Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
arXiv:1903.07788
Abstract
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously and accuracies drop dramatically. To address this problem, we propose an end-to-end framework called PENCIL, which can update both network parameters and label estimations as label distributions. PENCIL is independent of the backbone network structure and does not need an auxiliary clean dataset or prior information about noise, thus it is more general and robust than existing methods and is easy to apply. PENCIL outperforms previous state-of-the-art methods by large margins on both synthetic and real-world datasets with different noise types and noise rates. Experiments show that PENCIL is robust on clean datasets, too.
arXiv commentCVPR 2019
References in corpus (3)
Cited by in corpus (14)
- DivideMix: Learning with Noisy Labels as Semi-supervised Learning
- Combating noisy labels by agreement: A joint training method with co-regularization
- Label Noise Types and Their Effects on Deep Learning
- MoPro: Webly Supervised Learning with Momentum Prototypes
- Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
- Combining Self-Supervised and Supervised Learning with Noisy Labels
- Boosting Co-teaching with Compression Regularization for Label Noise
- Multi-Class Classification from Noisy-Similarity-Labeled Data
- Semi-supervised Learning for Few-shot Image-to-Image Translation
- Network Cooperation with Progressive Disambiguation for Partial Label Learning
- Reliable Label Bootstrapping for Semi-Supervised Learning
- A Tale Of Two Long Tails
- Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
- Do We Really Need Gold Samples for Sample Weighting Under Label Noise?