DCSAU-Net

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

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

Medical5 results

Medical Image SegmentationonISIC 2018
DSC· 2022-02-02
90.35
best: 90.96 (EMCAD)
SOTA
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation arXiv:2202.00972
Medical Image SegmentationonSegPC-2021
mIoU· 2022-02-02
0.8048
SOTA
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation arXiv:2202.00972
Medical Image SegmentationonISIC 2018 Task 1
mIoU· 2022-02-02
0.8301
SOTA
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation arXiv:2202.00972
Medical Image Segmentationon2018 Data Science Bowl
Recall· 2022-02-02
0.924
best: 0.9402 (MSRF-Net)
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation arXiv:2202.00972
Medical Image Segmentationon2018 Data Science Bowl
mIoU· 2022-02-02
0.8501
best: 87.22 (ReN-UNet)
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation arXiv:2202.00972