AI Paper Atlas

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

MOODv2: Masked Image Modeling for Out-of-Distribution Detection

Jingyao Li, Pengguang Chen, Shaozuo Yu, Shu Liu, Jiaya Jia

TPAMI 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 19 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
use BEiT masked image modeling pretraining instead of classification ViT (ablation)ViM score · ImageNet ID (avg 4 OOD sets)AUROC: 77.65 -> 95.68Improved
use BEiT pretraining instead of classification ViT (ablation)MSP score · ImageNet ID (avg 4 OOD sets)AUROC: 76.77 -> 89.00Improved
use BEiT pretraining instead of classification ViT (ablation)Energy score · ImageNet ID (avg 4 OOD sets)AUROC: 65.85 -> 89.85Improved
use BEiT pretraining instead of classification ViT (ablation)Residual score · ImageNet ID (avg 4 OOD sets)AUROC: 74.86 -> 94.88Improved
use DINOv2 contrastive pretraining instead of classification ViT (ablation)ViM score · ImageNet ID (avg 4 OOD sets)AUROC: 77.65 -> 61.32Hurt
use MoCov3 contrastive pretraining instead of classification ViT (ablation)ViM score · ImageNet ID (avg 4 OOD sets)AUROC: 77.65 -> 72.07Hurt
use BEiT pretraining instead of classification ViT (ablation)ViM score · CIFAR-10 ID (avg 4 OOD sets)AUROC: 99.63 -> 99.98Improved
use BEiT pretraining instead of DINOv2 (ablation)MSP score · CIFAR-10 ID (avg 4 OOD sets)AUROC: 76.59 -> 59.68Hurt
MOODv2 (BEiT with ViM, no ID finetuning variant) over MOODv1MOOD · ImageNet ID (avg 4 OOD sets)AUROC: 93.51 -> 95.68Improved
MOODv2 over MOODv1MOOD · ImageNet ID (avg 4 OOD sets)FPR95: 31.60 -> 20.22Improved
MOODv2 over MOODv1MOOD · CIFAR-10 one-class (avg)AUROC: 97.83 -> 98.20Improved
MOODv2 over MOODv1MOOD · CIFAR-10 one-class (avg)FPR95: 10.33 -> 9.49Improved

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