# ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition

arXiv: https://arxiv.org/abs/2506.10226 · HTML: https://mlsanity.com/paper/2506.10226/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)
- Synthetic data and self-improvement for LLMs / [Model collapse from synthetic data](https://mlsanity.com/synth/model-collapse-from-synthetic-data/)

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [Low-Resolution Face Recognition](https://mlsanity.com/paper/1811.08965/) (2018)
- [Dataset Enhancement with Instance-Level Augmentations](https://mlsanity.com/paper/2406.08249/) (2024)
- [ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition](https://mlsanity.com/paper/2409.17576/) (2024)
- [Mechanisms of Projective Composition of Diffusion Models](https://mlsanity.com/paper/2502.04549/) (2025)
- [How to Boost Face Recognition with StyleGAN?](https://mlsanity.com/paper/2210.10090/) (2022)
- [VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition](https://mlsanity.com/paper/2412.06235/) (2024)
- [Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups](https://mlsanity.com/paper/2309.08442/) (2023)
- [Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognition](https://mlsanity.com/paper/2407.07627/) (2024)

## Abstract (arXiv)

Synthetic data generation is increasingly used in machine learning for training and data augmentation. Yet, current strategies often rely on external foundation models or datasets, whose usage is restricted in many scenarios due to policy or legal constraints. We propose ScoreMix, a self-contained synthetic generation method to produce hard synthetic samples for recognition tasks by leveraging the score compositionality of diffusion models. The approach mixes class-conditioned scores along reverse diffusion trajectories, yielding domain-specific data augmentation without external resources. We systematically study class-selection strategies and find that mixing classes distant in the discriminator's embedding space yields larger gains, providing up to 3% additional average improvement, compared to selection based on proximity. Interestingly, we observe that condition and embedding spaces are largely uncorrelated under standard alignment metrics, and the generator's condition space has a negligible effect on downstream performance. Across 8 public face recognition benchmarks, ScoreMix improves accuracy by up to 7 percentage points, without hyperparameter search, highlighting both robustness and practicality. Our method provides a simple yet effective way to maximize discriminator performance using only the available dataset, without reliance on third-party resources. Paper website: https://parsa-ra.github.io/scoremix/.