Uncertainty Quantification in Computational Imaging
Abstract:
This session aims to cover recent advances in the theory and methods of uncertainty quantification for computational imaging, including but not limited to approaches that involve learning-based methodologies.
Organiser & chair: Mujdat Cetin
Session Schedule
- 17:30 - 17:50
- Invited talk: Does your computational imaging algorithm know what it doesn’t know?
- Mujdat Cetin
- 17:50 - 18:10
- Invited talk: Testing Semantic Importance via Betting
- Jeremias Sulam
- 18:10 - 18:30
- Invited talk: Uncertainty Visualization via Posterior PCA and Posterior Hierarchical Trees
- Tomer Michaeli
- 18:30 - 18:50
- Invited talk: Estimating Epistemic and Aleatoric Uncertainty with a Single Model
- Christopher Metzler
- 18:50 - 19:10
- Invited talk: Generalized Locality for Robust, Lightweight Imaging Architectures
- Ivan Dokmanić
- 19:10 - 20:30
- Steering Committee Poster: Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction
- Philip Schniter
- 19:10 - 20:30
- Invited poster: Posterior Variance Based Error Quantification in Imaging
- Andreas Habring*
- 19:10 - 20:30
- Invited poster: Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
- Amit Pal Kohli*
- 19:10 - 20:30
- Contributed poster: Intriguing Properties of Modern GANs
- Roy Friedman*
- 19:10 - 20:30
- Contributed poster: Uncertainty Quantification for Fast Reconstruction Methods Using Augmented Equivariant Bootstrap: Application to Radio Interferometry
- Tobias Ignacio Liaudat