What question did this study set out to answer?

To develop a method for accurately identifying multiple similar crop pests using a visual language model.

April 23, 2026Pest Management Science0 citations

Identification method for multiple similar crop pests: A visual language model combined with coarse–finegrain cross‐modal matching

YCY ChenDalian Maritime University YGYuan GaoDalian Maritime University YWYì WángBGI Group (China)

Key Points

To develop a method for accurately identifying multiple similar crop pests using a visual language model.
Utilized the IP102 dataset from real field environments and data from Li and Xie.
Implemented a cross-modal matching approach for improved identification accuracy.
Conducted comparative analysis against previous models.
Achieved an average accuracy improvement of 11.68% over prior models.
Also improved accuracy by 4.26% and 5.90% compared to other cross-modal models.
Demonstrated suitability for monitoring and detecting pests in complex agricultural settings.

Abstract

Our approach is validated using the IP102 dataset collected from real field environments and the dataset provided by Li and Xie. Compared to previous cross-modal models, the classification average accuracy improves by 11.68%, 4.26% and 5.90%, respectively. Experimental results demonstrate that the model is suitable for monitoring and detecting crop pests and diseases in complex environments. © 2026 Society of Chemical Industry.

问 AI

Bookmark

View Full Paper