Kinship Representation Learning with Face Componential Relation
It addresses kinship recognition, a challenging problem in computer vision, with a novel method that improves accuracy for applications like family photo organization, though it is incremental in its approach.
The paper tackles kinship recognition by learning discriminative representations that incorporate spatial correlations between face components, using a cross-attention mechanism and a guided loss function, achieving state-of-the-art results on the FIW benchmark with significant performance improvements.
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 (e.g., eyes, nose, etc.). To achieve this goal, we propose the Face Componential Relation Network, which learns the relationship between face components among images with a cross-attention mechanism, which automatically learns the important facial regions for kinship recognition. Moreover, we propose Face Componential Relation Network (FaCoRNet), 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 the largest public kinship recognition FIW benchmark.