PofoliaShared via Pofolia

arXiv (Cornell University)· 2020· Preprint

A Simple Framework for Contrastive Learning of Visual Representations

Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. Hinton

Short summary

SimCLR, a new framework for self-supervised visual representation learning, achieves 76.5% top-1 accuracy on ImageNet using a linear classifier, surpassing prior methods by 7% and matching supervised ResNet-50 performance.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Artificial Intelligence

Artificial IntelligenceComputer Science