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.
翻译:近些年来,半悬浮物体探测(裁军特别联大)的发展显示了利用未贴标签的数据改善物体探测器的前景,然而,迄今为止,这些方法假定,未贴标签的数据并不包含分发(OOOD)类,而与规模较大的未贴标签的数据集不切实际。在本文件中,我们认为一个更实际但更具挑战性的问题,即开放的SOD半悬浮物体探测(OGRE)。我们首先发现,现有的裁军特别联大方法在开放设定的条件中取得了较低的性能增益,这是语义扩展造成的,在这种扩展中,转移注意力的OOOD对象被错误地错误地假定为半监督培训的在分配的假标签。为了解决这一问题,我们考虑在线和离线的OOODD检测模块,这些模块与裁军特别联大的方法相结合。我们发现,利用以自上封的愿景转换器为基础的离线 OOODD检测器,与在线 OODD检测器相比表现得更好,因为其稳健度与不贴标签的干扰作用。在试验中,我们提议的OOOIFI框架的大规模扩展,包括不同程度的不断核查。