Progressive Class-based Expansion Learning For Image Classification

TL;DR

This paper introduces class-based expansion learning, a novel scheme that enhances fine-grained classification by focusing on confusing classes and improving boundary learning through a bottom-up growth strategy.

Contribution

It proposes a new class-based expansion learning method with a class confusion criterion, emphasizing fine-grained boundary learning for confusing classes in image classification.

Findings

Improves classification accuracy on benchmarks.

Enhances boundary learning for confusing classes.

Demonstrates effectiveness through experiments.

Abstract

In this paper, we propose a novel image process scheme called class-based expansion learning for image classification, which aims at improving the supervision-stimulation frequency for the samples of the confusing classes. Class-based expansion learning takes a bottom-up growing strategy in a class-based expansion optimization fashion, which pays more attention to the quality of learning the fine-grained classification boundaries for the preferentially selected classes. Besides, we develop a class confusion criterion to select the confusing class preferentially for training. In this way, the classification boundaries of the confusing classes are frequently stimulated, resulting in a fine-grained form. Experimental results demonstrate the effectiveness of the proposed scheme on several benchmarks.