数字农科院2.0

Generalized zero-shot pest and disease image classification based on causal gating model

文献类型： 外文期刊

作者： Shansong Wang;Qingtian Zeng;Guiyuan Yuan;Weijian Ni;Chao Li;Hua Duan;Nengfu Xie;Fengjin Xiao;Xiaofeng Yang

作者机构：

关键词： Agricultural Pests and Diseases;Generalized Zero-shot Learning;Image Classification;Structural Causal Model

期刊名称： Computers and Electronics in Agriculture

ISSN： 0168-1699

年卷期： 2025 年 230 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Images of scarce agricultural pests and diseases categories are often hard to obtain, and there are frequently no visual examples in web search engines. Therefore, it is challenging to build an image classification model based on supervised learning. To address this issue, Generalized Zero-shot Learning (GZSL) based on Generative Adversarial Networks (GANs) offers an effective solution. However, a major challenge of GZSL is that the model tends to overfit on seen class data, causing unseen classes to be frequently misclassified as seen classes. To meet this challenge, we propose a novel Structural Causal Model-based Binary Domain Classifier (SCM-BDC) for generalized zero-shot pest and disease image classification. Our method introduces a Structural Causal Model (SCM) to extract causal features from visual features to reduce the impact of non-causal features that blur the distinction between seen and unseen classes. Furthermore, we use an Angular Linear Layer (ALL) to project class-level attributes and causal features onto the unit hypersphere and identify a boundary for each seen class. During the testing phase, if the similarity between the sample and all seen attributes is less than the corresponding threshold, it is classified as an unseen class; otherwise, as a seen class. Finally, we use a seen classifier and an unseen classifier to predict the corresponding samples, respectively. Extensive experiments on APTV99, ADTV68, AWA1, AWA2, CUB, SUN, and FLO demonstrate that the proposed method can significantly improve the performance of GZSL. For the APTV99 and ADTV68 datasets, our method achieves a 5.2 % and 1.4 % improvement in GZSL classification accuracy over state-of-the-art methods.

分类号：

  • 相关文献

[1]APD-229: a textual-visual database for agricultural pests and diseases. Wang, Shan-Song,Ni, Wei-Jian,Zeng, Qing-Tian,Xie, Neng-Fu,Li, Chao. 2023

[2]A Spectral Signature Shape-Based Algorithm for Landsat Image Classification. Chen, Yuanyuan,Duan, Si-Bo,Li, Zhao-Liang,Chen, Yuanyuan,Wang, Yanlong,Duan, Si-Bo,Li, Zhao-Liang,Wang, Quanfang,Wang, Yanlong,Xu, Miaozhong. 2016

[3]An Efficient Classification Method of Fully Polarimetric SAR Image Based on Polarimetric Features and Spatial Features. Xue, Xiaorong,Xue, Xiaorong,Di, Liping,Guo, Liying,Lin, Li,Guo, Liying. 2015

[4]A rapid, low-cost deep learning system to classify strawberry disease based on cloud service. Guo feng YANG,Yong YANG,Zi kang HE,Xin yu ZHANG,Yong HE. 2022

[5]A dataset of the quality of soybean harvested by mechanization for deep-learning-based monitoring and analysis. Chen, Man,Jin, Chengqian,Ni, Youliang,Yang, Tengxiang,Xu, Jinshan. 2024

[6]GACDNet:Mapping winter wheat by generative adversarial cross-domain networks with transformer integration for zero-sample extraction. Chunyang Wang,Kai Li,Wei Yang,Xinbing Wang,Jian Wang,Zongze Zhao,Yanan Gu,Zhaozhao Xu. 2024

[7]A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage. Fubing Liao,Xiangqian Feng,Ziqiu Li,Danying Wang,Chunmei Xu,Guang Chu,Hengyu Ma,Qing Yao,Song Chen. 2024

[8]Enhancing rice phenology identification by synergistic learning canopy optical signals and plant height dynamics. Ziqiu Li,Weiyuan Hong,Xiangqian Feng,Aidong Wang,Hengyu Ma,Ruijie Li,Qing Yao,Hao Jiang,Song Chen. 2025

[9]TCSRNet: a lightweight tobacco leaf curing stage recognition network model. Panzhen Zhao,Songfeng Wang,Shijiang Duan,Aihua Wang,Lingfeng Meng,Yichong Hu. 2024

[10]The Bayesian mixture expert recognition model for tobacco leaf curing stages based on feature fusion. Panzhen Zhao,Shijiang Duan,Songfeng Wang,Aihua Wang,Lingfeng Meng,Zhicheng Wang,Yingpeng Dai. 2025

作者其他论文 更多>>