NDP models prediction distributions and uses Perlin noise OOD synthesis to reach 61.31% point-level AP on STU LiDAR benchmark, over 10x prior best.
Partial and asymmetric contrastive learning for out-of-distribution detection in long- tailed recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Distribution Prior for LiDAR Out-of-Distribution Detection
NDP models prediction distributions and uses Perlin noise OOD synthesis to reach 61.31% point-level AP on STU LiDAR benchmark, over 10x prior best.