ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. AI in Food, Agriculture and Water
Volume 8 - 2025 | doi: 10.3389/frai.2025.1643582
Enhancing detection of common bean diseases using fast gradient sign method-trained Vision Transformers
Provisionally accepted
- The Nelson Mandela African Institution of Science and Technology, Arusha, Tanzania
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Common bean production in Tanzania is threatened by diseases such as bean rust and bean anthracnose, with early detection critical for effective management. This study presents a Vision Transformer (ViT)-based deep learning model enhanced with adversarial training to improve disease detection robustness under real-world farm conditions. A dataset of 100,000 annotated images augmented with geometric, color, and FGSM-based perturbations, simulating field variability. FGSM was selected for its computational efficiency in low-resource settings. The model, fine-tuned using transfer learning and validated through cross-validation, achieved an accuracy of 99.4%. Results highlight the effectiveness of integrating adversarial robustness to enhance model reliability for mobile-based plant disease detection in resource-constrained environments
Keywords: Bean rust, Bean anthracnose, deep learning, Vision Transformers (ViT), adversarial attacks, Fast Gradient Sign Method
Received: 09 Jun 2025; Accepted: 24 Jul 2025.
Copyright: © 2025 MWAIBALE, Mduma, Laizer and Mgawe. 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: UPENDO Jimson MWAIBALE, The Nelson Mandela African Institution of Science and Technology, Arusha, Tanzania
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.