Facial Recognition Leveraging Generative Adversarial Networks
This addresses the problem of data scarcity in face recognition for practical applications, representing an incremental improvement.
The paper tackled the challenge of limited training data for deep learning-based face recognition by proposing a GAN-based data augmentation method, which improved face recognition accuracy by 12.7% on the LFW benchmark compared to baselines.
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.