mlsanityData to 7 Oct 2026

A Mathematical Explanation of UNet

arXiv 2410.04434 ↗First posted 6 Oct 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The UNet architecture has transformed image segmentation. UNet's versatility and accuracy have driven its widespread adoption, significantly advancing fields reliant on machine learning problems with images. In this work, we give a clear and concise mathematical explanation of UNet. We explain what is the meaning and function of each of the components of UNet. We will show that UNet is solving a control problem. We decompose the control variables using multigrid methods. Then, operator-splitting techniques is used to solve the problem, whose architecture exactly recovers the UNet architecture. Our result shows that UNet is a one-step operator-splitting algorithm for the control problem.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 6 Oct 2024.

Builds on

25 of 49 references.

References · 25

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  7. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
  8. 2016Error bounds for approximations with deep ReLU networkscited by 567
  9. 2017Stable Architectures for Deep Neural Networkscited by 340
  10. 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
  11. 2018Universality of Deep Convolutional Neural Networkscited by 176
  12. 2019Real Image Denoising with Feature Attentioncited by 176
13 more
  1. 2019Machine Learning from a Continuous Viewpointcited by 50
  2. 2022SUNet: Swin Transformer UNet for Image Denoisingcited by 43
  3. 2019MgNet: A Unified Framework of Multigrid and Convolutional Neural Networkcited by 41
  4. 2019Deep learning as optimal control problems: models and numerical methodscited by 33
  5. 2020Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentationcited by 31
  6. 2023PottsMGNet: A Mathematical Explanation of Encoder-Decoder Based Neural Networkscited by 17
  7. 2020A Color Elastica Model for Vector-Valued Image Regularizationcited by 11
  8. 2022DOSnet as a Non-Black-Box PDE Solver: When Deep Learning Meets Operator Splittingcited by 11
  9. 2021An Operator-Splitting Method for the Gaussian Curvature Regularization Model with Applications to Surface Smoothing and Imagingcited by 10
  10. 2023Double-well Net for Image Segmentationcited by 7
  11. 2024Deep Convolutional Neural Networks Meet Variational Shape Compactness Priors for Image Segmentationcited by 4
  12. 2023Connections between Operator-splitting Methods and Deep Neural Networks with Applications in Image Segmentationcited by 3
  13. 2024WANCO: Weak Adversarial Networks for Constrained Optimization problemscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025A Mathematical Explanation of Transformerscited by 2
  2. 2025Benchmarking machine learning models for multi-class state recognition in double quantum dot datacited by 1
  3. 2025CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processingcited by 1
  4. 2026Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximationscited by 0