Benchmark across architectures and shift regimes finds OOD detector rankings shift with representation collapse; proposes NC-based shortlist predictor and PCA filter without extra OOD data.
For finite samples, the Iman–Davenport F -approximation is recommended (Iman & Davenport, 1980): FF = (N−1)Q N(k−1)−Q ∼F k−1,(k−1)(N−1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
Benchmark across architectures and shift regimes finds OOD detector rankings shift with representation collapse; proposes NC-based shortlist predictor and PCA filter without extra OOD data.