Example-based explainable AI and its application for remote sensing image classification
We present a method of explainable artificial intelligence (XAI), “What I Know (WIK)”, to provide additional information to verify the reliability of a deep learning model by showing an example of an instance in a training dataset that is similar to the input data to be inferred and demonstrate it i...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223000377 |
| _version_ | 1797842822267666432 |
|---|---|
| author | Shin-nosuke Ishikawa Masato Todo Masato Taki Yasunobu Uchiyama Kazunari Matsunaga Peihsuan Lin Taiki Ogihara Masao Yasui |
| author_facet | Shin-nosuke Ishikawa Masato Todo Masato Taki Yasunobu Uchiyama Kazunari Matsunaga Peihsuan Lin Taiki Ogihara Masao Yasui |
| author_sort | Shin-nosuke Ishikawa |
| collection | DOAJ |
| description | We present a method of explainable artificial intelligence (XAI), “What I Know (WIK)”, to provide additional information to verify the reliability of a deep learning model by showing an example of an instance in a training dataset that is similar to the input data to be inferred and demonstrate it in a remote sensing image classification task. One of the expected roles of XAI methods is verifying whether inferences of a trained machine learning model are valid for an application, and it is an important factor that what datasets are used for training the model as well as the model architecture. Our data-centric approach can help determine whether the training dataset is sufficient for each inference by checking the selected example data. If the selected example looks similar to the input data, we can confirm that the model was not trained on a dataset with a feature distribution far from the feature of the input data. With this method, the criteria for selecting an example are not merely data similarity with the input data but also data similarity in the context of the model task. Using a remote sensing image dataset from the Sentinel-2 satellite, the concept was successfully demonstrated with reasonably selected examples. This method can be applied to various machine-learning tasks, including classification and regression. |
| first_indexed | 2024-04-09T16:54:29Z |
| format | Article |
| id | doaj.art-1cbd639d34184560af5d3b5421b0b10e |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-09T16:54:29Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-1cbd639d34184560af5d3b5421b0b10e2023-04-21T06:41:02ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-04-01118103215Example-based explainable AI and its application for remote sensing image classificationShin-nosuke Ishikawa0Masato Todo1Masato Taki2Yasunobu Uchiyama3Kazunari Matsunaga4Peihsuan Lin5Taiki Ogihara6Masao Yasui7Graduate School of Artificial Intelligence and Science, Rikkyo University, Tokyo 171-8501, Japan; Strategic Digital Business Unit, Mamezou Co., Ltd., Tokyo 163-0434, Japan; Corresponding author at: Graduate School of Artificial Intelligence and Science, Rikkyo University, Tokyo 171-8501, Japan.Strategic Digital Business Unit, Mamezou Co., Ltd., Tokyo 163-0434, JapanGraduate School of Artificial Intelligence and Science, Rikkyo University, Tokyo 171-8501, JapanGraduate School of Artificial Intelligence and Science, Rikkyo University, Tokyo 171-8501, JapanStrategic Digital Business Unit, Mamezou Co., Ltd., Tokyo 163-0434, JapanStrategic Digital Business Unit, Mamezou Co., Ltd., Tokyo 163-0434, JapanStrategic Digital Business Unit, Mamezou Co., Ltd., Tokyo 163-0434, JapanMamezou Co., Ltd., Tokyo 163-0434, JapanWe present a method of explainable artificial intelligence (XAI), “What I Know (WIK)”, to provide additional information to verify the reliability of a deep learning model by showing an example of an instance in a training dataset that is similar to the input data to be inferred and demonstrate it in a remote sensing image classification task. One of the expected roles of XAI methods is verifying whether inferences of a trained machine learning model are valid for an application, and it is an important factor that what datasets are used for training the model as well as the model architecture. Our data-centric approach can help determine whether the training dataset is sufficient for each inference by checking the selected example data. If the selected example looks similar to the input data, we can confirm that the model was not trained on a dataset with a feature distribution far from the feature of the input data. With this method, the criteria for selecting an example are not merely data similarity with the input data but also data similarity in the context of the model task. Using a remote sensing image dataset from the Sentinel-2 satellite, the concept was successfully demonstrated with reasonably selected examples. This method can be applied to various machine-learning tasks, including classification and regression.http://www.sciencedirect.com/science/article/pii/S1569843223000377Machine learningDeep learningExplainable artificial intelligenceRemote sensing imagery |
| spellingShingle | Shin-nosuke Ishikawa Masato Todo Masato Taki Yasunobu Uchiyama Kazunari Matsunaga Peihsuan Lin Taiki Ogihara Masao Yasui Example-based explainable AI and its application for remote sensing image classification International Journal of Applied Earth Observations and Geoinformation Machine learning Deep learning Explainable artificial intelligence Remote sensing imagery |
| title | Example-based explainable AI and its application for remote sensing image classification |
| title_full | Example-based explainable AI and its application for remote sensing image classification |
| title_fullStr | Example-based explainable AI and its application for remote sensing image classification |
| title_full_unstemmed | Example-based explainable AI and its application for remote sensing image classification |
| title_short | Example-based explainable AI and its application for remote sensing image classification |
| title_sort | example based explainable ai and its application for remote sensing image classification |
| topic | Machine learning Deep learning Explainable artificial intelligence Remote sensing imagery |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223000377 |
| work_keys_str_mv | AT shinnosukeishikawa examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT masatotodo examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT masatotaki examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT yasunobuuchiyama examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT kazunarimatsunaga examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT peihsuanlin examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT taikiogihara examplebasedexplainableaianditsapplicationforremotesensingimageclassification AT masaoyasui examplebasedexplainableaianditsapplicationforremotesensingimageclassification |