TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Methodology/Domain Adaptation/MNIST-to-USPS

Domain Adaptation on MNIST-to-USPS

Metric: Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Accuracy▼AugmentationsPaperDate↕Code
1FACT98.8NoFACT: Federated Adversarial Cross Training2023-06-01Code
2FAMCD98.72No---
3DFA-MCD98.6NoDiscriminative Feature Alignment: Improving Tran...2020-06-23Code
4Mean teacher98.26NoSelf-ensembling for visual domain adaptation2017-06-16Code
5DRANet98.2NoDRANet: Disentangling Representation and Adaptat...2021-03-24Code
6SHOT98NoDo We Really Need to Access the Source Data? Sou...2020-02-20Code
7DFA-ENT97.9NoDiscriminative Feature Alignment: Improving Tran...2020-06-23Code
8CyCleGAN (Light-weight Calibrator)97.1NoLight-weight Calibrator: a Separable Component f...2019-11-28Code
93CATN96.1NoCycle-consistent Conditional Adversarial Transfe...2019-09-17Code
10rRevGrad+CAT96NoCluster Alignment with a Teacher for Unsupervise...2019-03-24Code
11DeepJDOT95.7NoDeepJDOT: Deep Joint Distribution Optimal Transp...2018-03-27Code
12SRDA (RAN)94.76NoLearning Smooth Representation for Unsupervised ...2019-05-26Code
13MCD93.8NoMaximum Classifier Discrepancy for Unsupervised ...2017-12-07Code
14ADDN90.1NoAdversarial Discriminative Domain Adaptation2017-02-17Code