Shiwei Wen
Papers
1
Total Citations
7
H-Index
1
About
Shiwei Wen is a leading researcher in agricultural artificial intelligence, specializing in lightweight deep learning models for real-time fruit detection in natural environments. His most significant contribution is the development of PcMNet, an efficient apple detection algorithm that addresses the critical challenge of deploying AI on resource-constrained edge devices. Wen’s innovative work integrates Transformer-based Cross Channel Feature Fusion (CCFF) into a redesigned Faster-CCFF neck structure, and introduces the PR module and Pconv-block using partial convolution for parameter efficiency. The impact of this research is demonstrated by PcMNet’s remarkable performance: achieving 92 frames per second on an NVIDIA Jetson Orin NX with TensorRT acceleration, while compressing the model to just 3.2 MB with only 0.81 million parameters. This breakthrough enables high-speed, accurate fruit detection in orchards without requiring powerful cloud computing, making precision agriculture more accessible. With 7 citations since its 2024 publication, Wen’s work is rapidly gaining recognition for its practical implications in smart farming, setting a new benchmark for balancing speed, accuracy, and model size in agricultural computer vision.
Research Focus
Key Achievements
Top Papers
- 1