# MiAMix: Enhancing Image Classification through a Multi-stage Augmented Mixed Sample Data Augmentation Method

arXiv: https://arxiv.org/abs/2308.02804 · HTML: https://mlsanity.com/paper/2308.02804/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [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)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [A Unified Sequence Interface for Vision Tasks](https://mlsanity.com/paper/2206.07669/) (2022)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective](https://mlsanity.com/paper/2208.09913/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning](https://mlsanity.com/paper/2209.04851/) (2022)
- [FMix: Enhancing Mixed Sample Data Augmentation](https://mlsanity.com/paper/2002.12047/) (2020)
- [RandoMix: A mixed sample data augmentation method with multiple mixed modes](https://mlsanity.com/paper/2205.08728/) (2022)

## Built on by (most cited first, 8 of 8)

- [DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2405.14881/) (2024)
- [GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing](https://mlsanity.com/paper/2412.02366/) (2024)
- [Image compositing is all you need for data augmentation](https://mlsanity.com/paper/2502.13936/) (2025)
- [Cross-Attribute Matrix Factorization Model with Shared User Embedding](https://mlsanity.com/paper/2308.07284/) (2023)
- [Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection](https://mlsanity.com/paper/2311.18332/) (2023)
- [GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction](https://mlsanity.com/paper/2606.02498/) (2026)
- [AlphaZero Gomoku](https://mlsanity.com/paper/2309.01294/) (2023)
- [BPDec: Unveiling the Potential of Masked Language Modeling Decoder in BERT pretraining](https://mlsanity.com/paper/2401.15861/) (2024)

## Abstract (arXiv)

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various computer vision tasks. While various strategies have been proposed, Mixed Sample Data Augmentation (MSDA) has shown great potential for enhancing model performance and generalization. We introduce a novel mixup method called MiAMix, which stands for Multi-stage Augmented Mixup. MiAMix integrates image augmentation into the mixup framework, utilizes multiple diversified mixing methods concurrently, and improves the mixing method by randomly selecting mixing mask augmentation methods. Recent methods utilize saliency information and the MiAMix is designed for computational efficiency as well, reducing additional overhead and offering easy integration into existing training pipelines. We comprehensively evaluate MiaMix using four image benchmarks and pitting it against current state-of-the-art mixed sample data augmentation techniques to demonstrate that MIAMix improves performance without heavy computational overhead.