Statements (59)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:television_channel
|
| gptkbp:adapted_into |
3 D Image Segmentation
Multi-class Segmentation Multi-modal Segmentation Real-time Segmentation |
| gptkbp:applies_to |
Biomedical Image Analysis
|
| gptkbp:architectural_style |
Encoder-Decoder
|
| gptkbp:based_on |
Fully Convolutional Networks
|
| gptkbp:can_be_extended_by |
gptkb:3_DU-Net
gptkb:Attention_U-Net gptkb:Nested_U-Net Res U Net |
| gptkbp:consists_of |
Contracting Path
Expansive Path |
| gptkbp:developed_by |
gptkb:Olaf_Ronneberger
|
| gptkbp:has |
Symmetric Architecture
|
| gptkbp:has_achievements |
State-of-the-art Results
|
| https://www.w3.org/2000/01/rdf-schema#label |
Standard U-Net
|
| gptkbp:improves |
Segmentation Accuracy
|
| gptkbp:introduced |
gptkb:2015
|
| gptkbp:is_characterized_by |
High Performance
|
| gptkbp:is_designed_for |
Image Segmentation
|
| gptkbp:is_documented_in |
Research Articles
Technical Reports Online Tutorials Git Hub Repositories |
| gptkbp:is_evaluated_by |
gptkb:MICCAI_Challenge
Cross-validation Test Datasets Intersection over Union (Io U) Dice Coefficient ISIC Challenge |
| gptkbp:is_implemented_in |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
| gptkbp:is_influenced_by |
gptkb:U-Net++
gptkb:Deep_Lab gptkb:Seg_Net |
| gptkbp:is_often_used_in |
Medical Imaging
|
| gptkbp:is_popular_in |
Deep Learning Community
|
| gptkbp:is_supported_by |
Community Contributions
Open-source Libraries |
| gptkbp:is_used_for |
Cell Segmentation
Organ Segmentation Tumor Segmentation Satellite Image Segmentation |
| gptkbp:is_used_in |
Research Papers
Industrial Applications Medical Applications Agricultural Applications |
| gptkbp:requires |
Large Datasets
|
| gptkbp:training |
Backpropagation
Stochastic Gradient Descent |
| gptkbp:uses |
Skip Connections
|
| gptkbp:utilizes |
Convolutional Layers
Pooling Layers Up-sampling Layers |
| gptkbp:bfsParent |
gptkb:Attention_U-Net
gptkb:Nested_U-Net |
| gptkbp:bfsLayer |
4
|