AI Paper Atlas

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

Two-phase Pseudo Label Densification for Self-training based Domain Adaptation

Inkyu Shin, Sanghyun Woo, Fei Pan, In So Kweon

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 124 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 TPLDCRST(MRKLD) · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 47.0 -> 51.2Improved
add TPLDCRST(MRKLD) · GTA5->Cityscapes (rare classes, Deeplabv2-ResNet101)R-mIoU: 30.3 -> 35.1Improved
add TPLDCRST(MRKLD) · SYNTHIA->Cityscapes (Deeplabv3-ResNet101, 13 classes)mIoU*: 48.1 -> 55.7Improved
add TPLDCBST · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 45.9 -> 47.8Improved
add TPLDCRST(LRENT) · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 45.9 -> 47.3Improved
add TPLDCBST · SYNTHIA->Cityscapes (Deeplabv2-ResNet101)mIoU: 42.6 -> 45.6Improved
add TPLDCRST(LRENT) · SYNTHIA->Cityscapes (Deeplabv2-ResNet101)mIoU: 42.7 -> 47.0Improved
lower selection threshold of CRST (p=0.4) (ablation)CRST · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 47.0 -> 47.1No clear effect
lower selection threshold of CRST (p=0.6) (ablation)CRST · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 47.0 -> 45.7Hurt
add voting stage before easy-hard classification (ablation)TPLD · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 38.1 -> 51.2Improved
add easy-hard classification stage (ablation)TPLD · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 49.5 -> 51.2Improved
order voting first then easy-hard classification (ablation)TPLD · GTA5->Cityscapes (Deeplabv2-ResNet101)mIoU: 49.1 -> 51.2Improved

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