AI Paper Atlas

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

Uncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation

Yuxi Wang, Junran Peng, ZhaoXiang Zhang

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 113 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 adversarial adaptation (ablation)source-only model · GTA5->CityscapesmIoU: 36.6 -> 42.9Improved
add image translation (ablation)AA baseline · GTA5->CityscapesmIoU: 42.9 -> 45.3Improved
add soft-balance resampling on source domain (ablation)AA+IT · GTA5->CityscapesmIoU: 45.3 -> 46.1Improved
add target-guided uncertainty rectifying adversarial adaptation (TGAA) (ablation)AA+IT+SR · GTA5->CityscapesmIoU: 46.1 -> 48.8Improved
add uncertainty-aware pseudo-label self-training (UPST) (ablation)UncerDA (AA) · GTA5->CityscapesmIoU: 48.8 -> 52.6Improved
use class-balance sampling instead of no balance (ablation)multi-level adaptation baseline · GTA5->CityscapesmIoU: 42.9 -> 45.7Improved
use soft-balance sampling lambda 0.9 instead of class-balance (ablation)multi-level adaptation baseline · GTA5->CityscapesmIoU: 45.7 -> 46.1Improved
use focal loss instead of no balance (ablation)multi-level adaptation baseline · GTA5->CityscapesmIoU: 42.9 -> 44.5Improved
use uncertainty-aware pseudo labels instead of CBST (ablation)AdaptSegNet · GTA5->CityscapesmIoU: 47.1 -> 47.8Improved
use uncertainty-aware pseudo labels instead of CBST (ablation)MRNet · GTA5->CityscapesmIoU: 49.7 -> 51.2Improved
use uncertainty-aware pseudo labels instead of CBST (ablation)UncerDA (AA) · GTA5->CityscapesmIoU: 51.2 -> 52.6Improved
vary top-k uncertain classes from 5 to 9 (ablation)UncerDA · GTA5/SYNTHIA->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