Project AURIONAI Use-Cases Research & Innovation
University of Freiburg
visionfamily

U-Net

Encoder-decoder segmentation network with a contracting path and a symmetric expanding path, first shown on biomedical images.

University of FreiburgUniversity of FreiburgGermany
Diagram of the U-Net encoder and decoder architecture from the authors page..
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released18 May 2015
Opennessunknown
Runs onmobile or NPU, CPU server
Statusactive

Lineage

20152016201720182019U-Net (2D)U-Net (2D), May 2015UNet++UNet++, Jul 2018

1 member has no release date in the notes, so it is not on this timeline.

Arizona State UniversityUNet++ belongs to this familyvision18 Jul 2018
University of FreiburgU-Net (2D) belongs to this familyvision18 May 2015
Google3D U-Net (TensorFlow volumetric models) belongs to this familyvision
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

Industry Use Cases

Healthcare
Medical image segmentation

R&D Topics

Semantic, instance and panoptic segmentation architecturesproduced byMedical image segmentation and screening AI (radiology)produced by

Identity

Developer
University of Freiburg
Family
not in the notes
Released
18 May 2015 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
U-Net 2D and 3D, UNet++ (arXiv 1807.10165), medical builds in NVIDIA DLE, OpenVINO BraTS model and TensorFlow volumetric models.
Context length
not in the notes
Input
image
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU, CPU server
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Sources

  1. arxiv.org/abs/1505.04597 https://arxiv.org/abs/1505.04597
  2. aihub.qualcomm.com/models/unet_segmentation https://aihub.qualcomm.com/models/unet_segmentation
  3. github.com/milesial/Pytorch-UNet https://github.com/milesial/Pytorch-UNet
  4. github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/brain-tumor-segmentation-0002
  5. catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/unet_2d-medical_... https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/unet_2d-medical_tf1_ckpt
  6. pytorch.org/hub/mateuszbuda_brain-segmentation-pytorch_unet https://pytorch.org/hub/mateuszbuda_brain-segmentation-pytorch_unet
  7. raw.githubusercontent.com/pytorch/hub/master/mateuszbuda_brain-segmenta... https://raw.githubusercontent.com/pytorch/hub/master/mateuszbuda_brain-segmentation-pytorch_unet.md
  8. arxiv.org/html/1505.04597 https://arxiv.org/html/1505.04597

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "U-Net", https://aurion.semai.id/models/u-net/, records of October 2026.