AI Paper Atlas

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

Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis

Boyang Dai, Chaoqi Chen, Yizhou Yu

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 0 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
add reconstruction loss L_aux (ablation)OCO · ImageNet-200 OODAUROC: 92.77 -> 93.69Improved
add OCO score without L_aux (ablation)slot-based classifier · ImageNet-200 OODAUROC: 90.76 -> 89.43Hurt
add L_aux when no OCO score used (ablation)slot-based classifier · ImageNet-200 OODAUROC: 90.76 -> 92.77Improved
add OCO score given L_aux (ablation)slot-based classifier with L_aux · ImageNet-200 OODFPR95: 30.70 -> 28.23Improved
add OCO score given L_aux (ablation)slot-based classifier with L_aux · ImageNet-200 FS-OODAUROC: 67.74 -> 69.56Improved
add OCO score without L_aux (ablation)slot-based classifier · ImageNet-200 FS-OODFPR95: 72.50 -> 74.70Hurt
use scenario-specific scores (S1 single pattern) (ablation)OCO · ImageNet-200 OOD, scenario S1FPR95: FPR95 decreased by 17.28%Improved
use scenario-specific scores (S2 typical pattern) (ablation)OCO · ImageNet-200 OOD, scenario S2AUROC: AUROC increased by 7.41%; FPR95 decreased by 16.79%Improved
use scenario-specific scores (S3 atypical pattern) (ablation)OCO · ImageNet-200 OOD, scenario S3AUROC: AUROC increased by 8.13%; FPR95 decreased by 11.53%Improved
increase slot count up to K=6 (ablation)OCO · ImageNet-200 OODFPR95/AUROCImproved
increase slot count beyond K=6 (ablation)OCO · ImageNet-200 OODFPR95/AUROCHurt
use object-centric classification (label in any slot prediction)slot classifier · ImageNet-200accuracy: 94.04 -> 96.51Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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