Self-Supervised Representation Learning: Introduction, advances, and challenges
Open accessThe DOI matches its Crossref record; 111 of the 125 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Self-supervised representation learning (SSRL) methods aim to provide powerful, deep feature learning without the requirement of large annotated data sets, thus alleviating the annotation bottleneck—one of the main barriers to the practical deployment of deep learning today. These techniques have advanced rapidly in recent years, with their efficacy approaching and sometimes surpassing fully supervised pretraining alternatives across a variety of data modalities, including image, video, sound, text, and graphs. This article introduces this vibrant area, including key concepts, the four main families of approaches and associated state-of-the-art techniques, and how self-supervised methods are applied to diverse modalities of data. We further discuss practical considerations including workflows, representation transferability, and computational cost. Finally, we survey major open challenges in the field, that provide fertile ground for future work.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“The various self-supervised pretexts are divided into five broad families: transformation prediction, masked prediction, instance discrimination, clustering, and contrastive instance discrimination.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [28]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Contrastive learning [56-58] is in fact a training procedure used in recent artificial intelligence models as a way to efficiently learn semantic representations.”
From How Adversarial REM Dreams May Facilitate Creativity, and Why We Become Aware of Them (2024) · cites this paper as [58]
The cited source says what the claim attributes to it.
In the citing paper
“For example, Ericsson et al. [28] provides a very comprehensive review of pretext tasks for multiple modalities, including image, video, text, audio, time series, and graph.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [28]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 4×
“State of the art architectures usually start with CNN representation encoding hθ(·), with ResNet [1] being widely used, before appending task-specific”
InfluentialVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 3×
“long been used to model the context while recent works have moved to Transformer-based architectures with self-attention [2], which allow longer range connections to be made across words in a sentence, but require more data for training.”
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 9×
“Self-supervised strategies have been leveraged successfully to improve sample efficiency of learning across a variety of modalities, from image [5]–[7], video [8], [9], speech [10], [11], text [12], [13], and graphs [14], [15].”
InfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“As in much of computer vision, ImageNet [35] is the most typical source data set for self-supervised pretraining [5]–[7], [40], consisting of 1.28 million training images across 1,000 object categories, with the most commonly used resolution at 224 × 224.”
InfluentialBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 9×
“Self-supervised strategies have been leveraged successfully to improve sample efficiency of learning across a variety of modalities, from image [5]–[7], video [8], [9], speech [10], [11], text [12], [13], and graphs [14], [15].”
InfluentialAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472 · cited 1×
“One notable version is a vision transformer [58], which is increasingly being used by recent self-supervised methods on image data [43].”
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970 · cited 2×
“These range from classic shallow approaches such as Gaussian mixtures [21] to deep methods such as variational autoencoders (VAEs) and generative adversarial networks (GANs) [18].”
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853 · cited 1×
“Graph NNs (GNNs) [89] have advanced all these tasks significantly, especially where massive-labeled data are available.”
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 6×
“With data annotation being a major bottleneck, NLP was the first discipline to make major and successful use of self-supervision [22].”
Influential
Research works printed but not linked: 4
- 0, Youtube-8m A large and diverse labeled video dataset for video understanding research
- gokaslan, 2019, OpenWebText Corpus
- radford, 2019, Language Models are Unsupervised Multitask Learners
- goodfellow, 2016, Deep Learning
Cited by
Items 501–600 of 641
Enhancing image colorization with semantic-guided diffusion and lightweight fine-tuning
Osooli, M., & Tavassolipour, M. (2026) · The Visual Computer · doi:10.1007/s00371-026-04577-w
Lagattu, K., Alham, R., Chaffre, T., Artusi, E., Santos, P. E., Chenadec, G. L., Sammut, K., & Clément, B. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261451002
EvoGraphConPain: an adaptive multimodal graph intelligence framework for neonatal pain assessment
Othmani, O. E., & Ouersighni, R. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01861-6
VIP: A visual insulated pipeline dataset for computer vision tasks
Papadam, D. R., Zamioudis, A., Mentesidis, P., Charalampakis, E., Valsamara, I., Spatharis, E., Mygdalis, V., & Pitas, I. (2025) · Journal of Pipeline Science and Engineering · doi:10.1016/j.jpse.2025.100421
Decoupled Feature Interaction for Sparse EEG-Based Emotion Recognition
Fan, T., Tian, F., Zhu, L., Zhang, H., Liu, J., & Hu, B. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3665596
“Self-Supervised Representation (SSR) learning [41], [42] is a classical feature enhancement method that has been widely used in EEG-related tasks [43], [44], [45].”
Miao, C., Jiang, Y., Cui, Y., Chen, Y., & Sun, T. (2025) · Applied Intelligence · doi:10.1007/s10489-025-07035-7
Lazarine, B., Samtani, S., Zhu, H., & Ramesh, V. (2026) · Journal of Management Information Systems · doi:10.1080/07421222.2026.2692274
“SSL refers to learning tasks that operate on limited labeled data by deriving additional labels (i.e., pseudo-labels) from intrinsic input data attributes for downstream tasks [23].”
Yazdani, E., Karamzadeh-Ziarati, N., Cheshmi, S. S., Sadeghi, M., Geramifar, P., Vosoughi, H., Jahromi, M. K., & Kheradpisheh, S. R. (2024) · Figshare · doi:10.6084/m9.figshare.25322912
Yazdani, E., Karamzadeh-Ziarati, N., Cheshmi, S. S., Sadeghi, M., Geramifar, P., Vosoughi, H., Jahromi, M. K., & Kheradpisheh, S. R. (2024) · Figshare · doi:10.6084/m9.figshare.25322963
Less is More: Unlabeled Data Selection for Efficient Tabular Self-supervised Learning
Stevanoska, S., Villalón, C. L. C., Džeroski, S., & Dost, K. (2026) · Machine Learning · doi:10.1007/s10994-026-07133-8
“Pretraining typically requires processing large volumes of unlabeled data, which can be prohibitive in time and resources (Ericsson et al., 2022).”
Challenges of Self-Supervised Learning for Unified, Multi-Modal, Multi-Task Transformer Models
Annett, G., Andersen, T., & Annett, R. D. (2022) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci58124.2022.00056
“and amount of scalable data with intrinsic structure they can simultaneously learn from [7].”
BackgroundMethodChatterjee, M. J. V. (2024) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2024-16267
Cross-Architecture Relational Consistency for Point Cloud Self-Supervised Learning
Li, H., Zhang, Y., & Yang, D. (2023) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai59109.2023.00103
“The intention of self-supervised learning (SSL) is to learn generic feature representations from the large-scale unlabeled dataset, which then serves as a good initialization for down-stream tasks such as classification, detection, and semantic segmentation [1], [2].”
BackgroundSong, Y., Yang, T., Zhou, C., Jiao, C., Li, X., Zhang, X. H., Ren, X., & Fan, X. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00630-9
A Theoretical Formulation on the Use of Multiple Positive Views in Contrastive Learning
Liang, Z., Luo, Y., Beese, M., & Reiske, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-85181-0_7
Metarep: improving meta-learning accuracy by learning episodic representation
Faysal, A., Rostami, M., Wang, H., Sahoo, A., & Antle, R. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02917-1
Peng, Y., Zhao, J., & Yang, X. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111188
Benchmarking Voice-Based Parkinson’s Severity Prediction and Limits of Contrastive Feature Masking
Sirohi, D., Goyal, L., & Gupta, H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-26373-5_30
Wang, J., Luo, H., Zhang, G., Song, P., Wang, J., Wang, Y., Sun, Z., & Gao, S. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114861
Amiri, M., Mokari, A., & Bocklitz, T. W. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02369-8
“compute-optimal scaling [33, 36, 39, 45, 134–137].”
Jayaweera, V. L., Maduranga, M. W. P., Nayyar, A., & Saengudomlert, P. (2026) · Optical Switching and Networking · doi:10.1016/j.osn.2026.100876
Tsuchiya, Y., Hirono, Y., & Sonobe, R. (2026) · AgriEngineering · doi:10.3390/agriengineering8010036
Low-Resource Text Data Augmentation Algorithms and Representation Learning Optimization Methods
Zhu, Z., & Li, S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.07.281
Ren, Y., & Wu, J. (2026) · Discover Computing · doi:10.1007/s10791-026-10721-w
“…imbalanced data, for instance in molecular property prediction Zhang et al. [31], and surveys review low-shot learning under class imbalance Polak et al. [32] and self-supervised representation learning that uses unlabeled data to reduce annotation cost Ericsson et al. [33], Alzubaidi et al. [34].”
Computing requirements and techniques to support signal processing
Dutta, P., Chelliah, P. R., Singh, B., & Kaunert, C. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33172-5.00017-0
Shahin, A., ALibrahim, M. F., Kawas, M. E., & Elawi, R. (2026) · Discover Oncology · doi:10.1007/s12672-026-05608-7
“Self-supervised learning (SSL) extends this paradigm by learning representations from unlabeled medical images—an abundant but underutilized resource in hospital archives [25].”
Li, Y., Jing, G., Zhang, T., Gao, S., & Zhang, M. (2026) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2026.154704
Recognition of Signal Modulation Pattern Based on Multi-task Self-supervised Learning
Cheng, D., Wu, X., Xie, Z., Cui, Z., Li, Q., Tong, E., Niu, W., Wei, Z., & Zhao, X. (2024) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-57919-6_3
Yang, L., Zhou, M., Wang, X., Yang, Y., Yang, P., & Qi, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5530660
Deep Learning Survival Model to Predict Atrial Fibrillation From ECGs and EHR Data
Baj, G., Scagnetto, A., Bortolussi, L., & Barbati, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-49011-8_18
SQL injection detection using self-supervised pre-training and multimodal techniques
Yeboah, P. N., Kayes, A. S. M., Rahayu, W. J., Pardede, E., & Mahbub, S. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200702
VIRTUAL: Vector-based Dynamic Power Estimation via Decoupled Multi-Modality Learning
Lu, Y., Wang, M., Wen, Y., Han, B., Mu, J., Li, H., & Yu, B. (2025) · doi:10.1109/iccad66269.2025.11240833
“…learning techniques, has emerged as a promising solution to identify power-relevant patterns from large waveform vector and RTL graph data with limited or no labels, substantially improving both prediction accuracy and the ability to generalize across different designs and inputs [20], [21], [22].”
Jonathan, A. L., Cai, D., Bamisile, O., Ukwuoma, C. C., Victor, K., Nkou, J. J. N., & Huang, Q. (2026) · Solar Energy · doi:10.1016/j.solener.2026.115104
A Review of the Applications of Self-Supervised Learning in Multimodal Models
Tu, Y. (2025) · Advances in Engineering Technology Research · doi:10.56028/aetr.14.1.1491.2025
A classification framework of large language model in the post-transformer era
Athiya, R., & Gupta, A. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133034
Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive AgentPreprint
Hoppmann, B., & Scholz, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.19837
“Instead, self-supervised learning techniques [57], [37] are used to learn patterns in available, but potentially unlabeled, data, so that foundation models are often defined as "large-scale transfer-learning models pre-trained via self-supervised learning" [16].”
DASTNet-X: an explainable dual-attention based spatio-temporal network for arrhythmia classification
Choudhury, A., Sarma, K. K., Dutta, L., Deka, S., Das, A., Misra, D. D., Lyanova, A. I., Voznesensky, A., & Kaplun, D. (2026) · Scientific Reports · doi:10.1038/s41598-026-64908-8
A Foundation Model pre-trained on Serialized EHR RepresentationsPreprint
Qin, Q., Chou, Z., & Li, S. (2025) · doi:10.36227/techrxiv.176127291.14956389/v1
Su, S., Su, S.-C., Liu, J., Yu, Z., & Ma, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133946
Li, T., Wang, Y., Xiong, T., Bai, J., Wang, P., Yan, H., Yuan, L., Li, C., Liu, S., & Wang, J. (2026) · Infrared Physics & Technology · doi:10.1016/j.infrared.2026.106940
Survey on Vision-Based Risk Assessment for Automated Very Light Rail Transportation
Bescop, J. J. J., Allaert, B., & Vandeborre, J. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3655146
“Transferring knowledge from a self-supervised model to a supervised one [208], along with pretraining on pretext tasks [209], has become a highly studied and popular approach.”
Data-Driven Remaining Useful Life Prediction of Energy-Intensive Industrial Assets
Söderkvist Vermelin, W. (2025) · DiVA (Mälardalen University College)
Deep Learning-based Solutions to Improve Diagnosis in Wireless Capsule Endoscopy
Laiz, P. (2023) · Dipòsit Digital de la Universitat de Barcelona (Universitat de Barcelona)
Masked Image Modeling for Representation Learning in Earth Observation
Hernandez-Hernandez, H. (2023) · elib (German Aerospace Center)
Musically-Inspired Colored Pitch Features for Emotion and Speaker Recognition in Speech
Li, X., & Kang, J. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401704
“However, their effectiveness is often contingent on access to vast datasets and extensive computational resources, such as powerful GPUs [4].”
Self-Supervised Reservoir Water Area Detection Across Multi-Source Optical Imagery
Mo, G., Yang, Q. K., & Zhou, X. (2026) · Remote Sensing · doi:10.3390/rs18060918
Multimodala modeller för produktlikhet
Φραντζόλας, Χ. (2023) · KTH Publication Database DiVA (KTH Royal Institute of Technology)
Transfer learning of sentiment analysis between highly dissimilar domains
Coop, G. (2025) · University of Birmingham Institutional Research Archive (University of Birmingham)
MVR-3D : Reflectance-Based Multi-View 3D ReconstructionPreprint
Gacem, T., Abada, L., Bourzam, S. A., Mezabiat, A. S., Bouguera, L. R., & Kadiri, H. (2025) · Research Square · doi:10.21203/rs.3.rs-6994016/v1
Possibilities of convolutions in AI-reconstructed music
Metsälä, M. (2024) · Osuva (University of Vaasa)
Van Vorst, K., & Shen, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.05570
“C V ] 10 J a n 2024 often with much less supervision than a model that is learned from scratch [8].”
BackgroundInfluentialComparaisons d’algorithmes d’apprentissage profond pour les ensembles de données fortement bruités
Sene, N. A. (2024) · Constellation (Université du Québec à Chicoutimi)
Self-supervised Representation Learning on Audio-Video Data
Wang, S. (2025) · Tampere University Institutional Repository (Tampere University)
Preventing Latent Rehearsal Decay in Online Continual SSL with SOLARPreprint
Cignoni, G., Magistri, S., Bagdanov, A. D., & Carta, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.10586
“In SSL, an encoder network f : X → F is trained to map an input x ∈ X to a feature representation z ∈ F by solving pretext tasks requiring no labels (Ericsson et al., 2022).”
Wodziński, M., & Wells, W. M. (2027) · Lecture notes in computer science · doi:10.1007/978-3-032-31709-4_40
Liu, Z., Jiang, H., Lian, S., Li, A., Yang, J., Liu, Y., Zhu, S., & Lv, X. (2026) · Analytical Chemistry · doi:10.1021/acs.analchem.6c01315
Multimodal Urban Scene Understanding
Singh, R. (2022) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.7116360
Enhancing contrastive language-vision pre-training with generative dialogue
Tsaprazlis, E. (2025) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.28346
Recognizing Human Actions and Goals in an Open Environment a Brain-Inspired Approach
Van Horenbeke, F. A. (2024) · Libera Università di Bolzano
Deep Graph Representation Learning and its Application on Graph Clustering
Zheng, H. (2024) · Bournemouth University Research Online (Bournemouth University)
Sabater Vilchez, B. (2025) · UPCommons institutional repository (Universitat Politècnica de Catalunya)
Flight Trajectory Representation Learning Model Based on Self-Supervised Learning
Lu, G., Si, X., Hu, Q., Ou, Y., & Liang, J. (2026) · International Journal of Aeronautical and Space Sciences · doi:10.1007/s42405-026-01218-3
Concept Learning: Understanding and Extracting Domain-specific concepts in medical Observations
Silva, M. G. (2024) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Tödt, K., Granas, B., & Büching, C. (2026) · Springer eBooks · doi:10.1007/978-3-032-26816-7
Identifiability and Statistical Inference in Latent Variable Modeling
Sturma, N., Drton, M., & München, T. U. (2024)
Deep learning in Ultrasound Imaging and beyond: from discriminative analysis to generative models
Marzola, F. (2024) · PORTO@Iris
STARFISH: faST Accuracy Recovery in pruned networks From Internal State HealingPreprint
Maon, S., Melamed, O., & Shamir, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.01126
“A related line of work uses representation alignment in self-supervised and unsupervised learning, where models learn useful embeddings by aligning related views, target networks, or even neural network weights without relying on manual labels [3, 10, 6].”
Graph signal processing technology based on multi-task processing model
Zhang, S., Kang, Y., & Guan, H. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251361844
Towards embodied agents for navigating and recognizing human activity
Hu, S. (n.d.) · Summit (Simon Fraser University)
Domain-Adaptive Self-Supervised Contrastive Hashing for Scalable Chest Radiograph Retrieval
Pan, S. (2026) · IEEE Access · doi:10.1109/access.2026.3713435
“Concurrently, the rapid advancement of self-supervised learning (SSL) has introduced novel opportunities for representation learning that are independent of human labels [14].”
Wang, Q., Meng, W., Gan, C., Yu, H., & Cheng, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109866
Huang, L., Deng, W., Li, N., & Zhang, R. (2026) · Circuits Systems and Signal Processing · doi:10.1007/s00034-026-03695-z
Liu, K., Xu, W., Li, Z., Hu, W., & Zhong, C. M. (2026) · Materials Today Energy · doi:10.1016/j.mtener.2026.102448
Vickers, P. G. J. (2024) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)
Ensembles of Informative Representations for Self-Supervised Learning
Polyzos, K. D., Traganitis, P. A., Singh, M. K., & Giannakis, G. B. (2024) · Machine learning for signal processing ... · doi:10.1109/mlsp58920.2024.10734769
“Recently, a new form of TL, termed self-supervised learning (SSL) has gained traction [13, 1, 5].”
BackgroundShalma., P., & Kanimozhi., N. (2026) · doi:10.1109/icosics70095.2026.11746766
“SimSiam [7] showed that self-supervised learning can be performed efficiently without momentum encoders, while Ericsson et al. [8] conducted a review of recent developments in SSL.”
Smart Energy System for Carbon Reduction and Energy Saving: Planning, Operation and Equipments
(2026) · Frontiers research topics · doi:10.3389/978-2-8325-5387-9
Towards Foundation Models for Relational Databases with Language Models and Graph Neural NetworksPreprint
Wu, J., Thapa, R. B., Nayyeri, M., Etteldorf, L., Finkenbeiner, M., Leeske, F., & Staab, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.16085
“Their effectiveness stems from self-supervised representation learning [10] combined with transfer learning across datasets and tasks [11].”
Zhang, J., Liu, X., Li, H., & Du, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-61333-9
“Recent advances in self-supervised learning offer a promising avenue for this purpose 22,23 .”
Chen, C., Bai, Y., & Amiri, M. (2026) · Scientific Reports · doi:10.1038/s41598-026-69479-2
Hernández, E. L. C. (2025) · Investigo repository of University of Vigo (University of Vigo) · doi:10.35869/11093/10153
Seo, S., & Kim, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133357
Self-Supervised Representation Learning for Time Series Classification
Tin, D. (2026) · UNSWorks (University of New South Wales, Sydney, Australia) · doi:10.26190/unsworks/32359
Kanatas, A.-N. (2025) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.30638
Zhang, Y., & Cheng, H. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835850
Self-supervised Representation Learning for Cell Event Recognition through Time Arrow PredictionPreprint
Chen, C., Namboodiri, V. P., & Sero, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.03924
“Compared to Gallusser et al. (2023), our work provides a comprehensive evaluation of cell event recognition using features maps learned from SSRL and offers insight into the application of SSRL for cell event recognition.”
BackgroundInfluentialExploiting social relationships for robust recommendation
Sun, Y. (2025) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/201653
Graph Reduction for Representation Learning
dos Santos, N. R. (2025) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.55.2025.tde-15012026-144922
Self-supervised Learning for Pathological Speech Analysis of Parkinson’s Disease
Uniyal, A. K., Liang, H., & Ojha, V. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-78937-3_7
Semi-Supervised Learning via Swapped Prediction for Communication Signal RecognitionPreprint
Wang, W., Liao, H., & Gan, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.08179
“In recent years, self-supervised learning has flourished [27].”
BackgroundLow data image based urban noise estimationPreprint
Sarma-Sarkar, P., & Saini, R. (2026) · Research Square · doi:10.21203/rs.3.rs-8807523/v1
(2025) · International journal for housing science and its applications. · doi:10.70517/ijhsa464280
Vali, E. A. (2025) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.30124
Contributions to Label-Efficient Learning in Computer Vision and Remote SensingPreprint
Pham, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.15973
Ibrahim, E. (2026) · PolyPublie (École Polytechnique de Montréal)
Karampinis, V. (2024) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.26927
Video Understanding by Design: How Datasets Shape Video ModelsPreprint
Wang, L., Li, S.-H., Koniusz, P., & Gao, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.09151
Metadata
- Authors
- Ericsson, L., Gouk, H., Loy, C. C., & Hospedales, T. M.
- Affiliations
- University of Edinburgh (GB)
- Nanyang Technological University (SG)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2022-05
- Volume
- 39
- Issue
- 3
- Pages
- 42-62
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W3207924272
- Cited by
- 433
- References
- 125
- Citations by year
- 2026: 89 · 2025: 105 · 2024: 132 · 2023: 86 · 2022: 20
- FWCI
- 28.22
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by-nd)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EP/S000631/1, EP/L016427/1, EP/R026173/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- self-supervised representation learning, pre-training, deep feature learning, image representation, video representation, sound representation, text representation, graph representation, computational cost, open problems
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.