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/U-Net++

U-Net++

Reported on 8 benchmarks across 1 task · 2 papers · 4 SOTA

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

Medical8 results

  • Medical Image SegmentationonKvasir-SEG
    Average MAE· 2018-07-18
    0.048
    best: 0.021 (BDG-Net)
    SOTA
    UNet++: A Nested U-Net Architecture for Medical Image SegmentationarXiv:1807.10165
  • Medical Image SegmentationonKvasir-SEG
    S-Measure· 2018-07-18
    0.862
    best: 0.929 (CaraNet)
    SOTA
    UNet++: A Nested U-Net Architecture for Medical Image SegmentationarXiv:1807.10165
  • Medical Image SegmentationonKvasir-SEG
    max E-Measure· 2018-07-18
    0.91
    best: 0.972 (BDG-Net)
    SOTA
    UNet++: A Nested U-Net Architecture for Medical Image SegmentationarXiv:1807.10165
  • Medical Image SegmentationonKvasir-SEG
    mean Dice· 2018-07-18
    0.821
    best: 0.9502 (DUCK-Net)
    SOTA
    UNet++: A Nested U-Net Architecture for Medical Image SegmentationarXiv:1807.10165
  • Medical Image SegmentationonGlaS
    Dice· 2021-09-09
    87.56
    best: 93.25 (Hi-gMISnet)
    UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with TransformerarXiv:2109.04335
  • Medical Image SegmentationonGlaS
    F1· 2021-09-09
    87.56
    best: 93.25 (Hi-gMISnet)
    UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with TransformerarXiv:2109.04335
  • Medical Image SegmentationonGlaS
    IoU· 2021-09-09
    79.13
    best: 85.13 (MDM)
    UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with TransformerarXiv:2109.04335
  • Medical Image SegmentationonCVC-ClinicDB
    mean Dice· 2018-07-18
    0.794
    best: 0.9684 (DUCK-Net)
    UNet++: A Nested U-Net Architecture for Medical Image SegmentationarXiv:1807.10165