# FMix: Enhancing Mixed Sample Data Augmentation

arXiv: https://arxiv.org/abs/2002.12047 · HTML: https://mlsanity.com/paper/2002.12047/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2020.

## Built on by (most cited first, 11 of 11)

- [ProMix: Combating Label Noise via Maximizing Clean Sample Utility](https://mlsanity.com/paper/2207.10276/) (2022)
- [DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.09600/) (2021)
- [Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning](https://mlsanity.com/paper/2207.00234/) (2022)
- [MiAMix: Enhancing Image Classification through a Multi-stage Augmented Mixed Sample Data Augmentation Method](https://mlsanity.com/paper/2308.02804/) (2023)
- [Nonlinear Transformations Against Unlearnable Datasets](https://mlsanity.com/paper/2406.02883/) (2024)
- [On Data-centric Myths](https://mlsanity.com/paper/2111.11514/) (2021)
- [Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition](https://mlsanity.com/paper/2207.12808/) (2022)
- [Similarity Transfer for Knowledge Distillation](https://mlsanity.com/paper/2103.10047/) (2021)
- [On the Effects of Artificial Data Modification](https://mlsanity.com/paper/2110.13968/) (2021)
- [Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix](https://mlsanity.com/paper/2408.01040/) (2024)
- [On Pitfalls of Measuring Occlusion Robustness through Data Distortion](https://mlsanity.com/paper/2211.13734/) (2022)

## Abstract (arXiv)

Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years, with many successful variants such as MixUp and CutMix. By studying the mutual information between the function learned by a VAE on the original data and on the augmented data we show that MixUp distorts learned functions in a way that CutMix does not. We further demonstrate this by showing that MixUp acts as a form of adversarial training, increasing robustness to attacks such as Deep Fool and Uniform Noise which produce examples similar to those generated by MixUp. We argue that this distortion prevents models from learning about sample specific features in the data, aiding generalisation performance. In contrast, we suggest that CutMix works more like a traditional augmentation, improving performance by preventing memorisation without distorting the data distribution. However, we argue that an MSDA which builds on CutMix to include masks of arbitrary shape, rather than just square, could further prevent memorisation whilst preserving the data distribution in the same way. To this end, we propose FMix, an MSDA that uses random binary masks obtained by applying a threshold to low frequency images sampled from Fourier space. These random masks can take on a wide range of shapes and can be generated for use with one, two, and three dimensional data. FMix improves performance over MixUp and CutMix, without an increase in training time, for a number of models across a range of data sets and problem settings, obtaining a new single model state-of-the-art result on CIFAR-10 without external data. Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further. Code for all experiments is provided at https://github.com/ecs-vlc/FMix .