通过傅里叶角度对齐，提升遥感图像旋转目标检测精度
Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
- 利用傅里叶频谱分析方向信息，统一特征主方向
- 在DOTA-v1.0上达78.72% mAP，刷新单尺度检测性能
- 模块可即插即用，适合遥感目标检测任务
在遥感旋转目标检测中，主流方法存在检测器颈部方向不一致和检测头任务冲突两大瓶颈。本文利用傅里叶旋转等变性，提出傅里叶角度对齐（Fourier Angle Alignment），通过频谱分析角度信息，并将主方向对齐至特定方向。进而设计两个即插即用模块：FAAFusion用于检测器颈部，对齐高层特征主方向并与低层特征融合；FAA Head作为新检测头，在分类与回归前将预对齐的RoI特征与原始特征相加。在DOTA-v1.0、DOTA-v1.5和HRSC2016数据集上的实验表明，该方法显著提升现有模型性能。尤其在单尺度训练测试下，于DOTA-v1.0达到78.72% mAP，DOTA-v1.5达72.28% mAP，验证了方法的有效性。代码已开源。
原文摘要 · Abstract (English)
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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。