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

Enhancing Stability in DeepCluster

This chapter explores the challenges encountered in integrating training improvements from the CIMCLR paper into DeepCluster, particularly focusing on stability issues during training. The speakers discuss their innovative solution of using clustered centroids and a learnable prototype system to enhance training effectiveness and adaptability.

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