With the increasing demand for oriented object detection e.g. in autonomous driving and remote sensing, the oriented annotation has become a labor-intensive work. To make full use of existing horizontally annotated datasets and reduce the annotation cost, a weakly-supervised detector H2RBox for learning the rotated box (RBox) from the horizontal box (HBox) has been proposed and received great attention. This paper presents a new version, H2RBox-v2, to further bridge the gap between HBox-supervised and RBox-supervised oriented object detection. While exploiting axisymmetry via flipping and rotating consistencies is available through our theoretical analysis, H2RBox-v2, using a weakly-supervised branch similar to H2RBox, is embedded with a novel self-supervised branch that learns orientations from the symmetry inherent in the image of objects. Complemented by modules to cope with peripheral issues, e.g. angular periodicity, a stable and effective solution is achieved. To our knowledge, H2RBox-v2 is the first symmetry-supervised paradigm for oriented object detection. Compared to H2RBox, our method is less susceptible to low annotation quality and insufficient training data, which in such cases is expected to give a competitive performance much closer to fully-supervised oriented object detectors. Specifically, the performance comparison between H2RBox-v2 and Rotated FCOS on DOTA-v1.0/1.5/2.0 is 72.31%/64.76%/50.33% vs. 72.44%/64.53%/51.77%, 89.66% vs. 88.99% on HRSC, and 42.27% vs. 41.25% on FAIR1M.
翻译:随着自动驾驶和远程感测等领域对定向目标检测的需求不断增加,面向斜倾定向目标的标注工作已成为一项劳动密集型工作。为了充分利用现有的水平标注数据集并降低标注成本,提出了一种弱监督定向目标检测器H2RBox,用于从水平框(HBox)中学习旋转框(RBox),受到了广泛关注。本文提出了一种新版本H2RBox-v2,进一步弥合了基于HBox监督和基于RBox监督的定向目标检测之间的差距。当利用翻转和旋转的一致性来探求轴对称性时,我们可以通过理论分析, H2RBox-v2,使用一种类似于H2RBox的弱监督分支,嵌入了一种新的自监督分支,从对象图像中固有的对称性中学习方向。通过辅助处理角度周期性等问题的模块,达到了稳定而有效的解决方案。据我们所知,H2RBox-v2是第一个用对称度监督的定向目标检测范例。与H2RBox相比,我们的方法对低标注质量和训练数据不足的影响较小,在这种情况下,其预期性能应接近全监督的定向目标检测器,具有竞争力。具体而言,H2RBox-v2和Rotated FCOS在DOTA-v1.0/1.5/2.0上的性能比较为72.31%/64.76%/50.33% vs. 72.44%/64.53%/51.77%,在HRSC上为89.66% vs. 88.99%,在FAIR1M上为42.27% vs. 41.25%。