用生成对抗网络增强小样本人脸识别，准确率提升12.7%
Facial Recognition Leveraging Generative Adversarial Networks
- 设计残差嵌入生成器缓解梯度消失爆炸问题
- 在LFW上比基线方法提升12.7%识别准确率
- 端到端优化生成与识别，适合数据少的场景
基于深度学习的人脸识别严重依赖大规模训练数据，而实际应用中数据往往难以获取。为解决此问题，本文提出一种基于GAN的数据增强方法，有三项关键贡献：(1) 采用残差嵌入生成器缓解梯度消失/爆炸问题；(2) 使用Inception ResNet-V1结构的FaceNet作为判别器，提升对抗训练效果；(3) 构建端到端框架，联合优化数据生成与识别性能。实验表明，该方法实现稳定训练动态，在LFW基准上相比基线方法识别准确率提升12.7%，且在有限训练样本下仍保持良好泛化能力。
原文摘要 · Abstract (English)
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.
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。