Learned Greedy Method (LGM): A novel neural architecture for sparse coding and beyond
The fields of signal and image processing have been deeply influenced by the introduction of deep neural networks. Despite their impressive success, the architectures used in these solutions come with no clear justification, being “black box” machines that lack interpretability. A constructive remed...
Saved in:
| Published in: | Journal of visual communication and image representation Vol. 77; p. 103095 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Inc
01.05.2021
|
| Subjects: | |
| ISSN: | 1047-3203, 1095-9076 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The fields of signal and image processing have been deeply influenced by the introduction of deep neural networks. Despite their impressive success, the architectures used in these solutions come with no clear justification, being “black box” machines that lack interpretability. A constructive remedy to this drawback is a systematic design of networks by unfolding well-understood iterative algorithms. A popular representative of this approach is LISTA, evaluating sparse representations of processed signals. In this paper, we revisit this task and propose an unfolded version of a greedy pursuit algorithm for the same goal. More specifically, we concentrate on the well-known OMP algorithm, and introduce its unfolded and learned version. Key features of our Learned Greedy Method (LGM) are the ability to accommodate a dynamic number of unfolded layers, and a stopping mechanism based on representation error. We develop several variants of the proposed LGM architecture and demonstrate their flexibility and efficiency.
•Unfolding greedy sparse pursuit algorithms to deep neural networks, known as LGM.•Most of LGM features are well justified from sparse representation point of view.•Learning the parameters of LGM in a supervised fashion via back-propagation.•Demonstrating LGM capabilities in various experiments. |
|---|---|
| AbstractList | The fields of signal and image processing have been deeply influenced by the introduction of deep neural networks. Despite their impressive success, the architectures used in these solutions come with no clear justification, being “black box” machines that lack interpretability. A constructive remedy to this drawback is a systematic design of networks by unfolding well-understood iterative algorithms. A popular representative of this approach is LISTA, evaluating sparse representations of processed signals. In this paper, we revisit this task and propose an unfolded version of a greedy pursuit algorithm for the same goal. More specifically, we concentrate on the well-known OMP algorithm, and introduce its unfolded and learned version. Key features of our Learned Greedy Method (LGM) are the ability to accommodate a dynamic number of unfolded layers, and a stopping mechanism based on representation error. We develop several variants of the proposed LGM architecture and demonstrate their flexibility and efficiency.
•Unfolding greedy sparse pursuit algorithms to deep neural networks, known as LGM.•Most of LGM features are well justified from sparse representation point of view.•Learning the parameters of LGM in a supervised fashion via back-propagation.•Demonstrating LGM capabilities in various experiments. |
| ArticleNumber | 103095 |
| Author | Simon, Dror Elad, Michael Khatib, Rajaei |
| Author_xml | – sequence: 1 givenname: Rajaei orcidid: 0000-0002-1376-1840 surname: Khatib fullname: Khatib, Rajaei email: rajaee95@technion.ac.il – sequence: 2 givenname: Dror orcidid: 0000-0002-9056-2933 surname: Simon fullname: Simon, Dror email: dror.simon@cs.technion.ac.il – sequence: 3 givenname: Michael surname: Elad fullname: Elad, Michael email: elad@cs.technion.ac.il |
| BookMark | eNqFkE1LAzEQhoNUsK3-Ai856mHrZLNfETwU0Sps8WLPIZvM2iw1Kcm20H_v1nryoKd3GOYZeJ8JGTnvkJBrBjMGrLjrZt1e2zBLIWXDhoPIz8iYDZEIKIvRcc7KhKfAL8gkxg4AuODZmKxqVMGhoYuAaA50if3aG3pTL5a393ROnd_jhjrcBbWhKui17VH3u4C09YHGrQoRqfbGug-qnKENHrwzl-S8VZuIVz85Javnp_fHl6R-W7w-zutEc-B9UoFQChrGS1AMtCqh5Trnoi1zXeaqKireCDW0SbO80m2mh9OKC1GmwBoocj4l_PRXBx9jwFZug_1U4SAZyKMZ2clvM_JoRp7MDJT4RWnbq9561wdlN_-wDycWh1p7i0FGbdFpNDYMYqTx9k_-C0y8gIw |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2024_3430010 crossref_primary_10_1109_MGRS_2024_3494754 crossref_primary_10_1016_j_isatra_2024_01_027 crossref_primary_10_1109_TIP_2021_3090531 crossref_primary_10_1109_TIP_2023_3245323 crossref_primary_10_1137_22M1489228 crossref_primary_10_1109_JSEN_2023_3332755 crossref_primary_10_32604_cmc_2023_041416 crossref_primary_10_1109_TCI_2022_3175309 crossref_primary_10_1016_j_knosys_2022_110185 crossref_primary_10_2478_amns_2023_1_00174 |
| Cites_doi | 10.1109/TIP.2007.911828 10.1109/TPAMI.2019.2895793 10.1109/CVPR.2019.00406 10.1109/TIP.2018.2839891 10.1109/CVPRW50498.2020.00270 10.1109/TPAMI.2010.161 10.1109/TPAMI.2015.2439281 10.1137/S0097539792240406 10.1109/TSP.2006.881199 10.1109/TCI.2020.2964202 10.1109/TIT.2005.864420 10.1109/78.258082 10.1109/TIT.2009.2016006 10.1109/TIP.2006.881969 10.1109/TIP.2017.2662206 10.1109/TIT.2005.860430 10.1109/TIP.2015.2447836 10.1109/TIP.2014.2323127 10.1016/j.optlaseng.2018.05.014 10.1109/TSP.2010.2052460 10.1109/TSP.2017.2733447 10.1109/TIP.2010.2050625 10.1137/16M1102884 10.1002/cpa.20042 10.1109/TIP.2016.2631888 10.1109/TNNLS.2013.2249088 10.1109/TGRS.2013.2253612 10.1109/TPAMI.2008.79 10.1109/MSP.2007.914728 10.1109/TIP.2012.2221729 10.1109/TIP.2011.2108306 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier Inc. |
| Copyright_xml | – notice: 2021 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.jvcir.2021.103095 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Journalism & Communications Engineering |
| EISSN | 1095-9076 |
| ExternalDocumentID | 10_1016_j_jvcir_2021_103095 S1047320321000560 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29L 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMHC ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG5 LX9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K WH7 WUQ XPP YQT ZMT ZU3 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c303t-809aa0b1370a10ca70f3c539f75c75a8683b9a3092458cf4cb1383997201b0653 |
| ISICitedReferencesCount | 13 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000675405700005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1047-3203 |
| IngestDate | Tue Nov 18 22:30:30 EST 2025 Sat Nov 29 07:05:35 EST 2025 Fri Feb 23 02:45:38 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Unfolding pursuit algorithms Interpretable image processing architectures Sparse representation Orthogonal Matching Pursuit Deraining Denoising |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c303t-809aa0b1370a10ca70f3c539f75c75a8683b9a3092458cf4cb1383997201b0653 |
| ORCID | 0000-0002-9056-2933 0000-0002-1376-1840 |
| ParticipantIDs | crossref_primary_10_1016_j_jvcir_2021_103095 crossref_citationtrail_10_1016_j_jvcir_2021_103095 elsevier_sciencedirect_doi_10_1016_j_jvcir_2021_103095 |
| PublicationCentury | 2000 |
| PublicationDate | May 2021 2021-05-00 |
| PublicationDateYYYYMMDD | 2021-05-01 |
| PublicationDate_xml | – month: 05 year: 2021 text: May 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of visual communication and image representation |
| PublicationYear | 2021 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Pati, Rezaiifar, Krishnaprasad (b38) 1993 Zhang, Zuo, Chen, Meng, Zhang (b1) 2017; 26 Huang, Kang, Yang, Lin, Wang (b56) 2012 Arbeláez, Maire, Fowlkes, Malik (b58) 2011; 33 Huang, Song, Cui, Peng, Xu (b27) 2014; 52 Zhou, Jiang, Gong, Xie (b33) 2018; 110 Elad, Aharon (b5) 2006; 15 Papyan, Sulam, Elad (b53) 2017; 65 Pfister, Bresler (b30) 2014 Aharon, Elad, Bruckstein (b11) 2006; 54 Wright, Yang, Ganesh, Sastry, Ma (b35) 2009; 31 D. Ren, W. Zuo, Q. Hu, P. Zhu, D. Meng, Progressive image deraining networks: A better and simpler baseline, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 3937–3946. Mairal, Elad, Sapiro (b26) 2008; 17 Fu, Huang, Zeng, Huang, Ding, Paisley (b62) 2017 Daubechies, Defrise, De Mol (b22) 2004; 57 Chen, Liu, Wang, Yin (b44) 2018 Zhang, Ghanem (b47) 2018 Dong, Zhang, Shi, Wu (b24) 2011; 20 Tropp (b42) 2006; 52 Gu, Zhang, Zuo, Feng (b7) 2014 Yang, Wright, Huang, Ma (b28) 2010; 19 Luo, Xu, Ji (b31) 2015 Simon, Elad (b16) 2019 Yang, Chu, Zhang, Xu, Yang (b36) 2013; 24 Mallat, Zhang (b49) 1993; 41 Niknejad, Rabbani, Babaie-Zadeh (b13) 2015; 24 K. Gregor, Y. LeCun, Learning fast approximations of sparse coding, in: Proceedings of the 27th International Conference on International Conference on Machine Learning, 2010, pp. 399–406. Li, Tan, Guo, Lu, Brown (b57) 2016 Kingma, Ba (b54) 2015 Zhang, Zhao, Gao (b12) 2014; 23 Ben-Haim, Eldar, Elad (b43) 2010; 58 Petersen, Pedersen (b48) 2008 Mairal, Sapiro, Elad (b55) 2007 Yang, Yu, Gong, Huang (b34) 2009 Monga, Li, Eldar (b14) 2019 Sreter, Giryes (b21) 2018 Donoho, Elad, Temlyakov (b41) 2006; 52 Wang, Liu, Yang, Han, Huang (b46) 2015 Ma, Duanmu, Wu, Wang, Yong, Li, Zhang (b59) 2017; 26 Yavneh, Elad (b39) 2008 Elad (b23) 2010 Nah, Kim, Lee (b3) 2017 Romano, Elad, Milanfar (b9) 2017; 10 Rubinstein, Zibulevsky, Elad (b51) 2008 Scetbon, Elad, Milanfar (b17) 2019 Grosse, Raina, Kwong, Ng (b40) 2012; 9 G. Vaksman, M. Elad, P. Milanfar, LIDIA: Lightweight learned image denoising with instance adaptation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 524–525. Dabov, Foi, Katkovnik, Egiazarian (b6) 2006 Yang, Tan, Feng, Guo, Yan, Liu (b60) 2020; 42 Dong, Loy, He, Tang (b4) 2016; 38 Lustig, Donoho, Santos, Pauly (b29) 2008; 25 Dai, Milenkovic (b50) 2009; 55 Zhang, Zuo, Zhang (b2) 2018; 27 Liu, Chen (b45) 2019 Dong, Shi, Li (b10) 2013; 22 Li, Tofighi, Geng, Monga, Eldar (b15) 2020; 6 Horev, Bryt, Rubinstein (b32) 2012 Natarajan (b37) 1995; 24 Lecouat, Ponce, Mairal (b19) 2019 Zoran, Weiss (b8) 2011 Giryes, Elad (b25) 2014 Plaut, Giryes (b52) 2018 Ma (10.1016/j.jvcir.2021.103095_b59) 2017; 26 Tropp (10.1016/j.jvcir.2021.103095_b42) 2006; 52 Aharon (10.1016/j.jvcir.2021.103095_b11) 2006; 54 Mairal (10.1016/j.jvcir.2021.103095_b26) 2008; 17 Grosse (10.1016/j.jvcir.2021.103095_b40) 2012; 9 Arbeláez (10.1016/j.jvcir.2021.103095_b58) 2011; 33 Yang (10.1016/j.jvcir.2021.103095_b28) 2010; 19 Yavneh (10.1016/j.jvcir.2021.103095_b39) 2008 Elad (10.1016/j.jvcir.2021.103095_b5) 2006; 15 Sreter (10.1016/j.jvcir.2021.103095_b21) 2018 Simon (10.1016/j.jvcir.2021.103095_b16) 2019 Mallat (10.1016/j.jvcir.2021.103095_b49) 1993; 41 Dong (10.1016/j.jvcir.2021.103095_b24) 2011; 20 Mairal (10.1016/j.jvcir.2021.103095_b55) 2007 Wright (10.1016/j.jvcir.2021.103095_b35) 2009; 31 Rubinstein (10.1016/j.jvcir.2021.103095_b51) 2008 Zhang (10.1016/j.jvcir.2021.103095_b1) 2017; 26 Petersen (10.1016/j.jvcir.2021.103095_b48) 2008 Gu (10.1016/j.jvcir.2021.103095_b7) 2014 10.1016/j.jvcir.2021.103095_b18 Liu (10.1016/j.jvcir.2021.103095_b45) 2019 Zhang (10.1016/j.jvcir.2021.103095_b12) 2014; 23 Scetbon (10.1016/j.jvcir.2021.103095_b17) 2019 Yang (10.1016/j.jvcir.2021.103095_b34) 2009 Huang (10.1016/j.jvcir.2021.103095_b56) 2012 10.1016/j.jvcir.2021.103095_b20 Monga (10.1016/j.jvcir.2021.103095_b14) 2019 Donoho (10.1016/j.jvcir.2021.103095_b41) 2006; 52 Lustig (10.1016/j.jvcir.2021.103095_b29) 2008; 25 10.1016/j.jvcir.2021.103095_b61 Zhang (10.1016/j.jvcir.2021.103095_b47) 2018 Zhou (10.1016/j.jvcir.2021.103095_b33) 2018; 110 Yang (10.1016/j.jvcir.2021.103095_b36) 2013; 24 Dong (10.1016/j.jvcir.2021.103095_b10) 2013; 22 Ben-Haim (10.1016/j.jvcir.2021.103095_b43) 2010; 58 Giryes (10.1016/j.jvcir.2021.103095_b25) 2014 Zhang (10.1016/j.jvcir.2021.103095_b2) 2018; 27 Dabov (10.1016/j.jvcir.2021.103095_b6) 2006 Chen (10.1016/j.jvcir.2021.103095_b44) 2018 Pati (10.1016/j.jvcir.2021.103095_b38) 1993 Luo (10.1016/j.jvcir.2021.103095_b31) 2015 Elad (10.1016/j.jvcir.2021.103095_b23) 2010 Dai (10.1016/j.jvcir.2021.103095_b50) 2009; 55 Zoran (10.1016/j.jvcir.2021.103095_b8) 2011 Plaut (10.1016/j.jvcir.2021.103095_b52) 2018 Romano (10.1016/j.jvcir.2021.103095_b9) 2017; 10 Lecouat (10.1016/j.jvcir.2021.103095_b19) 2019 Nah (10.1016/j.jvcir.2021.103095_b3) 2017 Wang (10.1016/j.jvcir.2021.103095_b46) 2015 Fu (10.1016/j.jvcir.2021.103095_b62) 2017 Huang (10.1016/j.jvcir.2021.103095_b27) 2014; 52 Niknejad (10.1016/j.jvcir.2021.103095_b13) 2015; 24 Horev (10.1016/j.jvcir.2021.103095_b32) 2012 Yang (10.1016/j.jvcir.2021.103095_b60) 2020; 42 Li (10.1016/j.jvcir.2021.103095_b15) 2020; 6 Papyan (10.1016/j.jvcir.2021.103095_b53) 2017; 65 Kingma (10.1016/j.jvcir.2021.103095_b54) 2015 Dong (10.1016/j.jvcir.2021.103095_b4) 2016; 38 Natarajan (10.1016/j.jvcir.2021.103095_b37) 1995; 24 Li (10.1016/j.jvcir.2021.103095_b57) 2016 Daubechies (10.1016/j.jvcir.2021.103095_b22) 2004; 57 Pfister (10.1016/j.jvcir.2021.103095_b30) 2014 |
| References_xml | – start-page: 257 year: 2017 end-page: 265 ident: b3 article-title: Deep multi-scale convolutional neural network for dynamic scene deblurring publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – year: 2010 ident: b23 article-title: Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing – volume: 38 start-page: 295 year: 2016 end-page: 307 ident: b4 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 25 start-page: 72 year: 2008 end-page: 82 ident: b29 article-title: Compressed sensing MRI publication-title: IEEE Signal Process. Mag. – start-page: 9061 year: 2018 end-page: 9071 ident: b44 article-title: Theoretical linear convergence of unfolded ista and its practical weights and thresholds publication-title: Advances in Neural Information Processing Systems – start-page: 370 year: 2015 end-page: 378 ident: b46 article-title: Deep networks for image super-resolution with sparse prior publication-title: 2015 IEEE International Conference on Computer Vision (ICCV) – volume: 55 start-page: 2230 year: 2009 end-page: 2249 ident: b50 article-title: Subspace pursuit for compressive sensing signal reconstruction publication-title: IEEE Trans. Inform. Theory – volume: 52 start-page: 6 year: 2006 end-page: 18 ident: b41 article-title: Stable recovery of sparse overcomplete representations in the presence of noise publication-title: IEEE Trans. Inform. Theory – volume: 27 start-page: 4608 year: 2018 end-page: 4622 ident: b2 article-title: Ffdnet: Toward a fast and flexible solution for CNN-based image denoising publication-title: IEEE Trans. Image Process. – start-page: 2274 year: 2019 end-page: 2284 ident: b16 article-title: Rethinking the CSC model for natural images publication-title: Advances in Neural Information Processing Systems – volume: 10 start-page: 1804 year: 2017 end-page: 1844 ident: b9 article-title: The little engine that could: Regularization by denoising (RED) publication-title: SIAM J. Imaging Sci. – reference: G. Vaksman, M. Elad, P. Milanfar, LIDIA: Lightweight learned image denoising with instance adaptation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 524–525. – start-page: 479 year: 2011 end-page: 486 ident: b8 article-title: From learning models of natural image patches to whole image restoration publication-title: 2011 International Conference on Computer Vision – reference: K. Gregor, Y. LeCun, Learning fast approximations of sparse coding, in: Proceedings of the 27th International Conference on International Conference on Machine Learning, 2010, pp. 399–406. – volume: 24 start-page: 227 year: 1995 end-page: 234 ident: b37 article-title: Sparse approximate solutions to linear systems publication-title: SIAM J. Comput. – year: 2008 ident: b39 article-title: Mmse approximation for denoising using several sparse representations publication-title: 4th World Conf of the IASC – year: 2019 ident: b19 article-title: Revisiting non local sparse models for image restoration – volume: 52 start-page: 1693 year: 2014 end-page: 1704 ident: b27 article-title: Spatial and spectral image fusion using sparse matrix factorization publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 41 start-page: 3397 year: 1993 end-page: 3415 ident: b49 article-title: Matching pursuits with time-frequency dictionaries publication-title: IEEE Trans. Signal Process. – year: 2015 ident: b54 article-title: Adam: A method for stochastic optimization publication-title: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings – start-page: 2839 year: 2014 end-page: 2843 ident: b25 article-title: Sparsity based poisson inpainting publication-title: 2014 IEEE International Conference on Image Processing (ICIP) – start-page: 164 year: 2012 end-page: 169 ident: b56 article-title: Context-aware single image rain removal publication-title: 2012 IEEE International Conference on Multimedia and Expo – start-page: 2736 year: 2016 end-page: 2744 ident: b57 article-title: Rain streak removal using layer priors publication-title: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 1715 year: 2017 end-page: 1723 ident: b62 article-title: Removing rain from single images via a deep detail network publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 9 year: 2012 ident: b40 article-title: Shift-invariant sparse coding for audio classification publication-title: Cortex – volume: 24 start-page: 1023 year: 2013 end-page: 1035 ident: b36 article-title: Sparse representation classifier steered discriminative projection with applications to face recognition publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 17 start-page: 53 year: 2008 end-page: 69 ident: b26 article-title: Sparse representation for color image restoration publication-title: IEEE Trans. Image Process. – start-page: 6847 year: 2018 end-page: 6851 ident: b52 article-title: Matching pursuit based convolutional sparse coding publication-title: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – volume: 65 start-page: 5687 year: 2017 end-page: 5701 ident: b53 article-title: Working locally thinking globally: Theoretical guarantees for convolutional sparse coding publication-title: IEEE Trans. Signal Process. – volume: 19 start-page: 2861 year: 2010 end-page: 2873 ident: b28 article-title: Image super-resolution via sparse representation publication-title: IEEE Trans. Image Process. – start-page: 40 year: 1993 end-page: 44 ident: b38 article-title: Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition publication-title: Proceedings of 27th Asilomar Conference on Signals, Systems and Computers, Vol. 1 – volume: 22 start-page: 700 year: 2013 end-page: 711 ident: b10 article-title: Nonlocal image restoration with bilateral variance estimation: A low-rank approach publication-title: IEEE Trans. Image Process. – volume: 15 start-page: 3736 year: 2006 end-page: 3745 ident: b5 article-title: Image denoising via sparse and redundant representations over learned dictionaries publication-title: IEEE Trans. Image Process. – volume: 26 start-page: 1004 year: 2017 end-page: 1016 ident: b59 article-title: Waterloo exploration database: New challenges for image quality assessment models publication-title: IEEE Trans. Image Process. – volume: 110 start-page: 72 year: 2018 end-page: 79 ident: b33 article-title: Double-image compression and encryption algorithm based on co-sparse representation and random pixel exchanging publication-title: Opt. Lasers Eng. – year: 2019 ident: b14 article-title: Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing – year: 2019 ident: b45 article-title: Alista: Analytic weights are as good as learned weights in lista publication-title: International Conference on Learning Representations (ICLR) – volume: 23 start-page: 3336 year: 2014 end-page: 3351 ident: b12 article-title: Group-based sparse representation for image restoration publication-title: IEEE Trans. Image Process. – start-page: III year: 2007 end-page: 105–III – 108 ident: b55 article-title: Multiscale sparse image representationwith learned dictionaries publication-title: 2007 IEEE International Conference on Image Processing, Vol. 3 – volume: 6 start-page: 666 year: 2020 end-page: 681 ident: b15 article-title: Efficient and interpretable deep blind image deblurring via algorithm unrolling publication-title: IEEE Trans. Comput. Imaging – year: 2008 ident: b51 article-title: Efficient Implementation of the K-SVD Algorithm using Batch Orthogonal Matching Pursuit – volume: 58 start-page: 5030 year: 2010 end-page: 5043 ident: b43 article-title: Coherence-based performance guarantees for estimating a sparse vector under random noise publication-title: IEEE Trans. Signal Process. – volume: 26 start-page: 3142 year: 2017 end-page: 3155 ident: b1 article-title: Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising publication-title: IEEE Trans. Image Process. – start-page: 3397 year: 2015 end-page: 3405 ident: b31 article-title: Removing rain from a single image via discriminative sparse coding publication-title: 2015 IEEE International Conference on Computer Vision (ICCV) – volume: 33 start-page: 898 year: 2011 end-page: 916 ident: b58 article-title: Contour detection and hierarchical image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 54 start-page: 4311 year: 2006 end-page: 4322 ident: b11 article-title: K-svd: An algorithm for designing overcomplete dictionaries for sparse representation publication-title: IEEE Trans. Signal Process. – start-page: 1794 year: 2009 end-page: 1801 ident: b34 article-title: Linear spatial pyramid matching using sparse coding for image classification publication-title: 2009 IEEE Conference on Computer Vision and Pattern Recognition – volume: 20 start-page: 1838 year: 2011 end-page: 1857 ident: b24 article-title: Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization publication-title: IEEE Trans. Image Process. – year: 2006 ident: b6 article-title: Image denoising with block-matching and 3D filtering publication-title: Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, Vol. 6064 – volume: 31 start-page: 210 year: 2009 end-page: 227 ident: b35 article-title: Robust face recognition via sparse representation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2008 ident: b48 article-title: The Matrix Cookbook – volume: 24 start-page: 3624 year: 2015 end-page: 3636 ident: b13 article-title: Image restoration using Gaussian mixture models with spatially constrained patch clustering publication-title: IEEE Trans. Image Process. – reference: D. Ren, W. Zuo, Q. Hu, P. Zhu, D. Meng, Progressive image deraining networks: A better and simpler baseline, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 3937–3946. – start-page: 2191 year: 2018 end-page: 2195 ident: b21 article-title: Learned convolutional sparse coding publication-title: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – volume: 42 start-page: 1377 year: 2020 end-page: 1393 ident: b60 article-title: Joint rain detection and removal from a single image with contextualized deep networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 2862 year: 2014 end-page: 2869 ident: b7 article-title: Weighted nuclear norm minimization with application to image denoising publication-title: 2014 IEEE Conference on Computer Vision and Pattern Recognition – year: 2019 ident: b17 article-title: Deep k-svd denoising – start-page: 6914 year: 2014 end-page: 6918 ident: b30 article-title: Tomographic reconstruction with adaptive sparsifying transforms publication-title: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – volume: 57 start-page: 1413 year: 2004 end-page: 1457 ident: b22 article-title: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint publication-title: Commun. Pure Appl. Math. J. Issued Courant Inst. Math. Sci. – start-page: 1828 year: 2018 end-page: 1837 ident: b47 article-title: Ista-net: Interpretable optimization-inspired deep network for image compressive sensing publication-title: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 592 year: 2012 end-page: 595 ident: b32 article-title: Adaptive image compression using sparse dictionaries publication-title: 2012 19th International Conference on Systems, Signals and Image Processing (IWSSIP) – volume: 52 start-page: 1030 year: 2006 end-page: 1051 ident: b42 article-title: Just relax: convex programming methods for identifying sparse signals in noise publication-title: IEEE Trans. Inform. Theory – volume: 17 start-page: 53 issue: 1 year: 2008 ident: 10.1016/j.jvcir.2021.103095_b26 article-title: Sparse representation for color image restoration publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2007.911828 – start-page: 9061 year: 2018 ident: 10.1016/j.jvcir.2021.103095_b44 article-title: Theoretical linear convergence of unfolded ista and its practical weights and thresholds – start-page: 2839 year: 2014 ident: 10.1016/j.jvcir.2021.103095_b25 article-title: Sparsity based poisson inpainting – start-page: 3397 year: 2015 ident: 10.1016/j.jvcir.2021.103095_b31 article-title: Removing rain from a single image via discriminative sparse coding – volume: 42 start-page: 1377 issue: 6 year: 2020 ident: 10.1016/j.jvcir.2021.103095_b60 article-title: Joint rain detection and removal from a single image with contextualized deep networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2019.2895793 – start-page: 40 year: 1993 ident: 10.1016/j.jvcir.2021.103095_b38 article-title: Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition – start-page: 164 year: 2012 ident: 10.1016/j.jvcir.2021.103095_b56 article-title: Context-aware single image rain removal – ident: 10.1016/j.jvcir.2021.103095_b61 doi: 10.1109/CVPR.2019.00406 – start-page: 257 year: 2017 ident: 10.1016/j.jvcir.2021.103095_b3 article-title: Deep multi-scale convolutional neural network for dynamic scene deblurring – volume: 27 start-page: 4608 issue: 9 year: 2018 ident: 10.1016/j.jvcir.2021.103095_b2 article-title: Ffdnet: Toward a fast and flexible solution for CNN-based image denoising publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2018.2839891 – ident: 10.1016/j.jvcir.2021.103095_b18 doi: 10.1109/CVPRW50498.2020.00270 – start-page: 2191 year: 2018 ident: 10.1016/j.jvcir.2021.103095_b21 article-title: Learned convolutional sparse coding – start-page: 1715 year: 2017 ident: 10.1016/j.jvcir.2021.103095_b62 article-title: Removing rain from single images via a deep detail network – volume: 33 start-page: 898 issue: 5 year: 2011 ident: 10.1016/j.jvcir.2021.103095_b58 article-title: Contour detection and hierarchical image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2010.161 – year: 2008 ident: 10.1016/j.jvcir.2021.103095_b39 article-title: Mmse approximation for denoising using several sparse representations – volume: 38 start-page: 295 issue: 2 year: 2016 ident: 10.1016/j.jvcir.2021.103095_b4 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2439281 – volume: 24 start-page: 227 issue: 2 year: 1995 ident: 10.1016/j.jvcir.2021.103095_b37 article-title: Sparse approximate solutions to linear systems publication-title: SIAM J. Comput. doi: 10.1137/S0097539792240406 – volume: 54 start-page: 4311 issue: 11 year: 2006 ident: 10.1016/j.jvcir.2021.103095_b11 article-title: K-svd: An algorithm for designing overcomplete dictionaries for sparse representation publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2006.881199 – year: 2006 ident: 10.1016/j.jvcir.2021.103095_b6 article-title: Image denoising with block-matching and 3D filtering – volume: 6 start-page: 666 year: 2020 ident: 10.1016/j.jvcir.2021.103095_b15 article-title: Efficient and interpretable deep blind image deblurring via algorithm unrolling publication-title: IEEE Trans. Comput. Imaging doi: 10.1109/TCI.2020.2964202 – volume: 52 start-page: 1030 issue: 3 year: 2006 ident: 10.1016/j.jvcir.2021.103095_b42 article-title: Just relax: convex programming methods for identifying sparse signals in noise publication-title: IEEE Trans. Inform. Theory doi: 10.1109/TIT.2005.864420 – year: 2019 ident: 10.1016/j.jvcir.2021.103095_b17 – ident: 10.1016/j.jvcir.2021.103095_b20 – volume: 41 start-page: 3397 issue: 12 year: 1993 ident: 10.1016/j.jvcir.2021.103095_b49 article-title: Matching pursuits with time-frequency dictionaries publication-title: IEEE Trans. Signal Process. doi: 10.1109/78.258082 – volume: 55 start-page: 2230 issue: 5 year: 2009 ident: 10.1016/j.jvcir.2021.103095_b50 article-title: Subspace pursuit for compressive sensing signal reconstruction publication-title: IEEE Trans. Inform. Theory doi: 10.1109/TIT.2009.2016006 – volume: 15 start-page: 3736 issue: 12 year: 2006 ident: 10.1016/j.jvcir.2021.103095_b5 article-title: Image denoising via sparse and redundant representations over learned dictionaries publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2006.881969 – start-page: 2274 year: 2019 ident: 10.1016/j.jvcir.2021.103095_b16 article-title: Rethinking the CSC model for natural images – start-page: 1794 year: 2009 ident: 10.1016/j.jvcir.2021.103095_b34 article-title: Linear spatial pyramid matching using sparse coding for image classification – start-page: III year: 2007 ident: 10.1016/j.jvcir.2021.103095_b55 article-title: Multiscale sparse image representationwith learned dictionaries – start-page: 6847 year: 2018 ident: 10.1016/j.jvcir.2021.103095_b52 article-title: Matching pursuit based convolutional sparse coding – volume: 26 start-page: 3142 issue: 7 year: 2017 ident: 10.1016/j.jvcir.2021.103095_b1 article-title: Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2017.2662206 – year: 2008 ident: 10.1016/j.jvcir.2021.103095_b51 – volume: 52 start-page: 6 issue: 1 year: 2006 ident: 10.1016/j.jvcir.2021.103095_b41 article-title: Stable recovery of sparse overcomplete representations in the presence of noise publication-title: IEEE Trans. Inform. Theory doi: 10.1109/TIT.2005.860430 – volume: 24 start-page: 3624 issue: 11 year: 2015 ident: 10.1016/j.jvcir.2021.103095_b13 article-title: Image restoration using Gaussian mixture models with spatially constrained patch clustering publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2447836 – year: 2019 ident: 10.1016/j.jvcir.2021.103095_b45 article-title: Alista: Analytic weights are as good as learned weights in lista – year: 2008 ident: 10.1016/j.jvcir.2021.103095_b48 – volume: 23 start-page: 3336 issue: 8 year: 2014 ident: 10.1016/j.jvcir.2021.103095_b12 article-title: Group-based sparse representation for image restoration publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2014.2323127 – start-page: 6914 year: 2014 ident: 10.1016/j.jvcir.2021.103095_b30 article-title: Tomographic reconstruction with adaptive sparsifying transforms – start-page: 370 year: 2015 ident: 10.1016/j.jvcir.2021.103095_b46 article-title: Deep networks for image super-resolution with sparse prior – volume: 110 start-page: 72 year: 2018 ident: 10.1016/j.jvcir.2021.103095_b33 article-title: Double-image compression and encryption algorithm based on co-sparse representation and random pixel exchanging publication-title: Opt. Lasers Eng. doi: 10.1016/j.optlaseng.2018.05.014 – year: 2010 ident: 10.1016/j.jvcir.2021.103095_b23 – start-page: 2736 year: 2016 ident: 10.1016/j.jvcir.2021.103095_b57 article-title: Rain streak removal using layer priors – volume: 58 start-page: 5030 issue: 10 year: 2010 ident: 10.1016/j.jvcir.2021.103095_b43 article-title: Coherence-based performance guarantees for estimating a sparse vector under random noise publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2010.2052460 – start-page: 1828 year: 2018 ident: 10.1016/j.jvcir.2021.103095_b47 article-title: Ista-net: Interpretable optimization-inspired deep network for image compressive sensing – volume: 65 start-page: 5687 issue: 21 year: 2017 ident: 10.1016/j.jvcir.2021.103095_b53 article-title: Working locally thinking globally: Theoretical guarantees for convolutional sparse coding publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2017.2733447 – year: 2015 ident: 10.1016/j.jvcir.2021.103095_b54 article-title: Adam: A method for stochastic optimization – start-page: 479 year: 2011 ident: 10.1016/j.jvcir.2021.103095_b8 article-title: From learning models of natural image patches to whole image restoration – volume: 19 start-page: 2861 issue: 11 year: 2010 ident: 10.1016/j.jvcir.2021.103095_b28 article-title: Image super-resolution via sparse representation publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2010.2050625 – volume: 10 start-page: 1804 issue: 4 year: 2017 ident: 10.1016/j.jvcir.2021.103095_b9 article-title: The little engine that could: Regularization by denoising (RED) publication-title: SIAM J. Imaging Sci. doi: 10.1137/16M1102884 – volume: 57 start-page: 1413 issue: 11 year: 2004 ident: 10.1016/j.jvcir.2021.103095_b22 article-title: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint publication-title: Commun. Pure Appl. Math. J. Issued Courant Inst. Math. Sci. doi: 10.1002/cpa.20042 – volume: 26 start-page: 1004 issue: 2 year: 2017 ident: 10.1016/j.jvcir.2021.103095_b59 article-title: Waterloo exploration database: New challenges for image quality assessment models publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2016.2631888 – volume: 24 start-page: 1023 issue: 7 year: 2013 ident: 10.1016/j.jvcir.2021.103095_b36 article-title: Sparse representation classifier steered discriminative projection with applications to face recognition publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2013.2249088 – year: 2019 ident: 10.1016/j.jvcir.2021.103095_b14 – start-page: 592 year: 2012 ident: 10.1016/j.jvcir.2021.103095_b32 article-title: Adaptive image compression using sparse dictionaries – volume: 52 start-page: 1693 issue: 3 year: 2014 ident: 10.1016/j.jvcir.2021.103095_b27 article-title: Spatial and spectral image fusion using sparse matrix factorization publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2013.2253612 – volume: 31 start-page: 210 issue: 2 year: 2009 ident: 10.1016/j.jvcir.2021.103095_b35 article-title: Robust face recognition via sparse representation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2008.79 – start-page: 2862 year: 2014 ident: 10.1016/j.jvcir.2021.103095_b7 article-title: Weighted nuclear norm minimization with application to image denoising – volume: 25 start-page: 72 issue: 2 year: 2008 ident: 10.1016/j.jvcir.2021.103095_b29 article-title: Compressed sensing MRI publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2007.914728 – year: 2019 ident: 10.1016/j.jvcir.2021.103095_b19 – volume: 9 year: 2012 ident: 10.1016/j.jvcir.2021.103095_b40 article-title: Shift-invariant sparse coding for audio classification publication-title: Cortex – volume: 22 start-page: 700 issue: 2 year: 2013 ident: 10.1016/j.jvcir.2021.103095_b10 article-title: Nonlocal image restoration with bilateral variance estimation: A low-rank approach publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2012.2221729 – volume: 20 start-page: 1838 issue: 7 year: 2011 ident: 10.1016/j.jvcir.2021.103095_b24 article-title: Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2011.2108306 |
| SSID | ssj0003934 |
| Score | 2.3798862 |
| Snippet | The fields of signal and image processing have been deeply influenced by the introduction of deep neural networks. Despite their impressive success, the... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 103095 |
| SubjectTerms | Denoising Deraining Interpretable image processing architectures Orthogonal Matching Pursuit Sparse representation Unfolding pursuit algorithms |
| Title | Learned Greedy Method (LGM): A novel neural architecture for sparse coding and beyond |
| URI | https://dx.doi.org/10.1016/j.jvcir.2021.103095 |
| Volume | 77 |
| WOSCitedRecordID | wos000675405700005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect Freedom Collection - Elsevier customDbUrl: eissn: 1095-9076 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003934 issn: 1047-3203 databaseCode: AIEXJ dateStart: 19950301 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3fb9MwELZKxwM8IBggxgD5ASHQCHLjZrZ5q1D5JW1CsEl9ixzXFa26dGq7MP577nxxmjGYAImXKLXsuPF9tb_ad98x9tShWZ20CQp9JH3jVWJTdBrXum9UNsY1JiSbUIeHejQynzqdbzEWppqrstTn5-b0v5oaysDYGDr7F-ZuHgoFcA9GhyuYHa5_ZPigmOpxmwkWpu97ByFFdMjc8e4A_vdTKHq5qPx8D8UsUSugfZiAbocwyyyDG_s4hjAWIdDlN0y2mq7OgsxIK9aEDiVO0CMo6GbGGKfNof9X-BgOgz7bmfXTZqsHwEMz4XLROA4P54TEtpN_vVWR9jaOgbR_FmNoLrh4Bq0ImQqa5nxdhhkkBWWGifM0pXu5NOXT7sPs1axyUxR4TXsoJCAodedPWtpfsDPsK8VjDSB719hWqjKju2xr8GE4-tgs4tKQQ0L8clGwKrgGXurq16SmRVSObrNbtV34gJBxh3V8uc1utnQnt9luXWm6OuHP-IUYodVddlwjiBOCOCGIPwf8vHjNBzxghxN2eBs7HLDDCTucsMMBBZywc48dvx0evXmf1Nk3Ege0Zg3UxVgrip5UwvaEs0pMpMukmajMqczqfS0LY-Ht036m3aTvoCqwbaOAUhaoeHyfdctF6R8wLiw8Qlk_kUB3vci0HIsiy4CMSm-91zssjcOXu1qaHjOkzPPogzjLw5jnOOY5jfkOe9k0OiVllqur70e75DW5JNKYA5CuavjwXxvushubH8Ej1l0vz_xjdt1V6-lq-aQG3A-BW5xm |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learned+Greedy+Method+%28LGM%29%3A+A+novel+neural+architecture+for+sparse+coding+and+beyond&rft.jtitle=Journal+of+visual+communication+and+image+representation&rft.au=Khatib%2C+Rajaei&rft.au=Simon%2C+Dror&rft.au=Elad%2C+Michael&rft.date=2021-05-01&rft.pub=Elsevier+Inc&rft.issn=1047-3203&rft.eissn=1095-9076&rft.volume=77&rft_id=info:doi/10.1016%2Fj.jvcir.2021.103095&rft.externalDocID=S1047320321000560 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1047-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1047-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1047-3203&client=summon |