UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning-Reference-Cited by-同舟云学术

UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Karim Nazmul¹,Rizve Mamshad Nayeem²,Rahnavard Nazanin¹,Mian Ajmal³,Shah Mubarak²

Affiliation:

1. UCF,Department of Electrical and Computer Engineering,USA

2. UCF,Center for Research in Computer Vision,USA

3. UWA,Department of Computer Science and Software Engineering,Australia

Funder

National Science Foundation

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09880390.pdf?arnumber=9880390

Reference72 articles.

1. Meta Label Correction for Noisy Label Learning

2. Generalized cross entropy loss for training deep neural networks with noisy labels;zhang;32nd Conference on Neural Information Processing Systems (NeurIPS),0

3. Learning with feature-dependent label noise: A progressive approach;zhang;ArXiv Preprint,2021

4. Multi-Objective Interpolation Training for Robustness to Label Noise

5. Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation

Cited by 63 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. Mitigating data imbalance and noise: A divergence-based approach with enhanced sample selection;Neurocomputing;2024-11

2. SV-Learner: Support-Vector Contrastive Learning for Robust Learning With Noisy Labels;IEEE Transactions on Knowledge and Data Engineering;2024-10

3. Learning with noisy labels via clean-aware sharpness-aware minimization;2024-09-14

4. Cross-to-merge training with class balance strategy for learning with noisy labels;Expert Systems with Applications;2024-09

5. ECLB: Efficient contrastive learning on bi-level for noisy labels;Knowledge-Based Systems;2024-09