AI Paper Atlas

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

Domain Adaptation with a Single Vision-Language Embedding

Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette

IJCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 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
fine-tune classifier on PIN-augmented features from a single promptsource-only model · ACDC Night (CS source)mIoU (%): 18.31 -> 25.03Improved
use PODA instead of CLIPstyler stylized imagessource-only model · Cityscapes (GTA5 source)mIoU (%): 31.50 -> 40.08Improved
CLIPstyler stylized images for adaptationsource-only model · ACDC Rain (CS source)mIoU (%): 38.20 -> 37.17Hurt
freeze CLIP backbone during source training (ablation)CLIP-RN50 segmenter · ACDC Snow (CS source)mIoU (%): 22.27 -> 39.28Improved
augment Layer2/3/4 features in addition to Layer1 (ablation)PODA · ACDC Night (CS source)mIoU (%): 25.03 -> 23.43, 22.93, 21.05Hurt
increase number of mined styles from 1 to 2975 (ablation)PODA · ACDC Night (CS source)mIoU (%): 16.00 -> 25.03Improved
use semantically unrelated random prompts (ablation)PODA · ACDC Night (CS source)mIoU (%): 25.03 -> 20.45Hurt
paraphrase prompt with ChatGPT (relevant prompts) (ablation)PODA · ACDC Night (CS source)mIoU (%): 25.03 -> 24.82No clear effect
add optimized concept S* to style text (ablation)PODA · ACDC Snow (CS source)mIoU (%): 43.90 -> 44.72Improved
use style text only without content word driving (ablation)PODA · ACDC Snow (CS source)mIoU (%): 43.90 -> 40.45Hurt
initialize style stats from zeros/ones instead of source statistics (ablation)PODA · ACDC Night (CS source)mIoU (%): 25.03 -> 8.59Hurt
skip source-only pretraining, train from scratch on augmented features (ablation)PODA · ACDC Snow (CS source)mIoU (%): 43.90 -> 36.73Hurt

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