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

TL;DR

This paper introduces a multi-task deep learning approach that leverages attribute relationships to improve attribute classification accuracy across various domains.

Contribution

It proposes a novel multi-task CNN architecture that shares features among related attributes and incorporates an auxiliary network for enhanced classification performance.

Findings

Improved attribute classification accuracy on benchmark datasets.

Effective utilization of attribute relationships enhances model performance.

Demonstrated superiority over existing methods in attribute recognition tasks.

Abstract

Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification. Improving the accuracy of attribute classifiers is an important first step in any application which uses these attributes. In most works to date, attributes have been considered to be independent. However, we know this not to be the case. Many attributes are very strongly related, such as heavy makeup and wearing lipstick. We propose to take advantage of attribute relationships in three ways: by using a multi-task deep convolutional neural network (MCNN) sharing the lowest layers amongst all attributes, sharing the higher layers for related attributes, and by building an auxiliary network on top of the MCNN which utilizes the scores from all attributes to improve the final classification of each attribute. We demonstrate the effectiveness of our method by producing results on two challenging publicly available datasets.