Facial Recognition Leveraging Generative Adversarial Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhongwen, Li, Zongwei, Li, Xiaoqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917237486518272
author Li, Zhongwen
Li, Zongwei
Li, Xiaoqi
author_facet Li, Zhongwen
Li, Zongwei
Li, Xiaoqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Facial Recognition Leveraging Generative Adversarial Networks
Li, Zhongwen
Li, Zongwei
Li, Xiaoqi
Computer Vision and Pattern Recognition
Cryptography and Security
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.
title Facial Recognition Leveraging Generative Adversarial Networks
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2505.11884