CoOD decomposes inputs into components and applies Component Shift Score plus Compositional Consistency Score to improve detection of both standard and compositional out-of-distribution data.
Neural Networks and the Bias/Variance Dilemma
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
-
Component-Based Out-of-Distribution Detection
CoOD decomposes inputs into components and applies Component Shift Score plus Compositional Consistency Score to improve detection of both standard and compositional out-of-distribution data.