G-FAN: Graph-Based Feature Aggregation Network for Video Face Recognition

• Published in: 2020 25th International Conference on Pattern Recognition (ICPR) pp. 1672 - 1678
• Main Authors: Zhao, He, Shi, Yongjie, Tong, Xin, Wen, Jingsi, Ying, Xianghua, Zha, Hongbin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.01.2021
• Subjects: Aggregates; Benchmark testing; Correlation; Face recognition; Feature extraction; Memory management; Predictive models
• DOI: 10.1109/ICPR48806.2021.9413081

In this paper, we propose a graph-based feature aggregation network (G-FAN) for video face recognition. Compared with the still image, video face recognition exhibits great challenges due to huge intra-class variability and high interclass ambiguity. To address this problem, our G-FAN first uses a Convolutional Neural Network to extract deep features for every input face of a subject. Then, we build an affinity graph based on the relationship between facial features and apply Graph Convolutional Network to generate fine-grained quality vectors for each frame. Finally, the features among multiple frames are adaptively aggregated into a discriminative vector to represent a video face. Different from previous works that take a single image as input, our G-FAN could utilize the correlation information between image pairs and aggregate a template of face images simultaneously. The experiments on video face recognition benchmarks, including YTF, IJB-A, and IJB-C show that: (i) G-FAN automatically learns to advocate high-quality frames while repelling low-quality ones. (ii) G-FAN significantly boosts recognition accuracy and outperforms other state-of-the-art aggregation methods.