Dictionary Learning for Few-Shot Remote Sensing Scene Classification
With deep learning-based methods growing (even with scarce data in some fields), few-shot remote sensing scene classification (FSRSSC) has received a lot of attention. One mainstream approach uses base data to train a feature extractor (FE) in the pre-training phase and employs novel data to design...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/773 |
| _version_ | 1827759587134013440 |
|---|---|
| author | Yuteng Ma Junmin Meng Baodi Liu Lina Sun Hao Zhang Peng Ren |
| author_facet | Yuteng Ma Junmin Meng Baodi Liu Lina Sun Hao Zhang Peng Ren |
| author_sort | Yuteng Ma |
| collection | DOAJ |
| description | With deep learning-based methods growing (even with scarce data in some fields), few-shot remote sensing scene classification (FSRSSC) has received a lot of attention. One mainstream approach uses base data to train a feature extractor (FE) in the pre-training phase and employs novel data to design the classifier and complete the classification task in the meta-test phase. Due to the scarcity of remote sensing data, obtaining a suitable feature extractor for remote sensing data and designing a robust classifier have become two major challenges. In this paper, we propose a novel dictionary learning (DL) algorithm for few-shot remote sensing scene classification to address these two difficulties. First, we use natural image datasets with sufficient data to obtain a pre-trained feature extractor. We fine-tune the parameters with the remote sensing dataset to make the feature extractor suitable for remote sensing data. Second, we design the kernel space classifier to map the features to a high-dimensional space and embed the label information into the dictionary learning to improve the discrimination of features for classification. Extensive experiments on four popular remote sensing scene classification datasets demonstrate the effectiveness of our proposed dictionary learning method. |
| first_indexed | 2024-03-11T09:27:47Z |
| format | Article |
| id | doaj.art-d730cec9c6b74824a8756db23de76a55 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:47Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d730cec9c6b74824a8756db23de76a552023-11-16T17:54:02ZengMDPI AGRemote Sensing2072-42922023-01-0115377310.3390/rs15030773Dictionary Learning for Few-Shot Remote Sensing Scene ClassificationYuteng Ma0Junmin Meng1Baodi Liu2Lina Sun3Hao Zhang4Peng Ren5First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, ChinaFirst Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, ChinaCollege of Control Science and Engineering, China University of Petroleum (East China), Qingdao 266580, ChinaFirst Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, ChinaFirst Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, ChinaTechnology Innovation Center for Ocean Telemetry, Ministry of Natural Resources, Qingdao 266061, ChinaWith deep learning-based methods growing (even with scarce data in some fields), few-shot remote sensing scene classification (FSRSSC) has received a lot of attention. One mainstream approach uses base data to train a feature extractor (FE) in the pre-training phase and employs novel data to design the classifier and complete the classification task in the meta-test phase. Due to the scarcity of remote sensing data, obtaining a suitable feature extractor for remote sensing data and designing a robust classifier have become two major challenges. In this paper, we propose a novel dictionary learning (DL) algorithm for few-shot remote sensing scene classification to address these two difficulties. First, we use natural image datasets with sufficient data to obtain a pre-trained feature extractor. We fine-tune the parameters with the remote sensing dataset to make the feature extractor suitable for remote sensing data. Second, we design the kernel space classifier to map the features to a high-dimensional space and embed the label information into the dictionary learning to improve the discrimination of features for classification. Extensive experiments on four popular remote sensing scene classification datasets demonstrate the effectiveness of our proposed dictionary learning method.https://www.mdpi.com/2072-4292/15/3/773remote sensing scenedictionary learningfew-shot image classification |
| spellingShingle | Yuteng Ma Junmin Meng Baodi Liu Lina Sun Hao Zhang Peng Ren Dictionary Learning for Few-Shot Remote Sensing Scene Classification Remote Sensing remote sensing scene dictionary learning few-shot image classification |
| title | Dictionary Learning for Few-Shot Remote Sensing Scene Classification |
| title_full | Dictionary Learning for Few-Shot Remote Sensing Scene Classification |
| title_fullStr | Dictionary Learning for Few-Shot Remote Sensing Scene Classification |
| title_full_unstemmed | Dictionary Learning for Few-Shot Remote Sensing Scene Classification |
| title_short | Dictionary Learning for Few-Shot Remote Sensing Scene Classification |
| title_sort | dictionary learning for few shot remote sensing scene classification |
| topic | remote sensing scene dictionary learning few-shot image classification |
| url | https://www.mdpi.com/2072-4292/15/3/773 |
| work_keys_str_mv | AT yutengma dictionarylearningforfewshotremotesensingsceneclassification AT junminmeng dictionarylearningforfewshotremotesensingsceneclassification AT baodiliu dictionarylearningforfewshotremotesensingsceneclassification AT linasun dictionarylearningforfewshotremotesensingsceneclassification AT haozhang dictionarylearningforfewshotremotesensingsceneclassification AT pengren dictionarylearningforfewshotremotesensingsceneclassification |