UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation

Abstract

Traditionally for improving the segmentation performance of models, most approaches prefer to use adding more complex modules. And this is not suitable for the medical field, especially for mobile medical devices, where computationally loaded models are not suitable for real clinical environments due to computational resource constraints. Recently, state-space models (SSMs), represented by Mamba, have become a strong competitor to traditional CNNs and Transformers. In this paper, we deeply explore the key elements of parameter influence in Mamba and propose an UltraLight Vision Mamba UNet (UltraLight VM-UNet) based on this. Specifically, we propose a method for processing features in parallel Vision Mamba, named PVM Layer, which achieves excellent performance with the lowest computational load while keeping the overall number of processing channels constant. We conducted comparisons and ablation experiments with several state-of-the-art lightweight models on three skin lesion public datasets and demonstrated that the UltraLight VM-UNet exhibits the same strong performance competitiveness with parameters of only 0.049M and GFLOPs of 0.060. In addition, this study deeply explores the key elements of parameter influence in Mamba, which will lay a theoretical foundation for Mamba to possibly become a new mainstream module for lightweighting in the future. The code is available from https://github.com/wurenkai/UltraLight-VM-UNet .

References in corpus (14)

• Decoupled Weight Decay Regularization
• Attention U-Net: Learning Where to Look for the Pancreas
• The Medical Segmentation Decathlon
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
• VMamba: Visual State Space Model
• U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation
• VM-UNet: Vision Mamba UNet for Medical Image Segmentation
• H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation
• HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
• UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation
• LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation
• Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation

Cited by in corpus (3)

• UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation
• SliceMamba with Neural Architecture Search for Medical Image Segmentation
• FU-Mamba: A Frequency-Enhanced Dynamic Scanning Framework for Oralscan Image Segmentation