Pith. sign in

REVIEW 1 cited by

Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data

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 2208.14024 v2 pith:4UFCUCV6 submitted 2022-08-30 cs.LG

classification cs.LG
keywords datalikelihoodoutliercontrastivedatasetdetectionnormalizingauxiliary
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Detecting test data deviating from training data is a central problem for safe and robust machine learning. Likelihoods learned by a generative model, e.g., a normalizing flow via standard log-likelihood training, perform poorly as an outlier score. We propose to use an unlabelled auxiliary dataset and a probabilistic outlier score for outlier detection. We use a self-supervised feature extractor trained on the auxiliary dataset and train a normalizing flow on the extracted features by maximizing the likelihood on in-distribution data and minimizing the likelihood on the contrastive dataset. We show that this is equivalent to learning the normalized positive difference between the in-distribution and the contrastive feature density. We conduct experiments on benchmark datasets and compare to the likelihood, the likelihood ratio and state-of-the-art anomaly detection methods.

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. Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation

    physics.data-an 2025-05 conditional novelty 5.0 of 10

    A hybrid of contrastive normalizing flows and a deep classifier yields signal-strength estimates with narrower confidence intervals than a likelihood-based method on the HiggsML Uncertainty Challenge dataset.

Pith tools