# A survey on Self Supervised learning approaches for improving Multimodal representation learning

arXiv: https://arxiv.org/abs/2210.11024 · HTML: https://mlsanity.com/paper/2210.11024/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 5 of 5)

- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models](https://mlsanity.com/paper/1711.06420/) (2017)
- [Self-Supervised learning with cross-modal transformers for emotion recognition](https://mlsanity.com/paper/2011.10652/) (2020)

## Built on by (most cited first, 2 of 2)

- [P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds](https://mlsanity.com/paper/2307.14726/) (2023)
- [Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities](https://mlsanity.com/paper/2406.05496/) (2024)

## Abstract (arXiv)

Recently self supervised learning has seen explosive growth and use in variety of machine learning tasks because of its ability to avoid the cost of annotating large-scale datasets. This paper gives an overview for best self supervised learning approaches for multimodal learning. The presented approaches have been aggregated by extensive study of the literature and tackle the application of self supervised learning in different ways. The approaches discussed are cross modal generation, cross modal pretraining, cyclic translation, and generating unimodal labels in self supervised fashion.