SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.08790 · 2020

UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 17 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ZJUGiveLab/UNet-Version canonical 1 of 1
hamidriasat/UNet-3-Plus pwc_unofficial 5 of 13
Owais-Ansari/Unet3plus reimplementation 3 of 3
FunctionStatusWhere it lives
BCE_loss Ran ZJUGiveLab/UNet-Version/loss/bceLoss.py
pointer only (licence: NONE) · get_code("056e2e87a305e0a2")
conv2dTranspose Ran Owais-Ansari/Unet3plus/utils/models.py
code served (permissive licence) · get_code("9d9f51c95a9339d6")
conv_block Ran hamidriasat/UNet-3-Plus/models/unet3plus_utils.py
code served (permissive licence) · get_code("dc407cea8c628ee7")
dot_product Ran hamidriasat/UNet-3-Plus/models/unet3plus_utils.py
code served (permissive licence) · get_code("f5be84a091639139")
double_conv Ran Owais-Ansari/Unet3plus/utils/models.py
code served (permissive licence) · get_code("a505d8b9327be637")
focal_loss Ran hamidriasat/UNet-3-Plus/losses/loss.py
code served (permissive licence) · get_code("7b23f6df494f23b1")
iou Ran hamidriasat/UNet-3-Plus/losses/loss.py
code served (permissive licence) · get_code("c937560f46f9d96f")
iou_loss Ran hamidriasat/UNet-3-Plus/losses/loss.py
code served (permissive licence) · get_code("013ffa32c7802109")
single_conv Ran Owais-Ansari/Unet3plus/utils/models.py
code served (permissive licence) · get_code("3649cd96f92a4aa2")
prepare_model Not yet run hamidriasat/UNet-3-Plus/models/model.py
code served (permissive licence) · get_code("0862fd72cdccf945")
unet3p_hybrid_loss Not yet run hamidriasat/UNet-3-Plus/losses/unet_loss.py
code served (permissive licence) · get_code("7c0582a5703a92bd")
unet3plus Not yet run hamidriasat/UNet-3-Plus/models/unet3plus.py
code served (permissive licence) · get_code("54e2be300f32a118")
unet3plus_backbone Not yet run hamidriasat/UNet-3-Plus/models/backbones.py
code served (permissive licence) · get_code("407f5cbe72a47e63")
unet3plus_deepsup Not yet run hamidriasat/UNet-3-Plus/models/unet3plus_deep_supervision.py
code served (permissive licence) · get_code("ab0d3102a089be66")
unet3plus_deepsup_cgm Not yet run hamidriasat/UNet-3-Plus/models/unet3plus_deep_supervision_cgm.py
code served (permissive licence) · get_code("94663be587a24995")
vgg16_backbone Not yet run hamidriasat/UNet-3-Plus/models/backbones.py
code served (permissive licence) · get_code("3ca7d63a43c639c4")
vgg19_backbone Not yet run hamidriasat/UNet-3-Plus/models/backbones.py
code served (permissive licence) · get_code("16077947846367b1")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, a growing interest has been seen in deep learning-based semantic segmentation. UNet, which is one of deep learning networks with an encoder-decoder architecture, is widely used in medical image segmentation. Combining multi-scale features is one of important factors for accurate segmentation. UNet++ was developed as a modified Unet by designing an architecture with nested and dense skip connections. However, it does not explore sufficient information from full scales and there is still a large room for improvement. In this paper, we propose a novel UNet 3+, which takes advantage of full-scale skip connections and deep supervisions. The full-scale skip connections incorporate low-level details with high-level semantics from feature maps in different scales; while the deep supervision learns hierarchical representations from the full-scale aggregated feature maps. The proposed method is especially benefiting for organs that appear at varying scales. In addition to accuracy improvements, the proposed UNet 3+ can reduce the network parameters to improve the computation efficiency. We further propose a hybrid loss function and devise a classification-guided module to enhance the organ boundary and reduce the over-segmentation in a non-organ image, yielding more accurate segmentation results. The effectiveness of the proposed method is demonstrated on two datasets. The code is available at: github.com/ZJUGiveLab/UNet-Version

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2004.08790")
get_code_for_paper("2004.08790")
have("2004.08790")

Connect an agent — have() is free.