UNet (MICCAI'2016/Nat. Methods'2019)
@inproceedings{ronneberger2015u,
title={U-net: Convolutional networks for biomedical image segmentation},
author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
booktitle={International Conference on Medical image computing and computer-assisted intervention},
pages={234--241},
year={2015},
organization={Springer}
}
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 256x256 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.08% | 79.78% | cfg | model | log |
PSPNet | - | UNet-S5-D16 | 256x256 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.25% | 80.11% | cfg | model | log |
DeepLabV3 | - | UNet-S5-D16 | 256x256 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.40% | 80.40% | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 64x64 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
PSPNet | - | UNet-S5-D16 | 64x64 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
DeepLabV3 | - | UNet-S5-D16 | 64x64 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
PSPNet | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
DeepLabV3 | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.91% | 81.28% | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.52% | 80.36% | cfg | model | log |
PSPNet | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.57% | 80.48% | cfg | model | log |
DeepLabV3 | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.60% | 80.53% | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 256x256 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
PSPNet | - | UNet-S5-D16 | 256x256 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
DeepLabV3 | - | UNet-S5-D16 | 256x256 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 64x64 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
PSPNet | - | UNet-S5-D16 | 64x64 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
DeepLabV3 | - | UNet-S5-D16 | 64x64 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
PSPNet | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log | ||
DeepLabV3 | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | cfg | model | log |
Segmentor | Pretrain | Backbone | Crop Size | Schedule | Train/Eval Set | mDice | Dice | Download |
---|---|---|---|---|---|---|---|---|
FCN | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.59% | 80.50% | cfg | model | log |
PSPNet | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.51% | 80.37% | cfg | model | log |
DeepLabV3 | - | UNet-S5-D16 | 128x128 | LR/POLICY/BS/EPOCH: 0.01/poly/16/1 | train/val | 89.56% | 80.44% | cfg | model | log |
You can also download the model weights from following sources:
- BaiduNetdisk: https://pan.baidu.com/s/1gD-NJJWOtaHCtB0qHE79rA with access code s757