Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problems (2305.10124v3)

Published 17 May 2023 in cs.CV

Abstract: Uncertainty quantification for inverse problems in imaging has drawn much attention lately. Existing approaches towards this task define uncertainty regions based on probable values per pixel, while ignoring spatial correlations within the image, resulting in an exaggerated volume of uncertainty. In this paper, we propose PUQ (Principal Uncertainty Quantification) -- a novel definition and corresponding analysis of uncertainty regions that takes into account spatial relationships within the image, thus providing reduced volume regions. Using recent advancements in generative models, we derive uncertainty intervals around principal components of the empirical posterior distribution, forming an ambiguity region that guarantees the inclusion of true unseen values with a user-defined confidence probability. To improve computational efficiency and interpretability, we also guarantee the recovery of true unseen values using only a few principal directions, resulting in more informative uncertainty regions. Our approach is verified through experiments on image colorization, super-resolution, and inpainting; its effectiveness is shown through comparison to baseline methods, demonstrating significantly tighter uncertainty regions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Image-to-image regression with distribution-free uncertainty quantification and applications in imaging. In International Conference on Machine Learning, pages 717–730. PMLR, 2022.
  2. Conffusion: Confidence intervals for diffusion models. arXiv preprint arXiv:2211.09795, 2022.
  3. Regression quantiles. Econometrica: journal of the Econometric Society, pages 33–50, 1978.
  4. Semantic uncertainty intervals for disentangled latent spaces. arXiv preprint arXiv:2207.10074, 3, 2022.
  5. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
  6. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, 34:8780–8794, 2021.
  7. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning, pages 2256–2265. PMLR, 2015.
  8. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  9. Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res., 23(47):1–33, 2022.
  10. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  11. Palette: Image-to-image diffusion models. In ACM SIGGRAPH 2022 Conference Proceedings, pages 1–10, 2022.
  12. Algorithmic learning in a random world, volume 29. Springer, 2005.
  13. Distribution-free predictive inference for regression. Journal of the American Statistical Association, 113(523):1094–1111, 2018.
  14. A gentle introduction to conformal prediction and distribution-free uncertainty quantification. arXiv preprint arXiv:2107.07511, 2021.
  15. Learn then test: Calibrating predictive algorithms to achieve risk control. arXiv preprint arXiv:2110.01052, 2021.
  16. A comprehensive analysis of deep regression. IEEE transactions on pattern analysis and machine intelligence, 42(9):2065–2081, 2019.
  17. Generalized deep image to image regression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5609–5619, 2017.
  18. Attribute2image: Conditional image generation from visual attributes. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 776–791. Springer, 2016.
  19. Draw: A recurrent neural network for image generation. In International conference on machine learning, pages 1462–1471. PMLR, 2015.
  20. Generative adversarial networks. Communications of the ACM, 63(11):139–144, 2020.
  21. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, 32, 2019.
  22. Solving linear inverse problems using the prior implicit in a denoiser. arXiv preprint arXiv:2007.13640, 2020.
  23. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
  24. Stochastic image denoising by sampling from the posterior distribution. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1866–1875, 2021.
  25. Snips: Solving noisy inverse problems stochastically. Advances in Neural Information Processing Systems, 34:21757–21769, 2021.
  26. Denoising diffusion restoration models. arXiv preprint arXiv:2201.11793, 2022.
  27. Learning multi-scale local conditional probability models of images. arXiv preprint arXiv:2303.02984, 2023.
  28. Conformalized quantile regression. Advances in neural information processing systems, 32, 2019.
  29. Distributional conformal prediction. Proceedings of the National Academy of Sciences, 118(48):e2107794118, 2021.
  30. Conformal prediction using conditional histograms. Advances in Neural Information Processing Systems, 34:6304–6315, 2021.
  31. Nested conformal prediction and quantile out-of-bag ensemble methods. Pattern Recognition, 127:108496, 2022.
  32. Adaptive, distribution-free prediction intervals for deep networks. In International Conference on Artificial Intelligence and Statistics, pages 4346–4356. PMLR, 2020.
  33. Distribution-free, risk-controlling prediction sets. Journal of the ACM (JACM), 68(6):1–34, 2021.
  34. Conformal risk control. arXiv preprint arXiv:2208.02814, 2022.
  35. How to trust your diffusion model: A convex optimization approach to conformal risk control. In International Conference on Machine Learning, pages 33940–33960. PMLR, 2023.
  36. Yves Meyer. Orthonormal wavelets. In Wavelets: Time-Frequency Methods and Phase Space Proceedings of the International Conference, Marseille, France, December 14–18, 1987, pages 21–37. Springer, 1990.
  37. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196, 2017.
Citations (15)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now