Scholarlink

<p>The growing adoption of Artificial Intelligence (AI) in real-world applications highlights the need for Deep Learning (DL) models that are both efficient and accurate. However, the high computational requirements of DL often hinder deployment in resource-limited environments. In this paper, we propose an efficient and resource-conscious extension of Differentiable Architecture Search (DARTS) to design lightweight neural networks for driver distraction detection. The proposed method introduces a multi-objective optimization mechanism grounded in Pareto efficiency. It explicitly balances accuracy, latency, and model size to enable deployment-aware architecture search. Experiments conducted on the State Farm Dataset (SFD) and the American University in Cairo Dataset (AUCD2) demonstrate up to a 7<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times \)</EquationSource> </InlineEquation> reduction in parameters compared to state-of-the-art NAS methods while preserving high accuracy (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(98.17\%\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(95.80\%\)</EquationSource> </InlineEquation>, respectively, with only <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(-1.7\%\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(-0.98\%\)</EquationSource> </InlineEquation> accuracy trade-offs). The optimized models, with sizes as small as 0.25 Megabytes (MB) and 0.36 MB, achieve real-time inference latencies of 3–4 milliseconds on an Nvidia Jetson Xavier NX, significantly improving search efficiency and edge deployability.</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

Pareto optimized neural architecture search framework for edge based driver distraction detection

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月25日

查看全文
  • Yassamine Lala Bouali,
  • Olfa Ben Ahmed,
  • Abbas Bradai,
  • Smaine Mazouzi

摘要

The growing adoption of Artificial Intelligence (AI) in real-world applications highlights the need for Deep Learning (DL) models that are both efficient and accurate. However, the high computational requirements of DL often hinder deployment in resource-limited environments. In this paper, we propose an efficient and resource-conscious extension of Differentiable Architecture Search (DARTS) to design lightweight neural networks for driver distraction detection. The proposed method introduces a multi-objective optimization mechanism grounded in Pareto efficiency. It explicitly balances accuracy, latency, and model size to enable deployment-aware architecture search. Experiments conducted on the State Farm Dataset (SFD) and the American University in Cairo Dataset (AUCD2) demonstrate up to a 7 \(\times \) reduction in parameters compared to state-of-the-art NAS methods while preserving high accuracy ( \(98.17\%\) and \(95.80\%\) , respectively, with only \(-1.7\%\) and \(-0.98\%\) accuracy trade-offs). The optimized models, with sizes as small as 0.25 Megabytes (MB) and 0.36 MB, achieve real-time inference latencies of 3–4 milliseconds on an Nvidia Jetson Xavier NX, significantly improving search efficiency and edge deployability.