Robust Loss Functions under Label Noise for Deep Neural Networks

Abstract

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate approach would be to look for loss functions that are inherently noise-tolerant. For binary classification there exist theoretical results on loss functions that are robust to label noise. In this paper, we provide some sufficient conditions on a loss function so that risk minimization under that loss function would be inherently tolerant to label noise for multiclass classification problems. These results generalize the existing results on noise-tolerant loss functions for binary classification. We study some of the widely used loss functions in deep networks and show that the loss function based on mean absolute value of error is inherently robust to label noise. Thus standard back propagation is enough to learn the true classifier even under label noise. Through experiments, we illustrate the robustness of risk minimization with such loss functions for learning neural networks.

Appeared in AAAI 2017

References in corpus (1)

• Training Convolutional Networks with Noisy Labels

Cited by in corpus (12)

• Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
• QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction
• Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
• Contrastive Learning Improves Model Robustness Under Label Noise
• From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
• Weakly Supervised Learning with Side Information for Noisy Labeled Images
• On the Robustness of Monte Carlo Dropout Trained with Noisy Labels
• Detecting and Tracking Communal Bird Roosts in Weather Radar Data
• Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correction
• Towards Robust Pattern Recognition: A Review
• Do We Really Need Gold Samples for Sample Weighting Under Label Noise?
• Mixing between the Cross Entropy and the Expectation Loss Terms