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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/LSP.2021.3094174 | IEEE SIGNAL PROCESSING LETTERS |
Keywords | DocType | Volume |
Training, Pipelines, Optimization, Loss measurement, Learning systems, Feature extraction, Extraterrestrial measurements, Class-based expansion optimization, image classification | Journal | 28 |
ISSN | Citations | PageRank |
1070-9908 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hui Wang | 1 | 0 | 0.34 |
Hanbin Zhao | 2 | 6 | 2.86 |
Xi Li | 3 | 1850 | 137.71 |