ML Anthology

Structured Uncertainty Prediction Networks

Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill D. F. Campbell, Ivor Simpson
CVPR 2018
doi:10.1109/CVPR.2018.00574 /cvpr/2018/dorta2018cvpr-structured/

Abstract

This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image. Previous approaches have been mostly limited to predicting diagonal covariance matrices. Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation. We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.

PDF CVPR Semantic Scholar

Cite

Text

Dorta et al. "Structured Uncertainty Prediction Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00574

Markdown

[Dorta et al. "Structured Uncertainty Prediction Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/dorta2018cvpr-structured/) doi:10.1109/CVPR.2018.00574

BibTeX

@inproceedings{dorta2018cvpr-structured,
  title     = {{Structured Uncertainty Prediction Networks}},
  author    = {Dorta, Garoe and Vicente, Sara and Agapito, Lourdes and Campbell, Neill D. F. and Simpson, Ivor},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00574},
  url       = {https://mlanthology.org/cvpr/2018/dorta2018cvpr-structured/}
}