ActSub decomposes activations via SVD of the classifier head into decisive and insignificant subspaces, using cosine similarity on the insignificant part for far-OOD and shaped energy on the decisive part for near-OOD, achieving SOTA on standard benchmarks.
A baseline for detect- ing misclassified and out-of-distribution examples in neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Activation Subspaces for Out-of-Distribution Detection
ActSub decomposes activations via SVD of the classifier head into decisive and insignificant subspaces, using cosine similarity on the insignificant part for far-OOD and shaped energy on the decisive part for near-OOD, achieving SOTA on standard benchmarks.