Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Emerging Properties in Self-Supervised Vision Transformers - Paper Explained

Aleksa Gordić - The AI Epiphany via YouTube

Start learning Write review
Coursera Ad

AI, Data Science & Cloud Certificates from Google, IBM & Meta

Learn More → OpenLearning Ad

Future-Proof Your Career: AI Manager Masterclass

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This video explains DINO, a self-supervised learning method for vision transformers, using visual intuition and a pseudocode walkthrough. It covers multi-crop training, the teacher network, attention maps, emergent segmentation masks, feature quality, ablations, and representation collapse.

Syllabus

DINO main ideas, attention maps explained
DINO explained in depth
Pseudocode walk-through
Multi-crop and local-to-global correspondence
More details on the teacher network
Results
Ablations
Collapse analysis
Features visualized and outro

Taught by

Aleksa Gordić - The AI Epiphany

Reviews

Start your review of Emerging Properties in Self-Supervised Vision Transformers - Paper Explained

Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.