AI Paper Atlas

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

One-Sided Unsupervised Domain Mapping

Sagie Benaim, Lior Wolf

NeurIPS 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 54 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 pairwise distance preservation to the adversarial mappingDiscoGAN · car2carRMSE: 0.306 -> 0.135Improved
Add circularity to pairwise distance preservation (ablation)Distance · car2carRMSE: 0.135 -> 0.098Improved
Replace pairwise distances with within-image self-distances (ablation)Distance · car2carRMSE: 0.135 -> 0.117Improved
Add pairwise distance preservation to the adversarial mappingDiscoGAN · car2headRMSE: 0.137 -> 0.097Improved
Add circularity to pairwise distance preservation (ablation)Distance · car2headRMSE: 0.097 -> 0.273Hurt
Replace pairwise distances with within-image self-distances (ablation)Distance · car2headRMSE: 0.097 -> 0.197Hurt
Add pairwise distance preservation to CycleGANCycleGAN · SVHN to MNISTAccuracy: 26.1% -> 26.8%Improved
Add circularity to pairwise distance preservation (ablation)Distance · SVHN to MNISTAccuracy: 26.8% -> 18.0%Hurt
Use within-image self-distances instead of pairwise distances (ablation)Distance · SVHN to MNISTAccuracy: 26.8% -> 25.2%Hurt
Add pairwise distance preservationDiscoGAN · CelebA attribute translationsCosine similarity: 0.23 -> 0.32; 0.15 -> 0.24; 0.13 -> 0.42Improved
Add circularity to pairwise distance preservation (ablation)Distance · CelebA attribute translationsCosine similarity: 0.32 -> 0.35; 0.24 -> 0.24; 0.42 -> 0.41Mixed
Replace pairwise distances with within-image self-distances (ablation)Distance · CelebA attribute translationsCosine similarity: Male to Female: 0.32 -> 0.24; Blond to Black: 0.24 -> 0.24; Glasses to Without: 0.42 -> 0.34Mixed

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