Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
arXiv (Cornell University)(2023)
Abstract
Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the
synthesis of high-quality images. However, their inference process
characteristically requires numerous, potentially hundreds, of iterative steps,
which could exaggerate the problem of exposure bias due to the training and
inference discrepancy. Previous work has attempted to mitigate this issue by
perturbing inputs during training, which consequently mandates the retraining
of the DPM. In this work, we conduct a systematic study of exposure bias in DPM
and, intriguingly, we find that the exposure bias could be alleviated with a
novel sampling method that we propose, without retraining the model. We
empirically and theoretically show that, during inference, for each backward
time step t and corresponding state x̂_t, there might exist another
time step t_s which exhibits superior coupling with x̂_t. Based on
this finding, we introduce a sampling method named Time-Shift Sampler. Our
framework can be seamlessly integrated to existing sampling algorithms, such as
DDPM, DDIM and other high-order solvers, inducing merely minimal additional
computations. Experimental results show our method brings significant and
consistent improvements in FID scores on different datasets and sampling
methods. For example, integrating Time-Shift Sampler to F-PNDM yields a
FID=3.88, achieving 44.49% improvements as compared to F-PNDM, on CIFAR-10
with 10 sampling steps, which is more performant than the vanilla DDIM with 100
sampling steps. Our code is available at https://github.com/Mingxiao-Li/TS-DPM.
MoreTranslated text
Key words
diffusion models,exposure bias
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined