AI Paper Atlas

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

GalLop: Learning global and local prompts for vision-language models

Marc Lafon, Elias Ramzi, Clément Rambour, Nicolas Audebert, Nicolas Thome

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Robust fine-tuning for OOD generalization · 42 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
combine learned global and local prompts in GalLoP (ablation)GalLoP · ImageNet 16-shottop-1 accuracy: 72.0 -> 75.1Improved
naively combine CoOp global and CoOp local prompts (ablation)CoOp · ImageNet 16-shottop-1 accuracy: 71.4 -> 69.5Hurt
combine global and local prompts in GalLoP on OOD detection (ablation)GalLoP · ImageNet OOD benchmarkFPR95: -8.9pt FPR95 vs local onlyImproved
keep only top-k local features (sparsity) instead of all (ablation)local prompt learning · ImageNet 16-shottop-1 accuracy: +18.4pt (zero-shot), +17.6pt (local prompt), +8.5pt (with linear)Improved
align local prompt with a linear projection (ablation)local prompt · ImageNet 16-shot, k=10top-1 accuracy: +10ptImproved
add prompt dropout when learning multiple global prompts (ablation)global prompts · ImageNet 16-shottop-1 accuracyImproved
increase local prompt scales from 1 to 4 (ablation)local prompts · ImageNet 16-shottop-1 accuracy: +1ptImproved
increase local prompt scales beyond 4 (ablation)local prompts · ImageNet 16-shottop-1 accuracyNo clear effect
use GalLoP instead of domain-generalization-specific PromptSRCdomain generalization · ImageNet variants averagetop-1 accuracy: +0.5pt average, +4.9pt ImageNetImproved
use GalLoP instead of LoCoOp for OOD detectionOOD detection · ImageNet OOD benchmarkFPR95: -1.4pt FPR95, +3.6pt top-1Improved

Later papers that compared with this method

2 later accepted papers report GalLoP as a baseline in their results tables; 1 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