References

A Simple Framework for Contrastive Learning of Visual Representations

Ting Chen, Simon Kornblith, Mohammad Norouzi, & Geoffrey Hinton (2020)

arXiv.

DOI: https://doi.org/10.48550/arxiv.2002.05709

Abstract. Introduces SimCLR, a contrastive self-supervised learning framework that learns visual representations by maximising agreement between differently augmented views of the same image. SimCLR closed much of the gap between self-supervised and supervised ImageNet features.

Tags: self-supervised contrastive-learning vision

This site is currently in Beta. Contact: Chris Paton

Textbook of Usability · Textbook of Digital Health

Auckland Maths and Science Tutoring

AI tools used: Claude (research, coding, text), ChatGPT (diagrams, images), Grammarly (editing).