Self-Supervised Learning for Scene Classification in Remote Sensing: Current State of the Art and Perspectives

被引:35
作者
Berg, Paul [1 ]
Minh-Tan Pham [1 ]
Courty, Nicolas [1 ]
机构
[1] Univ Bretagne Sud, Inst Rech Informat & Syst Aleatoires IRISA, UMR 6074, F-56000 Vannes, France
关键词
self-supervised learning; representation learning; scene classification; remote sensing; DATA FUSION; IMAGE-CLASSIFICATION; BENCHMARK-ARCHIVE; LARGE-SCALE; BIGEARTHNET; DATASET;
D O I
10.3390/rs14163995
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Deep learning methods have become an integral part of computer vision and machine learning research by providing significant improvement performed in many tasks such as classification, regression, and detection. These gains have been also observed in the field of remote sensing for Earth observation where most of the state-of-the-art results are now achieved by deep neural networks. However, one downside of these methods is the need for large amounts of annotated data, requiring lots of labor-intensive and expensive human efforts, in particular for specific domains that require expert knowledge such as medical imaging or remote sensing. In order to limit the requirement on data annotations, several self-supervised representation learning methods have been proposed to learn unsupervised image representations that can consequently serve for downstream tasks such as image classification, object detection or semantic segmentation. As a result, self-supervised learning approaches have been considerably adopted in the remote sensing domain within the last few years. In this article, we review the underlying principles developed by various self-supervised methods with a focus on scene classification task. We highlight the main contributions and analyze the experiments, as well as summarize the key conclusions, from each study. We then conduct extensive experiments on two public scene classification datasets to benchmark and evaluate different self-supervised models. Based on comparative results, we investigate the impact of individual augmentations when applied to remote sensing data as well as the use of self-supervised pre-training to boost the classification performance with limited number of labeled samples. We finally underline the current trends and challenges, as well as perspectives of self-supervised scene classification.
引用
收藏
页数:37
相关论文
共 108 条
[1]  
[Anonymous], 2015, P 32 INT C MACH LEAR
[2]  
[Anonymous], 2016, What makes imagenet good for transfer learning?
[3]  
Ayush K., 2021, P IEEE CVF INT C COM, P10181
[4]  
Bardes A., 2022, ARXIV
[5]   Representation Learning: A Review and New Perspectives [J].
Bengio, Yoshua ;
Courville, Aaron ;
Vincent, Pascal .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) :1798-1828
[6]   Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program [J].
Boryan, Claire ;
Yang, Zhengwei ;
Mueller, Rick ;
Craig, Mike .
GEOCARTO INTERNATIONAL, 2011, 26 (05) :341-358
[7]  
Caron M, 2020, ADV NEUR IN, V33
[8]   Emerging Properties in Self-Supervised Vision Transformers [J].
Caron, Mathilde ;
Touvron, Hugo ;
Misra, Ishan ;
Jegou, Herve ;
Mairal, Julien ;
Bojanowski, Piotr ;
Joulin, Armand .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :9630-9640
[9]  
Chen T, 2020, PR MACH LEARN RES, V119
[10]   Self-Supervised GANs via Auxiliary Rotation Loss [J].
Chen, Ting ;
Zhai, Xiaohua ;
Ritter, Marvin ;
Lucic, Mario ;
Houlsby, Neil .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :12146-12155