测量旋转等变性对航空图像目标检测的影响
Measuring the Impact of Rotation Equivariance on Aerial Object Detection
AI总结：
本文提出严格旋转等变主干与颈部网络及多分支头部检测器MessDet，定量验证旋转等变性对航空图像检测性能的影响，在DOTA和DIOR-R数据集上以极低参数量达到最先进水平。
摘要：
由于航空图像中目标的朝向具有任意性，旋转等变性是航空图像目标检测器的一个关键属性。然而，目前关于旋转等变航空图像目标检测的研究仍然很少。大多数检测器依赖数据增强使模型学习近似旋转等变特征。少数检测器构建了旋转等变网络，但由于典型的下采样过程会破坏严格的旋转等变性，这些网络仅能实现近似旋转等变的主干网络。严格的旋转等变性对于航空图像目标检测是否必要仍是一个开放问题。本文实现了一种具有更先进网络结构的严格旋转等变主干网络和颈部网络，并将其与近似旋转等变网络进行比较，以定量测量旋转等变性对航空图像检测器性能的影响。此外，利用旋转等变特征固有的分组特性，我们提出了一种多分支头部网络，在提高检测精度的同时减少了参数量。基于上述改进，本研究提出了多分支头部旋转等变单阶段检测器（MessDet），在具有挑战性的航空图像数据集 DOTA-v1.0、DOTA-v1.5 和 DIOR-R 上，以极低的参数量实现了最先进的性能。
英文摘要：
Due to the arbitrary orientation of objects in aerial images, rotation equivariance is a critical property for aerial object detectors. However, recent studies on rotation-equivariant aerial object detection remain scarce. Most detectors rely on data augmentation to enable models to learn approximately rotation-equivariant features. A few detectors have constructed rotation-equivariant networks, but due to the breaking of strict rotation equivariance by typical downsampling processes, these networks only achieve approximately rotation-equivariant backbones. Whether strict rotation equivariance is necessary for aerial image object detection remains an open question. In this paper, we implement a strictly rotation-equivariant backbone and neck network with a more advanced network structure and compare it with approximately rotation-equivariant networks to quantitatively measure the impact of rotation equivariance on the performance of aerial image detectors. Additionally, leveraging the inherently grouped nature of rotation-equivariant features, we propose a multi-branch head network that reduces the parameter count while improving detection accuracy. Based on the aforementioned improvements, this study proposes the Multi-branch head rotation-equivariant single-stage Detector (MessDet), which achieves state-of-the-art performance on the challenging aerial image datasets DOTA-v1.0, DOTA-v1.5 and DIOR-R with an exceptionally low parameter count.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
