Sparse Focus Network for Multi-Source Remote Sensing Data Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911900599582720 |
|---|---|
| author | Jin, Xuepeng Lin, Junyan Gao, Feng Qi, Lin Zhou, Yang |
| author_facet | Jin, Xuepeng Lin, Junyan Gao, Feng Qi, Lin Zhou, Yang |
| contents | Multi-source remote sensing data classification has emerged as a prominent research topic with the advancement of various sensors. Existing multi-source data classification methods are susceptible to irrelevant information interference during multi-source feature extraction and fusion. To solve this issue, we propose a sparse focus network for multi-source data classification. Sparse attention is employed in Transformer block for HSI and SAR/LiDAR feature extraction, thereby the most useful self-attention values are maintained for better feature aggregation. Furthermore, cross-attention is used to enhance multi-source feature interactions, and further improves the efficiency of cross-modal feature fusion. Experimental results on the Berlin and Houston2018 datasets highlight the effectiveness of SF-Net, outperforming existing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01245 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sparse Focus Network for Multi-Source Remote Sensing Data Classification Jin, Xuepeng Lin, Junyan Gao, Feng Qi, Lin Zhou, Yang Image and Video Processing Multi-source remote sensing data classification has emerged as a prominent research topic with the advancement of various sensors. Existing multi-source data classification methods are susceptible to irrelevant information interference during multi-source feature extraction and fusion. To solve this issue, we propose a sparse focus network for multi-source data classification. Sparse attention is employed in Transformer block for HSI and SAR/LiDAR feature extraction, thereby the most useful self-attention values are maintained for better feature aggregation. Furthermore, cross-attention is used to enhance multi-source feature interactions, and further improves the efficiency of cross-modal feature fusion. Experimental results on the Berlin and Houston2018 datasets highlight the effectiveness of SF-Net, outperforming existing state-of-the-art methods. |
| title | Sparse Focus Network for Multi-Source Remote Sensing Data Classification |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2406.01245 |