AI Paper Atlas

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

Zero-Shot Domain Generalization via Domain Prompt Learning

Shiming Chen, Salman Khan, Salman Khan, Fahad Shahbaz Khan

IJCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 0 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 visual domain learning (VDL) on top of text domain learning (ablation)DoP · DG average (4 datasets, ViT-B/16)accuracy: 75.8 -> 82.0Improved
add text domain learning (TDL) on top of visual domain learning (ablation)DoP · DG average (4 datasets, ViT-B/16)accuracy: 77.1 -> 82.0Improved
add style token selection (STS) in TDL (ablation)DoP · DG average (4 datasets, ViT-B/16)accuracy: 81.4 -> 82.0Improved
prompt with unlearned 'A random style of a [class]' (DP) instead of standard promptZS-CLIP · ZSDG average (ViT-B/16)accuracy: 79.6 -> 76.3Hurt
prompt with unlearned random style (DP) instead of standard promptZS-CLIP · ZSDG average (ViT-L/14)accuracy: 83.0 -> 80.0Hurt
prompt with unlearned random style (DP) instead of standard promptZS-CLIP · ZSDG average (ResNet-50)accuracy: 70.2 -> 72.7Improved
use DoP instead of PromptStyler (selection plus visual refinement)PromptStyler · DG average (ViT-B/16)accuracy: 80.8 -> 82.0Improved
use DoP instead of PromptStylerPromptStyler · DG average (ResNet-50)accuracy: 74.7 -> 74.9Improved
use DoP instead of PromptStyler on PACS SketchPromptStyler · PACS Sketch (ViT-B/16)accuracy: 92.3 -> 91.5Hurt
use DoP instead of TPT with ViT-L/14TPT · ZSDG average (ViT-L/14)accuracy: 84.1 -> 83.3Hurt
refine only the selected style token instead of many prompt parametersTPT · PACS per-image test time (ms)time: 462.8 -> 170.5Improved
vary number of style tokens K too small or too large (ablation)DoP · PACS / OfficeHomeaccuracyMixed

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