Statements (56)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:television_channel
|
| gptkbp:application |
Medical Image Segmentation
|
| gptkbp:architectural_style |
Encoder-Decoder
|
| gptkbp:developed_by |
Zhou et al.
|
| gptkbp:enhances |
Context Aggregation
Feature Propagation |
| gptkbp:features |
Deep supervision
Nested skip pathways |
| gptkbp:has_achievements |
Higher Accuracy
Better Segmentation Quality |
| gptkbp:has_variants |
U-Net++ with Attention
U-Net++ with Dense Connections U-Net++ with Multi-Scale Inputs U-Net++ with Residual Connections |
| https://www.w3.org/2000/01/rdf-schema#label |
U-Net++
|
| gptkbp:improves |
gptkb:Alumni_Association
|
| gptkbp:input_output |
Segmentation Maps
2 D Images |
| gptkbp:is_cited_in |
Dissertations
Theses Numerous Research Papers Technical Reports |
| gptkbp:is_compared_to |
gptkb:Alumni_Association
gptkb:Seg_Net FCN |
| gptkbp:is_evaluated_by |
BRATS Dataset
DRIVE Dataset ISIC Dataset LIDC-IDRI Dataset |
| gptkbp:is_implemented_in |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
| gptkbp:is_optimized_for |
High-Resolution Images
Small Datasets |
| gptkbp:is_part_of |
Deep Learning Frameworks
|
| gptkbp:is_popular_in |
Academic Conferences
Research Publications Medical Imaging Community |
| gptkbp:is_related_to |
gptkb:viewpoint
gptkb:Artificial_Intelligence Image Processing |
| gptkbp:is_supported_by |
gptkb:document
Community Contributions Open Source Libraries Online Tutorials |
| gptkbp:is_used_in |
Brain Tumor Segmentation
Cardiac Segmentation Liver Segmentation Retinal Image Segmentation |
| gptkbp:losses |
Dice Loss
Binary Cross-Entropy Loss |
| gptkbp:published_year |
gptkb:2018
|
| gptkbp:uses |
Convolutional Layers
Pooling Layers Upsampling Layers |
| gptkbp:bfsParent |
gptkb:Standard_U-Net
|
| gptkbp:bfsLayer |
5
|