An joint end-to-end framework for learning with noisy labels
Authors:
- Qian ZhangQZQian Zhang
- Feifei LeeFLFeifei Lee
- Ya-Gang WangYWYa-Gang Wang
- Damin DingDDDamin Ding
- Wei YaoWYWei Yao
- Lu ChenLCLu Chen
- Qiu ChenQCQiu Chen
- 1 September 2021
- journal article
- research article
- Published by Elsevier in Applied Soft Computing
- Vol. 108
Abstract
No abstract availableKeywords
Funding Information
- Japan Society for the Promotion of Science
- National Natural Science Foundation of China
This publication has 6 references indexed in Scilit:
- New label noise injection methods for the evaluation of noise filtersKnowledge-Based Systems, 2019
- CNC-NOS: Class noise cleaning by ensemble filtering and noise scoringKnowledge-Based Systems, 2018
- Robust Loss Functions under Label Noise for Deep Neural NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Making risk minimization tolerant to label noiseNeurocomputing, 2015
- Design of robust neural network classifiers1998
- Learning From Noisy ExamplesMachine Learning, 1988