从嘈杂的标签中学习的朋友和敌人
Friends and Foes in Learning from Noisy Labels
摘要：
最近，从带有噪声标签的示例中学习引起了越来越多的关注。但是，本文将表明，常用的CIFAR为基础的数据集和准确性评估指标在文献中使用的都是不合适的，在这种情况下。本文提出了一种替代的有效的评估指标和新的数据集，以促进适当的研究和评估在这一领域。然后，从已有的方法中识别出友方和敌方，分别作为对噪声标记样本的深度学习有益或有害的技术组件，并对友方类别中的技术组件进行改进和组合，包括自监督学习、新的预热策略、实例过滤和标记校正。由此产生的F&F方法在建议的nCIFAR数据集和真实世界的Clothing1M数据集上的性能显着优于现有方法。
英文摘要：
Learning from examples with noisy labels has attracted increasing attention recently. But, this paper will show that the commonly used CIFAR-based datasets and the accuracy evaluation metric used in the literature are both inappropriate in this context. An alternative valid evaluation metric and new datasets are proposed in this paper to promote proper research and evaluation in this area. Then, friends and foes are identified from existing methods as technical components that are either beneficial or detrimental to deep learning from noisy labeled examples, respectively, and this paper improves and combines technical components from the friends category, including self-supervised learning, new warmup strategy, instance filtering and label correction. The resulting F&F method significantly outperforms existing methods on the proposed nCIFAR datasets and the real-world Clothing1M dataset.
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。
