Cooperative Learning for Noisy Supervision
| Autor: | Ya Zhang, Jiangchao Yao, Hao Wu, Yanfeng Wang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Cooperative learning
FOS: Computer and information sciences Computer Science - Machine Learning business.industry Computer science Deep learning DUAL (cognitive architecture) Machine learning computer.software_genre Machine Learning (cs.LG) Range (mathematics) Minification Artificial intelligence business computer |
| DOI: | 10.48550/arxiv.2108.05092 |
| Popis: | Learning with noisy labels has gained the enormous interest in the robust deep learning area. Recent studies have empirically disclosed that utilizing dual networks can enhance the performance of single network but without theoretic proof. In this paper, we propose Cooperative Learning (CooL) framework for noisy supervision that analytically explains the effects of leveraging dual or multiple networks. Specifically, the simple but efficient combination in CooL yields a more reliable risk minimization for unseen clean data. A range of experiments have been conducted on several benchmarks with both synthetic and real-world settings. Extensive results indicate that CooL outperforms several state-of-the-art methods. Comment: ICME 2021 Oral |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|