YoVDO

Emerging Properties in Self-Supervised Vision Transformers - Facebook AI Research Explained

Offered By: Yannic Kilcher via YouTube

Tags

Computer Vision Courses Self-supervised Learning Courses Attention Mechanisms Courses Representation Learning Courses

Course Description

Overview

Explore the groundbreaking DINO system developed by Facebook AI Research in this comprehensive video lecture. Delve into the fusion of self-supervised learning for computer vision with the innovative Vision Transformer (ViT) architecture. Discover how DINO achieves impressive results without labels, including the direct interpretation of attention maps as segmentation maps and the use of obtained representations for image retrieval and zero-shot k-nearest neighbor classifiers. Learn about Vision Transformers, self-supervised learning for images, self-distillation techniques, and the process of building a teacher from a student using moving averages. Examine the DINO pseudocode, understand the rationale behind using cross-entropy loss, and analyze experimental results. Gain insights into the lecturer's hypothesis on DINO's effectiveness and conclude with a discussion on the implications of this research for the field of computer vision and artificial intelligence.

Syllabus

- Intro & Overview
- Vision Transformers
- Self-Supervised Learning for Images
- Self-Distillation
- Building the teacher from the student by moving average
- DINO Pseudocode
- Why Cross-Entropy Loss?
- Experimental Results
- My Hypothesis why this works
- Conclusion & Comments


Taught by

Yannic Kilcher

Related Courses

Introduction to Artificial Intelligence
Stanford University via Udacity
Computer Vision: The Fundamentals
University of California, Berkeley via Coursera
Computational Photography
Georgia Institute of Technology via Coursera
Einführung in Computer Vision
Technische Universität München (Technical University of Munich) via Coursera
Introduction to Computer Vision
Georgia Institute of Technology via Udacity