A score-based metric computed on corrupted measurements is claimed to equal the KL divergence between training and test image distributions, enabling unsupervised shift detection and adaptation in inverse problems.
A Baseline for Detecting 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
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Models
A score-based metric computed on corrupted measurements is claimed to equal the KL divergence between training and test image distributions, enabling unsupervised shift detection and adaptation in inverse problems.