SigCo: Eliminate the inter-class competition via sigmoid for learning with noisy labels
Authors:
- Ang ChenACAng Chen
- Feng XuFXFeng Xu
- Tao ZengTZTao Zeng
- Xin LyuXLXin Lyu
- Xin LiXLXin Li
- 19 March 2024
- journal article
- research article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 294
Abstract
No abstract availableKeywords
This publication has 30 references indexed in Scilit:
- ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised LearningPattern Recognition, 2022
- LongReMix: Robust learning with high confidence samples in a noisy label environmentPattern Recognition, 2022
- Self-Training With Noisy Student Improves ImageNet Classification2020
- Probabilistic End-To-End Noise Correction for Learning With Noisy Labels2019
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images2018
- Learning with Biased Complementary Labels2018
- Joint Optimization Framework for Learning with Noisy Labels2018
- CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise2018
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016