AI Paper Atlas

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

Universal Domain Adaptation

Kaichao You, Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan

CVPR 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 501 citations (OpenAlex)

Check 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
use sample-level transferability weighting with domain similarity and prediction uncertaintyUAN · Office-Home (ξ = 0.15)average class accuracy (%): 73.39 -> 77.02Improved
use sample-level transferability weighting with domain similarity and prediction uncertaintyUAN · Office-31 (ξ = 0.32)average class accuracy (%): 86.68 -> 89.24Improved
use sample-level transferability weighting with domain similarity and prediction uncertaintyUAN · ImageNet-Caltech (ξ = 0.07), I → Caverage class accuracy (%): 72.19 -> 75.28Improved
use sample-level transferability weighting with domain similarity and prediction uncertaintyUAN · ImageNet-Caltech (ξ = 0.07), C → Iaverage class accuracy (%): 67.36 -> 70.17Improved
use sample-level transferability weighting with domain similarity and prediction uncertaintyUAN · VisDA2017 (ξ = 0.50)average class accuracy (%): 58.72 -> 60.83Improved
add domain similarity to the sample-level transferability criterion (ablation)UAN · Office-Home (ξ = 0.15)average class accuracy (%): 75.39 -> 77.02Improved
add prediction uncertainty to the sample-level transferability criterion (ablation)UAN · Office-Home (ξ = 0.15)average class accuracy (%): 72.91 -> 77.02Improved

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