Machine Learning Street Talk (MLST) cover image

SWaV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (Mathilde Caron)

Machine Learning Street Talk (MLST)

00:00

Boosting Self-Supervised Learning

This chapter explores the integration of technical advancements in self-supervised learning, showcasing a 4.2% performance boost on ImageNet. The discussion focuses on leveraging unlabeled data for model training, emphasizing effective evaluation through various downstream tasks while addressing challenges with conventional benchmarks.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app