A threshold-free OOD detection method that labels wild data as an extra class and clusters per-sample training losses to separate in-distribution from out-of-distribution data.
Latent space autore- gression for novelty detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
A threshold-free OOD detection method that labels wild data as an extra class and clusters per-sample training losses to separate in-distribution from out-of-distribution data.