PofoliaShared via Pofolia

arXiv (Cornell University)· 2022· Preprint

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods

Randall Balestriero, Yann LeCun

Short summary

A new framework unifies contrastive and non-contrastive self-supervised learning (SSL) methods, showing they correspond to spectral embedding techniques like Laplacian Eigenmaps and Multidimensional Scaling.

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: General Engineering

General EngineeringEngineering