With the rapidly increasing demand for oriented object detection e.g. in autonomous driving and remote sensing, the recently proposed paradigm involving weakly-supervised detector H2RBox for learning rotated box (RBox) from the (currently) more readily-available horizontal box (HBox) has shown promise. This paper presents H2RBox-v2, to further bridge the gap between HBox-supervised and RBox-supervised oriented object detection. Specifically, we propose to leverage the reflection symmetry via flip and rotate consistencies, using a weakly-supervised network branch similar to H2RBox, together with a novel self-supervised branch that learns orientations from the symmetry inherent in visual objects. The detector is further stabilized and enhanced by practical techniques to cope with peripheral issues e.g. angular periodicity. To our best knowledge, H2RBox-v2 is the first symmetry-aware self-supervised paradigm for oriented object detection. In particular, our method shows less susceptibility to low-quality annotation and insufficient training data compared to H2RBox. Specifically, H2RBox-v2 achieves very close performance to a rotation annotation trained counterpart -- Rotated FCOS: 1) DOTA-v1.0/1.5/2.0: 72.31%/64.76%/50.33% vs. 72.44%/64.53%/51.77%; 2) HRSC: 89.66% vs. 88.99%; 3) FAIR1M: 42.27% vs. 41.25%.

翻译：随着自动驾驶、遥感等领域对旋转目标检测需求的快速增长，近期提出的弱监督检测器H2RBox通过学习从（当前）更易获取的水平框（HBox）生成旋转框（RBox）的范式展现出良好前景。本文提出H2RBox-v2，旨在进一步缩小HBox监督与RBox监督的旋转目标检测之间的差距。具体而言，我们通过翻转与旋转一致性来利用反射对称性，结合与H2RBox类似的弱监督网络分支，以及一个从视觉目标内在对称性学习方向的新型自监督分支。通过应对角周期性等外围问题的实用技术，检测器得到进一步稳定和增强。据我们所知，H2RBox-v2是首个感知对称性的自监督旋转目标检测范式。特别地，相比于H2RBox，我们的方法对低质量标注和训练数据不足的敏感性更低。具体性能方面，H2RBox-v2与旋转标注训练方法Rotated FCOS的检测精度非常接近：1）DOTA-v1.0/1.5/2.0：72.31%/64.76%/50.33%对比72.44%/64.53%/51.77%；2）HRSC：89.66%对比88.99%；3）FAIR1M：42.27%对比41.25%。