Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.11544 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911228656353280 |
|---|---|
| author | Rahimi, Parsa Teney, Damien Marcel, Sebastien |
| author_facet | Rahimi, Parsa Teney, Damien Marcel, Sebastien |
| contents | The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Synthetic data generation offers a promising alternative; however, most existing methods depend heavily on external datasets or pre-trained models, increasing complexity and resource demands. In this paper, we introduce AugGen, a self-contained synthetic augmentation technique. AugGen strategically samples from a class-conditional generative model trained exclusively on the target FR dataset, eliminating the need for external resources. Evaluated across 8 FR benchmarks, including IJB-C and IJB-B, our method achieves 1-12% performance improvements, outperforming models trained solely on real data and surpassing state-of-the-art synthetic data generation approaches, while using less real data. Notably, these gains often exceed those from architectural enhancements, underscoring the value of synthetic augmentation in data-limited scenarios. Our findings demonstrate that carefully integrated synthetic data can both mitigate privacy constraints and substantially enhance recognition performance. Paper website: https://parsa-ra.github.io/auggen/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11544 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition Rahimi, Parsa Teney, Damien Marcel, Sebastien Computer Vision and Pattern Recognition The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Synthetic data generation offers a promising alternative; however, most existing methods depend heavily on external datasets or pre-trained models, increasing complexity and resource demands. In this paper, we introduce AugGen, a self-contained synthetic augmentation technique. AugGen strategically samples from a class-conditional generative model trained exclusively on the target FR dataset, eliminating the need for external resources. Evaluated across 8 FR benchmarks, including IJB-C and IJB-B, our method achieves 1-12% performance improvements, outperforming models trained solely on real data and surpassing state-of-the-art synthetic data generation approaches, while using less real data. Notably, these gains often exceed those from architectural enhancements, underscoring the value of synthetic augmentation in data-limited scenarios. Our findings demonstrate that carefully integrated synthetic data can both mitigate privacy constraints and substantially enhance recognition performance. Paper website: https://parsa-ra.github.io/auggen/. |
| title | AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.11544 |