Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification
Remote sensing image scene classification (RSISC), which aims to classify scene categories for remote sensing imagery, has broad applications in various fields. Recent deep learning (DL) successes have led to a new wave of RSISC applications; however, they lack explainability and trustworthiness. He...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/16/3943 |
| _version_ | 1797408108363907072 |
|---|---|
| author | Jiangfan Feng Dini Wang Zhujun Gu |
| author_facet | Jiangfan Feng Dini Wang Zhujun Gu |
| author_sort | Jiangfan Feng |
| collection | DOAJ |
| description | Remote sensing image scene classification (RSISC), which aims to classify scene categories for remote sensing imagery, has broad applications in various fields. Recent deep learning (DL) successes have led to a new wave of RSISC applications; however, they lack explainability and trustworthiness. Here, we propose a bidirectional flow decision tree (BFDT) module to create a reliable RS scene classification framework. Our algorithm combines BFDT and Convolutional Neural Networks (CNNs) to make the decision process easily interpretable. First, we extract multilevel feature information from the pretrained CNN model, which provides the basis for constructing the subsequent hierarchical structure. Then the model uses the discriminative nature of scene features at different levels to gradually refine similar subsets and learn the interclass hierarchy. Meanwhile, the last fully connected layer embeds decision rules for the decision tree from the bottom up. Finally, the cascading softmax loss is used to train and learn the depth features based on the hierarchical structure formed by the tree structure that contains rich remote sensing information. We also discovered that superclass results can be obtained well for unseen classes due to its unique tree structure hierarchical property, which results in our model having a good generalization effect. The experimental results align with theoretical predictions using three popular datasets. Our proposed framework provides explainable results, leading to correctable and trustworthy approaches. |
| first_indexed | 2024-03-09T03:53:36Z |
| format | Article |
| id | doaj.art-8b9e00c11ae74afdb0bb7766bd43c7ab |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T03:53:36Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8b9e00c11ae74afdb0bb7766bd43c7ab2023-12-03T14:24:17ZengMDPI AGRemote Sensing2072-42922022-08-011416394310.3390/rs14163943Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene ClassificationJiangfan Feng0Dini Wang1Zhujun Gu2School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSchool of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaPearl River Water Resources Research Institute, Pearl River Water Resources Commission, Guangzhou 510610, ChinaRemote sensing image scene classification (RSISC), which aims to classify scene categories for remote sensing imagery, has broad applications in various fields. Recent deep learning (DL) successes have led to a new wave of RSISC applications; however, they lack explainability and trustworthiness. Here, we propose a bidirectional flow decision tree (BFDT) module to create a reliable RS scene classification framework. Our algorithm combines BFDT and Convolutional Neural Networks (CNNs) to make the decision process easily interpretable. First, we extract multilevel feature information from the pretrained CNN model, which provides the basis for constructing the subsequent hierarchical structure. Then the model uses the discriminative nature of scene features at different levels to gradually refine similar subsets and learn the interclass hierarchy. Meanwhile, the last fully connected layer embeds decision rules for the decision tree from the bottom up. Finally, the cascading softmax loss is used to train and learn the depth features based on the hierarchical structure formed by the tree structure that contains rich remote sensing information. We also discovered that superclass results can be obtained well for unseen classes due to its unique tree structure hierarchical property, which results in our model having a good generalization effect. The experimental results align with theoretical predictions using three popular datasets. Our proposed framework provides explainable results, leading to correctable and trustworthy approaches.https://www.mdpi.com/2072-4292/14/16/3943explainable artificial intelligence (XAI)scene classificationdecision treecascaded softmaxremote sensing big data |
| spellingShingle | Jiangfan Feng Dini Wang Zhujun Gu Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification Remote Sensing explainable artificial intelligence (XAI) scene classification decision tree cascaded softmax remote sensing big data |
| title | Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification |
| title_full | Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification |
| title_fullStr | Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification |
| title_full_unstemmed | Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification |
| title_short | Bidirectional Flow Decision Tree for Reliable Remote Sensing Image Scene Classification |
| title_sort | bidirectional flow decision tree for reliable remote sensing image scene classification |
| topic | explainable artificial intelligence (XAI) scene classification decision tree cascaded softmax remote sensing big data |
| url | https://www.mdpi.com/2072-4292/14/16/3943 |
| work_keys_str_mv | AT jiangfanfeng bidirectionalflowdecisiontreeforreliableremotesensingimagesceneclassification AT diniwang bidirectionalflowdecisiontreeforreliableremotesensingimagesceneclassification AT zhujungu bidirectionalflowdecisiontreeforreliableremotesensingimagesceneclassification |