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.

Models/DynAE

DynAE

Reported on 8 benchmarks across 1 task · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

  • Image ClusteringonMNIST-full
    Accuracy· 2019-01-23
    0.987
    best: 0.992 (SPC)
    SOTA
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonMNIST-full
    NMI· 2019-01-23
    0.964
    best: 0.975 (SPC)
    SOTA
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonUSPS
    Accuracy· 2019-01-23
    0.981
    best: 0.984 (SPC)
    SOTA
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonUSPS
    NMI· 2019-01-23
    0.948
    best: 0.954 (SPC)
    SOTA
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonMNIST-test
    Accuracy· 2019-01-23
    0.987
    SOTA
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonMNIST-test
    NMI· 2019-01-23
    0.963
    SOTA
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonFashion-MNIST
    Accuracy· 2019-01-23
    0.591
    best: 0.791 (PRCut (DinoV2))
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752
  • Image ClusteringonFashion-MNIST
    NMI· 2019-01-23
    0.642
    best: 0.758 (PRCut (DinoV2))
    Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionarXiv:1901.07752