A Comparative Study of Deep Learning-Based Pest Detection Models with Interpretability and Deployment Strategies for Medicinal Plants

A comparative study of deep learning models for tomato disease detection

An Empirical Evaluation of Lightweight YOLO Architectures for Plant Pest Detection

Automated pest detection plays a critical role in supporting agricultural productivity by enabling accurate and efficient recognition of pest species in field conditions. This study presents a comparative evaluation and ablation analysis of four lightweight object detection models, namely YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n, for plant pest detection tasks. All models were trained and tested on the IP102 dataset, a large-scale benchmark comprising 102 pest categories captured across diverse field environments. Each model was evaluated under four optimization scenarios: AdamW optimizer, Mixup and Mosaic augmentation, a combination of both strategies, and Test-Time Augmentation (TTA). Performance was measured using precision, recall, F1-score, mAP@0.5, and mAP@0.5:0.95 to assess both detection accuracy and bounding box localization quality. The results demonstrate that YOLOv12n consistently achieves superior performance across the majority of evaluation metrics. Under the TTA scenario, YOLOv12n attained a precision of 0.590, recall of 0.698, F1-score of 0.639, mAP@0.5 of 0.689, and mAP@0.5:0.95 of 0.444, representing the highest scores among all evaluated configurations. TTA proved to be the most consistent optimization strategy, delivering stable improvements across all model architectures. In contrast, combining AdamW with data augmentation degraded performance across all models, likely due to over-regularization effects in lightweight network designs. These findings highlight that inference-level strategies can be more beneficial than training-level augmentation for compact detection models. This study provides practical insights for selecting and optimizing lightweight detectors in real-world agricultural deployment scenarios.

A Comparative Study of Convolutional Neural Network based Transfer Learning Models for Plant Disease Detection

The study demonstrates that transfer learning effectively enhances plant disease classification, enabling faster, more reliable and resource efficient detection for precision agriculture.

A Comprehensive Review of Deep Learning Approaches for Automated Farm Weed Classification

One of the biggest obstacles to agricultural output is weed infestation, which causes a significant drop in crop production, increases production costs, and affects food security. Conventional ways of controlling weeds, such as hand weeding and using herbicides, are usually very laborious, expensive, and unsustainable. In recent years, deep learning has become an attractive option in automated weed detection and classification in precision agriculture. This paper is a review of the extensive classification of farm weeds through deep learning models with special emphasis on object detection networks, convolutional neural networks (CNNs), transfer learning models, transformer-based models and data augmentation techniques. Applicable literature was methodically evaluated with reference to datasets, model structures, and performance parameters, including accuracy, F1-score, and mean average precision (mAP). The review indicates that other models, such as YOLO variants, ResNet, EfficientNet, and Vision Transformers, have demonstrated high classification accuracy under controlled conditions. Nevertheless, issues such as limited dataset diversity, inadequate real-world generalisation, excessive computational complexity, and standardised evaluation schemes continue to impede at-scale implementation. The research results have concluded that, in the future, lightweight models, larger-scale, more diverse data, and the integration of deep learning with IoT and autonomous systems should be the subject of research to make the processes of monitoring and controlling weeds in modern agriculture fully automated and sustainable.

Deep Learning for Plant Disease Detection: A Systematic Review

It is suggested that in order to be implementable in the field, future intelligent agricultural diagnosis systems must be able to balance predictive accuracy, explainability, computational efficiency and field adaptability.

A Deep Learning Methodology for the Early Identification of Chili Plant Diseases Utilizing SSD-ResNet-50 Architecture

This research presents an automated detection method using the Single Shot Detector (SSD) framework, with ResNet-50 as the backbone and a Feature Pyramid Network (FPN) to manage multi-scale feature representations to strengthen plant disease monitoring systems.