Max-Margin based Discriminative Feature Learning

TL;DR

This paper introduces a max-margin discriminative feature learning method that enhances robustness with group sparsity and exploits inter-class correlations for improved multi-class classification.

Contribution

It proposes a novel max-margin feature learning approach with group sparsity and multi-task correlation modeling, advancing discriminative feature extraction techniques.

Findings

Outperforms state-of-the-art methods in experiments.

Robust to noise due to $l_{2,1}$ norm constraint.

Effective in multi-class classification tasks.

Abstract

In this paper, we propose a new max-margin based discriminative feature learning method. Specifically, we aim at learning a low-dimensional feature representation, so as to maximize the global margin of the data and make the samples from the same class as close as possible. In order to enhance the robustness to noise, a $l_{2,1}$ norm constraint is introduced to make the transformation matrix in group sparsity. In addition, for multi-class classification tasks, we further intend to learn and leverage the correlation relationships among multiple class tasks for assisting in learning discriminative features. The experimental results demonstrate the power of the proposed method against the related state-of-the-art methods.