Symmetric Cross Entropy for Robust Learning with Noisy Labels

Abstract

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy labels on some classes ("easy" classes), but more surprisingly, it also suffers from significant under learning on some other classes ("hard" classes). Intuitively, CE requires an extra term to facilitate learning of hard classes, and more importantly, this term should be noise tolerant, so as to avoid overfitting to noisy labels. Inspired by the symmetric KL-divergence, we propose the approach of \textbf{Symmetric cross entropy Learning} (SL), boosting CE symmetrically with a noise robust counterpart Reverse Cross Entropy (RCE). Our proposed SL approach simultaneously addresses both the under learning and overfitting problem of CE in the presence of noisy labels. We provide a theoretical analysis of SL and also empirically show, on a range of benchmark and real-world datasets, that SL outperforms state-of-the-art methods. We also show that SL can be easily incorporated into existing methods in order to further enhance their performance.

arXiv commentICCV2019

References in corpus (5)

• Opening the Black Box of Deep Neural Networks via Information
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Training Convolutional Networks with Noisy Labels
• A Closer Look at Memorization in Deep Networks
• CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise

Cited by in corpus (17)

• Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
• Training Binary Neural Networks through Learning with Noisy Supervision
• Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
• ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
• Confidence Adaptive Regularization for Deep Learning with Noisy Labels
• Deep Learning from Small Amount of Medical Data with Noisy Labels: A Meta-Learning Approach
• Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
• On the Robustness of Monte Carlo Dropout Trained with Noisy Labels
• Analysis and Applications of Class-wise Robustness in Adversarial Training
• Noisy Annotation Refinement for Object Detection
• Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction
• Multiplicative Reweighting for Robust Neural Network Optimization
• Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
• Do We Really Need Gold Samples for Sample Weighting Under Label Noise?
• A Theoretical Analysis of Learning with Noisily Labeled Data
• Exploiting Class Similarity for Machine Learning with Confidence Labels and Projective Loss Functions
• Generalization by Recognizing Confusion