Pith. sign in

REVIEW 4 cited by

UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.01985 v4 pith:HDZORS6A submitted 2024-09-03 stat.ML cs.LGeess.SP

Julián Tachella , Mike Davies , Laurent Jacques This is my paper · ORCID
classification stat.MLcs.LGeess.SP
keywords methodsnoiseknowledgelearninglevelself-supervisedsureclass
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, many self-supervised learning methods for image reconstruction have been proposed that can learn from noisy data alone, bypassing the need for ground-truth references. Most existing methods cluster around two classes: i) Stein's Unbiased Risk Estimate (SURE) and similar approaches that assume full knowledge of the noise distribution, and ii) Noise2Self and similar cross-validation methods that require very mild knowledge about the noise distribution. The first class of methods tends to be impractical, as the noise level is often unknown in real-world applications, and the second class is often suboptimal compared to supervised learning. In this paper, we provide a theoretical framework that characterizes this expressivity-robustness trade-off and propose a new approach based on SURE, but unlike the standard SURE, does not require knowledge about the noise level. Throughout a series of experiments, we show that the proposed estimator outperforms other existing self-supervised methods on various imaging inverse problems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Fast Equivariant Imaging: Accelerating Unsupervised Learning and Model Adaptation via Inexact Splitting

    eess.IV 2025-07 conditional novelty 6.0 of 10

    Fast Equivariant Imaging trains unsupervised image reconstruction networks about ten times faster than standard Equivariant Imaging by alternating between a latent restoration step and a network update step.

  2. Self-supervised Conformal Prediction for Uncertainty Quantification in Imaging Problems

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A self-supervised conformal prediction method uses SURE estimates of reconstruction error, instead of ground truth, to calibrate prediction sets for linear image restoration problems.

  3. Domain Adaptation of Mismatched Proximal Denoiser for Plug-and-Play Image Reconstruction

    eess.IV 2026-07 conditional novelty 5.0 of 10

    For PnP-PGD, residual reconstruction error is bounded by average squared mismatch between the deployed denoiser and the target proximal map, motivating proximal-matching few-shot adaptation that outperforms MSE adapta...

  4. What is Adversarial Training for Diffusion Models?

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Diffusion models trained with an equivariant adversarial-smoothing regularizer tolerate heavy training-data corruption but lose image quality on clean data.

Pith tools