Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classification

TL;DR

This paper introduces a Local Foreground Selection attention mechanism that improves few-shot plant species classification by emphasizing foreground features and reducing background interference, leading to better discrimination.

Contribution

The paper proposes a novel LFS attention module that combines local and foreground selection attention to enhance feature discrimination in few-shot plant classification.

Findings

LFS improves classification accuracy on three plant datasets.

LFS outperforms previous feature reconstruction methods.

Focusing on foreground reduces intra-class variation.

Abstract

Plant species exhibit significant intra-class variation and minimal inter-class variation. To enhance classification accuracy, it is essential to reduce intra-class variation while maximizing inter-class variation. This paper addresses plant species classification using a limited number of labelled samples and introduces a novel Local Foreground Selection(LFS) attention mechanism. LFS is a straightforward module designed to generate discriminative support and query feature maps. It operates by integrating two types of attention: local attention, which captures local spatial details to enhance feature discrimination and increase inter-class differentiation, and foreground selection attention, which emphasizes the foreground plant object while mitigating background interference. By focusing on the foreground, the query and support features selectively highlight relevant feature sequences and disregard less significant background sequences, thereby reducing intra-class differences. Experimental results from three plant species datasets demonstrate the effectiveness of the proposed LFS attention mechanism and its complementary advantages over previous feature reconstruction methods.