mlsanityData to 7 Oct 2026

MRF-UNets: Searching UNet with Markov Random Fields

arXiv 2207.06168 ↗First posted 13 Jul 2022cs.LG cs.AI cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

UNet [27] is widely used in semantic segmentation due to its simplicity and effectiveness. However, its manually-designed architecture is applied to a large number of problem settings, either with no architecture optimizations, or with manual tuning, which is time consuming and can be sub-optimal. In this work, firstly, we propose Markov Random Field Neural Architecture Search (MRF-NAS) that extends and improves the recent Adaptive and Optimal Network Width Search (AOWS) method [4] with (i) a more general MRF framework (ii) diverse M-best loopy inference (iii) differentiable parameter learning. This provides the necessary NAS framework to efficiently explore network architectures that induce loopy inference graphs, including loops that arise from skip connections. With UNet as the backbone, we find an architecture, MRF-UNet, that shows several interesting characteristics. Secondly, through the lens of these characteristics, we identify the sub-optimality of the original UNet architecture and further improve our results with MRF-UNetV2. Experiments show that our MRF-UNets significantly outperform several benchmarks on three aerial image datasets and two medical image datasets while maintaining low computational costs. The code is available at: https://github.com/zifuwanggg/MRF-UNets.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 13 Jul 2022.

Builds on

35 of 45 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  8. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  9. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  10. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  11. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  12. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
23 more
  1. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  2. 2020CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentationcited by 307
  3. 2018Slimmable Neural Networkscited by 301
  4. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 276
  5. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  6. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 212
  7. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 187
  8. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
  9. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 129
  10. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  11. 2019NAS evaluation is frustratingly hardcited by 69
  12. 2022β-DARTS: Beta-Decay Regularization for Differentiable Architecture Searchcited by 63
  13. 2020Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Indexcited by 52
  14. 2021DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentationcited by 47
  15. 2020BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecturecited by 25
  16. 2021OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detectioncited by 19
  17. 2022On Redundancy and Diversity in Cell-based Neural Architecture Searchcited by 18
  18. 2020AOWS: Adaptive and optimal network width search with latency constraintscited by 17
  19. 2020MS-NAS: Multi-Scale Neural Architecture Search for Medical Image Segmentationcited by 16
  20. 2021BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentationcited by 13
  21. 2021Learning Versatile Neural Architectures by Propagating Network Codescited by 9
  22. 2020NADS: Neural Architecture Distribution Search for Uncertainty Awarenesscited by 8
  23. 2019Adaptive Compression-based Lifelong Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensingcited by 4
  2. 2024Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mappingcited by 4