AI Paper Atlas

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

Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection

Wenjun Miao, Guansong Pang, Zihan Wang, Jin Zheng, Xiao Bai

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 1 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 auxiliary outlier data via APT to SCTSCT (1-shot) · ImageNet-1k-OOD hard OODAUROC: 56.70 -> 65.62Improved
plug APT into LoCoOp and IDLikeLoCoOp, IDLike (1-shot) · ImageNet-1k standard OOD averageFPR95: 32.79 -> 28.02 (LoCoOp); 34.72 -> 31.05 (IDLike)Improved
add background regularization from auxiliary data (Back) (ablation)SCT (1-shot) · Standard OOD averageFPR95: 31.09 -> 29.02Improved
add foreground-background pair regularization (Pair) (ablation)SCT (1-shot) · ImageNet-1k-OODAUROC: 56.70 -> 63.10Improved
add Pair regularization on top of Back (ablation)SCT (1-shot) · ImageNet-1k-OODAUROC: 58.65 -> 65.62Improved
use Outlier Exposure (OE) with auxiliary data instead of APT (ablation)SCT (1-shot) · Standard OOD averageFPR95: 31.09 -> 36.47Hurt
use EnergyOE with auxiliary data (ablation)SCT (1-shot) · ImageNet-1k-OODFPR95: 94.06 -> 96.98Hurt
regularize foreground regions directly (Fore) without pairing (ablation)SCT (1-shot) · Places365 and SUN scene OODFPR95Hurt
APT on Textures OOD setSCT (1-shot) · TexturesFPR95: 48.87 -> 50.96Hurt
increase auxiliary data quantity relative to ID data (ablation)APT · ImageNet-1K 1-shotFPR95Improved
few-shot prompt tuning methods vs zero-shot on hard OODLoCoOp, IDLike, SCT · ImageNet-1k-OODAUROC: GL-MCM 60.32 vs LoCoOp 54.40Hurt

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