# Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification

## TL;DR

This paper introduces LRPABN, a novel neural network for few-shot fine-grained image classification that effectively captures subtle differences between classes using low-rank bilinear pooling and feature alignment.

## Contribution

The paper proposes a new low-rank pairwise bilinear pooling method and a feature alignment layer for improved few-shot fine-grained classification, trained end-to-end.

## Key findings

- Achieves superior performance on four fine-grained datasets.
- Outperforms state-of-the-art methods in few-shot fine-grained classification.
- Effectively captures subtle inter-class differences.

## Abstract

Deep neural networks have demonstrated advanced abilities on various visual classification tasks, which heavily rely on the large-scale training samples with annotated ground-truth. However, it is unrealistic always to require such annotation in real-world applications. Recently, Few-Shot learning (FS), as an attempt to address the shortage of training samples, has made significant progress in generic classification tasks. Nonetheless, it is still challenging for current FS models to distinguish the subtle differences between fine-grained categories given limited training data. To filling the classification gap, in this paper, we address the Few-Shot Fine-Grained (FSFG) classification problem, which focuses on tackling the fine-grained classification under the challenging few-shot learning setting. A novel low-rank pairwise bilinear pooling operation is proposed to capture the nuanced differences between the support and query images for learning an effective distance metric. Moreover, a feature alignment layer is designed to match the support image features with query ones before the comparison. We name the proposed model Low-Rank Pairwise Alignment Bilinear Network (LRPABN), which is trained in an end-to-end fashion. Comprehensive experimental results on four widely used fine-grained classification datasets demonstrate that our LRPABN model achieves the superior performances compared to state-of-the-art methods.