Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model. We argue that AP$_{50}$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation. Therefore, we advocate using high-precision metric, e.g. AP$_{75}$, to measure the performance of models. In this paper, we propose an Aspect Ratio Sensitive Oriented Object Detector with Transformer, termed ARS-DETR, which exhibits a competitive performance in high-precision oriented object detection. Specifically, a new angle classification method, calling Aspect Ratio aware Circle Smooth Label (AR-CSL), is proposed to smooth the angle label in a more reasonable way and discard the hyperparameter that introduced by previous work (e.g. CSL). Then, a rotated deformable attention module is designed to rotate the sampling points with the corresponding angles and eliminate the misalignment between region features and sampling points. Moreover, a dynamic weight coefficient according to the aspect ratio is adopted to calculate the angle loss. Comprehensive experiments on several challenging datasets show that our method achieves competitive performance on the high-precision oriented object detection task.

翻译：现有旋转目标检测方法通常采用度量AP$_{50}$衡量模型性能。我们认为AP$_{50}$在角度偏差容忍度较大，本质上不适用于旋转目标检测。因此，我们倡导使用高精度度量（如AP$_{75}$）评估模型性能。本文提出一种基于Transformer的长宽比敏感旋转目标检测器（ARS-DETR），在高精度旋转目标检测任务中展现出竞争性表现。具体而言，我们提出角度分类新方法——长宽比感知圆形平滑标签（AR-CSL），以更合理的方式平滑角度标签，并摒弃先前工作（如CSL）引入的超参数。随后，设计旋转可变形注意力模块，使采样点随对应角度旋转，消除区域特征与采样点之间的错位。此外，采用基于长宽比的动态权重系数计算角度损失。在多个具有挑战性的数据集上的综合实验表明，本方法在高精度旋转目标检测任务中取得了竞争性结果。