Scholarlink

<p>In this study, we propose a new hybrid deep learning architecture combining Vision Transformers (ViT) with Convolutional Attention Blocks (CAB), specifically designed for automated weed detection in precision agriculture. We introduce a novel coupled approach that combines transformer-based global contextual modelling with channel-wise attention-based local spatial feature extraction to classify images into four classes: broadleaf weeds, grass, soil, and soybean crops. Following training on a balanced dataset of 4795 samples resized to 224 × 224 pixels, the proposed model achieves an overall AUC of 0.97. While the ViT-only configuration achieves the highest classification accuracy (91%), the hybrid ViT-CAB architecture offers superior interpretability via Grad-CAM visualisations and more balanced per-class performance across morphologically similar vegetative categories, making it the preferred choice when explainability and class-balanced prediction are priorities for precision agricultural deployment. This compact model (412&#xa0;K parameters, 1.57&#xa0;MB) processes each image in 141&#xa0;ms per step and is thus practical for real-time use in intelligent weed management systems aiming at sustainable farming mechanisms.</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

HybridViT-CAB: a vision transformer and convolutional attention network for precision weed detection in agricultural systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月21日

查看全文
  • Geetha Reddy Yenna,
  • Nalli Vinaya Kumari,
  • Arun Singh Chouhan,
  • Syed Umar,
  • Sandhya Rani Macha

摘要

In this study, we propose a new hybrid deep learning architecture combining Vision Transformers (ViT) with Convolutional Attention Blocks (CAB), specifically designed for automated weed detection in precision agriculture. We introduce a novel coupled approach that combines transformer-based global contextual modelling with channel-wise attention-based local spatial feature extraction to classify images into four classes: broadleaf weeds, grass, soil, and soybean crops. Following training on a balanced dataset of 4795 samples resized to 224 × 224 pixels, the proposed model achieves an overall AUC of 0.97. While the ViT-only configuration achieves the highest classification accuracy (91%), the hybrid ViT-CAB architecture offers superior interpretability via Grad-CAM visualisations and more balanced per-class performance across morphologically similar vegetative categories, making it the preferred choice when explainability and class-balanced prediction are priorities for precision agricultural deployment. This compact model (412 K parameters, 1.57 MB) processes each image in 141 ms per step and is thus practical for real-time use in intelligent weed management systems aiming at sustainable farming mechanisms.