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/FOSNet

FOSNet

Reported on 16 benchmarks across 4 tasks · 1 paper · 16 SOTA

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

Computer Vision12 results

  • Scene ParsingonMIT Indoor Scenes
    Accuracy· 2019-07-17
    90.3
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • Scene ParsingonPlaces365
    Top 1 Accuracy· 2019-07-17
    60.14
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • Scene ParsingonPlaces365
    Top 5 Accuracy· 2019-07-17
    88.86
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • Scene ParsingonSUN397
    Accuracy· 2019-07-17
    77.28
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • AnimationonMIT Indoor Scenes
    Accuracy· 2019-07-17
    90.3
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • AnimationonPlaces365
    Top 1 Accuracy· 2019-07-17
    60.14
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • AnimationonPlaces365
    Top 5 Accuracy· 2019-07-17
    88.86
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • AnimationonSUN397
    Accuracy· 2019-07-17
    77.28
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 3D Character Animation From A Single PhotoonMIT Indoor Scenes
    Accuracy· 2019-07-17
    90.3
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 3D Character Animation From A Single PhotoonPlaces365
    Top 1 Accuracy· 2019-07-17
    60.14
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 3D Character Animation From A Single PhotoonPlaces365
    Top 5 Accuracy· 2019-07-17
    88.86
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 3D Character Animation From A Single PhotoonSUN397
    Accuracy· 2019-07-17
    77.28
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570

Audio4 results

  • 2D Semantic SegmentationonMIT Indoor Scenes
    Accuracy· 2019-07-17
    90.3
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 2D Semantic SegmentationonPlaces365
    Top 1 Accuracy· 2019-07-17
    60.14
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 2D Semantic SegmentationonPlaces365
    Top 5 Accuracy· 2019-07-17
    88.86
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570
  • 2D Semantic SegmentationonSUN397
    Accuracy· 2019-07-17
    77.28
    SOTA
    FOSNet: An End-to-End Trainable Deep Neural Network for Scene RecognitionarXiv:1907.07570