Image Generation with Probabilistic Diffusion Models

Introduction:

1. DDPM - Diffusion Models Beat GANs on Image Synthesis (Machine Learning Research Paper Explained)

2. Lil Log What are Diffusion Models?

Papers:

[1]Denoising Diffusion Probabilistic Models

[2] DENOISING DIFFUSION IMPLICIT MODELS

[3]On Fast Sampling of Diffusion Probabilistic Models

Problem 1: what is the problem the two papers aim to solve, and why is this problem important or interesting? (5 points)

Problem 2: 1) summarize the three methods, including high-level ideas as well as technical details: the relevant details that are important to focus on (e.g., if there’s a model, define it; if there is a theorem, state it and explain why it’s important, etc) 2) what are the major differences of the three methods? (15 points)

Problem 3: implement DDPM [1] and test it on MNIST dataset. You need to generate samples and perform an interpolation experiment with your trained model. (30 points)

Reference code: [login to view URL]

Problem 4: implement DDIM [2] and test it on MNIST dataset. You need to generate samples and perform an interpolation experiment with your trained model. (30 points)

Reference code: [login to view URL]

Problem 5: implement FastDPM [3] and test it on MNIST dataset. You need to generate samples and perform an interpolation experiment with your trained model. (30 points)

Reference code: [login to view URL]

Problem 6: visualize the denoising process on CIFAR-10 and CelebA-HQ datasets for all three methods, respectively (e.g., Figure 6 of [1]). You are allowed to use the pre-trained models provided by the authors. (20 points)

Problem 7: interpolate source images on CIFAR-10/100 and CelebA-HQ datasets with all three methods, respectively (e.g., Figure 8 of [1]). You are allowed to use the pre-trained models provided by the authors. (20 points)

Problem 8 (bonus): is it possible to use diffusion models to generate text data? If you think that it is impossible or tough, explain why; If you think that it is possible, you will get bonus credits by realizing the idea. (80 points)

Python Machine Learning (ML) Pytorch Keras Tensorflow

Project ID: #32234437

About the project