Self-Supervised Learning in Remote Sensing: A review
Open accessThe DOI matches its Crossref record; 263 of the 265 references it cites were found in a registry or an index.
Abstract
In deep learning research, self-supervised learning (SSL) has received great attention, triggering interest within both the computer vision and remote sensing communities. While there has been big success in computer vision, most of the potential of SSL in the domain of Earth observation remains locked. In this article, we provide an introduction to and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for Earth observation (SSL4EO) to pave the way for the fruitful interaction of both domains.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 201–265 of 265
Muhtar, D., Zhang, X., & Xiao, P. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3177770 · Cited by 51
Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation
Marsocci, V., & Scardapane, S. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3280029 · Cited by 51
Cruz, R. S., Fernando, B., Cherian, A., & Gould, S. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2873701 · Cited by 50
Zero-Shot Hyperspectral Image Denoising With Separable Image Prior
Imamura, R., Itasaka, T., & Okuda, M. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00178 · Cited by 50
Unsupervised Single-Scene Semantic Segmentation for Earth Observation
Saha, S., Shahzad, M., Mou, L., Song, Q., & Zhu, X. X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3174651 · Cited by 50
Self-citationSo2Sat LCZ42: A Benchmark Dataset for Global Local Climate Zones Classification
Zhu, X. X., Hu, J., Qiu, C., Shi, Y., Kang, J. S., Mou, L., Bagheri, H., Häberle, M., Hua, Y., Huang, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.12171 · Cited by 49
Self-citationLi, K., Qin, Y., Ling, Q., Wang, Y., Lin, Z., & An, W. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3063335 · Cited by 47
Self-citationDeep Spatial-Spectral Subspace Clustering for Hyperspectral Images Based on Contrastive Learning
Hu, X. Y., Li, T., Zhou, T., & Peng, Y. (2021) · Remote Sensing · doi:10.3390/rs13214418 · Cited by 45
Deeply Unsupervised Patch Re-Identification for Pre-Training Object Detectors
Ding, J., Xie, E., Xu, H., Jiang, C., Li, Z., Luo, P., & Xia, G.-S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3164911 · Cited by 45
A remote sensing image fusion method based on PCA transform and wavelet packet transform
Cao, W., Li, B., & Zhang, Y. (2003) · International Conference on Neural Networks and Signal Processing · doi:10.1109/icnnsp.2003.1280764 · Cited by 44
Adversarial Self-Supervised Learning for Robust SAR Target Recognition
Xu, Y., Sun, H., Chen, J., Lei, L., Ji, K., & Kuang, G. (2021) · Remote Sensing · doi:10.3390/rs13204158 · Cited by 44
Hyperspectral Image Restoration With Self-Supervised Learning: A Two-Stage Training Approach
Qian, Y., Zhu, H., Chen, L., & Zhou, J. W. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3137313 · Cited by 44
Few-Shot Scene Classification of Optical Remote Sensing Images Leveraging Calibrated Pretext Tasks
Ji, H., Gao, Z. Y., Zhang, Y., Wan, Y., Li, C., & Mei, T. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3184080 · Cited by 44
Self-Supervised Low-Rank Representation (SSLRR) for Hyperspectral Image Classification
Wang, Y., Mei, J., Zhang, L., Zhang, B., Li, A., Zheng, Y., & Zhu, P. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2823750 · Cited by 40
Self-citationSelf-Supervised GANs With Similarity Loss for Remote Sensing Image Scene Classification
Guo, D., Xia, Y. J., & Luo, X. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3056883 · Cited by 40
Zhang, X., Han, L., Sobeih, T., Lappin, L., Lee, M. A., Howard, A., & Kisdi, Á. (2022) · Remote Sensing · doi:10.3390/rs14061400 · Cited by 39
Hyperspectral Image Super-Resolution with Self-Supervised Spectral-Spatial Residual Network
Chen, W., Zheng, X., & Lu, X. (2021) · Remote Sensing · doi:10.3390/rs13071260 · Cited by 37
3D convolutional siamese network for few-shot hyperspectral classification
Cao, Z., Li, X., Jianfeng, J., & Zhao, L. (2020) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.14.048504 · Cited by 36
Semi-Supervised Learning for Joint SAR and Multispectral Land Cover Classification
Montanaro, A., Valsesia, D., Fracastoro, G., & Magli, E. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3195259 · Cited by 35
Contrastive Multiview Coding With Electro-Optics for SAR Semantic Segmentation
Cha, K., Seo, J., & Choi, Y. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3109345 · Cited by 34
A Self-Supervised Denoising Network for Satellite-Airborne-Ground Hyperspectral Imagery
Wang, X., Luo, Z., Li, W., Hu, X. Y., Zhang, L., & Zhong, Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3064429 · Cited by 33
Aerial scene understanding in the wild: Multi-scene recognition via prototype-based memory networks
Hua, Y., Mou, L., Lin, J., Heidler, K., & Zhu, X. X. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.04.006 · Cited by 27
Self-citationWU-Net: A Weakly-Supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery
Hong, D., Chanussot, J., Yokoya, N., Heiden, U., Heldens, W., & Zhu, X. X. (2019) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2019.8899865 · Cited by 26
Self-citationRethinking Self-Supervised Learning: Small is BeautifulPreprint
Cao, Y.-H., & Wu, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13559 · Cited by 26
Task-Related Self-Supervised Learning For Remote Sensing Image Change Detection
Cai, Z., Jiang, Z., & Yuan, Y. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414387 · Cited by 24
Self-supervised Remote Sensing Images Change Detection at Pixel-levelPreprint
Chen, Y.-X., & Bruzzone, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08501 · Cited by 24
Self Supervised Learning for Few Shot Hyperspectral Image Classification
Braham, N. A. A., Mou, L., Chanussot, J., Mairal, J., & Zhu, X. X. (2022) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss46834.2022.9884494 · Cited by 24
Self-citationRepresentation Learning for Remote Sensing: An Unsupervised Sensor Fusion ApproachPreprint
Swope, A., Rudelis, X., & Story, K. T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.05094 · Cited by 24
Alvarez, J. L. H., Ravanbakhsh, M., & Demir, B. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9324345 · Cited by 23
SELF-SUPERVISED LEARNING FOR MONOCULAR DEPTH ESTIMATION FROM AERIAL IMAGERY
Hermann, M., Ruf, B., Weinmann, M., & Hinz, S. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-2-2020-357-2020 · Cited by 21
Radar Target Detection With Multi-Task Learning in Heterogeneous Environment
He, J., Cheng, Y., Wu, H., & Wang, H. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3142519 · Cited by 21
Self-Supervised Deep Learning for Nonlinear Seismic Full Waveform Inversion
Gao, Z., Yang, W., Li, C., Li, F., Wang, Q., Ding, J., Gao, J., & Xu, Z. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3175184 · Cited by 21
Deep Mutual Information Subspace Clustering Network for Hyperspectral Images
Li, T., Cai, Y., Zhang, Y., Cai, Z., & Liu, X. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3178168 · Cited by 20
Shuffle and Learn: Unsupervised Learning using Temporal Order VerificationPreprint
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08561 · Cited by 19
Deep Self-Supervised Learning for Few-Shot Hyperspectral Image Classification
Li, Y., Zhang, L., Wei, W., & Zhang, Y. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9323305 · Cited by 18
Unsupervised Pretraining for Object Detection by Patch Reidentification.Preprint
Ding, J., Xie, E., Xu, H., et al. (2021) · arXiv (Cornell University) · Cited by 18
Patch-Level Unsupervised Planetary Change Detection
Saha, S., & Zhu, X. X. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3130862 · Cited by 17
Self-citationStevenson, M. M., Mues, C., & Bravo, C. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.03.015 · Cited by 17
Ryali, C. K., Schwab, D. J., & Morcos, A. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12719 · Cited by 17
A Laboratory Open-Set Martian Rock Classification Method Based on Spectral Signatures
Yang, J., Kang, Z., Yang, Z., Xie, J., Xue, B., Yang, J., & Tao, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3175996 · Cited by 16
An Empirical Study of Training Self-Supervised Vision TransformersPreprint
Chen, X., Xie, S., & He, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02057 · Cited by 16
Rotation Awareness Based Self-Supervised Learning for SAR Target Recognition
Zhang, S., Wen, Z., Liu, Z., & Pan, Q. (2019) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2019.8899169 · Cited by 15
Blind SAR Image Despeckling Using Self-Supervised Dense Dilated Convolutional Neural NetworkPreprint
Yuan, Y., Guan, J., & Sun, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.01608 · Cited by 13
Cao, Y., Wang, Y., Peng, J., Qiu, C., Ding, L., & Zhu, X. X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3044094 · Cited by 13
Self-citationA Semisupervised Convolution Neural Network for Partial Unlabeled Remote-Sensing Image Segmentation
Zhang, L., Lu, W., Zhang, J., & Wang, H. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3153607 · Cited by 13
Self-Supervised Learning for Monocular Depth Estimation from Aerial Imagery
Hermann, M., Ruf, B., Weinmann, M., et al. (2020) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000130854 · Cited by 12
Hyper-Embedder: Learning a Deep Embedder for Self-Supervised Hyperspectral Dimensionality Reduction
Wu, X., Hong, D., & Zhao, D. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3119339 · Cited by 11
Self-Supervised Spectral Matching Network for Hyperspectral Target Detection
Yao, C., Yuan, Y., & Jiang, Z. (2021) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss47720.2021.9554988 · Cited by 10
Wang, D., Zhang, C., & Han, M. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2022.2042617 · Cited by 9
Sharma, R. C., & Hara, K. (2021) · Journal of Imaging · doi:10.3390/jimaging7020030 · Cited by 8
Self-Supervised Remote Sensing Image Retrieval
Walter, K., Gibson, M., & Sowmya, A. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9323294 · Cited by 8
Self‐supervised learning with randomised layers for remote sensing
Jung, H., & Jeon, T. (2021) · Electronics Letters · doi:10.1049/ell2.12108 · Cited by 7
Multi-View Urban Scene Classification with a Complementary-Information Learning Model
Geng, W., Zhou, W., & Jin, S. (2021) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.21-00062r2 · Cited by 7
Self-supervised Hyperspectral Image Restoration using Separable Image PriorPreprint
Imamura, R., Itasaka, T., & Okuda, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.00651 · Cited by 7
Hu, J., Mou, L., & Zhu, X. X. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2020-1569-2020 · Cited by 6
Self-citationHeterogeneous Change Detection with Self-Supervised Deep Canonically Correlated Autoencoders
Tomenotti, F. F., Luppino, L. T., Hansen, M. A., Moser, G., & Anfinsen, S. N. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9323483 · Cited by 6
Li, H., Li, Y., Zhang, G., et al. (2021) · arXiv (Cornell University) · Cited by 5
Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial LossPreprint
Özkan, S., & Akar, G. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06859 · Cited by 4
Homography Augmented Momentum Contrastive Learning for SAR Image Retrieval
Park, S., Rysz, M., Dipple, K. M., & Pardalos, P. M. (2022) · Springer optimization and its applications · doi:10.1007/978-3-031-21225-3_3 · Cited by 4
Ryali, C. K., Schwab, D. J., & Morcos, A. S. (2021) · arXiv (Cornell University) · Cited by 3
Unsupervised Change Detection of Extreme Events Using ML On-BoardPreprint
Růžička, V., Vaughan, A., Martini, D. D., Fulton, J., Salvatelli, V., Bridges, C., Mateo‐García, G., & Zantedeschi, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02995 · Cited by 3
Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentationPreprint
Marsocci, V., & Scardapane, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.11319 · Cited by 2
Homography augumented momentum constrastive learning for SAR image retrievalPreprint
Park, S., Rysz, M., Dipple, K. M., & Pardalos, P. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.10329 · Cited by 1
Self-supervised Vision Transformers for Joint SAR-optical Representation Learning
Wang, Y., Albrecht, C. M., & Zhu, X. X. (2022) · elib (German Aerospace Center) · doi:10.48550/arxiv.2204.05381 · Cited by 1
Self-citationSelf-supervised spectral matching network for hyperspectral target detectionPreprint
Yao, C., Yuan, Y., & Jiang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04078 · Cited by 1
Research works printed but not linked: 3
- [55] Andrew Ng et al. 'Sparse autoencoder'. In: CS294A Lecture notes 72.2011 (2011), pp. 1-19 (cit. on p. 4). -
- [59] Ian Goodfellow et al. 'Generative adversarial nets'. In: Advances in neural information processing systems 27 (2014) (cit. on pp. 4, 5). -
- [233] Xinyu Wang et al. 'A Self-Supervised Denoising Network for Satellite-Airborne-Ground Hyperspectral Imagery'. In: IEEE Transactions on Geoscience and Remote Sensing (2021) (cit. on pp. 16, 18). - · DOI
Cited by
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing
Liu, F., Chen, D., Guan, Z., Zhou, X., Zhu, J., Ye, Q., Fu, L., & Zhou, J. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3390838 · Cited by 507
“The research landscape of SSL-based foundation models for remote sensing closely mirrors this categorization [31].”
BackgroundArtificial intelligence for geoscience: Progress, challenges, and perspectives
Zhao, T., Wang, S., Ouyang, C., Chen, M., Liu, C., Zhang, J., Yu, L., Wang, F., Xie, Y., Li, J., et al. (2024) · The Innovation · doi:10.1016/j.xinn.2024.100691 · Cited by 360
Vision-Language Models in Remote Sensing: Current progress and future trends
Li, X., Wen, C., Hu, Y., Yuan, Z., & Zhu, X. X. (2024) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2024.3383473 · Cited by 178
Self-citationVision Foundation Models in Remote Sensing: A survey
Lu, S., Guo, J., Zimmer-Dauphinee, J. R., Nieusma, J. M., Wang, X., VanValkenburgh, P., Wernke, S. A., & Huo, Y. (2025) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2025.3541952 · Cited by 261
Foundation Models for Remote Sensing and Earth Observation: A survey
Xiao, A., Xuan, W., Wang, J., Huang, J., Tao, D., Lu, S., & Yokoya, N. (2025) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2025.3576766 · Cited by 257
Metadata
- Authors
- Wang, Y., Albrecht, C. M., Braham, N. A. A., Mou, L., & Zhu, X. X.
- Affiliations
- Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) (DE)
- Venue
- IEEE Geoscience and Remote Sensing Magazine
- Published
- 2022-12
- Volume
- 10
- Issue
- 4
- Pages
- 213-247
- ISSN
- 2168-6831 (ISSN-L)
- 2473-2397
- 2373-7468
- OpenAlex
- W4283697304
- Cited by
- 364
- References
- 254
- Citations by year
- 2026: 90 · 2025: 121 · 2024: 95 · 2023: 49 · 2022: 9
- FWCI
- 28.62
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Geoscience and Remote Sensing Magazine (publishedVersion)
- elib (German Aerospace Center) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Research Council (ERC-2016-StG-714087, 957407)
- Helmholtz Association (ZT-I-PF-5-01)
- Helmholtz Klimainitiative (HICAM) and Helmholtz Excellent Professorship (W2-W3-100)
- German Federal Ministry of Education and Research (01DD20001)
- German Federal Ministry for Economic Affairs and Climate Action (50EE2201C)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- self-supervised learning, remote sensing, Earth observation, data augmentation, satellite imagery, deep learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.