The recently proposed open-world object and open-set detection have achieved a breakthrough in finding never-seen-before objects and distinguishing them from known ones. However, their studies on knowledge transfer from known classes to unknown ones are not deep enough, resulting in the scanty capability for detecting unknowns hidden in the background. In this paper, we propose the unknown sniffer (UnSniffer) to find both unknown and known objects. Firstly, the generalized object confidence (GOC) score is introduced, which only uses known samples for supervision and avoids improper suppression of unknowns in the background. Significantly, such confidence score learned from known objects can be generalized to unknown ones. Additionally, we propose a negative energy suppression loss to further suppress the non-object samples in the background. Next, the best box of each unknown is hard to obtain during inference due to lacking their semantic information in training. To solve this issue, we introduce a graph-based determination scheme to replace hand-designed non-maximum suppression (NMS) post-processing. Finally, we present the Unknown Object Detection Benchmark, the first publicly benchmark that encompasses precision evaluation for unknown detection to our knowledge. Experiments show that our method is far better than the existing state-of-the-art methods.
翻译:最近提出的开放世界物体和开放集合检测在查找从未见过的物体并将其与已知物体区分开方面取得了突破。然而,它们关于从已知类别向未知类别的知识转移的研究还不够深入,导致对隐藏在背景中的未知物体的检测能力不足。在本文中,我们提出了未知物体探测的嗅探器(UnSniffer),用于发现未知和已知物体。首先,引入了广义物体置信度(GOC)分数,它仅使用已知样本进行监督,并避免了对背景中未知物体的不适当抑制。这样从已知物体学习到的置信分数可以推广到未知物体。此外,我们提出了一种负能量抑制损失,以进一步抑制背景中的非物体样本。接下来,在推断过程中由于缺乏训练中的语义信息,每个未知物体的最佳框很难获得。为了解决这个问题,我们引入了基于图的确定方案,以代替手工设计的非极大值抑制(NMS)后处理。最后,我们提出了未知物体检测基准,这是我们所知道的第一个包含未知检测精度评估的公开基准。实验表明,我们的方法比现有的最先进方法要好得多。