中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Causality-inspired crop pest recognition based on Decoupled Feature Learning

文献类型：期刊论文

作者Hu, Tao2,3; Du, Jianming2; Yan, Keyu2,3; Dong, Wei4; Zhang, Jie2; Wang, Jun1; Xie, Chengjun2
刊名PEST MANAGEMENT SCIENCE
出版日期2024-07-18
关键词pest recognition Decoupled Feature Learning causal inference deep learning
ISSN号1526-498X
DOI10.1002/ps.8314
通讯作者Dong, Wei(dw06@163.com) ; Xie, Chengjun(cjxie@iim.ac.cn)
英文摘要BACKGROUNDEnsuring the efficient recognition and management of crop pests is crucial for maintaining the balance in global agricultural ecosystems and ecological harmony. Deep learning-based methods have shown promise in crop pest recognition. However, prevailing methods often fail to address a critical issue: biased pest training dataset distribution stemming from the tendency to collect images primarily in certain environmental contexts, such as paddy fields. This oversight hampers recognition accuracy when encountering pest images dissimilar to training samples, highlighting the need for a novel approach to overcome this limitation.RESULTSWe introduce the Decoupled Feature Learning (DFL) framework, leveraging causal inference techniques to handle training dataset bias. DFL manipulates the training data based on classification confidence to construct different training domains and employs center triplet loss for learning class-core features. The proposed DFL framework significantly boosts existing baseline models, attaining unprecedented recognition accuracies of 95.33%, 92.59%, and 74.86% on the Li, DFSPD, and IP102 datasets, respectively.CONCLUSIONExtensive testing on three pest datasets using standard baseline models demonstrates the superiority of DFL in pest recognition. The visualization results show that DFL encourages the baseline models to capture the class-core features. The proposed DFL marks a pivotal step in mitigating the issue of data distribution bias, enhancing the reliability of deep learning in agriculture. (c) 2024 Society of Chemical Industry. We propose the Decoupled Feature Learning framework to enhance the performance of deep learning models in pest recognition. This framework mitigates training dataset bias by employing causal inference to construct distinct training domains and utilizes center triplet loss to encourage the model to learn class-core features. image
资助项目National Natural Science Foundation of China[32171888] ; Dean's Fund of Hefei Institutes of Physical Science, Chinese Academy of Sciences[YZJJ2022QN32] ; Key program of Anhui Province Higher Education Science Research Project[2022AH052361] ; Natural Science Foundation of Anhui Province, China[2208085MC57]
WOS研究方向Agriculture ; Entomology
语种英语
WOS记录号WOS:001270494100001
出版者JOHN WILEY & SONS LTD
资助机构National Natural Science Foundation of China ; Dean's Fund of Hefei Institutes of Physical Science, Chinese Academy of Sciences ; Key program of Anhui Province Higher Education Science Research Project ; Natural Science Foundation of Anhui Province, China
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/137131]  
专题中国科学院合肥物质科学研究院
通讯作者Dong, Wei; Xie, Chengjun
作者单位1.Anhui Tech Coll Mech & Elect Engn, Sch Internet & Telecommun, Wuhu, Peoples R China
2.Chinese Acad Sci, Inst Intelligent Machines, Hefei Inst Phys Sci, Hefei 230031, Peoples R China
3.Univ Sci & Technol China, Sci Isl Branch, Grad Sch, Hefei, Peoples R China
4.Anhui Acad Agr Sci, Agr Econ & Informat Res Inst, Hefei 230001, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Tao,Du, Jianming,Yan, Keyu,et al. Causality-inspired crop pest recognition based on Decoupled Feature Learning[J]. PEST MANAGEMENT SCIENCE,2024.
APA Hu, Tao.,Du, Jianming.,Yan, Keyu.,Dong, Wei.,Zhang, Jie.,...&Xie, Chengjun.(2024).Causality-inspired crop pest recognition based on Decoupled Feature Learning.PEST MANAGEMENT SCIENCE.
MLA Hu, Tao,et al."Causality-inspired crop pest recognition based on Decoupled Feature Learning".PEST MANAGEMENT SCIENCE (2024).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。