mlsanityData to 14 Oct 2026

UNet-2022: Exploring Dynamics in Non-isomorphic Architecture

arXiv 2210.15566 ↗First posted 27 Oct 2022eess.IV cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent medical image segmentation models are mostly hybrid, which integrate self-attention and convolution layers into the non-isomorphic architecture. However, one potential drawback of these approaches is that they failed to provide an intuitive explanation of why this hybrid combination manner is beneficial, making it difficult for subsequent work to make improvements on top of them. To address this issue, we first analyze the differences between the weight allocation mechanisms of the self-attention and convolution. Based on this analysis, we propose to construct a parallel non-isomorphic block that takes the advantages of self-attention and convolution with simple parallelization. We name the resulting U-shape segmentation model as UNet-2022. In experiments, UNet-2022 obviously outperforms its counterparts in a range segmentation tasks, including abdominal multi-organ segmentation, automatic cardiac diagnosis, neural structures segmentation, and skin lesion segmentation, sometimes surpassing the best performing baseline by 4%. Specifically, UNet-2022 surpasses nnUNet, the most recognized segmentation model at present, by large margins. These phenomena indicate the potential of UNet-2022 to become the model of choice for medical image segmentation.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

28 of 42 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2022A ConvNet for the 2020scited by 3,579
  10. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  11. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  12. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
16 more
  1. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 586
  2. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 320
  3. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  4. 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
  5. 2021DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentationcited by 126
  6. 2021MISSFormer: An Effective Medical Image Segmentation Transformercited by 103
  7. 2021Mixed Transformer U-Net For Medical Image Segmentationcited by 95
  8. 2021LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentationcited by 85
  9. 2021Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reportscited by 80
  10. 2021Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contextscited by 60
  11. 2021TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentationcited by 41
  12. 2021Boundary-aware Transformers for Skin Lesion Segmentationcited by 39
  13. 2021ConvNets vs. Transformers: Whose Visual Representations are More Transferable?cited by 35
  14. 2020Difficulty-aware Glaucoma Classification with Multi-Rater Consensus Modelingcited by 17
  15. 2022PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentationcited by 16
  16. 2017Sunrise or Sunset: Selective Comparison Learning for Subtle Attribute Recognitioncited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 1.

6 papers.

  1. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 179
  2. 2023Channel prior convolutional attention for medical image segmentationcited by 8
  3. 2023Swin Deformable Attention Hybrid U-Net for Medical Image Segmentationcited by 1
  4. 2024Generalizing Segmentation Foundation Model Under Sim-to-real Domain-shift for Guidewire Segmentation in X-ray Fluoroscopycited by 1
  5. 2023Style Transfer and Self-Supervised Learning Powered Myocardium Infarction Super-Resolution Segmentationcited by 0
  6. 2025Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Imagescited by 0