Tutorial on Vision Transformers - Tutorial 3
Offered By: MICDE University of Michigan via YouTube
Course Description
Overview
Explore the intricacies of Vision Transformers in this comprehensive 49-minute tutorial presented by Bharath Ramsundar and Amal Sebastian at MICDE University of Michigan. Delve into the cutting-edge application of transformer architectures in computer vision tasks, gaining insights into their structure, functionality, and advantages over traditional convolutional neural networks. Learn about the key components of Vision Transformers, including self-attention mechanisms and positional encodings, and understand how these elements contribute to their remarkable performance in image recognition and classification tasks. Discover practical implementation techniques, best practices, and potential challenges when working with Vision Transformers, equipping yourself with valuable knowledge to leverage this powerful technology in your own computer vision projects.
Syllabus
Bharath Ramsundar & Amal Sebastian: Tutorial on Vision Transformers (Tutorial 3)
Taught by
MICDE University of Michigan
Related Courses
Vision Transformers Explained + Fine-Tuning in PythonJames Briggs via YouTube ConvNeXt- A ConvNet for the 2020s - Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube Do Vision Transformers See Like Convolutional Neural Networks - Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube Stable Diffusion and Friends - High-Resolution Image Synthesis via Two-Stage Generative Models
HuggingFace via YouTube Intro to Dense Vectors for NLP and Vision
James Briggs via YouTube