\dm_csml_event_details UCL ELLIS

Contrastive Self-Supervised Learning and Potential Limitations


Speaker

Ting Chen

Affiliation

Google Brain

Date

Friday, 03 December 2021

Time

15:00-16:00

Location

Zoom

Link

https://ucl.zoom.us/j/96937626478

Event series

Jump Trading/ELLIS CSML Seminar Series

Abstract

Abstract: Contrastive learning has achieved some impressive results recently for learning visual representations from images without human supervision. As an example, SimCLR (and many other subsequent work) is able to learn representations that rival or outperform supervised learning on ImageNet without using any labels. In this talk, I will cover a few topics on contrastive self-supervised learning, including an overview of a few basic contrastive methods, important factors in contrastive learning, simple approaches for semi-supervised learning (with lots of unlabeled images and a few labeled images), some intriguing properties and potential limitations of existing contrastive learning methods.

Biography