Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 1,414

The DOI matches its Crossref record; 102 of the 102 references it cites were found in a registry or an index.

Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing

Open access
Monga, Vishal, Li, Yuelong, Eldar, Yonina C.·2021·IEEE Signal Processing Magazine

Abstract

Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. An emerging technique called algorithm unrolling, or unfolding, offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are widely used in signal processing and deep neural networks. Unrolling methods were first proposed to develop fast neural network approximations for sparse coding. More recently, this direction has attracted enormous attention, and it is rapidly growing in both theoretic investigations and practical applications. The increasing popularity of unrolled deep networks is due, in part, to their potential in developing efficient, high-performance (yet interpretable) network architectures from reasonably sized training sets.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/msp.2020.3016905

Cites

102 of 102 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 102 references

Research works printed but not linked: 16

  1. 10.5555/3157382.3157583 · doi:10.5555/3157382.3157583
  2. 10.5555/3327546.3327581 · doi:10.5555/3327546.3327581
  3. 10.5555/3294771.3294940 · doi:10.5555/3294771.3294940
  4. 10.1109/TIT.2016.2556683 · DOI
  5. 10.1109/LSP.2010.2042530 · doi:10.1109/lsp.2010.2042530
  6. timofte, 0, Proc Asian Conf Computer Vision, 111
  7. zhang, 0, Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration, Proc Int Conf Learning Representations
  8. genevay, 0, Learning generative models with Sinkhorn divergences, Proc 21st Int Conf Artificial Intelligence and Statistics, 1608
  9. patrini, 0, Sinkhorn AutoEncoders, Proc Conf Uncertainty Artificial Intelligence, 733
  10. 10.5555/3045118.3045281 · doi:10.5555/3045118.3045281
  11. long, 0, PDE-Net: Learning PDEs from data, Proc 35th Int Conf Machine Learning, 3208
  12. bau, 0, GAN dissection: Visualizing and understanding generative adversarial networks, Proc Int Conf Learning Representations
  13. 10.5555/3104322.3104374 · doi:10.5555/3104322.3104374
  14. 10.5555/2986459.2986472 · doi:10.5555/2986459.2986472
  15. papyan, 2017, Convolutional neural networks analyzed via convolutional sparse coding, J Mach Learn Res, 18, 1
  16. 10.5555/3122009.3242022 · doi:10.5555/3122009.3242022

Cited by

See all 1,414

Metadata

Authors
Monga, V., Li, Y., & Eldar, Y. C.
Venue
IEEE Signal Processing Magazine
Published
2021-03
Volume
38
Issue
2
Pages
18-44
ISSN
  • 1053-5888 (ISSN-L)
  • 1558-0792
OpenAlex
W2995038946
Cited by
1,414
References
102
FWCI
122.16
Type
journal article
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing. https://app.cochat.ai/papers/10.1109/msp.2020.3016905
The paper
Monga, V., Li, Y., & Eldar, Y. C. (2021). Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing. IEEE Signal Processing Magazine. https://doi.org/10.1109/msp.2020.3016905

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.