Multi-task CNN Model for Attribute Prediction

TL;DR

This paper introduces a multi-task CNN framework for attribute prediction in images, enabling shared learning among attributes and improving performance through a novel parameter decomposition and attribute grouping strategy.

Contribution

The paper presents a new multi-task CNN model with parameter decomposition and attribute grouping, enhancing attribute prediction by sharing knowledge among related attributes.

Findings

Improved attribute prediction accuracy on benchmark datasets.

Effective sharing of information among related attributes.

Better performance for under-sampled attribute classes.

Abstract

This paper proposes a joint multi-task learning algorithm to better predict attributes in images using deep convolutional neural networks (CNN). We consider learning binary semantic attributes through a multi-task CNN model, where each CNN will predict one binary attribute. The multi-task learning allows CNN models to simultaneously share visual knowledge among different attribute categories. Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes. In our multi-task framework, we propose a method to decompose the overall model's parameters into a latent task matrix and combination matrix. Furthermore, under-sampled classifiers can leverage shared statistics from other classifiers to improve their performance. Natural grouping of attributes is applied such that attributes in the same group are encouraged to share more knowledge. Meanwhile, attributes in different groups will generally compete with each other, and consequently share less knowledge. We show the effectiveness of our method on two popular attribute datasets.