OPODet: Toward Open World Potential Oriented Object Detection in Remote Sensing Images

Despite recent advances in object detection, closed-set detectors with fixed training classes often overlook or misclassify unannotated objects during testing. To address this, open world object detection (OWOD) algorithms identify and label these objects as unknown, better aligning with real-world scenarios and human learning. However, remote sensing images, with their arbitrary object orientations and large interclass feature disparities, pose significant challenges for these algorithms. To tackle this, we propose OPODet, an Open-world Potential Oriented object Detection framework for remote sensing images. Specifically, we incorporate the oriented unknown-aware region proposal network (OUA-RPN) into traditional oriented object detection models, enabling the network to predict potential oriented objects. To address the significant interclass feature differences among potential unknown classes, we propose a multiunknown-class clustering aligning prototype (MCAP) learning method to prevent feature collapse in the feature space. In addition, to address the lack of rotation information for potential objects, we introduce a rotation potential target consistency (RPTC) algorithm to impose explicit rotation constraints for generating more accurate potential unknown proposals. Extensive experiments on DIOR-R, DOTA-v1.0, and HRSC2016 datasets demonstrate the effectiveness of our approach in detecting potential oriented objects.