Jifeng Shen
Papers
2
Total Citations
11
H-Index
2
About
Jifeng Shen is a researcher whose work bridges computer vision and practical engineering challenges, with key contributions in agricultural automation and infrastructure inspection. His research focuses on deep learning applications for fine-grained visual recognition, particularly in weed identification and sewer pipe defect classification. Shen’s most cited work, "Beet seedling and weed recognition based on convolutional neural network and multi-modality images" (2021, 9 citations), demonstrates his expertise in leveraging multi-modal imaging and CNNs for precision agriculture, enabling automated crop-weed differentiation. This work has implications for reducing herbicide use and improving yield. In a more recent study (2022, 2 citations), Shen tackles the nuanced task of fine-grained sewer pipe crack classification, addressing a critical gap in Pipeline Assessment Certification Program (PACP) requirements. By employing knowledge distillation to train a lightweight CNN model, he achieves efficient, deployable solutions for real-world inspection systems. His contributions are notable for their direct applicability—moving beyond generic defect detection to meet specific engineering standards. Shen’s work exemplifies how advanced computer vision can solve domain-specific problems, with potential impacts on sustainable farming and urban infrastructure maintenance.
Research Focus
Key Achievements
Top Papers
- 1
- 2