Comparative Evaluation of Convolutional and Transformer-Based Detectors for Automated Weed Detection in Precision Agriculture
Provides practical model selection criteria for precision agriculture practitioners choosing between efficiency and contextual modeling.
This paper compares convolutional and transformer-based object detectors for early weed detection, finding that CNN-based models (e.g., YOLOv26-nano) offer high accuracy with lower computational cost, while transformers provide better global context but require more resources.
This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in realistic scenarios. Representative models from each paradigm are considered, including YOLOv26-nano, a recent variant of the YOLO family, and transformer-based approaches such as RTDETR and RF-DETR. Experiments were conducted on the GROUNDBASED_ WEED dataset, allowing performance to be evaluated in terms of detection accuracy and computational efficiency using metrics such as precision, recall, average precision, and inference speed. The results highlight a clear trade-off between efficiency and contextual modeling: CNN-based detectors achieve high performance at a lower computational cost, while transformer-based approaches offer better global context capture at the expense of higher resource demands. These results provide practical criteria for model selection in precision agriculture applications.