Fourier Angle Alignment for Oriented Object Detection in Remote Sensing

2026-02-27

AI Summary

This work addresses the challenges of orientation inconsistency in the detector neck and task conflict in the detection head for remote sensing rotated object detection. To this end, it introduces Fourier rotation equivariance into this domain for the first time and proposes two plug-and-play modules: FAAFusion for orientation alignment during multi-scale feature fusion and FAA Head for RoI feature pre-alignment at the detection head stage. By leveraging frequency-domain analysis to extract dominant orientations and normalize them to a canonical direction, the method effectively mitigates orientation ambiguity and inter-task conflict. The approach achieves state-of-the-art performance under single-scale training and testing, attaining mAP scores of 78.72% on DOTA-v1.0 and 72.28% on DOTA-v1.5.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

In remote sensing rotated object detection, mainstream methods suffer from two bottlenecks, directional incoherence at detector neck and task conflict at detecting head. Ulitising fourier rotation equivariance, we introduce Fourier Angle Alignment, which analyses angle information through frequency spectrum and aligns the main direction to a certain orientation. Then we propose two plug and play modules : FAAFusion and FAA Head. FAAFusion works at the detector neck, aligning the main direction of higher-level features to the lower-level features and then fusing them. FAA Head serves as a new detection head, which pre-aligns RoI features to a canonical angle and adds them to the original features before classification and regression. Experiments on DOTA-v1.0, DOTA-v1.5 and HRSC2016 show that our method can greatly improve previous work. Particularly, our method achieves new state-of-the-art results of 78.72% mAP on DOTA-v1.0 and 72.28% mAP on DOTA-v1.5 datasets with single scale training and testing, validating the efficacy of our approach in remote sensing object detection. The code is made publicly available at https://github.com/gcy0423/Fourier-Angle-Alignment .

Problem

• oriented object detection
• remote sensing
• directional incoherence
• task conflict
• rotated object detection

Innovation

• Fourier rotation equivariance
• angle alignment
• oriented object detection
• feature fusion
• detection head