论文标题
开放式半监督对象检测
Open-Set Semi-Supervised Object Detection
论文作者
论文摘要
半监督对象检测（SSOD）的最新发展显示了利用未标记数据改善对象检测器的希望。但是，到目前为止，这些方法已经假设未标记的数据不包含分布外（OOD）类，这对于较大规模的未标记数据集是不现实的。在本文中，我们考虑了一个更实用但具有挑战性的问题，开放式半监督对象检测（OSSOD）。我们首先发现现有的SSOD方法在开放式条件下获得了较低的性能增长，这是由语义扩展引起的，在语义扩展中，分散注意力的OOD对象被错误预测为半监测训练的分布伪标签。为了解决此问题，我们考虑与SSOD方法集成的在线和离线OOD检测模块。通过广泛的研究，我们发现，基于自我监视的视力变压器的脱机OOD检测器对在线OOD探测器的表现良好，因为它稳健地对伪标记的干扰。在实验中，我们提出的框架有效地解决了语义扩展问题，并在许多OSSOD基准（包括大规模可可开放映像）上显示出一致的改进。我们还在不同的OSSOD条件下验证框架的有效性，包括不同数量的分布类别，不同程度的监督和不同标记集的组合。
Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain out-of-distribution (OOD) classes, which is unrealistic with larger-scale unlabeled datasets. In this paper, we consider a more practical yet challenging problem, Open-Set Semi-Supervised Object Detection (OSSOD). We first find the existing SSOD method obtains a lower performance gain in open-set conditions, and this is caused by the semantic expansion, where the distracting OOD objects are mispredicted as in-distribution pseudo-labels for the semi-supervised training. To address this problem, we consider online and offline OOD detection modules, which are integrated with SSOD methods. With the extensive studies, we found that leveraging an offline OOD detector based on a self-supervised vision transformer performs favorably against online OOD detectors due to its robustness to the interference of pseudo-labeling. In the experiment, our proposed framework effectively addresses the semantic expansion issue and shows consistent improvements on many OSSOD benchmarks, including large-scale COCO-OpenImages. We also verify the effectiveness of our framework under different OSSOD conditions, including varying numbers of in-distribution classes, different degrees of supervision, and different combinations of unlabeled sets.
