Progressive Class-based Expansion Learning For Image Classification
This work addresses fine-grained image classification challenges, particularly for confusing classes, but appears incremental as it builds on existing methods with a novel optimization strategy.
The paper tackles the problem of improving classification boundaries for confusing classes in image classification by proposing a class-based expansion learning scheme that prioritizes training on confusing classes, resulting in enhanced performance on several benchmarks.
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.