, EResearch Center, Monash University, Melbourne, VIC, Australia

4. Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates

5. National Engineering Research Center of Communications and Networking, Nanjing University of Posts and Telecommunications, Nanjing, China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Science Applications,Radiological and Ultrasound Technology,Software

Link

Reference67 articles.

1. Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels;pham;arXiv 1911 06475,2019

2. Regularizing neural networks by penalizing confident output distributions;pereyra;arXiv 1701 06548,2017

3. Curriculum loss: Robust learning and generalization against label corruption;lyu;arXiv 1905 10045,2019

5. Generalized cross entropy loss for training deep neural networks with noisy labels;zhang;Proc Adv Neural Inf Process Syst,2018

Cited by 44 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