RelationRS: Relationship Representation Network for Object Detection in Aerial Images

TL;DR

RelationRS introduces a novel network that leverages scene semantics and multi-scale feature fusion to significantly improve object detection accuracy in complex aerial images.

Contribution

The paper proposes RelationRS, a relationship representation network with dual relationship and bridging visual modules for enhanced aerial image object detection.

Findings

Achieves state-of-the-art detection performance on aerial image datasets.

Effectively models relationships between different scene regions and scales.

Improves detection accuracy in complex backgrounds and scale variations.

Abstract

Object detection is a basic and important task in the field of aerial image processing and has gained much attention in computer vision. However, previous aerial image object detection approaches have insufficient use of scene semantic information between different regions of large-scale aerial images. In addition, complex background and scale changes make it difficult to improve detection accuracy. To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution. The dual relationship module learns the potential relationship between features of different scales and learns the relationship between different scenes from different patches in a same iteration. In addition, the dual relationship module dynamically generates parameters to guide the fusion of multi-scale features. 2) Secondly, The bridging visual representations module (BVR) is introduced into the field of aerial images to improve the object detection effect in images with complex backgrounds. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed RelationRS achieves a state-of-the-art detection performance.