AI Paper Atlas

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

Unsupervised Domain Adaptation via Regularized Conditional Alignment

Safa Cicek, Stefano Soatto

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 135 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 VAT regularizers (ablation)joint-alignment UDA · MNIST->SVHNtarget accuracy (%): 60.65 -> 89.19Improved
add VAT regularizers (ablation)joint-alignment UDA · STL->CIFARtarget accuracy (%): 70.20 -> 77.76Improved
add entropy minimization to the no-VAT model (ablation)joint-alignment UDA · SVHN->MNIST and MNIST->SVHNtarget accuracy (%): SVHN->MNIST 88.33 -> 98.79; MNIST->SVHN 62.95 -> 60.65Mixed
add source alignment loss (ablation)joint-alignment UDA · MNIST->SVHNtarget accuracy (%): 75.78 -> 89.19Improved
add source alignment loss (ablation)joint-alignment UDA · SVHN->MNISTtarget accuracy (%): 88.91 -> 99.33Improved
add target alignment loss (ablation)joint-alignment UDA · MNIST->SVHNtarget accuracy (%): 71.59 -> 89.19Improved
add both source and target alignment losses (ablation)joint-alignment UDA · MNIST->SVHNtarget accuracy (%): 60.07 -> 89.19Improved
add both alignment losses (ablation)joint-alignment UDA · SVHN->MNISTtarget accuracy (%): 98.83 -> 99.33No clear effect
use class predictor instead of joint predictor at inference (ablation)joint-alignment UDA · MNIST->SVHNtarget accuracy (%): 87.88 -> 89.19Improved
add conditional joint alignment instead of source-only trainingUDA · STL->CIFARtarget accuracy (%): 65.44 -> 77.76Improved
add conditional joint alignment instead of source-only trainingUDA · CIFAR->STLtarget accuracy (%): 79.41 -> 81.65Improved
joint (conditional) alignment instead of marginal alignment with input smoothing (VADA+IN)UDA · MNIST->SVHNtarget accuracy (%): 73.3 -> 89.19Improved

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