Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification
Recently, hyperspectral image (HSI) classification has become a popular research direction in remote sensing. The emergence of convolutional neural networks (CNNs) has greatly promoted the development of this field and demonstrated excellent classification performance. However, due to the particular...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/16/3305 |
| _version_ | 1797522160255762432 |
|---|---|
| author | Zixian Ge Guo Cao Hao Shi Youqiang Zhang Xuesong Li Peng Fu |
| author_facet | Zixian Ge Guo Cao Hao Shi Youqiang Zhang Xuesong Li Peng Fu |
| author_sort | Zixian Ge |
| collection | DOAJ |
| description | Recently, hyperspectral image (HSI) classification has become a popular research direction in remote sensing. The emergence of convolutional neural networks (CNNs) has greatly promoted the development of this field and demonstrated excellent classification performance. However, due to the particularity of HSIs, redundant information and limited samples pose huge challenges for extracting strong discriminative features. In addition, addressing how to fully mine the internal correlation of the data or features based on the existing model is also crucial in improving classification performance. To overcome the above limitations, this work presents a strong feature extraction neural network with an attention mechanism. Firstly, the original HSI is weighted by means of the hybrid spectral–spatial attention mechanism. Then, the data are input into a spectral feature extraction branch and a spatial feature extraction branch, composed of multiscale feature extraction modules and weak dense feature extraction modules, to extract high-level semantic features. These two features are compressed and fused using the global average pooling and concat approaches. Finally, the classification results are obtained by using two fully connected layers and one Softmax layer. A performance comparison shows the enhanced classification performance of the proposed model compared to the current state of the art on three public datasets. |
| first_indexed | 2024-03-10T08:25:33Z |
| format | Article |
| id | doaj.art-918ac6eb23aa4e36aa1aab25ea0cff96 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:25:33Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-918ac6eb23aa4e36aa1aab25ea0cff962023-11-22T09:35:30ZengMDPI AGRemote Sensing2072-42922021-08-011316330510.3390/rs13163305Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image ClassificationZixian Ge0Guo Cao1Hao Shi2Youqiang Zhang3Xuesong Li4Peng Fu5School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaJiangsu Key Laboratory of Broadband Wireless Communication and Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaRecently, hyperspectral image (HSI) classification has become a popular research direction in remote sensing. The emergence of convolutional neural networks (CNNs) has greatly promoted the development of this field and demonstrated excellent classification performance. However, due to the particularity of HSIs, redundant information and limited samples pose huge challenges for extracting strong discriminative features. In addition, addressing how to fully mine the internal correlation of the data or features based on the existing model is also crucial in improving classification performance. To overcome the above limitations, this work presents a strong feature extraction neural network with an attention mechanism. Firstly, the original HSI is weighted by means of the hybrid spectral–spatial attention mechanism. Then, the data are input into a spectral feature extraction branch and a spatial feature extraction branch, composed of multiscale feature extraction modules and weak dense feature extraction modules, to extract high-level semantic features. These two features are compressed and fused using the global average pooling and concat approaches. Finally, the classification results are obtained by using two fully connected layers and one Softmax layer. A performance comparison shows the enhanced classification performance of the proposed model compared to the current state of the art on three public datasets.https://www.mdpi.com/2072-4292/13/16/3305hyperspectral image classificationdeep learningattention mechanismmultiscale feature extractionfeature fusionskip connection |
| spellingShingle | Zixian Ge Guo Cao Hao Shi Youqiang Zhang Xuesong Li Peng Fu Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification Remote Sensing hyperspectral image classification deep learning attention mechanism multiscale feature extraction feature fusion skip connection |
| title | Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification |
| title_full | Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification |
| title_fullStr | Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification |
| title_full_unstemmed | Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification |
| title_short | Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification |
| title_sort | compound multiscale weak dense network with hybrid attention for hyperspectral image classification |
| topic | hyperspectral image classification deep learning attention mechanism multiscale feature extraction feature fusion skip connection |
| url | https://www.mdpi.com/2072-4292/13/16/3305 |
| work_keys_str_mv | AT zixiange compoundmultiscaleweakdensenetworkwithhybridattentionforhyperspectralimageclassification AT guocao compoundmultiscaleweakdensenetworkwithhybridattentionforhyperspectralimageclassification AT haoshi compoundmultiscaleweakdensenetworkwithhybridattentionforhyperspectralimageclassification AT youqiangzhang compoundmultiscaleweakdensenetworkwithhybridattentionforhyperspectralimageclassification AT xuesongli compoundmultiscaleweakdensenetworkwithhybridattentionforhyperspectralimageclassification AT pengfu compoundmultiscaleweakdensenetworkwithhybridattentionforhyperspectralimageclassification |