Normalized Loss Functions for Deep Learning with Noisy Labels

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new loss functions have been designed, they are only partially robust. In this paper, we theoretically show by applying a simple normalization that: any loss can be made robust to noisy labels. However, in practice, simply being robust is not sufficient for a loss function to train accurate DNNs. By investigating several robust loss functions, we find that they suffer from a problem of underfitting. To address this, we propose a framework to build robust loss functions called Active Passive Loss (APL). APL combines two robust loss functions that mutually boost each other. Experiments on benchmark datasets demonstrate that the family of new loss functions created by our APL framework can consistently outperform state-of-the-art methods by large margins, especially under large noise rates such as 60% or 80% incorrect labels.

PDF Abstract ICML 2020 PDF

Results from the Paper


Ranked #21 on Image Classification on mini WebVision 1.0 (ImageNet Top-1 Accuracy metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification mini WebVision 1.0 NCE+MAE (ResNet-50) ImageNet Top-1 Accuracy 62.36 # 22
Image Classification mini WebVision 1.0 NCE+RCE (ResNet-50) ImageNet Top-1 Accuracy 62.64 # 21

Methods


No methods listed for this paper. Add relevant methods here