In or Out? Fixing ImageNet Out-of-distribution detection
Published in ICML, 2023
Recommended citation: J. Bitterwolf*, M. Müller* and Matthias Hein (*equal contribution) (2023) “In or out? Fixing ImageNet Out-of-distribution detection” ICML 2023 https://arxiv.org/abs/2306.00826
We show that previously used datasets for evaluating OOD detection on ImageNet are severly flawed, because they contain a significant fraction of ID samples. We present NINCO, a novel hand-cleaned dataset as a solution.
Recommended citation: J. Bitterwolf, M. Müller and Matthias Hein (*equal contribution) (2023) “In or out? Fixing ImageNet Out-of-distribution detection” ICML 2023