Kim, Minsoo Nam, Gi Pyo Kim, Haksub Park, Haesol Kim, Ig-Jae 2025-05-22T06:01:29Z 2025-05-22T06:01:29Z 2025-05-21 2025-04 https://pubs.kist.re.kr/handle/201004/152479 In the realm of face image quality assessment (FIQA), methods based on sample relative classification have shown impressive performance. However, the quality scores used as pseudo-labels assigned from images of classes with low intra-class variance could be unrelated to the actual quality in such methods. To address this issue, we present intra-class variance guidance for FIQA (IG-FIQA), a novel approach to guide FIQA training, introducing a weight parameter to alleviate the adverse impact of these classes. This method involves estimating sample intra-class variance at each iteration during training, ensuring minimal computational overhead and straightforward implementation. Furthermore, this paper proposes an on-the-fly data augmentation methodology for improved generalization performance in FIQA. Across various benchmark datasets, our proposed method, IG-FIQA, achieved notable accuracy improvements compared to conventional state-of-the-art (SOTA) FIQA methods and ensures stable performance in face recognition systems. English Institute of Electrical and Electronics Engineers Inc. IG-FIQA: Improving Classifiability-Based Face Image Quality Assessment Through Intra-Class Variance Guidance Article 10.1109/ACCESS.2025.3562654 1 IEEE Access, v.13, pp.73987 - 73998 IEEE Access 13 73987 73998 Y scie scopus 001480472500041 2-s2.0-105003494803 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article Image quality Prototypes Data augmentation Faces Computational modeling Benchmark testing Artificial neural networks Accuracy face image quality assessment image processing pattern recognition Training Face recognition