AI Paper Atlas

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

Regularized Wasserstein Means for Aligning Distributional Data

Liang Mi, Wen Zhang, Yalin Wang

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 9 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 class-label triplet regularization to Wasserstein mean updatesWasserstein means for Office-31 W → A with Decaf-fc6 · Office-31 W → A, Decaf-fc6classification accuracy (%): 33.9±2.1 -> 36.4±2.7Improved
Add class-label triplet regularization to Wasserstein mean updatesWasserstein means for Office-31 W → A with Decaf-fc7 · Office-31 W → A, Decaf-fc7classification accuracy (%): 35.8±1.5 -> 43.2±2.6Improved
Use class-label triplet regularization rather than unregularized Wasserstein meansWasserstein means for Office-31 W → A with Decaf-fc6 · Office-31 W → A, Decaf-fc6classification accuracy (%): 32.7±2.3 -> 36.4±2.7Improved
Use class-label triplet regularization rather than unregularized Wasserstein meansWasserstein means for Office-31 W → A with Decaf-fc7 · Office-31 W → A, Decaf-fc7classification accuracy (%): 34.6±2.2 -> 43.2±2.6Improved
Add a rigid-transformation prior to Wasserstein mean updatesRWM for two-moons point-set registration · Two moons, rotated domainstransformation recoveryMixed
Add topology, length, and curvature regularization to Wasserstein meansRWM for skeleton layout · Human shape point cloudtopology preservationImproved
Use OT-based correspondences instead of nearest-neighbor correspondencesRWM for point-set registration · Stanford Bunny point setstransformation recoveryImproved

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