AI Paper Atlas

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

RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection

Yue Song, Nicu Sebe, Wei Wang

NeurIPS 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 14 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
remove the dominant rank-1 feature matrixResNetv2-101 with RankFeat · ImageNet-1k OOD suite (average)FPR95: 57.66 -> 36.80Improved
combine Block 3 and Block 4 scores by averaging logits (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 36.80Improved
keep only the rank-1 matrix rather than remove it (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 58.49Hurt
remove rank-2 instead of rank-1 (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 57.92Hurt
remove rank-3 instead of rank-1 (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 61.94Hurt
apply rank-1 removal at shallow Block 1 rather than Block 4 (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 76.65Hurt
apply rank-1 removal at shallow Block 2 rather than Block 4 (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 73.23Hurt
use Block 3 rather than Block 4 features (ablation)RankFeat · ImageNet-1k OOD suite (average)AUROC: 87.84 -> 90.80Improved
use 20 power iterations to approximate the dominant singular component (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 39.75No clear effect
reduce the power iteration count to 5 (ablation)RankFeat · ImageNet-1k OOD suite (average)FPR95: 39.69 -> 41.36Hurt
remove the rank-1 component from OOD features (ablation)ID/OOD feature matrices at Block 4 · ImageNet-1k feature statisticsKL divergence to fitted MP distribution (OOD): 18.24 -> 15.79Improved

Later papers that compared with this method

1 later accepted paper reports RankFeat as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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