Hierarchical feature-pair relation networks for face recognition

Abstract

We propose a novel face recognition method using a Hierarchical Feature Relational Network (HFRN) which extracts facial part representations around facial landmark points, and predicts hierarchical latent relations between facial part representations. These hierarchical latent relations should be unique relations within the same identity and discriminative relations among different identities for face recognition task. To do this, the HFRN extracts appearance features as facial parts representations around facial landmark points on the feature maps, globally pool these extracted appearance features onto single feature vectors, and captures the relations for the pairs of appearance features. The HFRN captures the locally detailed relations in the low-level layers and the locally abstracted global relations in the high-level layers for the pairs of appearance features extracted around facial landmark points projected on each layer, respectively. These relations from low-level layers to high-level layers are concatenated into a single hierarchical relation feature. To further improve the accuracy of face recognition, we combine the global appearance feature with the hierarchical relation feature. In experiments, the proposed method achieves the comparable performance in the 1:1 face verification and 1:N face identification tasks compared to existing state-of-the-art methods on the challenging IARPA Janus Benchmark A (IJB-A) and IARPA Janus Benchmark B (IJB-B) datasets.