AI Paper Atlas

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

Out-of-Distribution Detection with Semantic Mismatch under Masking

Yijun Yang, Ruiyuan Gao, Qiang Xu

ECCV 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 32 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 MoodCat masked conditional synthesis detection compared with EBOResNet18 classifier · CIFAR-10 In-D, no external dataAUROC: 83.83 -> 91.39Improved
add unlabeled external ImageNet data to MoodCat trainingMoodCat · CIFAR-10 In-DFPR@TPR95: 38.83 -> 28.71Improved
add unlabeled external ImageNet data to MoodCat trainingMoodCat · CIFAR-100 In-DAUROC: 87.47 -> 89.33Improved
replace OE/UDG with MoodCat on CIFAR-100 with external dataResNet18 classifier · CIFAR-100 In-DFPR@TPR95: 75.45 -> 47.61Improved
use MoodCat instead of CVAECapOSRMoodCat · CIFAR-10 6 known classes OSRAUROC: 83.5 -> 89.48Improved
add conditional binary classifier scorer to LPIPS+DISTS (ablation)MoodCat scoring · CIFAR-10 vs CIFAR-100AUROC: 74.78 -> 89.57Improved
add LPIPS and DISTS scorers to the conditional binary classifier (ablation)MoodCat scoring · CIFAR-10 vs CIFAR-100AUROC: 89.13 -> 89.57Improved
add masking in training (random) versus none (ablation)MoodCat · CIFAR-10 vs CIFAR-100AUROC: 90.79 -> 91.78Improved
add label conditioning to the generator (ablation)MoodCat · CIFAR-10 In-D, CIFAR-100 OODAUROC: 63.62 -> 89.57Improved
add label conditioning to the generator (ablation)MoodCat · CIFAR-100 In-D, CIFAR-10 OODAUROC: 52.48 -> 87.76Improved
use random masking ratio instead of fixed high ratio (ablation)MoodCat · CIFAR-10 vs CIFAR-100 (with ImageNet)AUROC: 91.56 -> 91.66Improved
use shuffling instead of masking (ablation)MoodCat · CIFAR-10 vs CIFAR-100 (with ImageNet)AUROC: 91.26 -> 88.73Hurt

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