Using Augmented Face Images to Improve Facial Recognition Tasks

2022/05/13 by Shuo Cheng, Cheng, Shuo, Guoxian Song +7
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis #Graphics (cs.GR) #Image Retrieval and Classification Techniques

paper · pdf · doi:10.48550/arxiv.2205.06873

openalex publication_date 2022/05/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a framework that uses GAN-augmented images to complement certain specific attributes, usually underrepresented, for machine learning model training. This allows us to improve inference quality over those attributes for the facial recognition tasks.

Related

• Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy
• Facial Recognition Leveraging Generative Adversarial Networks
• MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias
• SD-GAN: Structural and Denoising GAN reveals facial parts under occlusion
• Analyzing the effectiveness of image augmentations for face recognition\n from limited data