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：近期提出的开放世界目标检测与开放集检测方法在发现从未见过的新目标并将其与已知目标区分方面取得了突破性进展。然而，这些方法在将已知类别的知识迁移至未知类别方面的研究尚不深入，导致对隐藏在背景中的未知目标的检测能力不足。本文提出未知目标嗅探器（UnSniffer），用于同时发现未知与已知目标。首先，引入广义目标置信度（GOC）评分，该评分仅使用已知样本进行监督，避免对背景中未知目标的不当抑制。值得注意的是，这种从已知目标习得的置信度评分可泛化至未知目标。此外，我们提出负能量抑制损失函数，进一步抑制背景中的非目标样本。针对推理过程中因缺乏未知目标语义信息而难以获取最优检测框的问题，引入基于图的判定机制替代传统手工设计的非极大值抑制（NMS）后处理流程。最后，我们发布未知目标检测基准（Unknown Object Detection Benchmark），据我们所知这是首个包含未知检测精度评估的公开基准。实验结果表明，本方法显著优于现有最优方法。