arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.05092cs.LG
收藏

噪声环境下的协作学习

Cooperative Learning for Noisy Supervision

Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

Hao Wu, Jiangchao Yao, Ya Zhang, Yanfeng Wang

摘要:

带噪声标签的学习在鲁棒深度学习领域引起了极大的兴趣。近年来的研究经验性地揭示了利用双网络可以提高单网络的性能,但没有理论证明。在本文中,我们提出了协作学习(CooL)框架的噪声监督,分析解释了利用双或多个网络的影响。具体而言,CooL中简单但有效的组合为看不见的干净数据产生了更可靠的风险最小化。一系列的实验已经进行了几个基准与合成和现实世界的设置。广泛的结果表明,CooL优于几个国家的最先进的方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑