重新思考开集目标检测：问题、新公式和分类
Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomy
AI总结：
本文重新思考开集目标检测问题，提出新的公式和分类，揭示现有方法在检测未知对象时的误分类问题。
摘要：
开集目标检测（OSOD）是一项涉及检测未知对象同时准确检测已知对象的任务，最近引起了关注。然而，我们发现当前OSOD研究中所采用的问题公式存在根本性的问题。对象检测本质上是知道“要检测什么”，这与识别“未知”对象的概念相矛盾。这使得OSOD区别于开集识别（OSR）。这种矛盾使对方法性能的正确评估变得复杂，而此前的研究忽略了这一点。接下来，我们提出了一种新的公式，其中检测器需要在指定的对象类超类内检测已知和未知类别。这种新公式摆脱了上述问题并具有实际应用。最后，我们设计了利用现有数据集的基准测试，并报告了现有OSOD方法的实验评估。结果表明，现有方法无法准确检测未知对象，原因在于已知和未知类别的误分类，而非错误的边界框预测。作为副产品，我们引入了OSOD的分类，解决了文献中普遍存在的混淆。我们预计我们的研究将促使研究社区重新考虑OSOD，并促进朝着正确方向的发展。
英文摘要：
Open-set object detection (OSOD), a task involving the detection of unknown objects while accurately detecting known objects, has recently gained attention. However, we identify a fundamental issue with the problem formulation employed in current OSOD studies. Inherent to object detection is knowing "what to detect," which contradicts the idea of identifying "unknown" objects. This sets OSOD apart from open-set recognition (OSR). This contradiction complicates a proper evaluation of methods' performance, a fact that previous studies have overlooked. Next, we propose a novel formulation wherein detectors are required to detect both known and unknown classes within specified super-classes of object classes. This new formulation is free from the aforementioned issues and has practical applications. Finally, we design benchmark tests utilizing existing datasets and report the experimental evaluation of existing OSOD methods. The results show that existing methods fail to accurately detect unknown objects due to misclassification of known and unknown classes rather than incorrect bounding box prediction. As a byproduct, we introduce a taxonomy of OSOD, resolving confusion prevalent in the literature. We anticipate that our study will encourage the research community to reconsider OSOD and facilitate progress in the right direction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
