Few-Shot Semantic Segmentation on Remote Sensing Images With Learnable Prototype

Deep learning-based semantic segmentation has been the dominant solution to quickly capture regions of interest (ROIs) in remote sensing images. However, the annotation and training cost of a fully-supervised segmentation model is often too high due to the requirement for elaborate masks. Additionally, trained models are limited to recognize only those classes defined in the training set. This has led to increased interest in how to cheaply adapt learned knowledge to new unseen objects. In this paper, we propose a meta-learning-based few-shot method called Learnable Prototype Few-Shot Segmentation (LPFS) to quickly adapt models to previously unseen geographic categories with only a few support examples of remote sensing images. Specifically, we first build a learnable prototype module based on variational auto-encoder (VAE) to eliminate inter-class ambiguity and extract high-level semantic prototypes from the support set effectively. We then design a global-attention correlation map to achieve low-level structural feature alignment between the support and query images. Additionally, we introduce a base learner to alleviate the bias caused by the meta-learning network on base classes. The extensive experiments on the public few-shot segmentation benchmark iSAID-5<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ⁱ</i> demonstrate that our method sets a new strong baseline for few-shot semantic segmentation on remote sensing images.