SGR: An Improved Point-Based Method for Remote Sensing Object Detection via Dual-Domain Alignment Saliency-Guided RepPoints

Abstract

With the advancement of deep neural networks, several methods leveraging convolution neural networks (CNNs) have gained prominence in the field of remote sensing object detection. Acquiring accurate feature representations from feature maps is a critical step in CNN-based object detection methods. Previously, region of interest (RoI)-based methods have been widely used, but of late, deformable convolution network (DCN)-based approaches have started receiving considerable attention. A significant challenge in the use of DCN-based methods is the inefficient distribution patterns of sampling points, stemming from a lack of effective and flexible guidance. To address this, our study introduces Saliency-Guided RepPoints (SGR), an innovative framework designed to enhance feature representation quality in remote sensing object detection. SGR employs a dynamic dual-domain alignment (DDA) training strategy to mitigate potential misalignment issues between spatial and feature domains during the learning process. Furthermore, we propose an interpretable visualization method to assess the alignment between feature representation and classification performance in DCN-based methods, providing theoretical analysis and validation for the effectiveness of sampling points. In this study, we assessed the proposed SGR framework through a series of experiments conducted on four varied and rigorous datasets: DOTA, HRSC2016, DIOR-R, and UCAS-AOD, all of which are widely employed in remote sensing object detection. The outcomes of these experiments substantiate the effectiveness of the SGR framework, underscoring its potential to enhance the accuracy of object detection within remote sensing imagery.