Improving Facial Attribute Recognition by Group and Graph Learning

TL;DR

This paper introduces a unified network that leverages spatial and non-spatial attribute correlations through group attention and graph learning to enhance facial attribute recognition performance.

Contribution

It proposes a novel Multi-scale Group and Graph Network that combines group attention and graph correlation learning for improved attribute recognition.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively models spatial and non-spatial attribute relationships.

Enhances recognition accuracy with coarse-to-fine graph features.

Abstract

Exploiting the relationships between attributes is a key challenge for improving multiple facial attribute recognition. In this work, we are concerned with two types of correlations that are spatial and non-spatial relationships. For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature. On the other hand, to discover the non-spatial relationship, we model a group-based Graph Correlation Learning to explore affinities of predefined part-based groups. We utilize such affinity information to control the communication between all groups and then refine the learned group features. Overall, we propose a unified network called Multi-scale Group and Graph Network. It incorporates these two newly proposed learning strategies and produces coarse-to-fine graph-based group features for improving facial attribute recognition. Comprehensive experiments demonstrate that our approach outperforms the state-of-the-art methods.