YoVDO

Elucidating the Design Space of Diffusion-Based Generative Models

Offered By: Finnish Center for Artificial Intelligence FCAI via YouTube

Tags

Diffusion Models Courses Machine Learning Courses Computer Vision Courses Neural Networks Courses Image Synthesis Courses Generative AI Courses ImageNet Courses CIFAR-10 Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the intricacies of diffusion-based generative models in this comprehensive conference talk presented at NeurIPS 2022. Delve into a newly proposed design space that simplifies the theory and practice of these models by clearly separating concrete design choices. Discover improvements to sampling and training processes, as well as score network preconditioning, leading to state-of-the-art results in both class-conditional and unconditional settings for CIFAR-10. Learn how these advancements significantly enhance efficiency and quality of pre-trained score networks, including a notable improvement in ImageNet-64 model performance. Gain insights from Miika Aittala, a Senior Research Scientist at NVIDIA Research, as he shares his expertise in neural generative modeling, image processing, and realistic image synthesis in computer graphics.

Syllabus

Miika Aittala: Elucidating the Design Space of Diffusion-Based Generative Models


Taught by

Finnish Center for Artificial Intelligence FCAI

Related Courses

Computer Vision for Data Scientists
LinkedIn Learning
AlexNet and ImageNet Explained
James Briggs via YouTube
Do ImageNet Classifiers Generalize to ImageNet? - Analyzing ML Progress and Challenges
Paul G. Allen School via YouTube
Fast and Accurate Deep Neural Networks Training
Paul G. Allen School via YouTube
Analysis of Large-Scale Visual Recognition - Bay Area Vision Meeting
Meta via YouTube