Augmentation Strategies for Learning with Noisy Labels
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8018-8027
Abstract
Imperfect labels are ubiquitous in real-world datasets. Several recent successful methods for training deep neural networks (DNNs) robust to label noise have used two primary techniques: filtering samples based on loss during a warm-up phase to curate an initial set of cleanly labeled samples, and using the output of a network as a pseudo-label for subsequent loss calculations. In this paper, we evaluate different augmentation strategies for algorithms tackling the "learning with noisy labels" problem. We propose and examine multiple augmentation strategies and evaluate them using synthetic datasets based on CIFAR-10 and CIFAR-100, as well as on the real-world dataset Clothing1M. Due to several commonalities in these algorithms, we find that using one set of augmentations for loss modeling tasks and another set for learning is the most effective, improving results on the state-of-the-art and other previous methods. Furthermore, we find that applying augmentation during the warm-up period can negatively impact the loss convergence behavior of correctly versus incorrectly labeled samples. We introduce this augmentation strategy to the state-of-the-art technique and demonstrate that we can improve performance across all evaluated noise levels. In particular, we improve accuracy on the CIFAR-10 benchmark at 90% symmetric noise by more than 15% in absolute accuracy, and we also improve performance on the Clothing1M dataset.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Self-Training With Noisy Student Improves ImageNet Classification2020
- Randaugment: Practical automated data augmentation with a reduced search space2020
- Probabilistic End-To-End Noise Correction for Learning With Noisy Labels2019
- MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition2019
- AutoAugment: Learning Augmentation Strategies From Data2019
- Learning to Learn From Noisy Labeled Data2019
- Joint Optimization Framework for Learning with Noisy Labels2018
- Smooth Neighbors on Teacher Graphs for Semi-Supervised Learning2018
- Focal Loss for Dense Object Detection2017
- Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach2017