AI Paper Atlas

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

Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

Yang Zhang, Philip David, Boqing Gong

ICCV 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 515 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 with image-level label distribution (ablation)NoAdapt · GTA -> Cityscapesmean IoU: 22.3 -> 23.1Improved
add superpixel label-distribution constraint (ablation)NoAdapt · GTA -> Cityscapesmean IoU: 22.3 -> 27.8Improved
combine image-level and superpixel label distributions (ablation)Ours (SP) · GTA -> Cityscapesmean IoU: 27.8 -> 28.9Improved
combine image-level and superpixel label distributions (ablation)Ours (I) · GTA -> Cityscapesmean IoU: 23.1 -> 28.9Improved
curriculum adaptation vs prior superpixel baselineSP · GTA -> Cityscapesmean IoU: 26.8 -> 28.9Improved
curriculum adaptation vs FCN in the WildFCN Wld · GTA -> Cityscapesmean IoU: 27.1 -> 28.9Improved

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