GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation

Given the serious economic burden that citrus diseases impose on fruit farmers and related industries, achieving rapid and accurate disease detection is particularly crucial. In response to the challenges posed by resource-limited platforms and complex backgrounds, this paper designs and proposes a...

Full description

Saved in:
Bibliographic Details
Main Authors: Linlin Yang, Zhonghao Huang, Yi Huangfu, Rui Liu, Xuerui Wang, Zhiwei Pan, Jie Shi
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/7/1515
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067568789815296
author Linlin Yang
Zhonghao Huang
Yi Huangfu
Rui Liu
Xuerui Wang
Zhiwei Pan
Jie Shi
author_facet Linlin Yang
Zhonghao Huang
Yi Huangfu
Rui Liu
Xuerui Wang
Zhiwei Pan
Jie Shi
author_sort Linlin Yang
collection DOAJ
description Given the serious economic burden that citrus diseases impose on fruit farmers and related industries, achieving rapid and accurate disease detection is particularly crucial. In response to the challenges posed by resource-limited platforms and complex backgrounds, this paper designs and proposes a lightweight method for the identification and localization of citrus diseases based on the RT-DETR-r18 model—GYS-RT-DETR. This paper proposes an optimization method for target detection that significantly enhances model performance through multi-dimensional technology integration. First, this paper introduces the following innovations in model structure: (1) A Gather-and-Distribute Mechanism is introduced in the Neck section, which effectively enhances the model’s ability to detect medium to large targets through global feature fusion and high-level information injection.(2) Scale Sequence Feature Fusion (SSFF) is used to optimize the Neck structure to improve the detection performance of the model for small targets in complex environments. (3) The Focaler-ShapeIoU loss function is used to solve the problems of unbalanced training samples and inaccurate positioning. Secondly, the model adopts two model optimization strategies: (1) The Group_taylor local pruning algorithm is used to reduce memory occupation and the number of computing parameters of the model. (2) The feature-logic knowledge distillation framework is proposed and adopted to solve the problem of information loss caused by the structural difference between teachers and students, and to ensure a good detection performance, while realizing the lightweight character of the model. The experimental results show that the GYS-RT-DETR model has a precision of 79.1%, a recall of 77.9%, an F1 score of 78.0%, a model size of 23.0 MB, and an mAP value of 77.8%. Compared to the original model, the precision, recall, the F1 score, the mAP value, and the FPS value have improved by 3.5%, 5.3%, 5.0%, 5.3%, and 10.3 f/s, respectively. Additionally, the memory usage of the GYS-RT-DETR model has decreased by 25.5 MB compared to the original model. The GYS-RT-DETR model proposed in this article can effectively detect various citrus diseases in complex backgrounds, addressing the time-consuming nature of manual detection and improving the accuracy of model detection, thereby providing an effective theoretical basis for the automated detection of citrus diseases.
format Article
id doaj-art-8a5f0791e6584dd09943c91b0f51de8a
institution DOAJ
issn 2073-4395
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-8a5f0791e6584dd09943c91b0f51de8a2025-08-20T02:48:16ZengMDPI AGAgronomy2073-43952025-06-01157151510.3390/agronomy15071515GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge DistillationLinlin Yang0Zhonghao Huang1Yi Huangfu2Rui Liu3Xuerui Wang4Zhiwei Pan5Jie Shi6Mechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaMechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaMechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaMechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaMechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaMechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaMechanical and Electrical Engineering College, Yunnan Agricultural University, Kunming 650201, ChinaGiven the serious economic burden that citrus diseases impose on fruit farmers and related industries, achieving rapid and accurate disease detection is particularly crucial. In response to the challenges posed by resource-limited platforms and complex backgrounds, this paper designs and proposes a lightweight method for the identification and localization of citrus diseases based on the RT-DETR-r18 model—GYS-RT-DETR. This paper proposes an optimization method for target detection that significantly enhances model performance through multi-dimensional technology integration. First, this paper introduces the following innovations in model structure: (1) A Gather-and-Distribute Mechanism is introduced in the Neck section, which effectively enhances the model’s ability to detect medium to large targets through global feature fusion and high-level information injection.(2) Scale Sequence Feature Fusion (SSFF) is used to optimize the Neck structure to improve the detection performance of the model for small targets in complex environments. (3) The Focaler-ShapeIoU loss function is used to solve the problems of unbalanced training samples and inaccurate positioning. Secondly, the model adopts two model optimization strategies: (1) The Group_taylor local pruning algorithm is used to reduce memory occupation and the number of computing parameters of the model. (2) The feature-logic knowledge distillation framework is proposed and adopted to solve the problem of information loss caused by the structural difference between teachers and students, and to ensure a good detection performance, while realizing the lightweight character of the model. The experimental results show that the GYS-RT-DETR model has a precision of 79.1%, a recall of 77.9%, an F1 score of 78.0%, a model size of 23.0 MB, and an mAP value of 77.8%. Compared to the original model, the precision, recall, the F1 score, the mAP value, and the FPS value have improved by 3.5%, 5.3%, 5.0%, 5.3%, and 10.3 f/s, respectively. Additionally, the memory usage of the GYS-RT-DETR model has decreased by 25.5 MB compared to the original model. The GYS-RT-DETR model proposed in this article can effectively detect various citrus diseases in complex backgrounds, addressing the time-consuming nature of manual detection and improving the accuracy of model detection, thereby providing an effective theoretical basis for the automated detection of citrus diseases.https://www.mdpi.com/2073-4395/15/7/1515characteristic distillationlogic distillationGroup_taylor pruningRT-DETR-r18GD mechanismSSFF mechanism
spellingShingle Linlin Yang
Zhonghao Huang
Yi Huangfu
Rui Liu
Xuerui Wang
Zhiwei Pan
Jie Shi
GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation
Agronomy
characteristic distillation
logic distillation
Group_taylor pruning
RT-DETR-r18
GD mechanism
SSFF mechanism
title GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation
title_full GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation
title_fullStr GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation
title_full_unstemmed GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation
title_short GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation
title_sort gys rt detr a lightweight citrus disease detection model based on integrated adaptive pruning and dynamic knowledge distillation
topic characteristic distillation
logic distillation
Group_taylor pruning
RT-DETR-r18
GD mechanism
SSFF mechanism
url https://www.mdpi.com/2073-4395/15/7/1515
work_keys_str_mv AT linlinyang gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation
AT zhonghaohuang gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation
AT yihuangfu gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation
AT ruiliu gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation
AT xueruiwang gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation
AT zhiweipan gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation
AT jieshi gysrtdetralightweightcitrusdiseasedetectionmodelbasedonintegratedadaptivepruninganddynamicknowledgedistillation