AQUAFace: Age-Invariant Quality Adaptive Face Recognition for Unconstrained Selfie vs ID Verification

Face recognition in the presence of age and quality variations poses a formidable challenge. While recent margin-based loss functions have shown promise in addressing these variations individually, real-world scenarios such as selfie versus ID face matching often involve simultaneous variations of both age and quality. In response, we propose a comprehensive framework aimed at mitigating the impact of these variations while preserving vital identity-related information crucial for accurate face recognition. The proposed adaptive margin-based loss function AQUAFace exhibits adaptiveness towards hard samples characterized by significant age and quality variations. This loss function is meticulously designed to prioritize the preservation of identity-related features while simultaneously mitigating the adverse effects of age and quality variations on face recognition accuracy. To validate the effectiveness of our approach, we focus on the specific task of selfie versus ID document matching. Our results demonstrate that AQUAFace effectively handles age and quality differences, leading to enhanced recognition performance. Additionally, we explore the benefits of fine-tuning the recognition model with synthetic data, further boosting performance. As a result, our proposed model, AQUAFace, achieves state-of-the-art performance on six benchmark datasets (CALFW, CPLFW, CFP-FP, AgeDB, IJB-C, and TinyFace), each exhibiting diverse age and quality variations.

Authors

• Shivang Agarwal Indian Institute of Technology, Jodhpur, India
• Jyoti Chaudhary Indian Institute of Technology, Jodhpur, India
• Sadiq Siraj Ebrahim Indian Institute of Technology, Jodhpur, India
• Mayank Vatsa Indian Institute of Technology, Jodhpur, India
• Richa Singh Indian Institute of Technology, Jodhpur, India
• Shyam Prasad Adhikari Swiggy
• Sangeeth Reddy Battu Swiggy

Keywords

No keywords are indexed for this paper.