mlsanityData to 7 Oct 2026

Unsupervised Knowledge-Transfer for Learned Image Reconstruction

arXiv 2107.02572 ↗First posted 6 Jul 2021eess.IV cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep learning-based image reconstruction approaches have demonstrated impressive empirical performance in many imaging modalities. These approaches usually require a large amount of high-quality paired training data, which is often not available in medical imaging. To circumvent this issue we develop a novel unsupervised knowledge-transfer paradigm for learned reconstruction within a Bayesian framework. The proposed approach learns a reconstruction network in two phases. The first phase trains a reconstruction network with a set of ordered pairs comprising of ground truth images of ellipses and the corresponding simulated measurement data. The second phase fine-tunes the pretrained network to more realistic measurement data without supervision. By construction, the framework is capable of delivering predictive uncertainty information over the reconstructed image. We present extensive experimental results on low-dose and sparse-view computed tomography showing that the approach is competitive with several state-of-the-art supervised and unsupervised reconstruction techniques. Moreover, for test data distributed differently from the training data, the proposed framework can significantly improve reconstruction quality not only visually, but also quantitatively in terms of PSNR and SSIM, when compared with learned methods trained on the synthetic dataset only.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 42 of its 84 references that are in the map. First posted on arXiv 6 Jul 2021.

Builds on

42 of 84 references.

References · 42

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2018Group Normalizationcited by 1,514
  7. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  8. 2017Deep Image Priorcited by 1,097
  9. 2015Weight Uncertainty in Neural Networkscited by 554
  10. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  11. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  12. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
30 more
  1. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  2. 2018Rethinking ImageNet Pre-trainingcited by 376
  3. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 366
  4. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  5. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  6. 2017Learned Primal-dual Reconstructioncited by 251
  7. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  8. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  9. 2019Practical Deep Learning with Bayesian Principlescited by 158
  10. 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
  11. 2020Test-Time Adaptable Neural Networks for Robust Medical Image Segmentationcited by 102
  12. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 86
  13. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 85
  14. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  15. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  16. 2017A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networkscited by 43
  17. 2017Recurrent Inference Machines for Solving Inverse Problemscited by 33
  18. 2017Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MRcited by 31
  19. 2017Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolutioncited by 29
  20. 2018Regularization by architecture: A deep prior approach for inverse problemscited by 26
  21. 2020Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigmscited by 23
  22. 2021Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imagingcited by 18
  23. 2021Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancementcited by 17
  24. 2019Fidelity Imposed Network Edit (FINE) for Solving Ill-Posed Image Reconstructioncited by 16
  25. 2019Higher-order total variation approaches and generalisationscited by 14
  26. 2020Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMMcited by 13
  27. 2019The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methodscited by 12
  28. 2020Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descentcited by 9
  29. 2020Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstructioncited by 6
  30. 2020Noise2Filter: fast, self-supervised learning and real-time reconstruction for 3D Computed Tomographycited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 0; 2023: 2.

4 papers.

  1. 2021An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstructioncited by 16
  2. 2021Deep Bayesian inference for seismic imaging with taskscited by 12
  3. 2023DRIP: Deep Regularizers for Inverse Problemscited by 7
  4. 2023Electrical Impedance Tomography with Deep Calder'on Methodcited by 3