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

Advances in Self-Supervised Learning

This chapter explores innovative self-supervised learning techniques for visual feature representation, such as online clustering and multi-scale cropping. It highlights the effectiveness of the SWAV method in extracting image features without labels, enhancing performance on tasks like image recognition. The discussion includes challenges and advancements in clustering algorithms, questioning traditional pairwise methods and offering insights into future directions for unsupervised learning.

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