AI Paper Atlas

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

Label-Free Text Prototype Adaptation for Open Vocabulary Segmentation

Keli Wang, Meixuan Li, Tianyu Li, Guoqing Wang

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 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 prototype refinement (fixed step) (ablation)SegEarth-OV · VaihingenmIoU: 29.1 -> 31.5Improved
add confident pixel selection (ablation)+P · VaihingenmIoU: 31.5 -> 32.9Improved
add reliability score and scaled step size (ablation)+P +A · VaihingenmIoU: 32.9 -> 35.3Improved
add reliability-aware orthogonalisation (ablation)+P +A +B · VaihingenmIoU: 32.9 -> 34.9Improved
combine scaled step and orthogonalisation (ablation)+P +A +B · VaihingenmIoU: 35.3 -> 37.2Improved
add pixel selection to reliability estimation (ablation)VPTA · VaihingenmIoU: 35.6 -> 37.2Improved
use reliability-descending ordering instead of random (ablation)VPTA · VaihingenmIoU: 36.4 -> 37.2Improved
replace class names with stronger naming (set C) (ablation)SegEarth-OV · VaihingenmIoU: 29.1 -> 40.1Improved
apply VPTA under stronger naming (ablation)SegEarth-OV · Vaihingen (C naming)mIoU: 40.1 -> 41.5Improved
adapt on LoveDA RGB images, evaluate on Vaihingen (ablation)VPTA · VaihingenmIoU: 40.1 -> 21.9Hurt
pool Vaihingen and Potsdam images for adaptation (ablation)VPTA · VaihingenmIoU: 40.1 -> 42.0Improved
use large uniform step beta=0.30 instead of reliability-scaled step (ablation)VPTA · LoveDAmIoUHurt

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