A Multi-Task Comparator Framework for Kinship Verification

TL;DR

This paper introduces a multi-task comparator network that addresses gender bias in kinship verification, improving robustness and extending capabilities to handle partial or unknown kinship relations.

Contribution

A novel comparator framework that mitigates gender bias in kinship verification and can be extended to partial or unknown kinship relations.

Findings

Achieves comparable results on RFIW Challenge 2020

Robust against gender bias in kinship verification

Extensible to partial and unknown kinship relations

Abstract

Approaches for kinship verification often rely on cosine distances between face identification features. However, due to gender bias inherent in these features, it is hard to reliably predict whether two opposite-gender pairs are related. Instead of fine tuning the feature extractor network on kinship verification, we propose a comparator network to cope with this bias. After concatenating both features, cascaded local expert networks extract the information most relevant for their corresponding kinship relation. We demonstrate that our framework is robust against this gender bias and achieves comparable results on two tracks of the RFIW Challenge 2020. Moreover, we show how our framework can be further extended to handle partially known or unknown kinship relations.