Scholarlink

<p>Accurate grain quality classification at scale requires models that are simultaneously lightweight and highly discriminative, yet existing approaches struggle to satisfy both constraints. This paper proposes a lightweight complementary network integrating a convolutional neural network (CNN) and Transformer, termed the Lite Grain Classification Network (LGC-Net), for semantic alignment of heterogeneous features in multi-grain defect recognition. To overcome the quadratic complexity of conventional self-attention, we introduce Fast Channel Additive Attention, which applies additive attention to a partial channel subset, reducing complexity from quadratic to linear while preserving global semantic modeling capacity. A Dual Attention Fusion Module is further proposed to align local spatial features from the CNN branch with global representations from the Transformer branch, effectively leveraging their complementary strengths. Experiments on a dataset comprising five grain types (maize, wheat, rice, barley, and sorghum) with over ten defect categories show that LGC-Net-XXS achieves 89.59% average accuracy with only 0.93&#xa0;M parameters and 0.43 G FLOPs, demonstrating its potential for real-time deployment in large-scale agricultural data analysis on resource-constrained edge devices.</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

Lightweight CNN-Transformer complementary network for large-scale analysis: semantic alignment of heterogeneous multi-modal features

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月10日

查看全文
  • Lei Shi,
  • Xintong Yan,
  • Jing Chen,
  • Weiyu Ye,
  • Pengfei Zhang,
  • Pengtao Lv,
  • Zhan Zhang,
  • Xiangcheng Feng

摘要

Accurate grain quality classification at scale requires models that are simultaneously lightweight and highly discriminative, yet existing approaches struggle to satisfy both constraints. This paper proposes a lightweight complementary network integrating a convolutional neural network (CNN) and Transformer, termed the Lite Grain Classification Network (LGC-Net), for semantic alignment of heterogeneous features in multi-grain defect recognition. To overcome the quadratic complexity of conventional self-attention, we introduce Fast Channel Additive Attention, which applies additive attention to a partial channel subset, reducing complexity from quadratic to linear while preserving global semantic modeling capacity. A Dual Attention Fusion Module is further proposed to align local spatial features from the CNN branch with global representations from the Transformer branch, effectively leveraging their complementary strengths. Experiments on a dataset comprising five grain types (maize, wheat, rice, barley, and sorghum) with over ten defect categories show that LGC-Net-XXS achieves 89.59% average accuracy with only 0.93 M parameters and 0.43 G FLOPs, demonstrating its potential for real-time deployment in large-scale agricultural data analysis on resource-constrained edge devices.