Litcius/Paper detail

EPFNet: Edge-Prototype Fusion Network Toward Few-Shot Semantic Segmentation for Aerial Remote-Sensing Images

Jiayi Wu, Chuan Qin, Yanli Ren, Guorui Feng

2023IEEE Geoscience and Remote Sensing Letters11 citationsDOI

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.

Topics & Concepts

Computer scienceSegmentationArtificial intelligenceShot (pellet)Image segmentationComputer visionEnhanced Data Rates for GSM EvolutionAerial imageMatching (statistics)Field (mathematics)Process (computing)Image (mathematics)Pattern recognition (psychology)StatisticsChemistryMathematicsOrganic chemistryOperating systemPure mathematicsAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning
EPFNet: Edge-Prototype Fusion Network Toward Few-Shot Semantic Segmentation for Aerial Remote-Sensing Images | Litcius