Kinship Representation Learning with Face Componential Relation

Abstract

Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin, which is an emerging and challenging problem. However, most previous methods focus on heuristic designs without considering the spatial correlation between face images. In this paper, we aim to learn discriminative kinship representations embedded with the relation information between face components. To achieve this goal, we propose the Face Componential Relation Network (FaCoRNet), which learns the relationship between face components among images with a cross-attention mechanism, to automatically learn the important facial regions for kinship recognition. Moreover, we propose Relation-Guided Contrastive Learning, which adapts the loss function by the guidance from cross-attention to learn more discriminative feature representations. The proposed FaCoRNet outperforms previous state-of-the-art methods by large margins for experiments on multiple public kinship recognition benchmarks. Our code is available at https://github.com/wtnthu/FaCoR.