Lookahead Diffusion Probabilistic Models for Refining Mean Estimation
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 00, pp. 1421-1429
- Issue Date:
- 2023-06-24
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 1665743.pdf | Published version | 274.47 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
We propose lookahead diffusion probabilistic models LA DPMs to exploit the correlation in the outputs of the deep neural networks DNNs over subsequent timesteps in diffusion probabilistic models DPMs to refine the mean estimation of the conditional Gaussian distributions in the backward process A typical DPM first obtains an estimate of the original data sample x by feeding the most recent state z i and index i into the DNN model and then computes the mean vector of the conditional Gaussian distribution for z i 1 We propose to calculate a more accurate estimate for x by performing extrapolation on the two estimates of x that are obtained by feeding z i 1 i 1 and z i i into the DNN model The extrapolation can be easily integrated into the backward process of existing DPMs by introducing an additional connection over two consecutive timesteps and fine tuning is not required Extensive experiments showed that plugging in the additional connection into DDPM DDIM DEIS S PNDM and high order DPM Solvers leads to a significant performance gain in terms of Fr chet inception distance FID score Our implementation is available at https github com guoqiang zhang x LA DPM
Please use this identifier to cite or link to this item: