• Home
  • Search
  • Self-supervised learning for remote sensing scene classification under the few shot scenario
  • Cite Icon20
  • https://doi.org/10.1038/s41598-022-27313-5Copy DOI Icon

Self-supervised learning for remote sensing scene classification under the few shot scenario

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Scene classification is a crucial research problem in remote sensing (RS) that has attracted many researchers recently. It has many challenges due to multiple issues, such as: the complexity of remote sensing scenes, the classes overlapping (as a scene may contain objects that belong to foreign classes), and the difficulty of gaining sufficient labeled scenes. Deep learning (DL) solutions and in particular convolutional neural networks (CNN) are now state-of-the-art solution in RS scene classification; however, CNN models need huge amounts of annotated data, which can be costly and time-consuming. On the other hand, it is relatively easy to acquire large amounts of unlabeled images. Recently, Self-Supervised Learning (SSL) is proposed as a method that can learn from unlabeled images, potentially reducing the need for labeling. In this work, we propose a deep SSL method, called RS-FewShotSSL, for RS scene classification under the few shot scenario when we only have a few (less than 20) labeled scenes per class. Under this scenario, typical DL solutions that fine-tune CNN models, pre-trained on the ImageNet dataset, fail dramatically. In the SSL paradigm, a DL model is pre-trained from scratch during the pretext task using the large amounts of unlabeled scenes. Then, during the main or the so-called downstream task, the model is fine-tuned on the labeled scenes. Our proposed RS-FewShotSSL solution is composed of an online network and a target network both using the EfficientNet-B3 CNN model as a feature encoder backbone. During the pretext task, RS-FewShotSSL learns discriminative features from the unlabeled images using cross-view contrastive learning. Different views are generated from each image using geometric transformations and passed to the online and target networks. Then, the whole model is optimized by minimizing the cross-view distance between the online and target networks. To address the problem of limited computation resources available to us, our proposed method uses a novel DL architecture that can be trained using both high-resolution and low-resolution images. During the pretext task, RS-FewShotSSL is trained using low-resolution images, thereby, allowing for larger batch sizes which significantly boosts the performance of the proposed pipeline on the task of RS classification. In the downstream task, the target network is discarded, and the online network is fine-tuned using the few labeled shots or scenes. Here, we use smaller batches of both high-resolution and low-resolution images. This architecture allows RS-FewshotSSL to benefit from both large batch sizes and full image sizes, thereby learning from the large amounts of unlabeled data in an effective way. We tested RS-FewShotSSL on three RS public datasets, and it demonstrated a significant improvement compared to other state-of-the-art methods such as: SimCLR, MoCo, BYOL and IDSSL.

Loading PDF

Similar Papers
  • PDF
  • Research Article
  • Citations16

A Generic Self-Supervised Learning (SSL) Framework for Representation Learning from Spectral–Spatial Features of Unlabeled Remote Sensing Imagery

  • Nov 03, 2023
  • Remote Sensing
  • Xin Zhang +1
  • Research Article
  • Citations8

RS-DeepSuperLearner: fusion of CNN ensemble for remote sensing scene classification

  • Jan 02, 2023
  • Annals of GIS
  • Haikel Alhichri
  • PDF
  • Research Article
  • Citations71

When Self-Supervised Learning Meets Scene Classification: Remote Sensing Scene Classification Based on a Multitask Learning Framework

  • Oct 09, 2020
  • Remote Sensing
  • Zhicheng Zhao +4
  • Research Article
  • Citations105

Learning Deep Cross-Modal Embedding Networks for Zero-Shot Remote Sensing Image Scene Classification

  • Jan 14, 2021
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yansheng Li +3
  • Research Article
  • Citations1

RDPN: Tackling the Data Shift Problem in Remote Sensing Scene Classification

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Xiang Zhang +4
  • Research Article
  • Citations12

Self-supervised learning improves robustness of deep learning lung tumor segmentation models to CT imaging differences.

  • Dec 05, 2024
  • Medical physics
  • Jue Jiang +2
  • Research Article
  • Citations137

EMTCAL: Efficient Multiscale Transformer and Cross-Level Attention Learning for Remote Sensing Scene Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xu Tang +5
  • Research Article
  • Citations8

Improving remote sensing scene classification using quality-based data augmentation

  • Mar 19, 2023
  • International Journal of Remote Sensing
  • Rowida Alharbi +4
  • PDF
  • Research Article
  • Citations343

Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention

  • Jan 01, 2021
  • IEEE Access
  • Haikel Alhichri +4
  • Conference Article
  • Citations6

Classification of Remote Sensing Scenes Based on Neural Architecture Search Network

  • Jul 01, 2019
  • Lingling Li +2
  • Research Article
  • Citations48

Searching for CNN Architectures for Remote Sensing Scene Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Clifford Broni-Bediako +3
  • PDF
  • Research Article
  • Citations18

Lightweight Channel Attention and Multiscale Feature Fusion Discrimination for Remote Sensing Scene Classification

  • Jan 01, 2021
  • IEEE Access
  • Huiyao Wan +7
  • PDF
  • Research Article
  • Citations68

Homo–Heterogenous Transformer Learning Framework for RS Scene Classification

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Jingjing Ma +5
  • PDF
  • Research Article
  • Citations4

Deep learning based on self-supervised pre-training: Application on sandstone content prediction

  • Jan 10, 2023
  • Frontiers in Earth Science
  • Chong Ming Wang +5
  • Research Article
  • Citations144

Domain Adaptation for Convolutional Neural Networks-Based Remote Sensing Scene Classification

  • Aug 01, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Shaoyue Song +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.