FTA-Net: Frequency-Temporal-Aware Network for Remote Sensing Change Detection
Change detection (CD) aims to explore surface changes in coaligned image pairs. However, many existing networks primarily focus on learning deep features, without considering the impact of attention and fusion strategies on detection performance. Therefore, a new frequency-temporal-aware network (FT...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824909/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Change detection (CD) aims to explore surface changes in coaligned image pairs. However, many existing networks primarily focus on learning deep features, without considering the impact of attention and fusion strategies on detection performance. Therefore, a new frequency-temporal-aware network (FTA-Net) is proposed, it recognizes changes by means of a frequency-domain temporal fusion module and supervised attention to multilevel time-difference features, while reducing the model size. The frequency temporal fusion module is designed to introduce the frequency attention mechanism into the fusion process. First, it has a two-branch Transformer-INN feature extractor using a Lite-Transformer that utilizes remote attention for low-frequency global features, and a invertible neural network that focuses on extracting high-frequency local information. The semantic information and details of the object in both high-frequency and low-frequency feature maps are further strengthened by fusing the high-frequency local features and low-frequency global representations. Then, a stepwise modification detection module is proposed to better extract temporal difference information from bitemporal features. In addition, a supervised learning module is constructed to reweight features to efficiently aggregate multilevel features from high-level to low-level. FTA-Net outperforms state-of-the-art methods on three challenging CD datasets, and it have fewer parameters (4.93M) and lower computational cost (6.71 G). |
|---|---|
| ISSN: | 1939-1404 2151-1535 |