AI Paper Atlas

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

Multi-marginal Wasserstein GAN

Jiezhang Cao, Langyuan Mo, Yifan Zhang, Kui Jia, Chunhua Shen, Mingkui Tan

NeurIPS 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 32 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 MWGAN's shared-potential multi-marginal objective instead of the strongest baselineCelebA single-attribute translation · CelebA hair and pale skinFID: 20.45 -> 19.63; 18.09 -> 15.91Improved
Use MWGAN's shared-potential multi-marginal objective instead of the strongest baselineCelebA single-attribute translation · CelebA eyeglasses and mustacheFID: 23.69 -> 22.94; 23.75 -> 23.69Improved
Use MWGAN instead of the strongest baselineCelebA single-attribute translation · CelebA hair, eyeglasses, mustache, and pale skinclassification accuracy: 96.00 -> 97.65; 99.51 -> 99.53; 99.06 -> 98.35; 92.48 -> 93.66Mixed
Use MWGAN instead of the strongest baselineCelebA multi-attribute synthesis · B+E, B+M, B+M+E, and B+M+E+Pclassification accuracy: 72.53 -> 75.82; 62.20 -> 69.01; 45.77 -> 53.75; 8.54 -> 19.95Improved
Use MWGAN instead of the strongest baselineEdge→CelebA translation · Black, blond, and brown hairFID: 53.41 -> 33.81; 81.00 -> 51.87; 57.51 -> 35.24Improved
Use a jointly matched multi-marginal objective rather than pairwise or mixed-distribution matchingToy distribution matching with dissimilar source and target distributions · Toy Gaussian source to Gaussian or Uniform targetsdistribution matching abilityImproved
Apply MWGAN to highly imbalanced domains instead of the compared translation methodsStyle painting translation · Real scene to Monet, Van Gogh, and Ukiyo-evisual qualityImproved

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