Class-wise Thresholding for Robust Out-of-Distribution Detection. (arXiv:2110.15292v3 [cs.LG] UPDATED)

We consider the problem of detecting OoD(Out-of-Distribution) input data when
using deep neural networks, and we propose a simple yet effective way to
improve the robustness of several popular OoD detection methods against label
shift. Our work is motivated by the observation that most existing OoD
detection algorithms consider all training/test data as a whole, regardless of
which class entry each input activates (inter-class differences). Through
extensive experimentation, we have found that such practice leads to a detector
whose performance …

arxiv detection distribution lg thresholding