mlsanityData to 7 Oct 2026

Structured Uncertainty Prediction Networks

arXiv 1802.07079 ↗First posted 20 Feb 2018stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 7; 2023: 6; 2024: 4; 2025: 7; 2026: 5.

34 papers.

Sort:

By area:

  1. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  2. 2024Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariancecited by 42
  3. 2021Interpretable Unsupervised Diversity Denoising and Artefact Removalcited by 26
  4. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  5. 2021Collaborative Uncertainty in Multi-Agent Trajectory Forecastingcited by 17
  6. 2023Learning a Depth Covariance Functioncited by 16
  7. 2023Uncertainty Quantification via Neural Posterior Principal Componentscited by 16
  8. 2022Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecastingcited by 13
  9. 2021Bayesian multiscale deep generative model for the solution of high-dimensional inverse problemscited by 12
  10. 2022VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimationcited by 9
  11. 2022Learning Structured Gaussians to Approximate Deep Ensemblescited by 8
  12. 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detectioncited by 7
22 more
  1. 2022MILD: Multimodal Interactive Latent Dynamics for Learning Human-Robot Interactioncited by 6
  2. 2023GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detectioncited by 5
  3. 2021Covariance Prediction via Convex Optimizationcited by 4
  4. 2022Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariancecited by 4
  5. 2023TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regressioncited by 4
  6. 2024Hierarchical Uncertainty Exploration via Feedforward Posterior Treescited by 4
  7. 2022Structured Uncertainty in the Observation Space of Variational Autoencoderscited by 3
  8. 2023Uncertainty Visualization via Low-Dimensional Posterior Projectionscited by 3
  9. 2024GUIDE-VAE: Advancing Data Generation with User Information and Pattern Dictionariescited by 3
  10. 2025Feature Hallucination for Self-supervised Action Recognitioncited by 3
  11. 2025Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regressioncited by 2
  12. 2025Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentrationcited by 2
  13. 2024Deep priors for satellite image restoration with accurate uncertaintiescited by 1
  14. 2026Toward generative machine learning for boosting ensembles of climate simulationscited by 1
  15. 2022Variational Heteroscedastic Volatility Modelcited by 0
  16. 2025Likelihood-Free Variational Autoencoderscited by 0
  17. 2025SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimescited by 0
  18. 2025Structured Uncertainty Similarity Score (SUSS): Learning a Probabilistic, Interpretable, Perceptual Metric Between Imagescited by 0
  19. 2026Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Imagescited by 0
  20. 2026Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registrationcited by 0
  21. 2026Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictionscited by 0
  22. 2026It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spacescited by 0