Remote Sensing Images Semantic Segmentation with General Remote Sensing Vision Model via a Self-Supervised Contrastive Learning Method

06/20/2021
by   Haifeng Li, et al.
9

A new learning paradigm, self-supervised learning (SSL), can be used to solve such problems by pre-training a general model with large unlabeled images and then fine-tuning on a downstream task with very few labeled samples. Contrastive learning is a typical method of SSL, which can learn general invariant features. However, most of the existing contrastive learning is designed for classification tasks to obtain an image-level representation, which may be sub-optimal for semantic segmentation tasks requiring pixel-level discrimination. Therefore, we propose Global style and Local matching Contrastive Learning Network (GLCNet) for remote sensing semantic segmentation. Specifically, the global style contrastive module is used to learn an image-level representation better, as we consider the style features can better represent the overall image features; The local features matching contrastive module is designed to learn representations of local regions which is beneficial for semantic segmentation. We evaluate four remote sensing semantic segmentation datasets, and the experimental results show that our method mostly outperforms state-of-the-art self-supervised methods and ImageNet pre-training. Specifically, with 1% annotation from the original dataset, our approach improves Kappa by 6% on the ISPRS Potsdam dataset and 3% on Deep Globe Land Cover Classification dataset relative to the existing baseline. Moreover, our method outperforms supervised learning when there are some differences between the datasets of upstream tasks and downstream tasks. Our study promotes the development of self-supervised learning in the field of remote sensing semantic segmentation. The source code is available at https://github.com/GeoX-Lab/G-RSIM.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 7

page 8

page 9

research
02/03/2023

Self-Supervised In-Domain Representation Learning for Remote Sensing Image Scene Classification

Transferring the ImageNet pre-trained weights to the various remote sens...
research
06/28/2023

GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation

Self-supervised contrastive learning (SSCL) has achieved significant mil...
research
11/19/2020

Geography-Aware Self-Supervised Learning

Contrastive learning methods have significantly narrowed the gap between...
research
04/19/2023

CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding

Self-supervised learning (SSL) has gained widespread attention in the re...
research
03/12/2023

DINO-MC: Self-supervised Contrastive Learning for Remote Sensing Imagery with Multi-sized Local Crops

Due to the costly nature of remote sensing image labeling and the large ...
research
07/27/2023

GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing

Classifying and segmenting patterns from a limited number of examples is...
research
04/13/2023

A Contrastive Method Based on Elevation Data for Remote Sensing with Scarce and High Level Semantic Labels

This work proposes a hybrid unsupervised/supervised learning method to p...

Please sign up or login with your details

Forgot password? Click here to reset