Relating CNN-Transformer Fusion Network for Change Detection
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_ | 1866910511754379264 |
|---|---|
| author | Gao, Yuhao Pei, Gensheng Sheng, Mengmeng Sun, Zeren Chen, Tao Yao, Yazhou |
| author_facet | Gao, Yuhao Pei, Gensheng Sheng, Mengmeng Sun, Zeren Chen, Tao Yao, Yazhou |
| contents | While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change learning. Additionally, transformer networks struggle with low-level details. RCTNet addresses these limitations by introducing \textbf{(1)} an early fusion backbone to exploit both spatial and temporal features early on, \textbf{(2)} a Cross-Stage Aggregation (CSA) module for enhanced temporal representation, \textbf{(3)} a Multi-Scale Feature Fusion (MSF) module for enriched feature extraction in the decoder, and \textbf{(4)} an Efficient Self-deciphering Attention (ESA) module utilizing transformers to capture global information and fine-grained details for accurate change detection. Extensive experiments demonstrate RCTNet's clear superiority over traditional RS image CD methods, showing significant improvement and an optimal balance between accuracy and computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03178 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Relating CNN-Transformer Fusion Network for Change Detection Gao, Yuhao Pei, Gensheng Sheng, Mengmeng Sun, Zeren Chen, Tao Yao, Yazhou Multimedia Computer Vision and Pattern Recognition Machine Learning While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change learning. Additionally, transformer networks struggle with low-level details. RCTNet addresses these limitations by introducing \textbf{(1)} an early fusion backbone to exploit both spatial and temporal features early on, \textbf{(2)} a Cross-Stage Aggregation (CSA) module for enhanced temporal representation, \textbf{(3)} a Multi-Scale Feature Fusion (MSF) module for enriched feature extraction in the decoder, and \textbf{(4)} an Efficient Self-deciphering Attention (ESA) module utilizing transformers to capture global information and fine-grained details for accurate change detection. Extensive experiments demonstrate RCTNet's clear superiority over traditional RS image CD methods, showing significant improvement and an optimal balance between accuracy and computational cost. |
| title | Relating CNN-Transformer Fusion Network for Change Detection |
| topic | Multimedia Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.03178 |