Less yet robust: crucial region selection for scene recognition

TL;DR

This paper introduces an adaptive region selection mechanism for scene recognition that enhances robustness by focusing on high-level features, especially in degraded aerial and underwater images.

Contribution

It proposes a learnable masking approach with regularization to select crucial regions, improving scene recognition performance under challenging conditions.

Findings

Outperforms state-of-the-art methods on two datasets.

Enhances robustness against image degradation.

Introduces a new underwater geological scene dataset.

Abstract

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene recognition tasks. However, low-quality images still impede model performance due to the inappropriate use of high-level semantic features. To address these challenges, we propose an adaptive selection mechanism to identify the most important and robust regions with high-level features. Thus, the model can perform learning via these regions to avoid interference. implement a learnable mask in the neural network, which can filter high-level features by assigning weights to different regions of the feature matrix. We also introduce a regularization term to further enhance the significance of key high-level feature regions. Different from previous methods, our learnable matrix pays extra attention to regions that are important to multiple categories but may cause misclassification and sets constraints to reduce the influence of such regions.This is a plug-and-play architecture that can be easily extended to other methods. Additionally, we construct an Underwater Geological Scene Classification dataset to assess the effectiveness of our model. Extensive experimental results demonstrate the superiority and robustness of our proposed method over state-of-the-art techniques on two datasets.