# SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

arXiv: https://arxiv.org/abs/2012.04846 · HTML: https://mlsanity.com/paper/2012.04846/

## Key facts

- Cited by 56 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 30 of 56)

- [DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2405.14881/) (2024)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps](https://mlsanity.com/paper/2306.16612/) (2023)
- [Human Attention in Fine-grained Classification](https://mlsanity.com/paper/2111.01628/) (2021)
- [Long-Tailed Continual Learning For Visual Food Recognition](https://mlsanity.com/paper/2307.00183/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Adversarial AutoMixup](https://mlsanity.com/paper/2312.11954/) (2023)
- [Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information](https://mlsanity.com/paper/2203.03253/) (2022)
- [RecursiveMix: Mixed Learning with History](https://mlsanity.com/paper/2203.06844/) (2022)
- [An overview of mixing augmentation methods and augmentation strategies](https://mlsanity.com/paper/2107.09887/) (2021)
- [GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing](https://mlsanity.com/paper/2412.02366/) (2024)
- [Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition](https://mlsanity.com/paper/2107.06538/) (2021)
- [SUMix: Mixup with Semantic and Uncertain Information](https://mlsanity.com/paper/2407.07805/) (2024)
- [Improved YOLOv5 network for real-time multi-scale traffic sign detection](https://mlsanity.com/paper/2112.08782/) (2021)
- [Background-Mixed Augmentation for Weakly Supervised Change Detection](https://mlsanity.com/paper/2211.11478/) (2022)
- [Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection](https://mlsanity.com/paper/2407.20078/) (2024)
- [Context-guided Responsible Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2503.10687/) (2025)
- [Local Patch AutoAugment with Multi-Agent Collaboration](https://mlsanity.com/paper/2103.11099/) (2021)
- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation](https://mlsanity.com/paper/2306.03511/) (2023)
- [LUMix: Improving Mixup by Better Modelling Label Uncertainty](https://mlsanity.com/paper/2211.15846/) (2022)
- [Decoupled Data Augmentation for Improving Image Classification](https://mlsanity.com/paper/2411.02592/) (2024)
- [Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization](https://mlsanity.com/paper/2208.01997/) (2022)
- [Regularizing Neural Networks with Meta-Learning Generative Models](https://mlsanity.com/paper/2307.13899/) (2023)
- [Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2306.04893/) (2023)
- [Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN](https://mlsanity.com/paper/2401.13193/) (2024)
- [SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation](https://mlsanity.com/paper/2505.11813/) (2025)

## Abstract (arXiv)

Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in subtle regions, methods along this line are prone to heavy label noise in fine-grained recognition. We propose in this paper a novel scheme, termed as Semantically Proportional Mixing (SnapMix), which exploits class activation map (CAM) to lessen the label noise in augmenting fine-grained data. SnapMix generates the target label for a mixed image by estimating its intrinsic semantic composition, and allows for asymmetric mixing operations and ensures semantic correspondence between synthetic images and target labels. Experiments show that our method consistently outperforms existing mixed-based approaches on various datasets and under different network depths. Furthermore, by incorporating the mid-level features, the proposed SnapMix achieves top-level performance, demonstrating its potential to serve as a solid baseline for fine-grained recognition. Our code is available at https://github.com/Shaoli-Huang/SnapMix.git.