Sparse internal snapshots at canonical low-noise levels from frozen diffusion backbones suffice for competitive out-of-distribution detection without full trajectories or large heads.
arXiv preprint arXiv:2310.17432 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
A score-based diffusion model estimates joint likelihoods of inputs and regression predictions to detect out-of-distribution cases in scientific tasks, with the likelihood correlating to prediction error.
citing papers explorer
-
Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
Sparse internal snapshots at canonical low-noise levels from frozen diffusion backbones suffice for competitive out-of-distribution detection without full trajectories or large heads.
-
Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI
A score-based diffusion model estimates joint likelihoods of inputs and regression predictions to detect out-of-distribution cases in scientific tasks, with the likelihood correlating to prediction error.