RIPoints: Pursuing Rotation-Insensitive Point Representation for Aerial Object Detection

Anchor-free aerial object detection methods have recently attracted much attention due to their simplicity and efficiency. However, the performance is still unsatisfactory due to the following two main limitations. On the one hand, the anchor-free detector employs ordinary convolution layers with axis-aligned receptive fields to extract object features, resulting in lacking internal mechanisms to handle the rotation variance. On the other hand, the detector sacrifices much semantic information to achieve faster detection, leading to the inability to deal with objects' high interclass similarity and intraclass diversity. To address these issues, in this article, we present a unique anchor-free detector, termed rotation-insensitive point representation ( \text{R}{2} IPoints), of which a set of category-aware points are employed to encode the spatial and semantic information of the arbitrary-oriented objects. Specifically, we first devise a stacked rotation convolution module (SRM) to encourage the learning of \text{R}{2} IPoints by adaptively modeling orientation-agnostic interdependencies over stochastically rotated features. Meanwhile, we further introduce a class-specific semantic enhancement module (CSM). It performs category-aware semantic activation to recalibrate features, thus enabling the point representation to be aware of object categories. Through jointly optimizing the two proposed modules in an end-to-end manner, \text{R}{2} IPoints could simultaneously generate rotation-insensitive and category-aware point representation. Extensive experiments on the challenging DIOR and DOTA datasets demonstrate the superiority of the proposed method. We achieve 72.7% mAP on DIOR and 74.34% mAP on DOTA, surpassing the baseline method of +2.4% mAP and +2.49% mAP, respectively. The code is available at https://github.com/shnew/R2IPoints.