AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey

Jindong Li, Yongguang Li, Yali Fu, Jiahong Liu, Yixin Liu, Menglin Yang, Irwin King

TPAMI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 33 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 prompt tuning (CoOp) to zero-shot CLIPCLIP ViT-B/16 · DG average (PACS, VLCS, Office-Home, DomainNet)accuracy (%): 77.3 -> 80.2Improved
add image-conditional prompts (CoCoOp) over CoOpCoOp · DG average (PACS, VLCS, Office-Home, DomainNet)accuracy (%): 80.2 -> 80.2No clear effect
add style-aware prompt learning (StyLIP) over CoOpCoOp · DG average (PACS, VLCS, Office-Home, DomainNet)accuracy (%): 80.2 -> 82.9Improved
add deeper multimodal prompts (MaPLe) over CoOpCoOp · DG average (PACS, VLCS, Office-Home, DomainNet)accuracy (%): 80.2 -> 80.4No clear effect
use source-free style prompts (PromptStyler) instead of source-based CoOpCoOp · DG average (PACS, VLCS, Office-Home, DomainNet)accuracy (%): 80.2 -> 80.8No clear effect
add CLIPood over zero-shot CLIPCLIP ViT-B/16 · DomainNet (DG)accuracy (%): 54.1 -> 63.5Improved
add domain adaptive prompts (DAPL) to zero-shot CLIPCLIP ResNet-50 · Office-Home DA average (ResNet-50)accuracy (%): 71.8 -> 74.5Improved
add ProDe source-free adaptation over DIFODIFO · Office-Home DA average (ResNet-50)accuracy (%): 79.4 -> 81.1Improved
scale CLIP backbone from ResNet-50 to ViT-BCLIP zero-shot · Office-Home DA averageaccuracy (%): 71.8 -> 82.4Improved
use ViT-B/32 instead of ViT-B/16 for ProDeProDe · Office-Home DA averageaccuracy (%): 84.5 vs 81.1 ResNet; below ViT-B/16 DAMP 87.1Hurt
source-free CDBN vs source-available DAMP (ViT-B)DAMP · Office-Home DA average (ViT-B)accuracy (%): 87.1 -> 86.2Hurt
add CMKD over DAPL (ViT-B)DAPL · Office-Home DA average (ViT-B)accuracy (%): 84.4 -> 88.4Improved

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