Abstract
Face recognition performance based on deep learning heavily relies on large-scale training data, which is often difficult to acquire in practical applications. To address this challenge, this paper proposes a GAN-based data augmentation method with three key contributions: (1) a residual-embedded generator to alleviate gradient vanishing/exploding problems, (2) an Inception ResNet-V1 based FaceNet discriminator for improved adversarial training, and (3) an end-to-end framework that jointly optimizes data generation and recognition performance. Experimental results demonstrate that our approach achieves stable training dynamics and significantly improves face recognition accuracy by 12.7% on the LFW benchmark compared to baseline methods, while maintaining good generalization capability with limited training samples.
Abstract (translated)
基于深度学习的面部识别性能很大程度上依赖于大规模训练数据，而这些数据在实际应用中往往难以获得。为了解决这一挑战，本文提出了一种基于生成对抗网络（GAN）的数据增强方法，该方法有三个关键贡献：(1) 嵌入残差的生成器以缓解梯度消失和爆炸问题；(2) 一个基于Inception ResNet-V1的FaceNet判别器，用于改进对抗训练；(3) 一种端到端框架，它同时优化数据生成和识别性能。实验结果表明，我们的方法实现了稳定的训练动力学，并且在LFW基准测试上相比基线方法将面部识别准确率提高了12.7%，同时还保持了在有限样本下的良好泛化能力。
URL
https://arxiv.org/abs/2505.11884
