[Self-Supervised Learning] Review: Bootstrap Your Own Latent -A New Approach to Self-Supervised Learning

Performance of BYOL on ImageNet

Description of BYOL

Mean squared error between the normalized predictions and target projections
Appendix A. Algorithm

Intuitions on BYOL’s behavior

Building intuitions with ablations

Decrease in top-1 accuracy of BYOL and reproduction of SimCLR, under linear evaluation on ImageNet
Ablations with top-1 accuracy at 300 epochs under linear evaluation on ImageNet
InfoNCE objective

Conclusion

--

--

AI researcher at Promedius Inc. Especially interested in theoretical physics, mathematics and deep learning.

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Seungmin Ha

Seungmin Ha

AI researcher at Promedius Inc. Especially interested in theoretical physics, mathematics and deep learning.