Exploration of Class Center for Fine-Grained Visual Classification

TL;DR

This paper introduces a novel loss function that leverages class centers to improve fine-grained visual classification by reducing intra-class variance, enlarging inter-class differences, and generating soft labels to prevent overfitting, achieving state-of-the-art results.

Contribution

The paper proposes a new class-center based loss function that enhances feature discrimination and label robustness in fine-grained visual classification tasks.

Findings

Achieves state-of-the-art performance on FGVC-Aircraft and CUB-200-2011 datasets.

Consistently improves accuracy across four fine-grained datasets.

Effectively reduces intra-class variance and enlarges inter-class differences.

Abstract

Different from large-scale classification tasks, fine-grained visual classification is a challenging task due to two critical problems: 1) evident intra-class variances and subtle inter-class differences, and 2) overfitting owing to fewer training samples in datasets. Most existing methods extract key features to reduce intra-class variances, but pay no attention to subtle inter-class differences in fine-grained visual classification. To address this issue, we propose a loss function named exploration of class center, which consists of a multiple class-center constraint and a class-center label generation. This loss function fully utilizes the information of the class center from the perspective of features and labels. From the feature perspective, the multiple class-center constraint pulls samples closer to the target class center, and pushes samples away from the most similar nontarget class center. Thus, the constraint reduces intra-class variances and enlarges inter-class differences. From the label perspective, the class-center label generation utilizes classcenter distributions to generate soft labels to alleviate overfitting. Our method can be easily integrated with existing fine-grained visual classification approaches as a loss function, to further boost excellent performance with only slight training costs. Extensive experiments are conducted to demonstrate consistent improvements achieved by our method on four widely-used fine-grained visual classification datasets. In particular, our method achieves state-of-the-art performance on the FGVC-Aircraft and CUB-200-2011 datasets.