A Novel Plug-in Module for Fine-Grained Visual Classification

TL;DR

This paper introduces a new plug-in module for neural networks that enhances fine-grained visual classification by automatically identifying discriminative regions, achieving state-of-the-art accuracy with end-to-end training.

Contribution

The novel plug-in module can be integrated into various backbone networks to improve fine-grained classification without multi-stage training.

Findings

Achieves 92.77% accuracy on CUB200-2011

Achieves 92.83% accuracy on NABirds

Outperforms existing state-of-the-art methods

Abstract

Visual classification can be divided into coarse-grained and fine-grained classification. Coarse-grained classification represents categories with a large degree of dissimilarity, such as the classification of cats and dogs, while fine-grained classification represents classifications with a large degree of similarity, such as cat species, bird species, and the makes or models of vehicles. Unlike coarse-grained visual classification, fine-grained visual classification often requires professional experts to label data, which makes data more expensive. To meet this challenge, many approaches propose to automatically find the most discriminative regions and use local features to provide more precise features. These approaches only require image-level annotations, thereby reducing the cost of annotation. However, most of these methods require two- or multi-stage architectures and cannot be trained end-to-end. Therefore, we propose a novel plug-in module that can be integrated to many common backbones, including CNN-based or Transformer-based networks to provide strongly discriminative regions. The plugin module can output pixel-level feature maps and fuse filtered features to enhance fine-grained visual classification. Experimental results show that the proposed plugin module outperforms state-of-the-art approaches and significantly improves the accuracy to 92.77\% and 92.83\% on CUB200-2011 and NABirds, respectively. We have released our source code in Github https://github.com/chou141253/FGVC-PIM.git.