SELF: Learning to Filter Noisy Labels with Self-Ensembling

Abstract

Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to progressively filter out the wrong labels during training. Our method improves the task performance by gradually allowing supervision only from the potentially non-noisy (clean) labels and stops learning on the filtered noisy labels. For the filtering, we form running averages of predictions over the entire training dataset using the network output at different training epochs. We show that these ensemble estimates yield more accurate identification of inconsistent predictions throughout training than the single estimates of the network at the most recent training epoch. While filtered samples are removed entirely from the supervised training loss, we dynamically leverage them via semi-supervised learning in the unsupervised loss. We demonstrate the positive effect of such an approach on various image classification tasks under both symmetric and asymmetric label noise and at different noise ratios. It substantially outperforms all previous works on noise-aware learning across different datasets and can be applied to a broad set of network architectures.

References in corpus (12)

• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Temporal Ensembling for Semi-Supervised Learning
• Learning to Reweight Examples for Robust Deep Learning
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
• Deep Learning is Robust to Massive Label Noise
• Shake-Shake regularization
• Combating Label Noise in Deep Learning Using Abstention
• Iterative Learning with Open-set Noisy Labels
• Auxiliary Image Regularization for Deep CNNs with Noisy Labels

Cited by in corpus (14)

• Co-learning: Learning from Noisy Labels with Self-supervision
• Active label cleaning for improved dataset quality under resource constraints
• Self-Adaptive Training: beyond Empirical Risk Minimization
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
• Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
• Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
• Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
• DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis
• MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
• On the Robustness of Monte Carlo Dropout Trained with Noisy Labels
• Scribble2Label: Scribble-Supervised Cell Segmentation via Self-Generating Pseudo-Labels with Consistency
• Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correction
• Robust Collaborative Learning with Noisy Labels