Scholarlink

<p>Real-time high-precision image segmentation on mobile and edge devices remains challenging due to the limited ability of traditional convolutional networks to model long-range dependencies and their high computational cost at high resolutions. We propose PUNet, a lightweight parallel U-Net variant that integrates depthwise separable convolutions (DSConv) with a structured state-space Mamba module in a dual-path encoder. The core component, the parallel structured state-space encoder, employs two branches to efficiently capture local spatial features (via DSConv) and model global semantic dependencies (via the visual Mamba layer). At the same time, a squeeze-and-excitation skip connection adaptively fuses multi-scale features. With only 0.26 M parameters and linear computational complexity, PUNet enables real-time inference on resource-constrained platforms. Experiments on the CamVid and CRACK500 datasets demonstrate superior performance, achieving validation Dice scores of 0.9208 and 0.7902, and mean Intersection-over-Union of 0.8643 and 0.6612, respectively, significantly outperforming other lightweight models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PUNet: a lightweight parallel U-Net architecture integrating Mamba–CNN for high-precision image segmentation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月6日

查看全文
  • Zhaoyan Xie,
  • Xiaowei Li,
  • Hongyao Ma,
  • Sihao Wu,
  • Dayou Cui

摘要

Real-time high-precision image segmentation on mobile and edge devices remains challenging due to the limited ability of traditional convolutional networks to model long-range dependencies and their high computational cost at high resolutions. We propose PUNet, a lightweight parallel U-Net variant that integrates depthwise separable convolutions (DSConv) with a structured state-space Mamba module in a dual-path encoder. The core component, the parallel structured state-space encoder, employs two branches to efficiently capture local spatial features (via DSConv) and model global semantic dependencies (via the visual Mamba layer). At the same time, a squeeze-and-excitation skip connection adaptively fuses multi-scale features. With only 0.26 M parameters and linear computational complexity, PUNet enables real-time inference on resource-constrained platforms. Experiments on the CamVid and CRACK500 datasets demonstrate superior performance, achieving validation Dice scores of 0.9208 and 0.7902, and mean Intersection-over-Union of 0.8643 and 0.6612, respectively, significantly outperforming other lightweight models.