# DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models

arXiv: https://arxiv.org/abs/2405.14881 · HTML: https://mlsanity.com/paper/2405.14881/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 32 of its 51 references that are in the map.
- First posted on arXiv 5 Apr 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [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)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://mlsanity.com/paper/2112.05135/) (2021)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [TransMix: Attend to Mix for Vision Transformers](https://mlsanity.com/paper/2111.09833/) (2021)
- [DADA: Differentiable Automatic Data Augmentation](https://mlsanity.com/paper/2003.03780/) (2020)
- [SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data](https://mlsanity.com/paper/2012.04846/) (2020)
- [TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers](https://mlsanity.com/paper/2210.07562/) (2022)
- [GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps](https://mlsanity.com/paper/2306.16612/) (2023)
- [You Only Cut Once: Boosting Data Augmentation with a Single Cut](https://mlsanity.com/paper/2201.12078/) (2022)
- [Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?](https://mlsanity.com/paper/2305.12954/) (2023)
- [CamDiff: Camouflage Image Augmentation via Diffusion Model](https://mlsanity.com/paper/2304.05469/) (2023)
- [Adversarial AutoMixup](https://mlsanity.com/paper/2312.11954/) (2023)
- [MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer](https://mlsanity.com/paper/2304.12043/) (2023)
- [IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers](https://mlsanity.com/paper/2310.04780/) (2023)

## Built on by (most cited first, 30 of 78)

- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing](https://mlsanity.com/paper/2412.02366/) (2024)
- [Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification](https://mlsanity.com/paper/2408.16266/) (2024)
- [Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2507.04051/) (2025)
- [Context-guided Responsible Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2503.10687/) (2025)
- [GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain](https://mlsanity.com/paper/2503.22397/) (2025)
- [MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding](https://mlsanity.com/paper/2510.23479/) (2025)
- [Decoupled Data Augmentation for Improving Image Classification](https://mlsanity.com/paper/2411.02592/) (2024)
- [Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2503.17984/) (2025)
- [SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing](https://mlsanity.com/paper/2509.11265/) (2025)
- [MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning](https://mlsanity.com/paper/2504.07288/) (2025)
- [SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation](https://mlsanity.com/paper/2505.11813/) (2025)
- [Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification](https://mlsanity.com/paper/2506.01368/) (2025)
- [FlowComposer: Composable Flows for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2603.16641/) (2026)
- [ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models](https://mlsanity.com/paper/2406.01432/) (2024)
- [CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning](https://mlsanity.com/paper/2410.11963/) (2024)
- [ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions](https://mlsanity.com/paper/2503.09399/) (2025)
- [D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition](https://mlsanity.com/paper/2504.06432/) (2025)
- [Beyond One-Hot Labels: Semantic Mixing for Model Calibration](https://mlsanity.com/paper/2504.13548/) (2025)
- [Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models](https://mlsanity.com/paper/2505.21574/) (2025)
- [Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation](https://mlsanity.com/paper/2506.02294/) (2025)
- [Vehicle-centric Perception via Multimodal Structured Pre-training](https://mlsanity.com/paper/2512.19934/) (2025)
- [On the Difficulty of Learning a Meta-network for Training Data Selection](https://mlsanity.com/paper/2606.00571/) (2026)
- [S2-FracMix: Label-Preserving Self-Saliency Mixup Augmentation](https://mlsanity.com/paper/2606.25784/) (2026)
- [FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2607.02284/) (2026)
- [Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model](https://mlsanity.com/paper/2410.18678/) (2024)
- [Mixup Regularization: A Probabilistic Perspective](https://mlsanity.com/paper/2502.13825/) (2025)
- [Narrowing Class-Wise Robustness Gaps in Adversarial Training](https://mlsanity.com/paper/2503.16179/) (2025)
- [ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis](https://mlsanity.com/paper/2505.04963/) (2025)
- [A Flat Minima Perspective on Understanding Augmentations and Model Robustness](https://mlsanity.com/paper/2505.24592/) (2025)

## Abstract (arXiv)

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an augmented image. Such methods may not only omit important portions of the input images but also introduce label ambiguities by mixing images across labels resulting in misleading supervisory signals. To address these limitations, we propose DiffuseMix, a novel data augmentation technique that leverages a diffusion model to reshape training images, supervised by our bespoke conditional prompts. First, concatenation of a partial natural image and its generated counterpart is obtained which helps in avoiding the generation of unrealistic images or label ambiguities. Then, to enhance resilience against adversarial attacks and improves safety measures, a randomly selected structural pattern from a set of fractal images is blended into the concatenated image to form the final augmented image for training. Our empirical results on seven different datasets reveal that DiffuseMix achieves superior performance compared to existing state-of the-art methods on tasks including general classification,fine-grained classification, fine-tuning, data scarcity, and adversarial robustness. Augmented datasets and codes are available here: https://diffusemix.github.io/