AI Paper Atlas

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

Adversarial Unsupervised Domain Adaptation With Conditional and Label Shift: Infer, Align and Iterate

Xiaofeng Liu, Zhenhua Guo, Site Li, Fangxu Xing, Jane You, C.-C. Jay Kuo, Georges El Fakhri, Jonghye Woo

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 89 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 joint parameterization of discriminator and classifier (ablation)CLS · VisDA17-valmean accuracy: 80.8 -> 81.6Improved
add fade-in of estimated target label distribution p_t(y) (ablation)CLS · VisDA17-valmean accuracy: 81.3 -> 81.6Improved
add joint parameterization to CLS+TDDA (ablation)CLS+TDDA · VisDA17-valmean accuracy: 82.2 -> 82.9Improved
combine CLS with TDDACLS · VisDA17-valmean accuracy: 81.6 -> 82.9Improved
use ResNet152 backbone instead of ResNet101CLS · VisDA17-valmean accuracy: 81.6 -> 83.8Improved
add joint parameterization (adversarial base) (ablation)CLS · GTA5 to CityscapesmIoU: 50.8 -> 51.2Improved
add joint parameterization (self-training combination) (ablation)CLS · GTA5 to CityscapesmIoU: 52.5 -> 53.0Improved
add joint parameterization on Office-31 partial UDA (ablation)CLS · Office-31 partial UDA (ResNet-50)mean accuracy: 97.94 -> 98.24Improved
add joint parameterization on ImageNet-Caltech partial UDA (ablation)CLS · ImageNet-Caltech partial UDA (ResNet-50)average accuracy: 83.52 -> 84.76Improved
replace DANN with CLS (conditional and label alignment)DANN · VisDA17-valmean accuracy: 57.4 -> 81.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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