Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images
Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper pro...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/14/3317 |
| _version_ | 1797416118548168704 |
|---|---|
| author | Qinglin Li Guoping Qiu |
| author_facet | Qinglin Li Guoping Qiu |
| author_sort | Qinglin Li |
| collection | DOAJ |
| description | Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the state-of-the-art image clustering models, achieving accuracy performance gains ranging from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.1</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>15.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote sensing images. |
| first_indexed | 2024-03-09T05:58:56Z |
| format | Article |
| id | doaj.art-20491debfedc4f39a8b8b1af5987d399 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:58:56Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-20491debfedc4f39a8b8b1af5987d3992023-12-03T12:10:31ZengMDPI AGRemote Sensing2072-42922022-07-011414331710.3390/rs14143317Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing ImagesQinglin Li0Guoping Qiu1College of Electronic and Information Engineering, Shenzhen University, Shenzhen 518052, ChinaCollege of Electronic and Information Engineering, Shenzhen University, Shenzhen 518052, ChinaImage clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the state-of-the-art image clustering models, achieving accuracy performance gains ranging from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.1</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>15.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote sensing images.https://www.mdpi.com/2072-4292/14/14/3317clusteringsample rankingremote sensing imagesmajority voting |
| spellingShingle | Qinglin Li Guoping Qiu Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images Remote Sensing clustering sample ranking remote sensing images majority voting |
| title | Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images |
| title_full | Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images |
| title_fullStr | Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images |
| title_full_unstemmed | Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images |
| title_short | Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images |
| title_sort | improving image clustering through sample ranking and its application to remote sensing images |
| topic | clustering sample ranking remote sensing images majority voting |
| url | https://www.mdpi.com/2072-4292/14/14/3317 |
| work_keys_str_mv | AT qinglinli improvingimageclusteringthroughsamplerankinganditsapplicationtoremotesensingimages AT guopingqiu improvingimageclusteringthroughsamplerankinganditsapplicationtoremotesensingimages |