MVOL trains OOD detectors by treating outliers as mixtures of noise and minor in-distribution features, yielding improved FPR95 on CIFAR-10/CIFAR-100 with auxiliary and wild outlier data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
MVOL trains OOD detectors by treating outliers as mixtures of noise and minor in-distribution features, yielding improved FPR95 on CIFAR-10/CIFAR-100 with auxiliary and wild outlier data.