Not All Boxes Are Equal: Learning to Optimize Bounding Boxes With Discriminative Distributions in Optical Remote Sensing Images

Detecting oriented objects in optical remote sensing images has been consistently challenging due to difficulties in bounding boxes' localization. The cascaded regression framework, widely used for high-quality bounding box refinement, has demonstrated effectiveness in this domain. However, our experiments reveal a discontinuity issue in bounding box optimization in cascaded regression framework. As a result, performance gain is not guaranteed across all stages in this framework. In this article, we propose a distribution discriminative detector (DDDet) to address the above issues and enhance the optimization of bounding boxes in oriented object detection. Specifically, a novel conditional anchor refinement framework (CARF) is designed to improve cascaded regression structure. CARF distinguishes bounding boxes with different distributions, adaptively optimizing them within the well-assigned regressors. Subsequently, the aligned convolution module (ACM) is integrated into each regressor, facilitating the continuous alignment between features and refined anchors. Furthermore, the geometry-guided training sample selection (GTSS) method is incorporated into CARF to assign labels based on object shape priors. Experimental results show that DDDet obtains state-of-the-art performance on mainstream datasets for oriented object detection in remote sensing image, which demonstrates the effectiveness of the proposed method. Our method surpasses many current single-stage detectors, two-stage detectors, and refine-stage detectors, achieving the mAP of 79.41% on the DOTA dataset and 44.15% on the FAIR1M dataset.