Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing
Remote Sensing Scene Classification (RSSC) is the discrete categorization of remote sensing images into various classes of scene categories based on their image content. RSSC plays an important role in many fields, such as agriculture, land mapping, and identification of disaster-prone areas. Theref...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2024-06-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | https://jurnal.iaii.or.id/index.php/RESTI/article/view/5731 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850119269097930752 |
|---|---|
| author | Rachmawan Atmaji Perdana Aniati Murni Arimurthy Risnandar |
| author_facet | Rachmawan Atmaji Perdana Aniati Murni Arimurthy Risnandar |
| author_sort | Rachmawan Atmaji Perdana |
| collection | DOAJ |
| description | Remote Sensing Scene Classification (RSSC) is the discrete categorization of remote sensing images into various classes of scene categories based on their image content. RSSC plays an important role in many fields, such as agriculture, land mapping, and identification of disaster-prone areas. Therefore, a reliable and accurate RSSC algorithm is required to ensure the accuracy of land identification. Many existing studies in recent years have used deep learning methods, especially CNN combined with attention modules to solve this problem. This study focuses on solving the RSSC problem by proposing a deep learning-based method (CNN) with the ConvNeXt-Tiny model integrated with Efficient Channel Attention Module (ECANet) and label smoothing regularization (LSR). The ConvNeXt-Tiny model shows that a persistent superior outperforms the ‘large’ model in convinced metrics. The ConvNeXt-Tiny model also has a huge advantage in high-precision positioning and higher classification accuracy and localization precision in a variety of complicated scenarios of remote sensing scene recognition. The experiments in this study also aim to prove that the integration of the attention module and LSR into the basic CNN network can improve precision, because the attention module can strengthen important features and weaken features that are less useful for classification. The experimental results proved that the integration of ECANet and LSR in the ConvNeXt-Tiny base network obtained a higher precision of 0.38% in the UC-Merced dataset, 0.7% in the AID, and 0.4% in the WHU-RS19 dataset than the ConvNeXt-Tiny model without ECANet and LSR. The ConvNeXt-Tiny model with ECANet integration and LSR obtained an accuracy of 99.00±0.41% in the UC-Merced dataset, 95.08±0.20% in AID, and 99.50±0.31% in the WHU-RS19 dataset. |
| format | Article |
| id | doaj-art-b9cc5accf9774ea3a7d8d87b595059c5 |
| institution | OA Journals |
| issn | 2580-0760 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj-art-b9cc5accf9774ea3a7d8d87b595059c52025-08-20T02:35:40ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602024-06-018338940010.29207/resti.v8i3.57315731Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label SmoothingRachmawan Atmaji Perdana0Aniati Murni Arimurthy1Risnandar2Badan Riset dan Inovasi NasionalUniversitas IndonesiaBadan Riset dan Inovasi NasionalRemote Sensing Scene Classification (RSSC) is the discrete categorization of remote sensing images into various classes of scene categories based on their image content. RSSC plays an important role in many fields, such as agriculture, land mapping, and identification of disaster-prone areas. Therefore, a reliable and accurate RSSC algorithm is required to ensure the accuracy of land identification. Many existing studies in recent years have used deep learning methods, especially CNN combined with attention modules to solve this problem. This study focuses on solving the RSSC problem by proposing a deep learning-based method (CNN) with the ConvNeXt-Tiny model integrated with Efficient Channel Attention Module (ECANet) and label smoothing regularization (LSR). The ConvNeXt-Tiny model shows that a persistent superior outperforms the ‘large’ model in convinced metrics. The ConvNeXt-Tiny model also has a huge advantage in high-precision positioning and higher classification accuracy and localization precision in a variety of complicated scenarios of remote sensing scene recognition. The experiments in this study also aim to prove that the integration of the attention module and LSR into the basic CNN network can improve precision, because the attention module can strengthen important features and weaken features that are less useful for classification. The experimental results proved that the integration of ECANet and LSR in the ConvNeXt-Tiny base network obtained a higher precision of 0.38% in the UC-Merced dataset, 0.7% in the AID, and 0.4% in the WHU-RS19 dataset than the ConvNeXt-Tiny model without ECANet and LSR. The ConvNeXt-Tiny model with ECANet integration and LSR obtained an accuracy of 99.00±0.41% in the UC-Merced dataset, 95.08±0.20% in AID, and 99.50±0.31% in the WHU-RS19 dataset.https://jurnal.iaii.or.id/index.php/RESTI/article/view/5731attention mechanismdeep learningcnnconvnext-tinylabel smooth regularization |
| spellingShingle | Rachmawan Atmaji Perdana Aniati Murni Arimurthy Risnandar Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) attention mechanism deep learning cnn convnext-tiny label smooth regularization |
| title | Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing |
| title_full | Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing |
| title_fullStr | Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing |
| title_full_unstemmed | Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing |
| title_short | Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing |
| title_sort | remote sensing scene classification using convnext tiny model with attention mechanism and label smoothing |
| topic | attention mechanism deep learning cnn convnext-tiny label smooth regularization |
| url | https://jurnal.iaii.or.id/index.php/RESTI/article/view/5731 |
| work_keys_str_mv | AT rachmawanatmajiperdana remotesensingsceneclassificationusingconvnexttinymodelwithattentionmechanismandlabelsmoothing AT aniatimurniarimurthy remotesensingsceneclassificationusingconvnexttinymodelwithattentionmechanismandlabelsmoothing AT risnandar remotesensingsceneclassificationusingconvnexttinymodelwithattentionmechanismandlabelsmoothing |