iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection. (arXiv:2201.02331v1 [cs.LG])

Machine learning methods such as deep neural networks (DNNs), despite their
success across different domains, are known to often generate incorrect
predictions with high confidence on inputs outside their training distribution.
The deployment of DNNs in safety-critical domains requires detection of
out-of-distribution (OOD) data so that DNNs can abstain from making predictions
on those. A number of methods have been recently developed for OOD detection,
but there is still room for improvement. We propose the new method iDECODe,
leveraging in-distribution …

arxiv detection distribution