AI Paper Atlas

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

Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score

Myong Chol Jung, Joanna F. Dipnall, Belinda Gabbe, He Zhao

IJCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 3 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 CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreCoOp · Near OOD, 13 datasets average (16-shot)AUROC: 80.74 -> 81.84Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreCoCoOp · Near OOD, 13 datasets average (16-shot)AUROC: 81.09 -> 82.74Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreIVLP · Near OOD, 13 datasets average (16-shot)AUROC: 81.12 -> 84.34Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreKgCoOp · Near OOD, 13 datasets average (16-shot)AUROC: 80.84 -> 83.12Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreProGrad · Near OOD, 13 datasets average (16-shot)AUROC: 79.77 -> 82.35Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreMaPLe · Near OOD, 13 datasets average (16-shot)AUROC: 81.06 -> 83.94Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scorePromptSRC · Near OOD, 13 datasets average (16-shot)AUROC: 83.85 -> 85.77Improved
add CLS-M scoring (subtract scaled null-class similarity) to the MaxLogit scoreLoCoOp · Near OOD, 13 datasets average (16-shot)AUROC: 77.55 -> 81.74Improved
add CLS-E scoring to the Energy scorePromptSRC 16-shot · Near OOD, 13 datasets averageAUROC: 84.60 -> 87.10Improved
use CLS-M instead of LoCoOp GL-MCMPromptSRC 16-shot · Near OOD, 13 datasets averageAUROC: 80.87 -> 87.07Improved
use CLS-M instead of MaxLogitLoCoOp · Far OOD, ImageNet ID averageAUROC: 96.92 -> 97.72Improved
use CLS-E instead of EnergyLoCoOp · Far OOD, ImageNet ID averageAUROC: 94.97 -> 96.91Improved

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