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

Exploring Synchron-Knob and Optimal Transport in Clustering

This chapter focuses on the Synchron-Knob algorithm within the realm of clustering and unsupervised learning, drawing connections to optimal transport theory. It highlights the method of balancing prototype assignments to avoid 'collapsing' while exploring the performance implications of soft versus hard clustering. The discussion also emphasizes how these concepts can enhance performance in machine learning tasks and the trade-offs involved with various clustering approaches.

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