AI Paper Atlas

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

Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training

Yang Zou, Zhiding Yu, B.V.K. Vijaya Kumar, Jinsong Wang

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 1,483 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 class-balanced pseudo-label selection (CBST) to self-training (ablation)ST, ResNet-38 · GTA5 to CityscapesmIoU (%): 41.5 -> 45.2Improved
add class-balanced selection (CBST) to self-training (ablation)ST, FCN8s-VGG16 · GTA5 to CityscapesmIoU (%): 28.1 -> 30.9Improved
add spatial priors to CBST (ablation)CBST, FCN8s-VGG16 · GTA5 to CityscapesmIoU (%): 30.9 -> 36.1Improved
add spatial priors to CBST (ablation)CBST, ResNet-38 · GTA5 to CityscapesmIoU (%): 45.2 -> 46.2Improved
add multi-scale testing (0.5,0.75,1.0) (ablation)CBST-SP, ResNet-38 · GTA5 to CityscapesmIoU (%): 46.2 -> 47.0Improved
add self-training (ST) over source-only modelResNet-38 · GTA5 to CityscapesmIoU (%): 35.4 -> 41.5Improved
add class-balanced selection (CBST) to self-training (ablation)ST, ResNet-38 · SYNTHIA to Cityscapes (16 classes)mIoU (%): 32.2 -> 42.5Improved
add class-balanced selection (CBST) to self-training (ablation)ST, FCN8s-VGG16 · SYNTHIA to Cityscapes (16 classes)mIoU (%): 23.9 -> 35.4Improved
add class-balanced selection (CBST) to self-training (ablation)ST, ResNet-38 · Cityscapes to NTHU (Rome)mIoU (%): 48.9 -> 53.6Improved
add class-balanced selection (CBST) to self-training (ablation)ST, ResNet-38 · Cityscapes to NTHU (Taipei)mIoU (%): 44.6 -> 50.3Improved
add class-balanced selection (CBST) to self-training (ablation)ST, ResNet-38 · Cityscapes to NTHU (Tokyo)mIoU (%): 44.6 -> 48.8Improved
add class-balanced selection (CBST) to self-training (ablation)ST, ResNet-38 · Cityscapes to NTHU (Rio)mIoU (%): 50.8 -> 52.2Improved

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