Out-of-distribution (OOD) detection empowers the model trained on the closed
set to identify unknown data in the open world. Though many prior techniques
have yielded considerable improvements, two crucial obstacles still remain.
Firstly, a unified perspective has yet to be presented to view the developed
arts with individual designs, which is vital for prov
在这篇论文中,我们提出了一个名为 Open World Semi-supervised Detection(OWSSD)的框架,该框架通过一种轻量级的自编码器网络对进行过 ID 数据训练从而有效地检测 OOD 数据,并从中学习,我们通过大量评估表明我们的方法在与最先进的 OOD 检测算法的竞争中表现出色,并显著改善了开放世界场景下的半监督学习性能。