Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box, leading to a gap between the readily available training corpus and the rising demand for oriented object detection. This paper proposes a simple yet effective oriented object detection approach called H2RBox merely using horizontal box annotation for weakly-supervised training, which closes the above gap and shows competitive performance even against those trained with rotated boxes. The cores of our method are weakly- and self-supervised learning, which predicts the angle of the object by learning the consistency of two different views. To our best knowledge, H2RBox is the first horizontal box annotation-based oriented object detector. Compared to an alternative i.e. horizontal box-supervised instance segmentation with our post adaption to oriented object detection, our approach is not susceptible to the prediction quality of mask and can perform more robustly in complex scenes containing a large number of dense objects and outliers. Experimental results show that H2RBox has significant performance and speed advantages over horizontal box-supervised instance segmentation methods, as well as lower memory requirements. While compared to rotated box-supervised oriented object detectors, our method shows very close performance and speed. The source code is available at PyTorch-based \href{https://github.com/yangxue0827/h2rbox-mmrotate}{MMRotate} and Jittor-based \href{https://github.com/yangxue0827/h2rbox-jittor}{JDet}.

翻译：摘要：旋转目标检测广泛应用于从航拍图像到自动驾驶的诸多场景，然而现有检测基准大多仅提供水平边界框标注（其成本低于精细旋转框标注），导致可获得的训练数据与日益增长的旋转目标检测需求之间存在鸿沟。本文提出一种简单而有效的旋转目标检测方法H2RBox，仅使用水平框标注进行弱监督训练即可弥合上述差距，其性能甚至可与采用旋转框训练的检测器相媲美。本方法的核心在于弱监督与自监督学习：通过令两个不同视角下的预测结果保持一致性来推断目标角度。据我们所知，H2RBox是首个基于水平框标注的旋转目标检测器。与另一种方案（即水平框监督的实例分割结合后处理的旋转目标检测适配方法）相比，本方法不受掩膜预测质量的影响，在包含大量密集目标与离群点的复杂场景中表现更鲁棒。实验结果表明，H2RBox相较于水平框监督的实例分割方法具有显著的速度与精度优势，且内存需求更低；而与旋转框监督的旋转目标检测器相比，本方法展现出极为接近的性能与速度。源代码已开源，提供基于PyTorch的MMRotate版本（https://github.com/yangxue0827/h2rbox-mmrotate）与基于Jittor的JDet版本（https://github.com/yangxue0827/h2rbox-jittor）。