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

Linus Ericsson

doi:10.1109/MSP.2021.3134634

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

2022-05-01

174

OA

AI

Timothy M. Hospedales

DOI：10.1109/MSP.2021.3134634

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Representation learning

Deep learning

Annotations

Computational efficiency

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

Abstract

Journal

Organization