AI Paper Atlas

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

Dual Mixup Regularized Learning for Adversarial Domain Adaptation

Yuan Wu, Diana Inkpen, Ahmed El-Roby

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 171 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 domain mixup (ablation)DMRL · Digits MNIST to USPSaccuracy (%): 94.8 -> 96.1Improved
add domain mixup (ablation)DMRL · Digits USPS to MNISTaccuracy (%): 97.8 -> 99.0Improved
add category mixup (ablation)DMRL · Digits MNIST to USPSaccuracy (%): 90.3 -> 96.1Improved
add category mixup (ablation)DMRL · Digits USPS to MNISTaccuracy (%): 92.6 -> 99.0Improved
add labeled category mixup (ablation)DMRL · Digits MNIST to USPSaccuracy (%): 95.0 -> 96.1Improved
add labeled category mixup (ablation)DMRL · Digits USPS to MNISTaccuracy (%): 97.9 -> 99.0Improved
add unlabeled category mixup (ablation)DMRL · Digits MNIST to USPSaccuracy (%): 90.7 -> 96.1Improved
add unlabeled category mixup (ablation)DMRL · Digits USPS to MNISTaccuracy (%): 93.3 -> 99.0Improved
add domain adaptation (full DMRL vs no adaptation)DMRL · Digits MNIST to USPSaccuracy (%): 82.2 -> 96.1Improved
add domain adaptation (full DMRL vs source-only ResNet-50)DMRL · Office-31 (average of 6 tasks)accuracy (%): 76.1 -> 87.9Improved
compare DMRL with CDAN on balanced domainsDMRL · ImageCLEF-DA (average of 6 tasks)accuracy (%): 87.1 -> 88.0Improved
increase lambda_t from 0.1 up to 2.0 then beyond (ablation)DMRL · Digits MNIST to USPSaccuracy (%): best at lambda_t=2.0Mixed

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