EPFNet: Edge-Prototype Fusion Network Toward Few-Shot Semantic Segmentation for Aerial Remote-Sensing Images
Jiayi Wu, Chuan Qin, Yanli Ren, Guorui Feng
Abstract
Few-shot semantic segmentation is a technique that is receiving increasing attention. The aim of this approach is to enable models to segment objects with a few support images (usually 1, 5, 10, etc.). At present, few-shot semantic segmentation has made great progress in the field of Natural Scene Image (NSI), but these methods cannot be applied directly to the field of Remote Sensing Image (RSI). In order to overcome this challenge, we propose a novel semantic segmentation network structure that integrates prototype information with global edge information to achieve more accurate prototype matching results. In addition, we design a comprehensive weighted loss function to monitor the training process to help overcome the challenges. Results of the performance comparison with state-of-the-art few-shot semantic segmentation methods demonstrate the superiority of the proposed method.