AI Paper Atlas

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

Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation

Zhengming Ding, Sheng Li, Ming Shao, Yun Fu

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 138 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
use soft-label MMD instead of hard-label MMD (ablation)GAKT · Office+Home 12 tasksaccuracy (%): soft-label version improves 1-2%Improved
add joint feature learning and label propagation over LP baselineLP · Office+Home Ar→Claccuracy (%): 20.36 -> 34.49Improved
add joint subspace learning and soft labels over label propagation on original featuresLP · Office-31+Caltech-256 C→Waccuracy (%): 80.34 -> 95.36Improved
replace separate label propagation and hard labels (LSC) with joint soft-label adaptationLSC · Office-31+Caltech-256 C→Waccuracy (%): 91.18 -> 95.36Improved
replace separate label propagation and hard labels (LSC) with joint soft-label adaptationLSC · Office+Home Ar→Claccuracy (%): 31.81 -> 34.49Improved
our method versus LSC on Office-31 A→CLSC · Office-31+Caltech-256 A→Caccuracy (%): 88.81 -> 90.18Improved
our method versus WDAN on Office-31 A→CWDAN · Office-31+Caltech-256 A→Caccuracy (%): 92.26 -> 90.18Hurt
our method versus LSC on Office+Home Rw→ClLSC · Office+Home Rw→Claccuracy (%): 42.88 -> 44.58Improved
our method versus DHN on Office+Home Rw→ClDHN · Office+Home Rw→Claccuracy (%): 45.13 -> 44.58Hurt
vary lambda in range 1 to 10 (ablation)GAKT · Office-31+Caltech-256 C→D, W→C, D→Aaccuracy (%)No clear effect
increase projection dimension (ablation)GAKT · Office-31+Caltech-256 C→D, W→C, D→Aaccuracy (%)Improved

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