Learning from Better Supervision: Self-distillation for Learning with Noisy Labels-Reference-Cited by-同舟云学术

Learning from Better Supervision: Self-distillation for Learning with Noisy Labels

Published:2022-08-21 Issue: Volume: Page:
ISSN:
Container-title:2022 26th International Conference on Pattern Recognition (ICPR)
language:
Short-container-title:

Author:

Baek Kyungjune¹,Lee Seungho¹,Shim Hyunjung²

Affiliation:

1. Yonsei University,School of Integrated Technology

2. Korea Advanced Institue of Science and Technology,Kim Jaechul Graduate School of AI

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9956007/9955631/09956388.pdf?arnumber=9956388

Reference37 articles.

1. Learning from massive noisy labeled data for image classification;xiao;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015

2. mixup: Beyond empirical risk minimization;zhang;ICLRE,2018

3. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels;jiang;International Conference on Machine Learning,2018

4. Dimensionality-driven learning with noisy labels;ma;International Conference on Machine Learning,2018

5. MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition

Cited by 3 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. Towards Robust Learning with Noisy and Pseudo Labels for Text Classification;Information Sciences;2024-03

2. GEIKD: Self-knowledge distillation based on gated ensemble networks and influences-based label noise removal;Computer Vision and Image Understanding;2023-10

3. Rank-Aware Negative Training for Semi-Supervised Text Classification;Transactions of the Association for Computational Linguistics;2023