MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.
Vra: Variational rectified activation for out- of-distribution detection.Advances in Neural Information Processing Systems, 36:28941–28959, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.