A Hybrid CNN-ViT-GNN Framework with GAN-Based Augmentation for Intelligent Weed Detection in Precision Agriculture

TL;DR

This paper introduces a hybrid deep learning framework combining CNNs, ViTs, and GNNs, enhanced with GAN-based augmentation and self-supervised pre-training, achieving high accuracy in weed detection for sustainable precision agriculture.

Contribution

The paper presents a novel hybrid CNN-ViT-GNN architecture with GAN augmentation and self-supervised learning, improving robustness and accuracy in weed detection under diverse field conditions.

Findings

Achieved 99.33% accuracy, precision, recall, and F1-score on benchmark datasets.

Demonstrated real-time deployment capability on edge devices.

Enhanced model robustness and interpretability in weed detection.

Abstract

The task of weed detection is an essential element of precision agriculture since accurate species identification allows a farmer to selectively apply herbicides and fits into sustainable agriculture crop management. This paper proposes a hybrid deep learning framework recipe for weed detection that utilizes Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Graph Neural Networks (GNNs) to build robustness to multiple field conditions. A Generative Adversarial Network (GAN)-based augmentation method was imposed to balance class distributions and better generalize the model. Further, a self-supervised contrastive pre-training method helps to learn more features from limited annotated data. Experimental results yield superior results with 99.33% accuracy, precision, recall, and F1-score on multi-benchmark datasets. The proposed model architecture enables local, global, and relational feature representations and offers high interpretability and adaptability. Practically, the framework allows real-time, efficient deployment to edge devices for automated weed detecting, reducing over-reliance on herbicides and providing scalable, sustainable precision-farming options.