AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

POEM: Out-of-Distribution Detection with Posterior Sampling

Yifei Ming, Ying Fan, Yixuan Li

ICML 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace greedy outlier mining with posterior samplingOOD detection with auxiliary outlier data · CIFAR-10; six OOD test datasetsFPR95: 4.38 -> 2.54Improved
replace greedy outlier mining with posterior samplingOOD detection with auxiliary outlier data · CIFAR-100; six OOD test datasetsFPR95: 19.96 -> 15.14Improved
replace random outlier sampling with posterior-sampled outlier miningenergy-regularized OOD detection · CIFAR-100; six OOD test datasetsFPR95: 19.25 -> 15.14Improved
add energy-regularized training instead of the K+1-class training scheme (ablation)POEM · CIFAR-10; six natural OOD test datasetsFPR95: 2.81 -> 2.54Improved
add energy-regularized training instead of the K+1-class training scheme (ablation)POEM · CIFAR-100; six natural OOD test datasetsFPR95: 17.11 -> 15.14Improved
decrease the auxiliary pool size by half (ablation)POEM · CIFAR-10; six OOD test datasetsFPR95: 2.54 -> 4.23Hurt
decrease the auxiliary pool size by half (ablation)POEM · CIFAR-10; six OOD test datasetsAUROC: 99.40 -> 99.29Hurt
stop outlier mining and posterior updates early while continuing regular training (ablation)POEM · CIFAR-100; six OOD test datasetsAUROC: 97.79 -> 97.33\%Hurt
use three times more randomly sampled outliers (ablation)Energy with auxiliary outlier data · CIFAR-100; six OOD test datasetsFPR95: 19.25 -> 19.19No clear effect
use TinyImages as the auxiliary outlier dataset (ablation)POEM · CIFAR-10; six OOD test datasetsFPR95: 3.27 -> 1.56Improved

Later papers that compared with this method

6 later accepted papers report POEM as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy