FCCDN: Feature Constraint Network for VHR Image Change Detection
This work addresses the challenge of accurate change detection for Earth observation applications, offering incremental improvements in performance and cost savings by eliminating the need for semantic segmentation labels.
The paper tackles the problem of change detection in very high-resolution images by proposing a feature constraint network (FCCDN) to improve supervision for change feature learning, achieving state-of-the-art results with an IoU of 0.8569 and F1 of 0.9229 on the LEVIR-CD dataset and an IoU of 0.8820 and F1 of 0.9373 on the WHU dataset.
Change detection is the process of identifying pixelwise differences in bitemporal co-registered images. It is of great significance to Earth observations. Recently, with the emergence of deep learning (DL), the power and feasibility of deep convolutional neural network (CNN)-based methods have been shown in the field of change detection. However, there is still a lack of effective supervision for change feature learning. In this work, a feature constraint change detection network (FCCDN) is proposed. We constrain features both in bitemporal feature extraction and feature fusion. More specifically, we propose a dual encoder-decoder network backbone for the change detection task. At the center of the backbone, we design a nonlocal feature pyramid network to extract and fuse multiscale features. To fuse bitemporal features in a robust way, we build a dense connection-based feature fusion module. Moreover, a self-supervised learning-based strategy is proposed to constrain feature learning. Based on FCCDN, we achieve state-of-the-art performance on two building change detection datasets (LEVIR-CD and WHU). On the LEVIR-CD dataset, we achieve an IoU of 0.8569 and an F1 score of 0.9229. On the WHU dataset, we achieve an IoU of 0.8820 and an F1 score of 0.9373. Moreover, for the first time, the acquisition of accurate bitemporal semantic segmentation results is achieved without using semantic segmentation labels. This is vital for the application of change detection because it saves the cost of labeling.