AI Paper Atlas

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

Pareto Domain Adaptation

Fangrui Lv, Jian Liang, Kaixiong Gong, Shuang Li, Chi Harold Liu, Han Li, Di Liu, Guoren Wang

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 8 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 ParetoDA to DANNDANN · Office-31average accuracy: 82.2 -> 90.2Improved
add ParetoDA to CDANCDAN · Office-31average accuracy: 87.7 -> 90.4Improved
add ParetoDA to MDDMDD · Office-31average accuracy: 88.9 -> 90.1Improved
add ParetoDA to DANNDANN · Office-Homeaverage accuracy: 57.6 -> 69.4Improved
add ParetoDA to CDANCDAN · Office-Homeaverage accuracy: 65.8 -> 70.6Improved
add ParetoDA to DANNDANN · VisDA-2017average accuracy: 57.4 -> 82.4Improved
add ParetoDA to CDANCDAN · VisDA-2017average accuracy: 73.9 -> 83.2Improved
add ParetoDA to AdvEntAdvEnt · GTA5 to CityscapesmIoU: 43.8 -> 46.1Improved
add ParetoDA to FDAFDA · GTA5 to CityscapesmIoU: 44.6 -> 47.2Improved
add ParetoDA to CBSTCBST · GTA5 to CityscapesmIoU: 45.2 -> 48.1Improved
use TCM loss instead of IM loss as guidance (ablation)DANN · Office-31average accuracy: 87.9 -> 88.4Improved
add conventional Pareto optimization (EPO) with fixed preference (ablation)DANN · Office-31average accuracy: 82.2 -> 87.7Improved

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