# Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning

## TL;DR

This paper introduces PABN, a novel meta-learning model that uses pairwise bilinear pooling and feature alignment to improve few-shot fine-grained recognition, outperforming existing methods.

## Contribution

It proposes a new pairwise bilinear pooling approach with feature alignment for few-shot fine-grained classification, enhancing subtle feature comparison.

## Key findings

- Outperforms state-of-the-art few-shot fine-grained methods.
- Effective in capturing nuanced differences between images.
- Validated on multiple fine-grained datasets.

## Abstract

The recognition ability of human beings is developed in a progressive way. Usually, children learn to discriminate various objects from coarse to fine-grained with limited supervision. Inspired by this learning process, we propose a simple yet effective model for the Few-Shot Fine-Grained (FSFG) recognition, which tries to tackle the challenging fine-grained recognition task using meta-learning. The proposed method, named Pairwise Alignment Bilinear Network (PABN), is an end-to-end deep neural network. Unlike traditional deep bilinear networks for fine-grained classification, which adopt the self-bilinear pooling to capture the subtle features of images, the proposed model uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric. In order to match base image features with query image features, we design feature alignment losses before the proposed pairwise bilinear pooling. Experiment results on four fine-grained classification datasets and one generic few-shot dataset demonstrate that the proposed model outperforms both the state-ofthe-art few-shot fine-grained and general few-shot methods.