Pith. sign in

REVIEW 1 cited by

A Geometric Explanation of the Likelihood OOD Detection Paradox

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.18910 v2 pith:UHCIUGPW submitted 2024-03-27 cs.LG cs.AIcs.CVstat.ML

classification cs.LGcs.AIcs.CVstat.ML
keywords detectiondatadgmsgeneratedhigherlikelihoodlikelihood-basedlikelihoods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Likelihood-based deep generative models (DGMs) commonly exhibit a puzzling behaviour: when trained on a relatively complex dataset, they assign higher likelihood values to out-of-distribution (OOD) data from simpler sources. Adding to the mystery, OOD samples are never generated by these DGMs despite having higher likelihoods. This two-pronged paradox has yet to be conclusively explained, making likelihood-based OOD detection unreliable. Our primary observation is that high-likelihood regions will not be generated if they contain minimal probability mass. We demonstrate how this seeming contradiction of large densities yet low probability mass can occur around data confined to low-dimensional manifolds. We also show that this scenario can be identified through local intrinsic dimension (LID) estimation, and propose a method for OOD detection which pairs the likelihoods and LID estimates obtained from a pre-trained DGM. Our method can be applied to normalizing flows and score-based diffusion models, and obtains results which match or surpass state-of-the-art OOD detection benchmarks using the same DGM backbones. Our code is available at https://github.com/layer6ai-labs/dgm_ood_detection.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. OOD Detection with immature Models

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Partially trained GLOW models match or outperform fully trained models for out-of-distribution image detection when scored by layer-wise gradient norms.

Pith tools