Calibrated Out-of-Distribution Detection with a Generic Representation

1 code implementation • 23 Mar 2023 • Tomas Vojir, Jan Sochman, Rahaf Aljundi, Jiri Matas

We propose a novel OOD method, called GROOD, that formulates the OOD detection as a Neyman-Pearson task with well calibrated scores and which achieves excellent performance, predicated by the use of a good generic representation.

Out-of-Distribution Detection