AI Paper Atlas

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

Revisit PCA-based Technique for Out-of-Distribution Detection

Xiaoyuan Guan, Zhouwu Liu, Wei-Shi Zheng, Yuren Zhou, Ruixuan Wang

ICCV 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 12 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
fuse regularized PCA reconstruction error into Energy score (ablation)Energy, ResNet50 · ImageNet-1K OOD averageFPR95: 58.41 -> 49.50Improved
fuse regularized reconstruction error into ReAct (ablation)ReAct, ResNet50 · ImageNet-1K OOD averageFPR95: 31.43 -> 18.66Improved
fuse regularized reconstruction error into MSP (ablation)MSP, ResNet50 · ImageNet-1K OOD averageFPR95: 66.95 -> 62.71Improved
fuse regularized reconstruction error into BATS (ablation)BATS, MobileNet-v2 · ImageNet-1K SUN/PlacesFPR95 and AUROC: iNaturalist FPR95 49.57 -> 50.51; Places 64.48 -> 66.43; average 52.91 -> 48.90Mixed
fuse regularized reconstruction error into Energy (ablation)Energy, ResNet34 · CIFAR-10 OOD averageFPR95: 24.71 -> 25.19No clear effect
fuse regularized reconstruction error into ReAct (ablation)ReAct, ResNet34 · CIFAR-10 OOD averageFPR95: 25.90 -> 27.49Hurt
fuse regularized reconstruction error into ReAct (ablation)ReAct, ResNet34 · CIFAR-100 OOD averageFPR95: 54.11 -> 43.64Improved
combine reconstruction error with LogitNorm on CIFAR-10LogitNorm, ResNet34 · CIFAR-10 OOD averageFPR95: 15.03 -> 13.06Improved
combine reconstruction error with LogitNorm on CIFAR-100 WideResNetLogitNorm, WideResNet28-10 · CIFAR-100 OOD averageFPR95: 51.23 -> 51.79No clear effect
reduce subspace dimension k so that less feature signal is preserved (ablation)regularized reconstruction error · CIFAR-100 and ImageNet-1KAUROCNo clear effect

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