用扩散模型生成合成数据，提升人脸识别性能且无需外部资源
AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition
- 基于目标数据集自训练的条件扩散模型生成合成样本
- 8个基准上提升1-12%，部分超越架构改进效果
- 适合数据少、隐私敏感场景下的模型增强
机器学习对大规模数据集的依赖带来显著的隐私与伦理挑战，尤其在人脸识别等敏感领域。合成数据生成提供了有前景的替代方案，但现有方法多依赖外部数据集或预训练模型，增加复杂性和资源开销。本文提出AugGen，一种自包含的合成增强技术。AugGen从仅在目标人脸识别数据集上训练的类别条件生成模型中策略性采样，无需外部资源。在包括IJB-C和IJB-B在内的8个人脸识别基准上评估，该方法实现1%-12%的性能提升，优于仅使用真实数据训练的模型，并超过当前最优的合成数据生成方法，同时使用的真数据更少。值得注意的是，这些增益常高于架构改进带来的提升，凸显了合成增强在数据受限场景中的价值。研究结果表明，精心集成的合成数据既能缓解隐私约束，又能显著提升识别性能。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。