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

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 14; pp. 1194 - 1206
• Main Authors: Chen, Jie, Yuan, Ziyang, Peng, Jian, Chen, Li, Huang, Haozhe, Zhu, Jiawei, Liu, Yu, Li, Haifeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Change detection; Data mining; Datasets; Deep learning; Detection; dual attention; Feature extraction; High resolution; high-resolution images; Image processing; Image resolution; Methods; Remote sensing; Resolution; Robustness; Satellite imagery; Siamese network; Spaceborne remote sensing; Task analysis; Wavelength division multiplexing; weighted double-margin contrastive (WDMC) loss
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2020.3037893

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.