Kinship Verification Based on Cross-Generation Feature Interaction Learning

TL;DR

This paper introduces a novel cross-generation feature interaction learning framework for kinship verification that integrates similarity learning with feature extraction, leveraging local and non-local features for improved accuracy.

Contribution

The proposed CFIL framework uniquely combines similarity weights with feature extraction in a unified deep learning model for kinship verification.

Findings

Outperforms state-of-the-art kinship verification methods

Effectively captures cross-generation relationships in facial features

Demonstrates robustness and efficiency in experiments

Abstract

Kinship verification from facial images has been recognized as an emerging yet challenging technique in many potential computer vision applications. In this paper, we propose a novel cross-generation feature interaction learning (CFIL) framework for robust kinship verification. Particularly, an effective collaborative weighting strategy is constructed to explore the characteristics of cross-generation relations by corporately extracting features of both parents and children image pairs. Specifically, we take parents and children as a whole to extract the expressive local and non-local features. Different from the traditional works measuring similarity by distance, we interpolate the similarity calculations as the interior auxiliary weights into the deep CNN architecture to learn the whole and natural features. These similarity weights not only involve corresponding single points but also excavate the multiple relationships cross points, where local and non-local features are calculated by using these two kinds of distance measurements. Importantly, instead of separately conducting similarity computation and feature extraction, we integrate similarity learning and feature extraction into one unified learning process. The integrated representations deduced from local and non-local features can comprehensively express the informative semantics embedded in images and preserve abundant correlation knowledge from image pairs. Extensive experiments demonstrate the efficiency and superiority of the proposed model compared to some state-of-the-art kinship verification methods.