A Comprehensive Survey of Deep Learning for Pest and Damage Detection in Smart Agriculture: From YOLOv5 to Hybrid Vision-Transformer Models

This survey confirms that deep learning has fundamentally changed how agricultural problems are diagnosed. Optimized YOLO models are the current standard for real-time object detection, excelling at high-speed identification of pests and damage. This achievement represents a massive step away from slow, human-centric visual inspection toward rapid, AI-driven diagnostics. We have witnessed a clear and strategic shift toward combining the unique power of different technolo-gies: the blending of YOLO’s fast localization capabilities with the profound understanding of visual context offered by Vision Transformers (ViTs). This successful integration marks the pathway toward highly sophisticated hybrid systems capable of both rapid localization and detailed severity analysis. The overall shift toward precise, efficient DL tools is a major victory for the future of sustainable crop management.

[1]     M. Vilar-Andreu, L. Garc´ıa, A.-J. Garcia-Sanchez, R. Asorey-Cacheda, and J. Garcia-Haro, ”Enhancing Precision Agriculture Pest Control: A Generalized Deep Learning Approach With YOLOv8-Based Insect Detection,” IEEE Access, vol. 12, pp. 84420-84434, 2024. [2]     E. Yilmaz, S. C. Bocekci, C. Safak, and K. Yildiz, ”Advancements in smart agriculture: A systematic literature review on state-of-the-art plant disease detection with computer vision,” IET Computer Vision, 2025. [3]     R. S, T. Anjali, A. S, S. Ramasubbareddy, and Y. Cho, ”The Power of Vision Transformers and Acoustic Sensors for Cotton Pest Detection,” IEEE Open Journal of the Computer Society, vol. 5, pp. 356-367, 2024. [4]     T. D. Salka, M. B. Hanafi, S. M. S. A. A. Rahman, D. B. M. Zulperi, and Z. Omar, ”Plant leaf disease detection and classification using convolution neural networks model: a review,” Artificial Intelligence Review, vol. 58, pp. 322-322, 2025. [5]     M. H. Tanveer, Z. Fatima, M. A. Khan, M. F. Shahid, and R. C. Voicu, ”Real-Time Plant Disease Detection Using YOLOv5 and Autonomous Robotic Platforms for Scalable Crop Monitoring,” in 2024 9th Interna-tional Conference on Control, Robotics and Cybernetics (CRC), pp. 1-4, 2024. [6]     S. Chakrabarty, P. R. Shashank, C. K. Deb, M. A. Haque, P. Thakur, D. Kamil, S. Marwaha, and M. K. Dhillon, ”Deep learning-based accurate detection of insects and damage in cruciferous crops using YOLOv5,” Smart Agricultural Technology, vol. 9, p. 100663, 2024. [7]     L. Du, J. Zhu, M. Liu, and L. Wang, ”YOLOv7-PSAFP: Crop pest and disease detection based on improved YOLOv7,” IET Image Processing, vol. 18, pp. 4913-4927, 2024. [8]     S. Huo, N. Duan, and Z. Xu, ”An improved multi-scale YOLOv8 for apple leaf dense lesion detection and recognition,” IET Image Processing, vol. 18, pp. 4913-4927, 2024. [9]     R. Sapkota, M. Flores-Calero, R. Qureshi, C. Badgujar, U. Nepal, A. Poulose, P. Zeno, U. B. P. Vaddevolu, S. Khan, M. Shoman, H. Yan, and M. Karkee, ”YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series,” Artificial Intelligence Review, vol. 58, pp. 274-274, 2025. [10]     B. T. Vamsi, J. Yadla, and G. V. Kumar, ”Application of IP102 Dataset in Pest Detection by using Deep Learning Techniques,” in 2023 Inter-national Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), pp. 1-6, 2023.