ViM-UNet: Vision Mamba for Biomedical Segmentation

Anwai Archit, Constantin Pape
4/11/2024
cs.CV

Official code: constantinpape/torch-em (129 stars, MIT, last commit 2026-04-27).

Abstract

CNNs, most notably the UNet, are the default architecture for biomedical segmentation. Transformer-based approaches, such as UNETR, have been proposed to replace them, benefiting from a global field of view, but suffering from larger runtimes and higher parameter counts. The recent Vision Mamba architecture offers a compelling alternative to transformers, also providing a global field of view, but at higher efficiency. Here, we introduce ViM-UNet, a novel segmentation architecture based on it and compare it to UNet and UNETR for two challenging microscopy instance segmentation tasks. We find that it performs similarly or better than UNet, depending on the task, and outperforms UNETR while being more efficient. Our code is open source and documented at https://github.com/constantinpape/torch-em/blob/main/vimunet.md.

View on arXivView PDF

Code Implementations(1)

constantinpape/torch-emOfficial100%
MIT

Deep-learning based semantic and instance segmentation for 3D Electron Microscopy and other bioimage analysis problems based on pytorch.

12932Shell, PythonMar 1, 20215 months agoMIT

Similar Papers

Going Beyond U-Net: Assessing Vision Transformers for Semantic Segmentation in Microscopy Image Analysis

89% match2024

TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation

88% match1 repo242024

J-CaPA : Joint Channel and Pyramid Attention Improves Medical Image Segmentation

87% match2024

Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?

87% match1 repo592024

Rethinking Attention Gated with Hybrid Dual Pyramid Transformer-CNN for Generalized Segmentation in Medical Imaging

87% match1 repo52024

nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation

86% match1 repo8.7k2024

Cite this paper

@article{archit2024vimunet,
  title  = {ViM-UNet: Vision Mamba for Biomedical Segmentation},
  author = {Anwai Archit and Constantin Pape},
  year   = {2024},
  eprint = {2404.07705},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.07705v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.07705.svg)](https://codeofpaper.com/paper/2404.07705)

Discussion