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 Performance with Multi-Crop Strategies

This chapter explores the impact of multi-crop strategies on self-supervised learning methods, particularly in relation to ImageNet performance. It highlights the significance of data augmentation techniques and their evolution, showcasing how specific augmentation sequences can lead to substantial improvements in model outcomes.

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