AI Paper Atlas

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

Open-Vocabulary Domain Generalization in Urban-Scene Segmentation

Dong Zhao, Qi Zang, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 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
replace cross-attention aggregation with selective SSM (ablation)CAT-Seg · Dv-19 avg, ViT-B/16 (CS-7)mIoU: 43.5 -> 45.6Improved
replace cross-attention aggregation with selective SSM (ablation)CAT-Seg · Dv-58 avg, ViT-B/16 (CS-7)mIoU: 43.5 -> 44.1Improved
add image/text-conditioned modulation (ablation)SSM aggregation · Dv-19 avg, ViT-B/16 (CS-7)mIoU: 45.6 -> 47.6Improved
add learnable geometric decay (ablation)SSM aggregation · Dv-19 avg, ViT-B/16 (CS-7)mIoU: 47.6 -> 48.3Improved
add chunk-wise aggregation (ablation)SSM aggregation · Dv-19 avg, ViT-L/14 (CS-7)mIoU: 53.2 -> 55.3Improved
add snake scanning (ablation)SSM aggregation · Dv-58 avg, ViT-B/16 (CS-7)mIoU: 47.3 -> 47.9Improved
use S2-Corr instead of CAT-Seg (real-to-real)CAT-Seg · Dv-19 avg, ViT-B/16 (CS-7)mIoU: 43.5 -> 50.3Improved
use S2-Corr instead of CAT-Seg (synthetic-to-real)CAT-Seg · Dv-58 avg, ViT-L/14 (GTA-7)mIoU: 48.2 -> 49.4Improved
train on COCO-Stuff instead of driving dataCAT-Seg · Dv-19mIoU: 49.3 -> 31.6Hurt
move training domain from synthetic GTA to real CityscapesCAT-Seg · Dv-19mIoU: 47.5 -> 49.3Improved
use S2-Corr instead of CAT-Seg for inference efficiencyCAT-Seg · vocab150 throughputFPS: 5.7 -> 18.3Improved
use S2-Corr instead of CAT-Seg for GPU memoryCAT-Seg · GPU memoryGPU memory (GB): 13.8 -> 9.2Improved

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