# Challenges of Adversarial Image Augmentations

arXiv: https://arxiv.org/abs/2111.12427 · HTML: https://mlsanity.com/paper/2111.12427/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 24 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Data Augmentation by Pairing Samples for Images Classification](https://mlsanity.com/paper/1801.02929/) (2018)
- [Faster AutoAugment: Learning Augmentation Strategies using Backpropagation](https://mlsanity.com/paper/1911.06987/) (2019)

## Built on by (most cited first, 4 of 4)

- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification](https://mlsanity.com/paper/2211.16040/) (2022)
- [Homomorphic Self-Supervised Learning](https://mlsanity.com/paper/2211.08282/) (2022)
- [Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts](https://mlsanity.com/paper/2401.11406/) (2024)

## Abstract (arXiv)

Image augmentations applied during training are crucial for the generalization performance of image classifiers. Therefore, a large body of research has focused on finding the optimal augmentation policy for a given task. Yet, RandAugment [2], a simple random augmentation policy, has recently been shown to outperform existing sophisticated policies. Only Adversarial AutoAugment (AdvAA) [11], an approach based on the idea of adversarial training, has shown to be better than RandAugment. In this paper, we show that random augmentations are still competitive compared to an optimal adversarial approach, as well as to simple curricula, and conjecture that the success of AdvAA is due to the stochasticity of the policy controller network, which introduces a mild form of curriculum.