Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MpoxMamba: A Grouped Mamba-based Lightweight Hybrid Network for Mpox Detection

Yubiao Yue, Jun Xue, Haihuang Liang, Zhenzhang Li, Yufeng Wang

TL;DR

Inspired by the success of Mamba in modeling long-range dependencies and its linear complexity, this work proposed a lightweight hybrid architecture called MpoxMamba for efficient mpox detection that outperforms state-of-the-art lightweight models and existing mpox detection methods.

Abstract

Due to the lack of effective mpox detection tools, the mpox virus continues to spread worldwide and has once again been declared a public health emergency of international concern by the World Health Organization. Lightweight deep learning model-based detection systems are crucial to alleviate mpox outbreaks since they are suitable for widespread deployment, especially in resource-limited scenarios. However, the key to its successful application depends on ensuring that the model can effectively model local features and long-range dependencies in mpox lesions while maintaining lightweight. Inspired by the success of Mamba in modeling long-range dependencies and its linear complexity, we proposed a lightweight hybrid architecture called MpoxMamba for efficient mpox detection. MpoxMamba utilizes depth-wise separable convolutions to extract local feature representations in mpox skin lesions and greatly enhances the model's ability to model the global contextual information by grouped Mamba modules. Notably, MpoxMamba's parameter size and FLOPs are 0.77M and 0.53G, respectively. Experimental results on two widely recognized benchmark datasets demonstrate that MpoxMamba outperforms state-of-the-art lightweight models and existing mpox detection methods. Importantly, we developed a web-based online application to provide free mpox detection (http://5227i971s5.goho.co:30290). The source codes of MpoxMamba are available at https://github.com/YubiaoYue/MpoxMamba.

MpoxMamba: A Grouped Mamba-based Lightweight Hybrid Network for Mpox Detection

TL;DR

Inspired by the success of Mamba in modeling long-range dependencies and its linear complexity, this work proposed a lightweight hybrid architecture called MpoxMamba for efficient mpox detection that outperforms state-of-the-art lightweight models and existing mpox detection methods.

Abstract

Due to the lack of effective mpox detection tools, the mpox virus continues to spread worldwide and has once again been declared a public health emergency of international concern by the World Health Organization. Lightweight deep learning model-based detection systems are crucial to alleviate mpox outbreaks since they are suitable for widespread deployment, especially in resource-limited scenarios. However, the key to its successful application depends on ensuring that the model can effectively model local features and long-range dependencies in mpox lesions while maintaining lightweight. Inspired by the success of Mamba in modeling long-range dependencies and its linear complexity, we proposed a lightweight hybrid architecture called MpoxMamba for efficient mpox detection. MpoxMamba utilizes depth-wise separable convolutions to extract local feature representations in mpox skin lesions and greatly enhances the model's ability to model the global contextual information by grouped Mamba modules. Notably, MpoxMamba's parameter size and FLOPs are 0.77M and 0.53G, respectively. Experimental results on two widely recognized benchmark datasets demonstrate that MpoxMamba outperforms state-of-the-art lightweight models and existing mpox detection methods. Importantly, we developed a web-based online application to provide free mpox detection (http://5227i971s5.goho.co:30290). The source codes of MpoxMamba are available at https://github.com/YubiaoYue/MpoxMamba.
Paper Structure (13 sections, 4 equations, 2 figures, 2 tables)

This paper contains 13 sections, 4 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. The Proposed Method
  3. Preliminaries
  4. The Overall architecture of MpoxMamba
  5. Vision Mamba Layer
  6. Grouped Mamba-based Local-Global Feature Fusion
  7. Experiments and Results
  8. Dataset and Evaluation Metrics
  9. Implementation Details
  10. Comparison of Results
  11. Ablation Experiment
  12. A Web-based Mpox Detection Application
  13. Conclusion

Figures (2)

  • Figure 1: The overall page of online mpox detection application.
  • Figure 2: Detailed architecture of MpoxMamba and its internal components. GAP, BN, PWConv, DWConv represents global average pooling, batch normalization, point-wise convolution and depth-wise convolution, respectively. a: The overall architecture of MpoxMamba. b: The detailed architecture of InResBlock. c: The detailed architecture of GMLGFF Block. d: The detailed architecture of Vision Mamba Layer.