通过优化人脸嵌入球面分布，生成高多样性的合成人脸识别数据集。
HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
- 在人脸嵌入的超球面上建模数据集生成为打包优化问题
- 用梯度下降优化嵌入分布，再通过条件生成模型合成图像
- 生成数据训练模型达当前合成数据最佳性能，适合隐私敏感场景
人脸识别数据集通常通过网络爬取获取，缺乏个体同意，引发伦理与隐私担忧。利用合成数据训练人脸识别模型成为有前景的替代方案。然而，合成数据生成仍具挑战，需兼顾类间与类内多样性。尽管生成模型已能有效提升类内变化（如姿态、光照等），类间差异的生成仍困难。本文将数据集生成建模为人脸识别模型嵌入空间（超球面）上的打包问题，提出新方法HyperFace。将打包问题形式化为优化问题，并采用基于梯度下降的方法求解。随后使用条件人脸生成模型从优化后的嵌入中合成图像。利用生成数据训练人脸识别模型，并在多个基准真实数据集上评估。实验结果表明，使用HyperFace生成的数据训练的模型，在合成数据训练中达到最先进水平。
原文摘要 · Abstract (English)
Face recognition datasets are often collected by crawling Internet and without individuals' consents, raising ethical and privacy concerns. Generating synthetic datasets for training face recognition models has emerged as a promising alternative. However, the generation of synthetic datasets remains challenging as it entails adequate inter-class and intra-class variations. While advances in generative models have made it easier to increase intra-class variations in face datasets (such as pose, illumination, etc.), generating sufficient inter-class variation is still a difficult task. In this paper, we formulate the dataset generation as a packing problem on the embedding space (represented on a hypersphere) of a face recognition model and propose a new synthetic dataset generation approach, called HyperFace. We formalize our packing problem as an optimization problem and solve it with a gradient descent-based approach. Then, we use a conditional face generator model to synthesize face images from the optimized embeddings. We use our generated datasets to train face recognition models and evaluate the trained models on several benchmarking real datasets. Our experimental results show that models trained with HyperFace achieve state-of-the-art performance in training face recognition using synthetic datasets.
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。