Mask Guided Attention For Fine-Grained Patchy Image Classification

TL;DR

This paper introduces a mask guided attention (MGA) method that leverages a pre-trained segmentation model to improve fine-grained patchy image classification, especially with limited training data.

Contribution

The novel MGA approach integrates auxiliary supervision from a segmentation model to enhance discriminative feature learning in data-scarce scenarios.

Findings

MGA outperforms state-of-the-art methods on three patchy image datasets.

Ablation study shows MGA improves accuracy by over 2% on key datasets.

MGA effectively filters insignificant image parts, boosting robustness.

Abstract

In this work, we present a novel mask guided attention (MGA) method for fine-grained patchy image classification. The key challenge of fine-grained patchy image classification lies in two folds, ultra-fine-grained inter-category variances among objects and very few data available for training. This motivates us to consider employing more useful supervision signal to train a discriminative model within limited training samples. Specifically, the proposed MGA integrates a pre-trained semantic segmentation model that produces auxiliary supervision signal, i.e., patchy attention mask, enabling a discriminative representation learning. The patchy attention mask drives the classifier to filter out the insignificant parts of images (e.g., common features between different categories), which enhances the robustness of MGA for the fine-grained patchy image classification. We verify the effectiveness of our method on three publicly available patchy image datasets. Experimental results demonstrate that our MGA method achieves superior performance on three datasets compared with the state-of-the-art methods. In addition, our ablation study shows that MGA improves the accuracy by 2.25% and 2% on the SoyCultivarVein and BtfPIS datasets, indicating its practicality towards solving the fine-grained patchy image classification.