AI Paper Atlas

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

FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection

Xinhua Lu, Runhe Lai, Yanqi Wu, Kanghao Chen, Wei-Shi Zheng, Ruixuan Wang

ICCV 2025 · 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
use forced cross-entropy loss FCE-K instead of standard CE (ablation)FA · ImageNet-1k OOD (16-shot) GL-MCMFPR95: 34.29 -> 25.68Improved
use forced cross-entropy loss FCE-K instead of standard CE (ablation)FA · ImageNet-1k OOD (16-shot) MCMAUROC: 91.01 -> 93.77Improved
add manual initialization to the original (reference) prompt (ablation)FA · ImageNet-1k OOD (16-shot) GL-MCMFPR95: 34.88 -> 26.39Improved
add manual initialization to the forced prompt on top of manual original prompt (ablation)FA · ImageNet-1k OOD (16-shot) GL-MCMFPR95: 26.39 -> 25.68Improved
manually initialize only the forced prompt (original prompt random) (ablation)FA · ImageNet-1k OOD (16-shot) GL-MCMFPR95: 34.88 -> 36.03Hurt
use shared learnable vector instead of per-class independent vectors (random init) (ablation)FA · ImageNet-1k OOD (16-shot) GL-MCMFPR95: 46.29 -> 34.88Improved
use shared learnable vector with manual init (ablation)FA · ImageNet-1k OOD (16-shot) MCMFPR95: 34.69 -> 29.07Improved
increase forced coefficient K from 1 to 6 (ablation)FA · ImageNet-1k OODAUROCNo clear effect
FA with GL-MCM vs SCT_GL baselineFA_GL · ImageNet-1k OOD (16-shot)FPR95: 27.27 -> 25.68Improved
FA_MCM vs SCT_GL baseline in 1-shotFA_MCM · ImageNet-1k OOD (1-shot)FPR95: 31.62 -> 31.37Improved
FA on SUN OOD set in 16-shot vs SCT_GLFA_GL · ImageNet-1k OOD SUN (16-shot)FPR95: 20.00 -> 27.65Hurt
FA_MCM vs LoCoOp_GL on EuroSAT IDFA_MCM · EuroSAT as ID (16-shot)FPR95: 78.69 -> 39.99Improved

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