COMPARATIVE BASELINE EVALUATION OF YOLOV5 AND YOLO11 FOR AGRICULTURAL WEED DETECTION
DOI:
https://doi.org/10.61837/mbuir040126127mKeywords:
YOLO11 architecture; Adaptive Weighted Box Fusion (WBF); C2PSA attention mechanism; Sliced Aided Hyper Inference (SAHI); P2/4 micro-scale detection head; Precision agricultural eradication; Domain-specific anchor optimizationAbstract
This paper presents a comparative baseline evaluation of YOLOv5 and YOLO11 object detection architectures applied to ambrosia detection in agricultural field imagery. Using a constrained dataset of 96 images (64 training, 32 validation), we systematically analyze the architectural characteristics, scaling mechanisms, and anchor box configurations of both frameworks. Baseline experiments establish performance benchmarks of mAP50=0.624 for YOLOv5 and mAP50=0.710 for YOLO11 under identical training conditions. Our analysis identifies key limitations of general-purpose architectures when applied to specialized botanical detection tasks with limited training data, providing a foundation for targeted domain-specific modifications. Results demonstrate that YOLO11’s enhanced backbone design with C2PSA modules achieves superior baseline precision (0.800 vs 0.694) while both architectures fall short of the target mAP50 > 0.85, motivating further architectural and post-processing research.
References
Redmon, J. et al., “You Only Look Once: Unified, Real-Time Object Detection,” CVPR 2016.
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. DOI: 10.48550/arXiv.2004.10934
Jocher, G. et al., “YOLOv5 by Ultralytics” 2020., Available at https://github.com/ultralytics/yolov5 (March 28, 2026)
Wang, C. Y., Liao, H. Y. M., Wu, Y. H., Chen, P. Y., Hsieh, J. W., & Yeh, I. H. (2020). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. Proceedings of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition Workshops. DOI:10.1109/ CVPRW50498.2020.00203
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. DOI: 10.1109/TPAMI.2015.2389824
Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path Aggregation Network for Instance Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI: 10.48550/arXiv.1803.01534
Jocher, G. et al., “Ultralytics YOLO11” 2024., Available at https://github.com/ultralytics/ultra lytics (March 28, 2026)
Khanam, R., & Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv:2410.17725 [cs.CV]. DOI: 10.48550/arX iv.2410.17725
Chen Xiaoming et al., “An improved algorithm based on YOLOv5 for detecting Ambrosia in UAV images,” 2023.
Tian, Z., Shen, C., Chen, H., & He, T. (2019). FCOS: Fully Convolutional One-Stage Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). DOI: 10.48550/arXiv.1904.01355
Solovyev, R., & Wang, W. (2021). Weighted Boxes Fusion: Ensembling Boxes from Different Object Detection Models. DOI: 10.1016/j.ima vis.2021.104117
Akyon, F. C., Altinuc, S. O., & Temizel, A. (2022). Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection. 2022 IEEE International Conference on Image Processing (ICIP). DOI: 10.48550/arXiv.2202.06934
