CoChat

Self-Supervised Representation Learning: Introduction, advances, and challenges

Open access
Ericsson, Linus, Gouk, Henry, Loy, Chen Change, Hospedales, Timothy M. · 2022 · IEEE Signal Processing Magazine

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/msp.2021.3134634

Cites

111 of 112 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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”
    Influential
  • Attention Is All You Need

    Vaswani, 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].”
    Influential
  • ImageNet: 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.”
    Influential
  • BERT: 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].”
    Influential
  • An 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

Show all 112 references

Research works printed but not linked: 4

  1. 0, Youtube-8m A large and diverse labeled video dataset for video understanding research
  2. gokaslan, 2019, OpenWebText Corpus
  3. radford, 2019, Language Models are Unsupervised Multitask Learners
  4. goodfellow, 2016, Deep Learning

Cited by

Items 301–400 of 641

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
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.