Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

TL;DR

This paper provides a comprehensive review of self-supervised representation learning methods for multimodal and temporal data, highlighting their architectures, objectives, applications, and future challenges.

Contribution

It is the first review to systematically categorize and analyze multimodal SSRL methods specifically for temporal data across various modalities.

Findings

Categorization of SSRL methods and their key components

Comparison of models based on objectives and architectures

Identification of current weaknesses and future research directions

Abstract

Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in the field of computer vision, speech, natural language processing (NLP), and recently, with other types of modalities, including time series from sensors. The popularity of self-supervised learning is driven by the fact that traditional models typically require a huge amount of well-annotated data for training. Acquiring annotated data can be a difficult and costly process. Self-supervised methods have been introduced to improve the efficiency of training data through discriminative pre-training of models using supervisory signals that have been freely obtained from the raw data. Unlike existing reviews of SSRL that have pre-dominately focused upon methods in the fields of CV or NLP for a single modality, we aim to provide the first comprehensive review of multimodal self-supervised learning methods for temporal data. To this end, we 1) provide a comprehensive categorization of existing SSRL methods, 2) introduce a generic pipeline by defining the key components of a SSRL framework, 3) compare existing models in terms of their objective function, network architecture and potential applications, and 4) review existing multimodal techniques in each category and various modalities. Finally, we present existing weaknesses and future opportunities. We believe our work develops a perspective on the requirements of SSRL in domains that utilise multimodal and/or temporal data