Towards a robust R2D2 paradigm for radio-interferometric imaging: revisiting DNN training and architecture

• URL: http://arxiv.org/abs/2503.02554v1
• Date: Tue, 04 Mar 2025 12:26:45 GMT
• Title: Towards a robust R2D2 paradigm for radio-interferometric imaging: revisiting DNN training and architecture
• Authors: Amir Aghabiglou, Chung San Chu, Chao Tang, Arwa Dabbech, Yves Wiaux,
• Abstract summary: The R2D2 Deep Neural Network (DNN) series was recently introduced for image formation in radio interferometry.<n>We revisit R2D2 on the grounds of series convergence, training methodology, and DNN architecture.<n>We introduce a convergence criterion whereby the reconstruction process stops when the data residual is compatible with noise.
• Score: 3.5872880578234816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The R2D2 Deep Neural Network (DNN) series was recently introduced for image formation in radio interferometry. It can be understood as a learned version of CLEAN, whose minor cycles are substituted with DNNs. We revisit R2D2 on the grounds of series convergence, training methodology, and DNN architecture, improving its robustness in terms of generalisability beyond training conditions, capability to deliver high data fidelity, and epistemic uncertainty. Firstly, while still focusing on telescope-specific training, we enhance the learning process by randomising Fourier sampling integration times, incorporating multi-scan multi-noise configurations, and varying imaging settings, including pixel resolution and visibility-weighting scheme. Secondly, we introduce a convergence criterion whereby the reconstruction process stops when the data residual is compatible with noise, rather than simply using all available DNNs. This not only increases the reconstruction efficiency by reducing its computational cost, but also refines training by pruning out the data/image pairs for which optimal data fidelity is reached before training the next DNN. Thirdly, we substitute R2D2's early U-Net DNN with a novel architecture (U-WDSR) combining U-Net and WDSR, which leverages wide activation, dense connections, weight normalisation, and low-rank convolution to improve feature reuse and reconstruction precision. As previously, R2D2 was trained for monochromatic intensity imaging with the Very Large Array (VLA) at fixed $512 \times 512$ image size. Simulations on a wide range of inverse problems and a case study on real data reveal that the new R2D2 model consistently outperforms its earlier version in image reconstruction quality, data fidelity, and epistemic uncertainty.

Related papers

• The R2D2 Deep Neural Network Series for Scalable Non-Cartesian Magnetic Resonance Imaging [7.220567225059911]
  We introduce the R2D2 Deep Neural Network (DNN) series paradigm for fast and scalable image reconstruction from non-Cartesian k-space acquisitions in MRI. A series with only few DNNs achieves superior reconstruction quality over its unrolled incarnation R2D2-Net.
  arXiv  Detail & Related papers  (2025-03-12T17:24:47Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets. Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• R2D2 image reconstruction with model uncertainty quantification in radio astronomy [1.7249361224827533]
  The Residual-to-Residual'' (R2D2) approach was recently introduced for Radio-Interferometric (RI) imaging in astronomy. R2D2's reconstruction is formed as a series of residual images, iteratively estimated as outputs of Deep Neural Networks (DNNs) We study the robustness of the R2D2 image estimation process, by studying the uncertainty associated with its series of learned models.
  arXiv  Detail & Related papers  (2024-03-26T19:10:08Z)
• Scalable Non-Cartesian Magnetic Resonance Imaging with R2D2 [6.728969294264806]
  We propose a new approach for non-esian magnetic resonance image reconstruction. We leverage the "Residual to-Residual DNN series for high range imaging (R2D2)"
  arXiv  Detail & Related papers  (2024-03-26T17:45:06Z)
• The R2D2 deep neural network series paradigm for fast precision imaging in radio astronomy [1.7249361224827533]
  Recent image reconstruction techniques have remarkable capability for imaging precision, well beyond CLEAN's capability. We introduce a novel deep learning approach, dubbed "Residual-to-Residual DNN series for high-Dynamic range imaging" R2D2's capability to deliver high precision is demonstrated in simulation, across a variety image observation settings using the Very Large Array (VLA)
  arXiv  Detail & Related papers  (2024-03-08T16:57:54Z)
• RMT: Retentive Networks Meet Vision Transformers [55.76528783956601]
  Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years.<n>Self-Attention lacks explicit spatial priors and bears a quadratic computational complexity.<n>We propose RMT, a strong vision backbone with explicit spatial prior for general purposes.
  arXiv  Detail & Related papers  (2023-09-20T00:57:48Z)
• CLEANing Cygnus A deep and fast with R2D2 [1.7249361224827533]
  A novel deep learning paradigm for synthesis imaging by radio interferometry in astronomy was recently proposed, dubbed "Residual-to-Residual DNN series for high-Dynamic range imaging" (R2D2) We show that R2D2's learning approach enables delivering high-precision imaging, superseding the resolution of CLEAN, and matching the precision of modern optimization and plug-and-play algorithms, respectively uSARA and AIRI.
  arXiv  Detail & Related papers  (2023-09-06T18:11:09Z)
• Learning Detail-Structure Alternative Optimization for Blind Super-Resolution [69.11604249813304]
  We propose an effective and kernel-free network, namely DSSR, which enables recurrent detail-structure alternative optimization without blur kernel prior incorporation for blind SR. In our DSSR, a detail-structure modulation module (DSMM) is built to exploit the interaction and collaboration of image details and structures. Our method achieves the state-of-the-art against existing methods.
  arXiv  Detail & Related papers  (2022-12-03T14:44:17Z)
• GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
  Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
  arXiv  Detail & Related papers  (2022-07-18T06:01:29Z)
• A New Backbone for Hyperspectral Image Reconstruction [90.48427561874402]
  3D hyperspectral image (HSI) reconstruction refers to inverse process of snapshot compressive imaging. Proposal is for a Spatial/Spectral Invariant Residual U-Net, namely SSI-ResU-Net. We show that SSI-ResU-Net achieves competing performance with over 77.3% reduction in terms of floating-point operations.
  arXiv  Detail & Related papers  (2021-08-17T16:20:51Z)
• Image Restoration by Deep Projected GSURE [115.57142046076164]
  Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
  arXiv  Detail & Related papers  (2021-02-04T08:52:46Z)

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.