Semi-Supervised Remote Sensing Image Semantic Segmentation via Consistency Regularization and Average Update of Pseudo-Label

Jiaxin Wang,Bin Luo,Sibao Chen,Chris H Q Ding,Chenggang He

doi:10.3390/rs12213603

Jiaxin Wang, Bin Luo + Show 3 more

Open Access

https://doi.org/10.3390/rs12213603

Copy DOI

Abstract

Image segmentation has made great progress in recent years, but the annotation required for image segmentation is usually expensive, especially for remote sensing images. To solve this problem, we explore semi-supervised learning methods and appropriately utilize a large amount of unlabeled data to improve the performance of remote sensing image segmentation. This paper proposes a method for remote sensing image segmentation based on semi-supervised learning. We first design a Consistency Regularization (CR) training method for semi-supervised training, then employ the new learned model for Average Update of Pseudo-label (AUP), and finally combine pseudo labels and strong labels to train semantic segmentation network. We demonstrate the effectiveness of the proposed method on three remote sensing datasets, achieving better performance without more labeled data. Extensive experiments show that our semi-supervised method can learn the latent information from the unlabeled data to improve the segmentation performance.

Highlights

The semantic segmentation of remote sensing image plays an important role in urban planning, change detection, and the construction of geographic information systems
We propose a semi-supervised remote sensing image semantic segmentation method based on Consistent Regularization (CR) training and Average Update of Pseudo-label (AUP)
We explore the semantic segmentation of remote sensing images in the absence of labeled data and propose a semi-supervised approach to solve the problem

Summary

Introduction

The semantic segmentation of remote sensing image plays an important role in urban planning, change detection, and the construction of geographic information systems. In the past few years, some researchers [1] have used SIFT information, texture information, and other features to classify the superpixel They select appropriate superpixels on multiple scales to segment the remote sensing image. Based on the superpixel method, many methods can segment different areas of a remote sensing image. Many methods for remote sensing image segmentation have been developed. They can obtain more precise segmentation results. For non-GRB remote sensing images, Wang et al [6] tried semi-supervised segmentation based on SVM. This paper aims to contribute to this growing area of research by exploring semi-supervised segmentation in remote sensing images

Objectives

Methods

Findings

Discussion

Conclusion