AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Generalizing Vision-Language Models with Dedicated Prompt Guidance

Xinyao Li, Yinjie Min, Hongbo Chen, Zhekai Du, Fengling Li, Jingjing Li

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 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 GuiDG to ERM (WF) fine-tuningERM (WF), CLIP ViT-B/16 · ImageNet-DG 16-shotaccuracy: 66.2 -> 67.9Improved
add GuiDG to ERM (WF) in 8-shot few-shot DGERM (WF), CLIP ViT-B/16 · OfficeHome 8-shotaccuracy: 82.7 -> 85.2Improved
add GuiDG to ERM (WF) with full dataERM (WF), CLIP ViT-B/16 · DomainNet full dataaccuracy: 60.2 -> 61.7Improved
add GuiDG to CLIPood with full dataCLIPood, CLIP ViT-B/16 · DomainNet full dataaccuracy: 63.4 -> 63.4No clear effect
add GuiDG to CLIPood on PACSCLIPood, CLIP ViT-B/16 · PACSaccuracy: 97.3 -> 97.3No clear effect
add GuiDG to CLIPood on TerraIncognitaCLIPood, CLIP ViT-B/16 · TerraIncognitaaccuracy: 60.0 -> 60.9Improved
add GuiDG to UEO (WF) on VLCSUEO (WF), CLIP ViT-B/16 · VLCSaccuracy: 81.3 -> 84.2Improved
add GuiDG to CLIPood on single-source ImageNet 16-shotCLIPood, CLIP ViT-B/16 · Single-source ImageNet 16-shotaccuracy: 62.7 -> 63.5Improved
add GuiDG to CLIPood on OfficeHome-Prod 16-shotCLIPood, CLIP ViT-B/16 · OfficeHome 16-shot, Art domainaccuracy: 86.2 -> 87.6Improved
train multiple domain experts instead of a single prompt (Step 1) (ablation)GuiDG · ImageNet-DG 16-shot ERM (WF)avg accuracyImproved
use learnable CMAttn weights instead of simple averaging (ablation)GuiDG · ImageNet-DG 16-shot ERM (WF)avg accuracyImproved
use i.i.d. data split between Step 1 and Step 2 (ablation)GuiDG · ImageNet-DG 16-shot ERM (WF)avg accuracyImproved

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