Improving Facial Attribute Recognition by Group and Graph Learning

by   Zhenghao Chen, et al.

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.


ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition

Representing the spatial properties of facial attributes is a vital chal...

Exploring Correlations in Multiple Facial Attributes through Graph Attention Network

Estimating multiple attributes from a single facial image gives comprehe...

BadLink: Combining Graph and Information-Theoretical Features for Online Fraud Group Detection

Frauds severely hurt many kinds of Internet businesses. Group-based frau...

Facial Action Unit Detection Using Attention and Relation Learning

Attention mechanism has recently attracted increasing attentions in the ...

Facial Attribute Capsules for Noise Face Super Resolution

Existing face super-resolution (SR) methods mainly assume the input imag...

Reachability Analysis for Attributes in ABAC with Group Hierarchy

Attribute-based access control (ABAC) models are widely used to provide ...

Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection

Facial Action Unit (AU) detection is a crucial task in affective computi...

Please sign up or login with your details

Forgot password? Click here to reset