Skip to main content

ORIGINAL RESEARCH article

Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
Volume 15 - 2024 | doi: 10.3389/fpls.2024.1396568
This article is part of the Research Topic Autonomous Weed Control for Crop Plants View all 6 articles

Performance Evaluation of Semi-Supervised Learning Frameworks for Multi-Class Weed Detection

Provisionally accepted
Jiajia Li Jiajia Li 1Dong Chen Dong Chen 2Xunyuan Yin Xunyuan Yin 3Zhaojian Li Zhaojian Li 1*
  • 1 Michigan State University, East Lansing, Michigan, United States
  • 2 University of Virginia, Charlottesville, Virginia, United States
  • 3 Nanyang Technological University, Singapore, Singapore

The final, formatted version of the article will be published soon.

    Precision weed management, driven by machine vision and deep learning advancements, not only enhances agricultural product quality and optimizes crop yield but also provides a sustainable alternative to herbicide use. However, existing deep learning algorithms on weed detection are mainly developed based on supervised learning approaches, typically demanding large-scale datasets with manual-labeled annotations, which can be time-consuming and labor-intensive. As such, label-efficient learning methods, especially semi-supervised learning, have gained increased attention in the broader domain of computer vision and have demonstrated promising performance. These methods aim to utilize a small number of labeled data samples along with a great number of unlabeled samples to develop high-performing models comparable to the supervised learning counterpart trained on a large amount of labeled data samples. In this study, we assess the effectiveness of a semi-supervised learning framework for multi-class weed detection, employing two well-known object detection frameworks, namely FCOS (Fully Convolutional One-Stage Object Detection) and Faster-RCNN (Faster Region-based Convolutional Networks). Specifically, we evaluate a generalized student-teacher framework with an improved pseudo-label generation module to produce reliable pseudo-labels for the unlabeled data. To enhance generalization, an ensemble student network is employed to facilitate the training process. Experimental results show that the proposed approach is able to achieve approximately 76% and 96% detection accuracy as the supervised methods with only 10% of labeled data in CottonWeedDet3 and CottonWeedDet12, respectively. We offer access to the source code, contributing a valuable resource for ongoing semi-supervised learning research in weed detection and beyond.

    Keywords: Precision weed management, precision agriculture, label-efficient learning, Computer Vision, and Deep Learning

    Received: 05 Mar 2024; Accepted: 24 Jul 2024.

    Copyright: © 2024 Li, Chen, Yin and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Zhaojian Li, Michigan State University, East Lansing, 48824, Michigan, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.