AI Paper Atlas

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

Rethinking Out-of-Distribution Detection From a Human-Centric Perspective

Yao Tai Zhu, Yuefeng Chen, Xiaodan Li, Rong Zhang, Hui Xue, Xiang Tian, Rongxin Jiang, Bolun Zheng, Yaowu Chen

IJCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 9 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
evaluate with only correctly classified ID images instead of all validation imagesMSP vs GradNorm on ResNet-50 · ImageNet OOD (iNaturalist, Places, SUN, Textures avg)FPR95: 27.54% worse than GradNorm -> surpasses GradNorm by 16.55%Improved
use MSP instead of ReActVGG19 · Human-centric OOD averageDER99: MSP surpasses ReAct by 1.87%Improved
use MSP instead of ViMVGG19 · Human-centric OOD averageDER99: MSP surpasses ViM by 36.5%Improved
use ViM instead of MSPSwin-B · Human-centric OOD averageDER99: MSP lags ViM by 0.14%No clear effect
use MSP instead of GradNormSwin-B · Human-centric OOD averageDER99: MSP surpasses ReAct and GradNorm by 2.62% and 34.03%Improved
use KNN instead of MSPSENet154 vs ResNet-50 · Human-centric OOD averageDER99: KNN surpasses MSP by 4.9% on SENet154 but drops dramatically on ResNet50Mixed
use ViM on VGG19 versus SwinViM · iNaturalistDER99: over 98% DER99 on VGG19Hurt
use larger ResNet-101 instead of ResNet-50 (ablation)ViM · Human-centric OOD averageDER99: 6.67% better than ResNet50, 1.92% better than ResNet152Improved
increase adversarial training strength to epsilon=1 (ablation)MSP on ResNet-50 · Human-centric OOD averageDER99: 15.32% worse than normal modelHurt
use knowledge-distilled ResNet-50 (ablation)KNN · Human-centric OOD averageDER99: improves by 26.95%Improved
use knowledge-distilled DeiT-B (ablation)KNN · Human-centric OOD averageDER99: degrades by 8.96%Hurt
use knowledge-distilled models (ablation)MSP · Human-centric OOD averageDER99Improved

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