Cooperative Learning for Noisy Supervision
This work addresses the challenge of noisy supervision in robust deep learning, providing a theoretical foundation for multi-network approaches, though it appears incremental as it builds on existing empirical findings.
The paper tackles the problem of learning with noisy labels by proposing the Cooperative Learning (CooL) framework, which analytically explains the benefits of using dual or multiple networks and achieves superior performance on benchmarks with synthetic and real-world noisy data.
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.