面向遥感旋转目标检测的傅里叶角度对齐
Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
利用傅里叶旋转等变性在频域提取主方向并对齐角度，为旋转目标检测中颈部网络方向不一致与检测头任务冲突提供即插即用的解决思路，可迁移到任何需要方向一致性的特征融合与RoI处理环节。
原文依据 Ulitising fourier rotation equivariance, we introduce Fourier Angle Alignment, which analyses angle information through frequency spectrum
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在遥感旋转目标检测中，主流方法受制于两个瓶颈：检测器颈部网络的方向不一致性，以及检测头处的任务冲突。利用傅里叶旋转等变性，我们引入傅里叶角度对齐，通过频谱分析角度信息并将主方向对齐到特定朝向。随后我们提出两个即插即用模块：FAAFusion 与 FAA Head。FAAFusion 作用于检测器颈部网络，将高层特征的主方向对齐到低层特征后再进行融合。FAA Head 作为一种新的检测头，将 RoI 特征预对齐到规范角度，并在分类与回归之前将其加回原始特征。在 DOTA-v1.0、DOTA-v1.5 和 HRSC2016 上的实验表明，我们的方法能大幅提升已有工作。特别地，在单尺度训练与测试下，我们的方法在 DOTA-v1.0 上取得 78.72% 平均精度均值、在 DOTA-v1.5 上取得 72.28% 平均精度均值的最优新结果，验证了该方法在遥感目标检测中的有效性。代码将在论文录用后公开。
英文原文摘要 1131 字符
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 will be public upon acceptance.