Elucidating the Design Space of Diffusion-Based Generative Models
Offered By: Finnish Center for Artificial Intelligence FCAI via YouTube
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 ScientistsLinkedIn 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