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.
Code (4)
Tasks
Deep LearningImage ClassificationLearning with noisy labelsSimilar Papers 제목 키워드 기반
Active Negative Loss Functions for Learning with Noisy Labels
Robust loss functions are essential for training deep neural networks in the presence of noisy labels. Some robust loss functions use Mean Absolute Error (MAE) as its necessary component. For example, the recently propos…
O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks
This paper proposes a novel noisy label detection approach, named O2U-net, for deep neural networks without human annotations. Different from prior work which requires specifically designed noise-robust loss functions or…
Active LearningLearning with noisy labelsActive Negative Loss: A Robust Framework for Learning with Noisy Labels
Deep supervised learning has achieved remarkable success across a wide range of tasks, yet it remains susceptible to overfitting when confronted with noisy labels. To address this issue, noise-robust loss functions offer…
Image SegmentationLearning with noisy labelsSemantic SegmentationPeer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
Learning with noisy labels is a common challenge in supervised learning. Existing approaches often require practitioners to specify noise rates, i.e., a set of parameters controlling the severity of label noises in the p…
Learning with noisy labelsAsymmetric Loss Functions for Learning with Noisy Labels
Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the sym…
Learning with noisy labels