Evaluation of Convolutional and Transformer-Based Detectors for Weed Detection in Tomato Plantations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Espinosa, Alcides Toledo, Hernández, Gerardo Antonio Álvarez, Zamora-Suárez, Ángel Eduardo, Bolaños, Miguel, Vásquez, Juan Irving
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917525931950080
author Espinosa, Alcides Toledo
Hernández, Gerardo Antonio Álvarez
Zamora-Suárez, Ángel Eduardo
Bolaños, Miguel
Vásquez, Juan Irving
author_facet Espinosa, Alcides Toledo
Hernández, Gerardo Antonio Álvarez
Zamora-Suárez, Ángel Eduardo
Bolaños, Miguel
Vásquez, Juan Irving
contents This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in tomato plantations. Representative models from each paradigm are considered, including YOLOv26-nano, a recent variant of the YOLO family, and RT-DETR Large and RF-DETR Medium as transformer-based architectures. The evaluation was conducted on the GROUNDBASED_WEED dataset, considering six weed classes and an additional category corresponding to unidentified plants, which allowed for the assessment of performance in terms of detection accuracy and computational efficiency using metrics such as precision, recall, average precision, and inference speed, as well as non-parametric statistical tests. 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00908
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluation of Convolutional and Transformer-Based Detectors for Weed Detection in Tomato Plantations
Espinosa, Alcides Toledo
Hernández, Gerardo Antonio Álvarez
Zamora-Suárez, Ángel Eduardo
Bolaños, Miguel
Vásquez, Juan Irving
Computer Vision and Pattern Recognition
This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in tomato plantations. Representative models from each paradigm are considered, including YOLOv26-nano, a recent variant of the YOLO family, and RT-DETR Large and RF-DETR Medium as transformer-based architectures. The evaluation was conducted on the GROUNDBASED_WEED dataset, considering six weed classes and an additional category corresponding to unidentified plants, which allowed for the assessment of performance in terms of detection accuracy and computational efficiency using metrics such as precision, recall, average precision, and inference speed, as well as non-parametric statistical tests. 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.
title Evaluation of Convolutional and Transformer-Based Detectors for Weed Detection in Tomato Plantations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.00908