# A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels

arXiv: https://arxiv.org/abs/2208.11176 · HTML: https://mlsanity.com/paper/2208.11176/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 23 Aug 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.06032/) (2019)
- [Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey](https://mlsanity.com/paper/1912.05170/) (2019)
- [Augmentation Strategies for Learning with Noisy Labels](https://mlsanity.com/paper/2103.02130/) (2021)
- [IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters](https://mlsanity.com/paper/1903.12141/) (2019)
- [A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?](https://mlsanity.com/paper/2012.03061/) (2020)
- [Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels](https://mlsanity.com/paper/2012.04193/) (2020)
- [PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels](https://mlsanity.com/paper/2110.11809/) (2021)
- [Photometric Transformer Networks and Label Adjustment for Breast Density Prediction](https://mlsanity.com/paper/1905.02906/) (2019)

## Built on by (most cited first, 3 of 3)

- [Noisy Early Stopping for Noisy Labels](https://mlsanity.com/paper/2409.06830/) (2024)
- [Domain Adaptation via Feature Refinement](https://mlsanity.com/paper/2508.16124/) (2025)
- [Can Domain Generalization be Guaranteed in Small-Sample Learning?](https://mlsanity.com/paper/2609.39512/) (2026)

## Abstract (arXiv)

Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strategies to address this problem, there are few studies that evaluate the impact of data augmentation as a design choice for training deep neural networks. In this work, we analyse the model robustness when using different data augmentations and their improvement on the training with the presence of noisy labels. We evaluate state-of-the-art and classical data augmentation strategies with different levels of synthetic noise for the datasets MNist, CIFAR-10, CIFAR-100, and the real-world dataset Clothing1M. We evaluate the methods using the accuracy metric. Results show that the appropriate selection of data augmentation can drastically improve the model robustness to label noise, increasing up to 177.84% of relative best test accuracy compared to the baseline with no augmentation, and an increase of up to 6% in absolute value with the state-of-the-art DivideMix training strategy.