An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection

• Published in: Pattern recognition Vol. 132; p. 108960
• Main Authors: Liu, Jia, Xuan, Wenjie, Gan, Yuhang, Zhan, Yibing, Liu, Juhua, Du, Bo
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.12.2022
• Subjects: Change Detection; Feature Adaptation; Image Adaptation; Supervised Domain Adaptation; Supervised Domain Adaptation; Feature Adaptation; Image Adaptation; Change Detection
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2022.108960

•A novel supervised domain adaptation framework SDACD for cross-domain change detection.•SDACD unifies image adaptation and feature adaptation in an end-to-end trainable manner.•SDACD can handle cross-domain change detection and consistently improve the performance as an easy-to-plug-in module.•Our SNUNet-based framework sets new state-of-the-art performance with an F1-score of 97.34% on CDD dataset and 92.36% on WHU building dataset. Change detection is a crucial but extremely challenging task in remote sensing image analysis, and much progress has been made with the rapid development of deep learning. However, most existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations. However, they ignore the universal domain shift induced by time-varying land cover changes, including luminance fluctuations and seasonal changes between pre-event and post-event images, thereby producing suboptimal results. In this paper, we propose an end-to-end supervised domain adaptation framework for cross-domain change detection named SDACD, to effectively alleviate the domain shift between bi-temporal images for better change predictions. Specifically, our SDACD presents collaborative adaptations from both image and feature perspectives with supervised learning. Image adaptation exploits generative adversarial learning with cycle-consistency constraints to perform cross-domain style transformation, which effectively narrows the domain gap in a two-side generation fashion. As for feature adaptation, we extract domain-invariant features to align different feature distributions in the feature space, which could further reduce the domain gap of cross-domain images. To further improve the performance, we combine three types of bi-temporal images for the final change prediction, including the initial input bi-temporal images and two generated bi-temporal images from the pre-event and post-event domains. Extensive experiments and analyses conducted on two benchmarks demonstrate the effectiveness and generalizability of our proposed framework. Notably, our framework pushes several representative baseline models up to new State-Of-The-Art records, achieving 97.34% and 92.36% on the CDD and WHU building datasets, respectively. The source code and models are publicly available at https://github.com/Perfect-You/SDACD.