Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations
Abstract
In this work, we address the challenge of multi-task image generation with limited data for denoising diffusion probabilistic models (DDPM), a class of generative models that produce high-quality images by reversing a noisy diffusion process. We propose a novel method, SR-DDPM, that leverages representation-based techniques from few-shot learning to effectively learn from fewer samples across different tasks. Our method consists of a core meta architecture with shared parameters, i.e., task-specific layers with exclusive parameters. By exploiting the similarity between diverse data distributions, our method can scale to multiple tasks without compromising the image quality. We evaluate our method on standard image datasets and show that it outperforms both unconditional and conditional DDPM in terms of FID and SSIM metrics.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2023
- DOI:
- 10.48550/arXiv.2311.16353
- arXiv:
- arXiv:2311.16353
- Bibcode:
- 2023arXiv231116353P
- Keywords:
-
- Computer Science - Machine Learning;
- Computer Science - Artificial Intelligence;
- Computer Science - Computer Vision and Pattern Recognition;
- Electrical Engineering and Systems Science - Image and Video Processing;
- Electrical Engineering and Systems Science - Signal Processing