AI Paper Atlas

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

Optimal Transport for Domain Adaptation

Nicolas Courty, Rémi Flamary, Devis Tuia, Alain Rakotomamonjy

TPAMI 2016 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 1,136 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 entropic regularization to exact OT (ablation)OT-exact · Digits mean (SURF)accuracy: 49.96 -> 59.20Improved
add class-based group-lasso regularizer to entropic OT (ablation)OT-IT · Office-Caltech mean (SURF)accuracy: 42.30 -> 47.70Improved
add class-based group-lasso regularizer to entropic OT (ablation)OT-IT · Digits mean (SURF)accuracy: 59.20 -> 63.90Improved
add Laplacian regularizer to entropic OT (ablation)OT-IT · Faces PIE mean (SURF)accuracy: 54.89 -> 56.10Improved
OT-GL vs JDA on PIE faces (ablation)OT-GL · Faces PIE mean (SURF)accuracy: 56.69 vs 55.88Hurt
use OT-GL instead of 1NN without adaptation1NN · Office-Caltech mean (SURF)accuracy: 28.47 -> 47.70Improved
add OT-GL adaptation to DeCAF layer 6 featuresDeCAF · Office-Caltech meanaccuracy: 65.20 -> 88.18Improved
use layer 7 instead of layer 6 features with OT-GL (ablation)OT-GL · Office-Caltech meanaccuracy: 88.18 -> 88.11No clear effect
add labeled target samples to transport plan (semi-supervised term) (ablation)OT-GL · Office-Caltech mean (SURF)accuracy: 46.6 -> 55.6Improved
add semi-supervised term (ablation)OT-IT · Office-Caltech mean (SURF)accuracy: 41.8 -> 54.8Improved
OT-GL semi-supervised vs MMDTOT-GL · Office-Caltech mean (SURF)accuracy: 52.5 -> 55.6Improved
add Laplacian regularization to OT at 40 degree rotation (ablation)OT-exact · Two moonserror rate: 0.109 -> 0.062Improved

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