Kinship Representation Learning with Face Componential Relation

Weng-Tai Su, Min-Hung Chen, Chien-Yi Wang, Shang-Hong Lai, Trista Pei-Chun Chen

Keywords: kinship recognition, attention, contrastive learning

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 (e.g., eyes, nose, etc.). 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, which automatically learns 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 the largest public kinship recognition FIW benchmark. The code will be publicly released upon acceptance.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

TL;DR: We achieve the SOTA kinship recognition performance by the learning face componential relation with contrastive learning.