S³Net: Superpixel-Guided Self-Supervised Learning Network for Multitemporal Image Change Detection

Deep learning (DL) has recently achieved outstanding performance in change detection of multitemporal images. However, most existing DL-based change detection methods still suffer from the problem of insufficient labeled training samples. To overcome this limitation, an unsupervised superpixel-guided self-supervised learning network (S3Net) is proposed for detecting changes occurred on the land surface. By performing principal component analysis on two input images, a triple-channel pseudocolor image containing the main information of both the images is first generated, which is used for superpixel segmentation to produce homogeneous image objects. Then, a Siamese network composing of two identical subnetworks with shared weight based on transfer learning is trained for pretext task in a self-supervised learning way, aiming to obtain multiscale object-level spatial feature difference images. On this basis, a high-quality difference image is generated by incorporating the pixel-level and object-level difference information using a simple weighted fusion strategy, which can be analyzed by thresholding to produce the final binary change map. The experimental results on four real-world datasets from different sensors show that the proposed approach can obtain superior performance in comparison to several state-of-the-art change detection methods, which further demonstrates its effectiveness and practicability. We make our data and code publicly available (https://github.com/OMEGA-RS/S3Net_CD).