# A data-centric approach to class-specific bias in image data augmentation

arXiv: https://arxiv.org/abs/2403.04120 · HTML: https://mlsanity.com/paper/2403.04120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [The Effects of Regularization and Data Augmentation are Class Dependent](https://mlsanity.com/paper/2204.03632/) (2022)

## Built on by (most cited first, 2 of 2)

- [Error-driven Data-efficient Large Multimodal Model Tuning](https://mlsanity.com/paper/2412.15652/) (2024)
- [ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification](https://mlsanity.com/paper/2510.17650/) (2025)

## Abstract (arXiv)

Data augmentation (DA) enhances model generalization in computer vision but may introduce biases, impacting class accuracy unevenly. Our study extends this inquiry, examining DA's class-specific bias across various datasets, including those distinct from ImageNet, through random cropping. We evaluated this phenomenon with ResNet50, EfficientNetV2S, and SWIN ViT, discovering that while residual models showed similar bias effects, Vision Transformers exhibited greater robustness or altered dynamics. This suggests a nuanced approach to model selection, emphasizing bias mitigation. We also refined a "data augmentation robustness scouting" method to manage DA-induced biases more efficiently, reducing computational demands significantly (training 112 models instead of 1860; a reduction of factor 16.2) while still capturing essential bias trends.