Explainable Deep Learning Study for Leaf Disease Classification

被引:30
作者
Wei, Kaihua [1 ]
Chen, Bojian [1 ]
Zhang, Jingcheng [1 ]
Fan, Shanhui [1 ]
Wu, Kaihua [1 ]
Liu, Guangyu [1 ]
Chen, Dongmei [1 ]
机构
[1] Hangzhou Dianzi Univ, Sch Automat, Hangzhou 310018, Peoples R China
来源
AGRONOMY-BASEL | 2022年 / 12卷 / 05期
基金
国家重点研发计划; 中国博士后科学基金;
关键词
deep learning; leaf disease; interpretability; attention module;
D O I
10.3390/agronomy12051035
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Explainable artificial intelligence has been extensively studied recently. However, the research of interpretable methods in the agricultural field has not been systematically studied. We studied the interpretability of deep learning models in different agricultural classification tasks based on the fruit leaves dataset. The purpose is to explore whether the classification model is more inclined to extract the appearance characteristics of leaves or the texture characteristics of leaf lesions during the feature extraction process. The dataset was arranged into three experiments with different categories. In each experiment, the VGG, GoogLeNet, and ResNet models were used and the ResNet-attention model was applied with three interpretable methods. The results show that the ResNet model has the highest accuracy rate in the three experiments, which are 99.11%, 99.4%, and 99.89%, respectively. It is also found that the attention module could improve the feature extraction of the model, and clarify the focus of the model in different experiments when extracting features. These results will help agricultural practitioners better apply deep learning models to solve more practical problems.
引用
收藏
页数:15
相关论文
共 26 条
[1]  
[Anonymous], 2015, PROC INT C LEARNING
[2]  
[Anonymous], 2014, P WORKSHOP ICLR
[3]  
[Anonymous], 2015, ARXIV151108060
[4]  
Daglarli E., 2021, Artificial Intelligence Paradigms for Smart Cyber-Physical Systems., P42
[5]   A tutorial survey of architectures, algorithms, and applications for deep learning [J].
Deng, Li .
APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2014, 3
[6]   Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to? [J].
Fernandez, Alberto ;
Herrera, Francisco ;
Cordon, Oscar ;
del Jesus, Maria Jose ;
Marcelloni, Francesco .
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2019, 14 (01) :69-81
[7]  
Gan C, 2015, PROC CVPR IEEE, P2568, DOI 10.1109/CVPR.2015.7298872
[8]   An explainable deep machine vision framework for plant stress phenotyping [J].
Ghosal, Sambuddha ;
Blystone, David ;
Singh, Asheesh K. ;
Ganapathysubramanian, Baskar ;
Singh, Arti ;
Sarkar, Soumik .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2018, 115 (18) :4613-4618
[9]   Deep learning for visual understanding: A review [J].
Guo, Yanming ;
Liu, Yu ;
Oerlemans, Ard ;
Lao, Songyang ;
Wu, Song ;
Lew, Michael S. .
NEUROCOMPUTING, 2016, 187 :27-48
[10]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778