Urban functional zone classification based on self-supervised learning: A case study in Beijing, China

Urban functional zones (UFZs) are the fundamental units for urban management and operation. The advance in earth observation and deep learning technology provides chances for automatically and intelligently classifying UFZs via remote sensing images. However, current methods based on deep learning require numerous high-quality annotations to train a well-performed model, which is time-consuming. Thus, how to train a reliable model using a few annotated data is a problem in UFZ classification. Self-supervised learning (SSL) can optimize models using numerous unannotated data. In this paper, we introduce SSL into UFZ classification to use the instance discrimination pretext task for guiding a model to learn useful features from over 50,000 unannotated remote sensing images and fine tune the model using 700 to 7,000 annotated data. The validation experiment in Beijing, China reveals that 1) using a few annotated data, SSL can achieve a kappa coefficient and an overall accuracy 2.1-11.8% and 2.0-10.0% higher than that of supervised learning (SL), and 2) can also gain results comparable to that got by the SL paradigm using two times annotated data for training. The less the data used for finetuning the more obvious the advantage of SSL to SL. Besides, the comparison experiment between the model pretrained on the research region and that pretrained on the benchmark reveals that the objects with displacement and incompleteness are more difficult for models to classify accurately.