BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification

TL;DR

BSNet introduces a bi-similarity approach for few-shot fine-grained image classification, leveraging two distinct similarity measures to learn more discriminative features and improve generalization.

Contribution

The paper proposes BSNet, a novel bi-similarity network that uses two similarity measures to enhance feature discrimination in few-shot fine-grained classification.

Findings

Significant improvement on fine-grained benchmarks

Effective in learning discriminative features

Enhances generalization in few-shot scenarios

Abstract

Few-shot learning for fine-grained image classification has gained recent attention in computer vision. Among the approaches for few-shot learning, due to the simplicity and effectiveness, metric-based methods are favorably state-of-the-art on many tasks. Most of the metric-based methods assume a single similarity measure and thus obtain a single feature space. However, if samples can simultaneously be well classified via two distinct similarity measures, the samples within a class can distribute more compactly in a smaller feature space, producing more discriminative feature maps. Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures. After the support images and the query images pass through the convolution-based embedding module, the bi-similarity module learns feature maps according to two similarity measures of diverse characteristics. In this way, the model is enabled to learn more discriminative and less similarity-biased features from few shots of fine-grained images, such that the model generalization ability can be significantly improved. Through extensive experiments by slightly modifying established metric/similarity based networks, we show that the proposed approach produces a substantial improvement on several fine-grained image benchmark datasets. Codes are available at: https://github.com/spraise/BSNet