Uncertainty quantification for fast reconstruction methods using augmented equivariant bootstrap: Application to radio interferometry

• URL: http://arxiv.org/abs/2410.23178v2
• Date: Mon, 02 Dec 2024 10:51:10 GMT
• Title: Uncertainty quantification for fast reconstruction methods using augmented equivariant bootstrap: Application to radio interferometry
• Authors: Mostafa Cherif, Tobías I. Liaudat, Jonathan Kern, Christophe Kervazo, Jérôme Bobin,
• Abstract summary: Next-generation radio interferometers like the Square Kilometer Array promise to revolutionise our radio astronomy capabilities. The unprecedented volume of data these devices generate requires fast and accurate image reconstruction algorithms to solve the ill-posed radio interferometric imaging problem. We propose an unsupervised technique based on a conformalized version of a radio-augmented equivariant bootstrapping method, which allows us to quantify uncertainties for fast reconstruction methods.
• Score: 2.8311497176067104
• License:
• Abstract: The advent of next-generation radio interferometers like the Square Kilometer Array promises to revolutionise our radio astronomy observational capabilities. The unprecedented volume of data these devices generate requires fast and accurate image reconstruction algorithms to solve the ill-posed radio interferometric imaging problem. Most state-of-the-art reconstruction methods lack trustworthy and scalable uncertainty quantification, which is critical for the rigorous scientific interpretation of radio observations. We propose an unsupervised technique based on a conformalized version of a radio-augmented equivariant bootstrapping method, which allows us to quantify uncertainties for fast reconstruction methods. Noticeably, we rely on reconstructions from ultra-fast unrolled algorithms. The proposed method brings more reliable uncertainty estimations to our problem than existing alternatives.

Related papers

• Radio Map Estimation via Latent Domain Plug-and-Play Denoising [24.114418244026957]
  Radio map estimation (RME) aims to reconstruct the strength of radio interference across different domains (e.g., space and frequency) The proposed method exploits the underlying physical structure of radio maps and proposes an ADMMnoises in a latent domain. This design significantly improves computational efficiency and enhances noise robustness.
  arXiv  Detail & Related papers  (2025-01-23T08:42:24Z)
• Deep priors for satellite image restoration with accurate uncertainties [4.879530644978008]
  We propose a generic method involving a single network to restore images from several sensors. VBLE-xz is a scalable method to get realistic posterior samples and accurate uncertainties. SatDPIR is a compelling alternative to direct inversion methods when uncertainty is not required.
  arXiv  Detail & Related papers  (2024-12-05T12:56:03Z)
• RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge [66.33067693672696]
  This paper addresses the critical problem of interference rejection in radio-frequency (RF) signals using a novel, data-driven approach. First, we present an insightful signal model that serves as a foundation for developing and analyzing interference rejection algorithms. Second, we introduce the RF Challenge, a publicly available dataset featuring diverse RF signals along with code templates. Third, we propose novel AI-based rejection algorithms, specifically architectures like UNet and WaveNet, and evaluate their performance across eight different signal mixture types.
  arXiv  Detail & Related papers  (2024-09-13T13:53:41Z)
• Instant Uncertainty Calibration of NeRFs Using a Meta-calibrator [60.47106421809998]
  We introduce the concept of a meta-calibrator that performs uncertainty calibration for NeRFs with a single forward pass. We show that the meta-calibrator can generalize on unseen scenes and achieves well-calibrated and state-of-the-art uncertainty for NeRFs.
  arXiv  Detail & Related papers  (2023-12-04T21:29:31Z)
• Scalable Bayesian uncertainty quantification with data-driven priors for radio interferometric imaging [5.678038945350452]
  Next-generation radio interferometrics have the potential to unlock scientific discoveries thanks to their unprecedented angular resolution and sensitivity. One key to unlocking their potential resides in handling the deluge and complexity of incoming data. This work proposes a method coined QuantifAI to address uncertainty quantification in radio-interferometric imaging.
  arXiv  Detail & Related papers  (2023-11-30T19:00:02Z)
• Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification [1.1744028458220426]
  We present a novel approach to transcranial ultrasound computed tomography that utilizes normalizing flows to improve the speed of imaging. We make use of a physics-informed summary statistic to incorporate the known ultrasound physics with the goal of compressing large incoming observations.
  arXiv  Detail & Related papers  (2023-03-06T20:13:41Z)
• Towards performant and reliable undersampled MR reconstruction via diffusion model sampling [67.73698021297022]
  DiffuseRecon is a novel diffusion model-based MR reconstruction method. It guides the generation process based on the observed signals. It does not require additional training on specific acceleration factors.
  arXiv  Detail & Related papers  (2022-03-08T02:25:38Z)
• Denoising Diffusion Restoration Models [110.1244240726802]
  Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
  arXiv  Detail & Related papers  (2022-01-27T20:19:07Z)
• Radio-Assisted Human Detection [61.738482870059805]
  We propose a radio-assisted human detection framework by incorporating radio information into the state-of-the-art detection methods. We extract the radio localization and identifer information from the radio signals to assist the human detection. Experiments on the simulative Microsoft COCO dataset and Caltech pedestrian datasets show that the mean average precision (mAP) and the miss rate can be improved with the aid of radio information.
  arXiv  Detail & Related papers  (2021-12-16T09:53:41Z)
• Simultaneous Reconstruction and Uncertainty Quantification for Tomography [0.0]
  In the absence of ground truth, quantifying the solution quality is highly desirable but under-explored. In this work, we address this challenge through Gaussian process modeling to flexibly and explicitly incorporate prior knowledge of sample features and experimental noises. Our proposed method yields not only comparable reconstruction to existing practical reconstruction methods but also an efficient way of quantifying solution uncertainties.
  arXiv  Detail & Related papers  (2021-03-29T18:16:57Z)
• Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction [63.202627467245584]
  We introduce a Bayesian variational framework to quantify the model-immanent (epistemic) uncertainty. We demonstrate that our approach yields competitive results for undersampled MRI reconstruction.
  arXiv  Detail & Related papers  (2021-02-12T18:08:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.