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.
@article{arxiv.2106.14412,
title = {Progressive Class-based Expansion Learning For Image Classification},
author = {Hui Wang and Hanbin Zhao and Xi Li},
journal= {arXiv preprint arXiv:2106.14412},
year = {2021}
}
Comments
Accepted to Journal of IEEE Signal Processing Letters