Scholarlink

<p>This study addresses the optimization of fully convolutional networks (FCNs) for deployment on resource-limited devices in real-time scenarios. While prior research has extensively applied quantization techniques to architectures like VGG-16, there is limited exploration of comprehensive layer-wise quantization specifically within the FCN-8 architecture. To fill this gap, we propose an innovative approach utilizing full-layer quantization with an <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_6848_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">\(L_2\)</EquationSource> </InlineEquation> error minimization algorithm, accompanied by sensitivity analysis to optimize fixed-point representation of network weights. Our results demonstrate that this method significantly enhances sparsity, achieving up to 40%, while preserving performance, yielding an impressive 89.3% pixel accuracy under extreme quantization conditions. The findings highlight the efficacy of full-layer quantization and retraining in simultaneously reducing network complexity and maintaining accuracy in both image classification and semantic segmentation tasks.</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

Optimizing FCN for devices with limited resources using quantization and sparsity enhancement

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月4日

查看全文
  • Muhammad Faizan-Khan,
  • Nisar Ali,
  • Raja Hashim Ali,
  • Areej Alasiry,
  • Mehrez Marzougui,
  • Shabbab Ali Algamdi,
  • Yunyoung Nam

摘要

This study addresses the optimization of fully convolutional networks (FCNs) for deployment on resource-limited devices in real-time scenarios. While prior research has extensively applied quantization techniques to architectures like VGG-16, there is limited exploration of comprehensive layer-wise quantization specifically within the FCN-8 architecture. To fill this gap, we propose an innovative approach utilizing full-layer quantization with an \(L_2\) error minimization algorithm, accompanied by sensitivity analysis to optimize fixed-point representation of network weights. Our results demonstrate that this method significantly enhances sparsity, achieving up to 40%, while preserving performance, yielding an impressive 89.3% pixel accuracy under extreme quantization conditions. The findings highlight the efficacy of full-layer quantization and retraining in simultaneously reducing network complexity and maintaining accuracy in both image classification and semantic segmentation tasks.