Adaptive Angle Module and Radian Regression Method for Rotated Object Detection

Yihao Xu, Ming Dai, Dejun Zhu, Wankou Yang

Abstract: Rotated object detectors commonly encounter instability during the training process, primarily due to background noise and angular periodicity. Targets with elongated or nonconvex shapes may introduce background noise during convolution, hindering accurately extracting features. Meanwhile, the periodicity of angles leads to predictions beyond the defined range, subsequently impeding the convergence. This letter introduces an angle adaptive module (AAM) designed for the backbone, enhancing the ability of the model to accurately extract object features and dynamically select the optimal angle. Moreover, to mitigate the effect of angle periodicity, a method called radian regression method (RRM) is proposed for predicting proper angles. It avoids directly regressing the value and instead produces the probability density distribution of the offset. We elaborately design numerous experiments to demonstrate the effectiveness of the proposed modules. As a result, the proposed method attains competitive results across various datasets, including DOTAv1.0, DOTAv1.5, DOTAv2.0, HRSC2016, and DIOR-R.