Explainable Deep Learning Study for Leaf Disease Classification
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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/5/1035 |
| _version_ | 1797502253128482816 |
|---|---|
| author | Kaihua Wei Bojian Chen Jingcheng Zhang Shanhui Fan Kaihua Wu Guangyu Liu Dongmei Chen |
| author_facet | Kaihua Wei Bojian Chen Jingcheng Zhang Shanhui Fan Kaihua Wu Guangyu Liu Dongmei Chen |
| author_sort | Kaihua Wei |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T03:30:19Z |
| format | Article |
| id | doaj.art-7fb4212fadaa4dbfbca58337d8621f4c |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T03:30:19Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-7fb4212fadaa4dbfbca58337d8621f4c2023-11-23T09:41:51ZengMDPI AGAgronomy2073-43952022-04-01125103510.3390/agronomy12051035Explainable Deep Learning Study for Leaf Disease ClassificationKaihua Wei0Bojian Chen1Jingcheng Zhang2Shanhui Fan3Kaihua Wu4Guangyu Liu5Dongmei Chen6School of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaExplainable 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.https://www.mdpi.com/2073-4395/12/5/1035deep learningleaf diseaseinterpretabilityattention module |
| spellingShingle | Kaihua Wei Bojian Chen Jingcheng Zhang Shanhui Fan Kaihua Wu Guangyu Liu Dongmei Chen Explainable Deep Learning Study for Leaf Disease Classification Agronomy deep learning leaf disease interpretability attention module |
| title | Explainable Deep Learning Study for Leaf Disease Classification |
| title_full | Explainable Deep Learning Study for Leaf Disease Classification |
| title_fullStr | Explainable Deep Learning Study for Leaf Disease Classification |
| title_full_unstemmed | Explainable Deep Learning Study for Leaf Disease Classification |
| title_short | Explainable Deep Learning Study for Leaf Disease Classification |
| title_sort | explainable deep learning study for leaf disease classification |
| topic | deep learning leaf disease interpretability attention module |
| url | https://www.mdpi.com/2073-4395/12/5/1035 |
| work_keys_str_mv | AT kaihuawei explainabledeeplearningstudyforleafdiseaseclassification AT bojianchen explainabledeeplearningstudyforleafdiseaseclassification AT jingchengzhang explainabledeeplearningstudyforleafdiseaseclassification AT shanhuifan explainabledeeplearningstudyforleafdiseaseclassification AT kaihuawu explainabledeeplearningstudyforleafdiseaseclassification AT guangyuliu explainabledeeplearningstudyforleafdiseaseclassification AT dongmeichen explainabledeeplearningstudyforleafdiseaseclassification |