Hybrid CNN–Transformer Models for Multi-Class Pest Classification
Abstract
This repository contains the complete source code for the experiments reported in the paper “Transformer-Augmented Hybrid Deep Learning for Reliable Multi-Class Pest Classification: An Explainable AI Framework for Precision Agriculture.” The repository includes model architectures (CNN and hybrid CNN–Transformer), training scripts, segmentation-based preprocessing pipelines, and evaluation utilities.
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 February 2026
- Document type
- Dataset