Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders

19 Feb 2022  ·  Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou ·

Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly because it needs many forward and reverse steps. We propose a faster and cheaper approach that adds noise not until the data become pure random noise, but until they reach a hidden noisy data distribution that we can confidently learn. Then, we use fewer reverse steps to generate data by starting from this hidden distribution that is made similar to the noisy data. We reveal that the proposed model can be cast as an adversarial auto-encoder empowered by both the diffusion process and a learnable implicit prior. Experimental results show even with a significantly smaller number of reverse diffusion steps, the proposed truncated diffusion probabilistic models can provide consistent improvements over the non-truncated ones in terms of performance in both unconditional and text-guided image generations.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation CIFAR-10 TDPM+ (TTrunc=99) FID 2.83 # 36
Recall 0.58 # 3
NFE 100 # 15
Text-to-Image Generation COCO TLDM FID 6.29 # 8
Text-to-Image Generation CUB TLDM FID 6.72 # 1
Image Generation LSUN Bedroom 256 x 256 TDPM+ (TTrunc=99) FID 1.88 # 3
NFE 100 # 1
Image Generation LSUN Churches 256 x 256 TDPM+ (TTrunc=99) FID 3.98 # 11
NFE 100 # 2