Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical

TL;DR

This paper introduces hierarchical reasoning graph networks for facial kinship verification, improving the fusion and reasoning of facial features to enhance verification accuracy.

Contribution

It proposes a novel Hierarchical Reasoning Graph Network that enhances reasoning capacity over traditional star-shaped models for kinship verification.

Findings

Achieves competitive results on four kinship databases.

Demonstrates the effectiveness of hierarchical reasoning in kinship verification.

Outperforms existing methods in accuracy and reasoning capability.

Abstract

In this paper, we investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. Conventional methods usually focus on learning discriminative features for each facial image of a paired sample and neglect how to fuse the obtained two facial image features and reason about the relations between them. To address this, we propose a Star-shaped Reasoning Graph Network (S-RGN). Our S-RGN first constructs a star-shaped graph where each surrounding node encodes the information of comparisons in a feature dimension and the central node is employed as the bridge for the interaction of surrounding nodes. Then we perform relational reasoning on this star graph with iterative message passing. The proposed S-RGN uses only one central node to analyze and process information from all surrounding nodes, which limits its reasoning capacity. We further develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity. More specifically, our H-RGN introduces a set of latent reasoning nodes and constructs a hierarchical graph with them. Then bottom-up comparative information abstraction and top-down comprehensive signal propagation are iteratively performed on the hierarchical graph to update the node features. Extensive experimental results on four widely used kinship databases show that the proposed methods achieve very competitive results.