Instance-Level Orientation Enhancement for Horizontal Box Supervised Oriented Object Detection in Remote Sensing Images

作者：Yang Xu, Zifang Xu, He Wang, Zhihui Wei, Zebin Wu · 发表于：IEEE Transactions on Image Processing · 年份：2025 · DOI：10.1109/tip.2025.3632224 · 被引用次数：2 · 研究领域：Remote-Sensing Image Classification、Advanced Neural Network Applications、Advanced Image and Video Retrieval Techniques

Most remote sensing datasets are annotated with horizontal bounding boxes (HBBs), which conflicts with mainstream oriented object detection methods that require oriented bounding boxes (OBBs). Horizontal box supervised oriented object detection has emerged as a promising solution, but existing methods suffer from two key limitations. First, they apply image-level geometric transformations for consistency learning, which binds object orientation to the global image and limits the model's ability to learn instance-specific orientation features. Second, they rely on data augmentation for orientation awareness while still using conventional horizontal convolutional neural networks (CNNs) for regression, failing to extract orientation-sensitive features effectively. To address these issues, we propose the Instance-Level Orientation Information Enhanced Detector (ILOEDet), which integrates the Instance-Aware Rotated Convolution Module (IARCM) and an Instance-Level Flip Consistency (IFC) mechanism to improve orientation sensitivity. Specifically, IARCM leverages classification and center-ness scores to select high-quality instances and their predicted angles, guiding a rotated convolution operation to embed instance-level orientation information into the feature maps. Meanwhile, IFC introduces a self-supervised branch that flips individual object instances to decouple their orientation from the image background, enforcing instance-level consistency constraints for more robust orient...