Benchmarking Domain Adaptation Methods on Aerial Datasets
Deep learning grew in importance in recent years due to its versatility and excellent performance on supervised classification tasks. A core assumption for such supervised approaches is that the training and testing data are drawn from the same underlying data distribution. This may not always be th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/8070 |
| _version_ | 1797507164046098432 |
|---|---|
| author | Navya Nagananda Abu Md Niamul Taufique Raaga Madappa Chowdhury Sadman Jahan Breton Minnehan Todd Rovito Andreas Savakis |
| author_facet | Navya Nagananda Abu Md Niamul Taufique Raaga Madappa Chowdhury Sadman Jahan Breton Minnehan Todd Rovito Andreas Savakis |
| author_sort | Navya Nagananda |
| collection | DOAJ |
| description | Deep learning grew in importance in recent years due to its versatility and excellent performance on supervised classification tasks. A core assumption for such supervised approaches is that the training and testing data are drawn from the same underlying data distribution. This may not always be the case, and in such cases, the performance of the model is degraded. Domain adaptation aims to overcome the domain shift between the source domain used for training and the target domain data used for testing. Unsupervised domain adaptation deals with situations where the network is trained on labeled data from the source domain and unlabeled data from the target domain with the goal of performing well on the target domain data at the time of deployment. In this study, we overview seven state-of-the-art unsupervised domain adaptation models based on deep learning and benchmark their performance on three new domain adaptation datasets created from publicly available aerial datasets. We believe this is the first study on benchmarking domain adaptation methods for aerial data. In addition to reporting classification performance for the different domain adaptation models, we present t-SNE visualizations that illustrate the benefits of the adaptation process. |
| first_indexed | 2024-03-10T04:44:44Z |
| format | Article |
| id | doaj.art-b29666a701c84c0fa8eb796715e60213 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:44:44Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b29666a701c84c0fa8eb796715e602132023-11-23T03:03:30ZengMDPI AGSensors1424-82202021-12-012123807010.3390/s21238070Benchmarking Domain Adaptation Methods on Aerial DatasetsNavya Nagananda0Abu Md Niamul Taufique1Raaga Madappa2Chowdhury Sadman Jahan3Breton Minnehan4Todd Rovito5Andreas Savakis6Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USADepartment of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USADepartment of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USADepartment of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USAAir Force Research Laboratory, Wright-Patterson Air Force Base, OH 45433, USAAir Force Research Laboratory, Wright-Patterson Air Force Base, OH 45433, USADepartment of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USADeep learning grew in importance in recent years due to its versatility and excellent performance on supervised classification tasks. A core assumption for such supervised approaches is that the training and testing data are drawn from the same underlying data distribution. This may not always be the case, and in such cases, the performance of the model is degraded. Domain adaptation aims to overcome the domain shift between the source domain used for training and the target domain data used for testing. Unsupervised domain adaptation deals with situations where the network is trained on labeled data from the source domain and unlabeled data from the target domain with the goal of performing well on the target domain data at the time of deployment. In this study, we overview seven state-of-the-art unsupervised domain adaptation models based on deep learning and benchmark their performance on three new domain adaptation datasets created from publicly available aerial datasets. We believe this is the first study on benchmarking domain adaptation methods for aerial data. In addition to reporting classification performance for the different domain adaptation models, we present t-SNE visualizations that illustrate the benefits of the adaptation process.https://www.mdpi.com/1424-8220/21/23/8070domain adaptationaerial datasetsunsupervised learningvisualizationdeep neural networks |
| spellingShingle | Navya Nagananda Abu Md Niamul Taufique Raaga Madappa Chowdhury Sadman Jahan Breton Minnehan Todd Rovito Andreas Savakis Benchmarking Domain Adaptation Methods on Aerial Datasets Sensors domain adaptation aerial datasets unsupervised learning visualization deep neural networks |
| title | Benchmarking Domain Adaptation Methods on Aerial Datasets |
| title_full | Benchmarking Domain Adaptation Methods on Aerial Datasets |
| title_fullStr | Benchmarking Domain Adaptation Methods on Aerial Datasets |
| title_full_unstemmed | Benchmarking Domain Adaptation Methods on Aerial Datasets |
| title_short | Benchmarking Domain Adaptation Methods on Aerial Datasets |
| title_sort | benchmarking domain adaptation methods on aerial datasets |
| topic | domain adaptation aerial datasets unsupervised learning visualization deep neural networks |
| url | https://www.mdpi.com/1424-8220/21/23/8070 |
| work_keys_str_mv | AT navyanagananda benchmarkingdomainadaptationmethodsonaerialdatasets AT abumdniamultaufique benchmarkingdomainadaptationmethodsonaerialdatasets AT raagamadappa benchmarkingdomainadaptationmethodsonaerialdatasets AT chowdhurysadmanjahan benchmarkingdomainadaptationmethodsonaerialdatasets AT bretonminnehan benchmarkingdomainadaptationmethodsonaerialdatasets AT toddrovito benchmarkingdomainadaptationmethodsonaerialdatasets AT andreassavakis benchmarkingdomainadaptationmethodsonaerialdatasets |