Robust Temporal Ensembling for Learning with Noisy Labels
Successful training of deep neural networks with noisy labels is an essential capability as most real-world datasets contain some amount of mislabeled data. Left unmitigated, label noise can sharply degrade typical supervised learning approaches. In this paper, we present robust temporal ensembling (RTE), which combines robust loss with semi-supervised regularization methods to achieve noise-robust learning. We demonstrate that RTE achieves state-of-the-art performance across the CIFAR-10, CIFAR-100, ImageNet, WebVision, and Food-101N datasets, while forgoing the recent trend of label filtering and/or fixing. Finally, we show that RTE also retains competitive corruption robustness to unforeseen input noise using CIFAR-10-C, obtaining a mean corruption error (mCE) of 13.50% even in the presence of an 80% noise ratio, versus 26.9% mCE with standard methods on clean data.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationLearning with noisy labelsRTESimilar Papers 제목 키워드 기반
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, an…
Semi-Supervised Image ClassificationSemi-Supervised RGBD Semantic SegmentationSemi-Supervised Semantic SegmentationSource Free Object DetectionRobust Temporal Ensembling
Successful training of deep neural networks with noisy labels is an essential capability as most real-world datasets contain some amount of mislabeled data. Left unmitigated, label noise can sharply degrade typical supe…
RTERobust Learning of Diffusion Models with Extremely Noisy Conditions
Conditional diffusion models have the generative controllability by incorporating external conditions. However, their performance significantly degrades with noisy conditions, such as corrupted labels in the image genera…
Conditional Image GenerationSELF: Learning to Filter Noisy Labels with Self-Ensembling
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 filter…
image-classificationImage ClassificationSelf-LearningTemporal Ensembling for Semi-Supervised Learning
In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a…
General ClassificationSemi-Supervised Image Classification