DASNet: Dual Attentive Fully Convolutional Siamese Networks for Change Detection in High-Resolution Satellite Images

By Jie Chen, Ziyang Yuan, Jian Peng, Li Chen, Haozhe Huang, Jiawei Zhu, Yu Liu, Haifeng Li. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020

616 citations recorded by the source corpus.

Change detection is a basic task of remote sensing image processing. The research objective is to identify the change information of interest and filter out the irrelevant change information as interference factors. Recently, the rise in deep learning has provided new tools for change detection, which have yielded impressive results. However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudochange information. To overcome the lack of resistance in current methods to pseudochanges, in this article, we propose a new method, namely, dual attentive fully convolutional Siamese networks, for change detection in high-resolution images. Through the dual attention mechanism, long-range dependencies are captured to obtain more discriminant feature representations to enhance the recognition performance of the model. Moreover, the imbalanced sample is a serious problem in change detection, i.e., unchanged samples are much more abundant than changed samples, which is one of the main reasons for pseudochanges. We propose the weighted double-margin contrastive loss to address this problem by punishing attention to unchanged feature pairs and increasing attention to changed feature pairs. The experimental results of our method on the change detection dataset and the building change detection dataset demonstrate that compared with other baseline methods, the proposed method realizes maximum improvements of 2.9% and 4.2%, respectively, in the F1 score. Our PyTorch implementation is available at https://github.com/lehaifeng/DASNet.

Subfields: Artificial Intelligence, Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/13b5e856f3e22072bc916ff45248a3d68100ce88

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Jing Zhang
3. Bo Du
4. Di Wang
5. Qiming Zhang
6. Yufei Xu
7. Sheng Fang
8. Zhe Li

In Atmospheric Science

1. Bo Du
2. Liangpei Zhang
3. Sheng Fang
4. Zhe Li
5. Kaiyu Li
6. Dacheng Tao
7. Liejun Wang
8. Shuli Cheng

In Media Technology

1. Bo Du
2. Liangpei Zhang
3. Sheng Fang
4. Zhe Li
5. Kaiyu Li
6. Dacheng Tao
7. Zhenwei Shi
8. Jing Zhang

Citations in the corpus

• Optical Remote Sensing Image Change Detection Based on Attention Mechanism and Image Difference (2021, methodology): “Chen et al. [41] increased the robustness of the pseudo-change information by introducing both spatial and channel attention into the convolution network [7].”
• Transformers in Remote Sensing: A Survey (2022, neutral): “Figure 8: Results of different CD methods visualized, such as FC-EF [62], FC-Siam-Conc [62], FC-Siam-Diff [62], CDNet [63], DASNet [64], STANet [61], and SwinSUNet [56] compared to (a)–(d) sample imagery sets the WHU-CD [60] test set.”
• A Deeply Supervised Attention Metric-Based Network and an Open Aerial Image Dataset for Remote Sensing Change Detection (2021, background): “Many previous studies have demonstrated that borrowing a CNN feature extractor with pretrained parameters is conducive to model convergence [29], [50].”
• SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection (2022, methodology): “We compared SwinSUNet with several excellent methods, such as CDNet [48], FC-EF [20], FC-Siam-conc [20], FC-Siam-diff [20], DASNet [22] and STANet [21].”
• Advancing Plain Vision Transformer Toward Remote Sensing Foundation Model (2022, methodology): “[4], [5], [6], [7], [8], [9], [10] In the current remote sensing (RS) field, convolutional neural networks (CNNs) are the most commonly used models for extracting hierarchical multiscale visual features.”
• SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images (2021, methodology): “DASNet [11] introduces a dual attention mechanism [19] to the contrastive method in change detection.”
• RS-Mamba for Large Remote Sensing Image Dense Prediction (2024, methodology): “…CNN-based models include FC-EF [36], FC-Siam-Diff [36], FC-Siam-Conc [36], STANet [39], DTCDSCN [54], SNUNet [55], CDNet [56], DDCNN [57], DASNet [58], DSIFN [59], and HANet [60], the compared transformer-based models include Change-Former [9], and the CNN-transformer hybrid models include BIT…”
• Remote Sensing Image Change Detection With Transformers (2021, methodology): “To increase the RF size, existing methods include employing a deeper CNN model [2, 6–8], using dilated convolution [7], and applying attention mechanisms [2, 6, 9–13].”