Exploring Correlations in Multiple Facial Attributes through Graph Attention Network

10/22/2018
by   Yan Zhang, et al.
0

Estimating multiple attributes from a single facial image gives comprehensive descriptions on the high level semantics of the face. It is naturally regarded as a multi-task supervised learning problem with a single deep CNN, in which lower layers are shared, and higher ones are task-dependent with the multi-branch structure. Within the traditional deep multi-task learning (DMTL) framework, this paper intends to fully exploit the correlations among different attributes by constructing a graph. The node in graph represents the feature vector from a particular branch for a given attribute, and the edge can be defined by either the prior knowledge or the similarity between two nodes in the embedding with a fully data-driven manner. We analyze that the attention mechanism actually takes effect in the latter case, and utilize the Graph Attention Layer (GAL) for exploring on the most relevant attribute feature and refining the task-dependant feature by considering other attributes. Experiments show that by mining the correlations among attributes, our method can improve the recognition accuracy on CelebA and LFWA dataset. And it also achieves competitive performance.

READ FULL TEXT
research
01/04/2016

Multi-task CNN Model for Attribute Prediction

This paper proposes a joint multi-task learning algorithm to better pred...
research
04/20/2018

A Deep Face Identification Network Enhanced by Facial Attributes Prediction

In this paper, we propose a new deep framework which predicts facial att...
research
05/28/2021

Improving Facial Attribute Recognition by Group and Graph Learning

Exploiting the relationships between attributes is a key challenge for i...
research
03/25/2019

Predicting Multiple Demographic Attributes with Task Specific Embedding Transformation and Attention Network

Most companies utilize demographic information to develop their strategy...
research
04/25/2016

Attributes for Improved Attributes: A Multi-Task Network for Attribute Classification

Attributes, or semantic features, have gained popularity in the past few...
research
07/27/2019

Attribute Aware Pooling for Pedestrian Attribute Recognition

This paper expands the strength of deep convolutional neural networks (C...
research
05/07/2019

Intentional Attention Mask Transformation for Robust CNN Classification

Convolutional Neural Networks have achieved impressive results in variou...

Please sign up or login with your details

Forgot password? Click here to reset