AI Paper Atlas

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

NAM: Non-Adversarial Unsupervised Domain Mapping

Yedid Hoshen, Lior Wolf

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 20 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 NAM (fixed pre-trained generator, no adversarial or cycle loss) instead of CycleGANCycleGAN · SVHN to MNIST translationtranslated digit classification accuracy (%): 26.8 -> 33.3Improved
use NAM instead of CycleGAN in the harder information-gaining directionCycleGAN · MNIST to SVHN translationtranslated digit classification accuracy (%): 17.7 -> 31.9Improved
use NAM instead of DiscoGANDiscoGAN · Car2Carroot median residual deviation from linear alignment: 13.81 -> 1.47Improved
use a stronger pre-trained generator (DCGAN, Spectral-Norm GAN) instead of VAE or GLO (ablation)NAM · Edges2Shoesqualitative translation qualityImproved
add VGG perceptual loss to reconstruction loss (ablation)NAM · image domain mappingqualitative analogy qualityImproved
add perceptual loss on Car2Car (versus plain pixel loss) (ablation)NAM · Car2Carorientation alignmentNo clear effect
apply NAM to car2head mappingNAM · Car2Headorientation relationHurt
map from X to Y (T maps generated image to source) rather than Y to XNAM · design choicemode collapseImproved

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