Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images
Ship classification using the synthetic aperture radar (SAR) images has a significant role in remote sensing applications. Aiming at the problems of excessive model parameters numbers and high energy consumption in the traditional deep learning methods for the SAR ship classification, this paper pro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/20/4966 |
| _version_ | 1827719919275343872 |
|---|---|
| author | Xinqiao Jiang Hongtu Xie Zheng Lu Jun Hu |
| author_facet | Xinqiao Jiang Hongtu Xie Zheng Lu Jun Hu |
| author_sort | Xinqiao Jiang |
| collection | DOAJ |
| description | Ship classification using the synthetic aperture radar (SAR) images has a significant role in remote sensing applications. Aiming at the problems of excessive model parameters numbers and high energy consumption in the traditional deep learning methods for the SAR ship classification, this paper provides an energy-efficient SAR ship classification paradigm that combines spiking neural networks (SNNs) with Siamese network architecture, for the first time in the field of SAR ship classification, which is called the Siam-SpikingShipCLSNet. It combines the advantage of SNNs in energy consumption and the advantage of the idea in performances that use the Siamese neuron network to fuse the features from dual-polarized SAR images. Additionally, we migrated the feature fusion strategy from CNN-based Siamese neural networks to the SNN domain and analyzed the effects of various spiking feature fusion methods on the Siamese SNN. Finally, an end-to-end error backpropagation optimization method based on the surrogate gradient has been adopted to train this model. Experimental results tested on the OpenSARShip2.0 dataset have demonstrated the correctness and effectiveness of the proposed SAR ship classification strategy, which has the advantages of the higher accuracy, fewer parameters and lower energy consumption compared with the mainstream deep learning method of the SAR ship classification. |
| first_indexed | 2024-03-10T20:55:23Z |
| format | Article |
| id | doaj.art-2035881acfd84d8583b8f713488dde8d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T20:55:23Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2035881acfd84d8583b8f713488dde8d2023-11-19T17:58:56ZengMDPI AGRemote Sensing2072-42922023-10-011520496610.3390/rs15204966Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR ImagesXinqiao Jiang0Hongtu Xie1Zheng Lu2Jun Hu3School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518107, ChinaSchool of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518107, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology, Beijing 100094, ChinaSchool of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518107, ChinaShip classification using the synthetic aperture radar (SAR) images has a significant role in remote sensing applications. Aiming at the problems of excessive model parameters numbers and high energy consumption in the traditional deep learning methods for the SAR ship classification, this paper provides an energy-efficient SAR ship classification paradigm that combines spiking neural networks (SNNs) with Siamese network architecture, for the first time in the field of SAR ship classification, which is called the Siam-SpikingShipCLSNet. It combines the advantage of SNNs in energy consumption and the advantage of the idea in performances that use the Siamese neuron network to fuse the features from dual-polarized SAR images. Additionally, we migrated the feature fusion strategy from CNN-based Siamese neural networks to the SNN domain and analyzed the effects of various spiking feature fusion methods on the Siamese SNN. Finally, an end-to-end error backpropagation optimization method based on the surrogate gradient has been adopted to train this model. Experimental results tested on the OpenSARShip2.0 dataset have demonstrated the correctness and effectiveness of the proposed SAR ship classification strategy, which has the advantages of the higher accuracy, fewer parameters and lower energy consumption compared with the mainstream deep learning method of the SAR ship classification.https://www.mdpi.com/2072-4292/15/20/4966synthetic aperture radar (SAR)energy-efficient and high-performanceSAR ship classificationSiamese spiking neural network (SNN)dual-polarized SAR ship images |
| spellingShingle | Xinqiao Jiang Hongtu Xie Zheng Lu Jun Hu Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images Remote Sensing synthetic aperture radar (SAR) energy-efficient and high-performance SAR ship classification Siamese spiking neural network (SNN) dual-polarized SAR ship images |
| title | Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images |
| title_full | Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images |
| title_fullStr | Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images |
| title_full_unstemmed | Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images |
| title_short | Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images |
| title_sort | energy efficient and high performance ship classification strategy based on siamese spiking neural network in dual polarized sar images |
| topic | synthetic aperture radar (SAR) energy-efficient and high-performance SAR ship classification Siamese spiking neural network (SNN) dual-polarized SAR ship images |
| url | https://www.mdpi.com/2072-4292/15/20/4966 |
| work_keys_str_mv | AT xinqiaojiang energyefficientandhighperformanceshipclassificationstrategybasedonsiamesespikingneuralnetworkindualpolarizedsarimages AT hongtuxie energyefficientandhighperformanceshipclassificationstrategybasedonsiamesespikingneuralnetworkindualpolarizedsarimages AT zhenglu energyefficientandhighperformanceshipclassificationstrategybasedonsiamesespikingneuralnetworkindualpolarizedsarimages AT junhu energyefficientandhighperformanceshipclassificationstrategybasedonsiamesespikingneuralnetworkindualpolarizedsarimages |