mlsanityData to 7 Oct 2026

Self-Supervised Learning from Noisy and Incomplete Data

arXiv 2601.03244 ↗First posted 6 Jan 2026stat.ML cs.LG eess.IVcited by 5

Not on the map. Why?

Abstract (arXiv)

Many important problems in science and engineering involve inferring a signal from noisy and/or incomplete observations, where the observation process is known. Historically, this problem has been tackled using hand-crafted regularization (e.g., sparsity, total-variation) to obtain meaningful estimates. Recent data-driven methods often offer better solutions by directly learning a solver from examples of ground-truth signals and associated observations. However, in many real-world applications, obtaining ground-truth references for training is expensive or impossible. Self-supervised learning methods offer a promising alternative by learning a solver from measurement data alone, bypassing the need for ground-truth references. This manuscript provides a comprehensive summary of different self-supervised methods for inverse problems, with a special emphasis on their theoretical underpinnings, and presents practical applications in imaging inverse problems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 58 of its 100 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

58 of 100 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  5. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  6. 2017Deep Image Priorcited by 1,097
  7. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 547
  8. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  9. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  10. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  11. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  12. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
38 more
  1. 2016Steerable CNNscited by 298
  2. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  3. 2017Learned Primal-dual Reconstructioncited by 251
  4. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 171
  5. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  6. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  7. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  8. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  9. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  10. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
  11. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  12. 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 94
  13. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  14. 2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 83
  15. 2024Learning Diffusion Priors from Observations by Expectation Maximizationcited by 60
  16. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  17. 2021Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurementscited by 56
  18. 2019Probabilistic Noise2Void: Unsupervised Content-Aware Denoisingcited by 51
  19. 2018Model-blind Video Denoising Via Frame-to-frame Trainingcited by 34
  20. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Datacited by 32
  21. 2023On the Posterior Distribution in Denoising: Application to Uncertainty Quantificationcited by 31
  22. 2022A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noisecited by 29
  23. 2022Sensing Theorems for Unsupervised Learning in Linear Inverse Problemscited by 28
  24. 2025DeepInverse: A Python package for solving imaging inverse problems with deep learningcited by 27
  25. 2021Interpretable Unsupervised Diversity Denoising and Artefact Removalcited by 26
  26. 2022Unsupervised Learning From Incomplete Measurements for Inverse Problemscited by 20
  27. 2021As if by magic: self-supervised training of deep despeckling networks with MERLINcited by 18
  28. 2021Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matchingcited by 18
  29. 2019Self-Supervised Physics-Based Deep Learning MRI Reconstruction Without Fully-Sampled Datacited by 17
  30. 2019Memory-efficient Learning for Large-scale Computational Imaging -- NeurIPS deep inverse workshopcited by 17
  31. 2021Speech Denoising Without Clean Training Data: A Noise2Noise Approachcited by 17
  32. 2023Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problemscited by 17
  33. 2021Adaptive Denoising via GainTuningcited by 16
  34. 2024UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimatecited by 16
  35. 2021Data fission: splitting a single data pointcited by 13
  36. 2024Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noisecited by 13
  37. 2019Extreme MRI: Large-Scale Volumetric Dynamic Imaging from Continuous Non-Gated Acquisitionscited by 12
  38. 2019The Practicality of Stochastic Optimization in Imaging Inverse Problemscited by 9

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoisingcited by 1
  2. 2026Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Imagescited by 0
  3. 2026SAGE: Subsurface AI-driven Geostatistical Extraction with proxy posteriorcited by 0
  4. 2026Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fieldscited by 0
  5. 2026Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problemscited by 0