AI Paper Atlas

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

Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation

Yogesh Balaji, Rama Chellappa, Soheil Feizi

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 57 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
replace Wasserstein distance with normalized Wasserstein (NW) for domain adaptationdomain adaptation · MNIST->MNIST-M (3 modes, imbalanced)accuracy (%): 61.75 -> 75.06Improved
replace Wasserstein distance with NW for domain adaptationdomain adaptation · MNIST->MNIST-M (5 modes, imbalanced)accuracy (%): 60.56 -> 76.16Improved
replace Wasserstein distance with NW for domain adaptationdomain adaptation · MNIST->MNIST-M (10 modes, imbalanced)accuracy (%): 58.22 -> 68.57Improved
apply DANN or Wasserstein alignment instead of no adaptation under imbalanced modessource-only baseline · MNIST->MNIST-M (3 modes, imbalanced)accuracy (%): 66.63 -> 62.34Hurt
replace Wasserstein distance with NW on pretrained ResNet-18domain adaptation · VISDA synthetic-to-real (3 classes, imbalanced)accuracy (%): 64.84 -> 73.23Improved
use NW instead of Wasserstein when modes are balanceddomain adaptation · MNIST->MNIST-M (mode-balanced, full data)accuracy (%): 83.47 -> 84.16No clear effect
use NW instead of Wasserstein when modes are balanceddomain adaptation · VISDA (3 classes, mode-balanced)accuracy (%): 90.08 -> 90.72No clear effect
replace Wasserstein distance with NW for denoising adaptationautoencoder domain adaptation · MNIST denoising (target reconstruction)target L2 reconstruction error: 0.52 -> 0.18Improved
learn mixture proportions (NWGAN) instead of fixed uniform proportions (MGAN) (ablation)mixture GAN · Mixture of 9 Gaussianspi estimation error: 0.7157 -> 0.0001Improved
optimize pi instead of fixing pi to 1/k (ablation)NWGAN k=2 · CIFAR-10 + CelebA mixturedisentanglement of modesImproved
use NWGAN with 4 modes instead of single WGAN-GP generatorWGAN-GP · CIFAR-10inception score: 7.56 -> 7.89Improved
replace k-means with NW adversarial clusteringclustering · Imbalanced MNIST (digits 2,4,6) clusteringcluster purity: 0.82 -> 0.98Improved

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