AI Paper Atlas

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

Distribution-Matching Embedding for Visual Domain Adaptation

Mahsa Baktashmotlagh, Mehrtash Harandi, Mathieu Salzmann

JMLR 2016 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 91 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 nonlinear mapping (NL-DME-H instead of DME-H)DME-H · Office+Caltech SURF kernel SVMaverage recognition accuracy (%): 52.3 -> 52.5Improved
add nonlinear mapping (NL-DME-H instead of DME-H)DME-H · Office+Caltech Decaf6 kernel SVMaverage recognition accuracy (%): 86.7 -> 87.9Improved
use Hellinger distance instead of MMD (DME-H vs DME-MMD)DME · Office+Caltech SURF kernel SVMaverage recognition accuracy (%): 50.9 -> 52.3Improved
use Hellinger distance instead of MMD (DME-H vs DME-MMD)DME · Office+Caltech Decaf7 linear SVMaverage recognition accuracy (%): 87.2 -> 87.7Improved
replace Gaussian kernel with degree-2 polynomial kernel in MMD (ablation)DME-MMD · Office+Caltech SURF kernel SVMaverage recognition accuracy (%): 50.9 -> 50.4No clear effect
add distribution matching (DME-H) over no adaptationNO ADAPT-SVM · Office+Caltech SURF kernel SVMaverage recognition accuracy (%): 44 -> 52.3Improved
add distribution matching (NL-DME-H) over no adaptationNO ADAPT-SVM · Office+Caltech Decaf8 kernel SVMaverage recognition accuracy (%): 79.7 -> 82.4Improved
add distribution matching (NL-DME-H) over no adaptationNO ADAPT-SVM · Office+Caltech Decaf8 linear SVMaverage recognition accuracy (%): 77.6 -> 79.3 (SVMA 80.5 higher)Hurt
use NL-DME-H instead of DDC deep domain confusionDDC · Office+Caltech 6 pairs Decaf7average recognition accuracy (%): 84.6 -> 85.2Improved
use NL-DME-H instead of SASA · Office+Caltech Decaf7 kernel SVMaverage recognition accuracy (%): 89.8 -> 88.3Hurt

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