Pith. sign in

REVIEW 1 cited by

Noise2Self: Blind Denoising by Self-Supervision

Not yet reviewed by Pith; the record is open.

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 1901.11365 v2 pith:H62YJTBY submitted 2019-01-30 cs.CV cs.LGstat.ML

classification cs.CVcs.LGstat.ML
keywords datadenoisingindependencenoiseestimateexhibitsexploitframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only assumption is that the noise exhibits statistical independence across different dimensions of the measurement, while the true signal exhibits some correlation. For a broad class of functions ("$\mathcal{J}$-invariant"), it is then possible to estimate the performance of a denoiser from noisy data alone. This allows us to calibrate $\mathcal{J}$-invariant versions of any parameterised denoising algorithm, from the single hyperparameter of a median filter to the millions of weights of a deep neural network. We demonstrate this on natural image and microscopy data, where we exploit noise independence between pixels, and on single-cell gene expression data, where we exploit independence between detections of individual molecules. This framework generalizes recent work on training neural nets from noisy images and on cross-validation for matrix factorization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Optimal Weighted Convolution for Classification and Denosing

    cs.CV 2025-05 reject novelty 3.0 of 10

    A fixed spatial density mask applied to convolution kernels improves reported CIFAR-100 accuracy and DIV2K denoising PSNR without adding parameters.

Pith tools