ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
This article is part of the Research TopicAdvanced Imaging and Phenotyping for Sustainable Plant Science and Precision Agriculture 4.0View all 8 articles
RFDAF-Net: A Novel Region-specific Feature Decoupling and Adaptive Fusion Network for Field Soybean Disease Identification in Precision Agriculture
Provisionally accepted
- 1Kaili University, Kaili, China
- 2Qiannan Normal College For Nationalities, Duyun, China
- 3Guizhou University, Guiyang, China
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
Soybean diseases pose a significant threat to global crop yield and food security, necessitating rapid and accurate identification for effective management. While deep learning offers promising solutions for plant disease recognition, existing models often struggle with the complexities of in-field soybean disease identification, particularly due to high intra-class variations and subtle inter-class differences. To address these challenges, we propose a novel region-specific feature decoupling and adaptive fusion network (RFDAF-Net) designed for robust and precise soybean disease recognition under real-world field conditions. The core of RFDAF-Net consists of two key components: a region-specific feature decoupling (RFD) module that enhances discriminative patterns and suppresses redundant information through a dual-pathway design, explicitly separating shallow, intermediate, and deep features; and a region-specific feature adaptive fusion (RFAF) module that dynamically integrates these multi-scale features via learned spatial attention. This hierarchical feature decomposition effectively isolates discriminative disease signatures while suppressing irrelevant variations. The architecture is flexible, enabling seamless integration with various backbone networks including both convolutional neural networks and Transformers. We evaluate RFDAF-Net extensively on a comprehensive soybean disease dataset containing images captured in diverse field environments. Experimental results show that our method significantly outperforms current state-of-the-art models across multiple architectures, achieving a top accuracy of 99.43% when implemented with a Swin-B backbone. The proposed framework offers an interpretable and field-ready solution for precision crop protection, demonstrating strong generalization ability and practical utility for real-world agricultural applications.
Keywords: Adaptive fusion, deep learning, label queue, region-specific feature decoupling, Soybean disease identification
Received: 28 Oct 2025; Accepted: 09 Dec 2025.
Copyright: © 2025 Pan, Yang, Cao and Chen. 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: Yang Chen
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.