Self-Supervised Multimodal Learning: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 5299-5318
DOI: 10.1109/tpami.2024.3429301 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Yongshuo Zong und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Supervised Machine Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 107-mal zitiert (Crossref) und nennt 200 Literaturangaben. Gefördert von: Yongshuo Zong is supported by the United Kingdom Research and Innovation, UKRI Centre for Doctoral Training in Biomedical AI at the University of Edinburgh.
Abstract (Originalsprache)
Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human annotations impedes scaling up models. Meanwhile, given the availability of large-scale unannotated data in the wild, self-supervised learning has become an attractive strategy to alleviate the annotation bottleneck. Building on these two directions, self-supervised multimodal learning (SSML) provides ways to learn from raw multimodal data. In this survey, we provide a comprehensive review of the state-of-the-art in SSML, in which we elucidate three major challenges intrinsic to self-supervised learning with multimodal data: 1) learning representations from multimodal data without labels, 2) fusion of different modalities, and 3) learning with unaligned data. We then detail existing solutions to these challenges. Specifically, we consider 1) objectives for learning from multimodal unlabeled data via self-supervision, 2) model architectures from the perspective of different multimodal fusion strategies, and 3) pair-free learning strategies for coarse-grained and fine-grained alignment. We also review real-world applications of SSML algorithms in diverse fields, such as healthcare, remote sensing, and machine translation. Finally, we discuss challenges and future directions for SSML.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Yongshuo Zong is supported by the United Kingdom Research and Innovation
- UKRI Centre for Doctoral Training in Biomedical AI at the University of Edinburgh
Zitieren
APA
Zong, Y., Aodha, O. M., & Hospedales, T. M. (2025). Self-Supervised Multimodal Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 5299-5318. https://doi.org/10.1109/tpami.2024.3429301
Vancouver
Zong Y, Aodha OM, Hospedales TM. Self-Supervised Multimodal Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):5299-5318. doi:10.1109/tpami.2024.3429301
BibTeX
@article{Zong2025,
author = {Zong, Yongshuo and Aodha, Oisin Mac and Hospedales, Timothy M},
title = {Self-Supervised Multimodal Learning: A Survey},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {7},
pages = {5299--5318},
doi = {10.1109/tpami.2024.3429301}
}
EUVIMED