AI Paper Atlas

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

A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes

Yang Zhang, Philip David, Hassan Foroosh, Boqing Gong

TPAMI 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 146 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 curriculum domain adaptation with image and landmark-superpixel label distributionsFCN-8s · GTA to CityscapesmIoU: 22.3 -> 28.9Improved
add curriculum domain adaptation with image and landmark-superpixel label distributionsFCN-8s · SYNTHIA to CityscapesmIoU: 22.0 -> 29.0Improved
add color constancy preprocessing to the full method (ablation)Ours (I+SP) · GTA to CityscapesmIoU: 28.9 -> 31.4Improved
add color constancy preprocessing to the full method (ablation)Ours (I+SP) · SYNTHIA to CityscapesmIoU: 29.0 -> 29.7Improved
add landmark superpixel distributions to image label distributions (ablation)Ours (I) · GTA to CityscapesmIoU: 23.1 -> 28.9Improved
add global image label distributions to landmark superpixel distributions (ablation)Ours (SP) · SYNTHIA to CityscapesmIoU: 28.1 -> 29.0Improved
add global image label distributions to landmark superpixel distributions (ablation)Ours (SP) · GTA to CityscapesmIoU: 27.8 -> 28.9Improved
add color constancy to the no-adaptation baseline (ablation)NoAdapt · GTA to CityscapesmIoU: 22.3 -> 26.2Improved
add color constancy to the no-adaptation baseline (ablation)NoAdapt · SYNTHIA to CityscapesmIoU: 22.0 -> 22.6Improved
replace CNN superpixel features with handcrafted BOW+FV features (ablation)Ours (CC) · GTA to CityscapesmIoU: 28.3 vs NoAdapt (CC) 26.2No clear effect
use landmark superpixels at 400 instead of 50 superpixels per image (ablation)SP (CC) · GTA to CityscapesmIoU: 22.9 -> 27.4Improved
use label distributions of all superpixels instead of only landmarks (ablation)Ours (SP) · GTA to CityscapesmIoUNo clear effect

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