Semantic Equalization Learning for Semi-Supervised SAR Building Segmentation

Synthetic aperture radar (SAR) building segmentation, which is one of the fundamental tasks in the remote sensing community, has been achieved remarkable performance using convolutional neural networks (CNNs). Since most methods do not consider distinctive characteristics of SAR images, they tend to be biased toward simple and large buildings while ignoring small- and complex-shaped ones. To build a general and powerful SAR building segmentation model, in this letter, we introduce a semi-supervised learning (SSL) framework with semantic equalization learning (SEL). Concretely, we leverage labeled SAR and electro-optical (EO) image pairs and unlabeled SAR images for SSL to extract representative SAR features with the help of context-rich EO features. Moreover, SEL aims to balance the training of well- and poor-performing samples via our purposed data augmentation technique and the objective functions. It consists of a semantic proportional CutMix (SP-CutMix) module to increase the sampling probability of underperformed samples during the training phase, and an equalized segmentation loss (ESL) to adjust the loss contribution depending on difficulties. By doing so, our method prevents the model from being biased to easy samples and increases the performance of difficult building samples. Experimental results on the SpaceNet-6 benchmark demonstrate the effectiveness of our framework, especially by significantly improving the most challenging scenarios, that is less labeled data available.