DiffSenseNet: Integrating Hierarchical Features and Angular Diffusion for Remote Sensing Object Detection

Songwen Pei, Hongli Ma, Xinyun Qiu, Libo Huang

Abstract: Object detection in remote sensing images is a significant and challenging task. The detection performance is difficult to further improve due to the wide variation in object scale and unpredictable orientations. However, traditional methods typically rely on Region Proposal Networks (RPN) with fixed anchor boxes, which makes it difficult to locate objects of multi-scale and multi-orientation. In this paper, we propose DiffSenseNet, a detection network that integrates Hierarchical Feature Fusion (HFF) and Angular Diffusion Augmentation (ADA). The HFF architecture integrates both bottom-up and top-down pathways to effectively merge features at different scales. The ADA strategy introduces directional information into noisy boxes by adding Gaussian noise to the ground truth boxes. On the DOTA and HRSC2016 datasets, DiffSenseNet achieves the accuracy of 75.89% and 86.24% mAP, respectively. Comprehensive experiments show that DiffSenseNet achieves relatively superior performance compared to previous state-of-the-art jobs.