AI Paper Atlas

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

LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

Yabin Zhang, Wenjie Zhu, Chenhang He, Lei Zhang

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 17 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
replace hand-crafted prompts with learned label-driven promptsNegLabel · ImageNet-1k, 4 OOD datasets averageFPR95: 25.40 -> 23.40Improved
replace hand-crafted prompts with LAPT on near-OODNegLabel · OpenOOD near-OODAUROC: 76.92 -> 82.63Improved
replace hand-crafted prompts with LAPT on far-OODNegLabel · OpenOOD far-OODAUROC: 93.30 -> 94.26Improved
learned prompts also raise ID classification accuracyNegLabel · OpenOOD ImageNet-1kID accuracy: 66.82 -> 67.86Improved
use distribution-aware prompts instead of unified or class-specific prompts (ablation)LAPT · OpenOODOOD detectionImproved
use longer learnable prompts (ablation)LAPT · OpenOODOOD detectionHurt
initialize prompts with 'The nice' instead of random (ablation)LAPT · OpenOODOOD detectionMixed
move class label position within the prompt (ablation)LAPT · OpenOODOOD detectionNo clear effect
use synthetic images instead of retrieved real images for training (ablation)LAPT · OpenOODOOD detectionImproved
combine synthetic and real images (ablation)LAPT · OpenOODOOD detectionImproved
use a stronger text-to-image generator (ablation)LAPT · OpenOODOOD detectionImproved
use larger-scale WebData for retrieval (ablation)LAPT · OpenOODOOD detectionImproved

Later papers that compared with this method

2 later accepted papers report LAPT as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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