Optimization-Inspired Compact Deep Compressive Sensing
In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network, dubbed OPINE-Net, for adaptive sampling and recovery. Both orthogonal and binary constraints of sampling matrix are incorporated into OPINE-Ne...
Saved in:
| Published in | IEEE journal of selected topics in signal processing Vol. 14; no. 4; pp. 765 - 774 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.05.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network, dubbed OPINE-Net, for adaptive sampling and recovery. Both orthogonal and binary constraints of sampling matrix are incorporated into OPINE-Net simultaneously. In particular, OPINE-Net is composed of three subnets: sampling subnet, initialization subnet and recovery subnet, and all the parameters in OPINE-Net (e.g. sampling matrix, nonlinear transforms, shrinkage threshold) are learned end-to-end, rather than hand-crafted. Moreover, considering the relationship among neighboring blocks, an enhanced version OPINE-Net<inline-formula><tex-math notation="LaTeX">^+</tex-math></inline-formula> is developed, which allows image blocks to be sampled independently but reconstructed jointly to further enhance the performance. In addition, some interesting findings of learned sampling matrix are presented. Compared with existing state-of-the-art network-based CS methods, the proposed hardware-friendly OPINE-Nets not only achieve better performance but also require much fewer parameters and much less storage space, while maintaining a real-time running speed. |
|---|---|
| AbstractList | In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network, dubbed OPINE-Net, for adaptive sampling and recovery. Both orthogonal and binary constraints of sampling matrix are incorporated into OPINE-Net simultaneously. In particular, OPINE-Net is composed of three subnets: sampling subnet, initialization subnet and recovery subnet, and all the parameters in OPINE-Net (e.g. sampling matrix, nonlinear transforms, shrinkage threshold) are learned end-to-end, rather than hand-crafted. Moreover, considering the relationship among neighboring blocks, an enhanced version OPINE-Net<inline-formula><tex-math notation="LaTeX">^+</tex-math></inline-formula> is developed, which allows image blocks to be sampled independently but reconstructed jointly to further enhance the performance. In addition, some interesting findings of learned sampling matrix are presented. Compared with existing state-of-the-art network-based CS methods, the proposed hardware-friendly OPINE-Nets not only achieve better performance but also require much fewer parameters and much less storage space, while maintaining a real-time running speed. In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network, dubbed OPINE-Net, for adaptive sampling and recovery. Both orthogonal and binary constraints of sampling matrix are incorporated into OPINE-Net simultaneously. In particular, OPINE-Net is composed of three subnets: sampling subnet, initialization subnet and recovery subnet, and all the parameters in OPINE-Net (e.g. sampling matrix, nonlinear transforms, shrinkage threshold) are learned end-to-end, rather than hand-crafted. Moreover, considering the relationship among neighboring blocks, an enhanced version OPINE-Net[Formula Omitted] is developed, which allows image blocks to be sampled independently but reconstructed jointly to further enhance the performance. In addition, some interesting findings of learned sampling matrix are presented. Compared with existing state-of-the-art network-based CS methods, the proposed hardware-friendly OPINE-Nets not only achieve better performance but also require much fewer parameters and much less storage space, while maintaining a real-time running speed. |
| Author | Zhang, Jian Zhao, Chen Gao, Wen |
| Author_xml | – sequence: 1 givenname: Jian orcidid: 0000-0001-5486-3125 surname: Zhang fullname: Zhang, Jian email: zhangjian@pkusz.edu.cn organization: School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China – sequence: 2 givenname: Chen surname: Zhao fullname: Zhao, Chen email: chen.zhao@kaust.edu.sa organization: Visual Computing Center, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia – sequence: 3 givenname: Wen surname: Gao fullname: Gao, Wen email: wgao@pku.edu.cn organization: School of Electronics Engineering and Computer Science, Peking University, Beijing, China |
| BookMark | eNp9kE1LAzEQhoNUsK3-Ab0UPG_Nd7JHqVYrhQqt55BmJ5LSZtdkK-ivt1948OBpZuB9ZpinhzqxjoDQNcFDQnB59zJfzF-HFFM8pKVSAqsz1CUlJwXmmnf2PaMFF4JdoF7OK4yFkoR3kZw1bdiEb9uGOhaTmJuQoBqM6k1jXTt4AGgOQ4KcwycM5hBziO-X6NzbdYarU-2jt_HjYvRcTGdPk9H9tHBMkrawgknuQUFFGVAmwFfCUucJKGcp1Vp76yUwKbivvK-WmhBFHV5a5wi2Feuj2-PeJtUfW8itWdXbFHcnDeWMEyqlUruUPqZcqnNO4I0L7eGjNtmwNgSbvSVzsGT2lszJ0g6lf9AmhY1NX_9DN0coAMAvUGJSaqHYD_GKdjo |
| CODEN | IJSTGY |
| CitedBy_id | crossref_primary_10_1016_j_neucom_2024_129071 crossref_primary_10_1109_TNNLS_2022_3202724 crossref_primary_10_3390_rs16234601 crossref_primary_10_1109_TCI_2025_3527880 crossref_primary_10_1109_TCI_2023_3244396 crossref_primary_10_1109_TIP_2024_3371351 crossref_primary_10_1007_s11760_023_02686_w crossref_primary_10_1007_s11263_023_01814_w crossref_primary_10_1007_s00530_024_01380_2 crossref_primary_10_1109_TGRS_2023_3281543 crossref_primary_10_1016_j_sigpro_2022_108737 crossref_primary_10_1109_TIP_2021_3088611 crossref_primary_10_1145_3701732 crossref_primary_10_1145_3701731 crossref_primary_10_3390_s23041886 crossref_primary_10_1109_TPAMI_2024_3357704 crossref_primary_10_1016_j_sigpro_2021_108239 crossref_primary_10_1364_JOSAA_523092 crossref_primary_10_1016_j_jvcir_2024_104092 crossref_primary_10_1016_j_neunet_2024_106541 crossref_primary_10_1109_TETCI_2023_3271322 crossref_primary_10_1109_TMM_2023_3301213 crossref_primary_10_1007_s11760_023_02516_z crossref_primary_10_1109_TCSVT_2024_3417287 crossref_primary_10_1109_TCI_2023_3315853 crossref_primary_10_1016_j_bspc_2024_107364 crossref_primary_10_1016_j_jrras_2024_100912 crossref_primary_10_1007_s00034_024_02699_x crossref_primary_10_1109_TIM_2025_3544335 crossref_primary_10_1109_TIP_2022_3195319 crossref_primary_10_1109_TMM_2023_3305828 crossref_primary_10_1109_ACCESS_2024_3482434 crossref_primary_10_3390_rs14174184 crossref_primary_10_1007_s11760_024_03095_3 crossref_primary_10_1109_TPAMI_2024_3504490 crossref_primary_10_1109_TCSVT_2024_3397012 crossref_primary_10_1126_sciadv_adj3608 crossref_primary_10_1137_20M1353368 crossref_primary_10_1016_j_engappai_2024_109099 crossref_primary_10_3390_e25121648 crossref_primary_10_1016_j_neucom_2025_129723 crossref_primary_10_1109_TCI_2023_3304472 crossref_primary_10_1007_s00371_024_03700_z crossref_primary_10_1109_ACCESS_2021_3130973 crossref_primary_10_1109_TPAMI_2022_3194001 crossref_primary_10_1109_LSP_2022_3205275 crossref_primary_10_1109_TMM_2021_3132489 crossref_primary_10_1109_TII_2022_3202203 crossref_primary_10_1109_JPHOT_2024_3420787 crossref_primary_10_1109_TIP_2021_3091834 crossref_primary_10_1109_TIM_2023_3304676 crossref_primary_10_1109_TCI_2022_3183411 crossref_primary_10_1109_TCI_2022_3181473 crossref_primary_10_1109_JIOT_2024_3505617 crossref_primary_10_1016_j_optcom_2025_131633 crossref_primary_10_1007_s11042_023_14939_4 crossref_primary_10_1109_TIM_2024_3398096 crossref_primary_10_1109_TCI_2022_3224281 crossref_primary_10_1109_TIP_2023_3263100 crossref_primary_10_1007_s11760_023_02879_3 crossref_primary_10_1109_TIP_2025_3533198 crossref_primary_10_1109_TIP_2023_3274988 crossref_primary_10_3390_electronics13173496 crossref_primary_10_3390_info15020075 crossref_primary_10_1109_ACCESS_2024_3522978 crossref_primary_10_1016_j_knosys_2023_110963 crossref_primary_10_1016_j_neucom_2022_08_034 crossref_primary_10_1109_TCSVT_2023_3325340 crossref_primary_10_1109_TSC_2023_3334446 crossref_primary_10_1145_3635308 crossref_primary_10_46387_bjesr_1452937 crossref_primary_10_1016_j_jvcir_2022_103723 crossref_primary_10_3390_s21196551 crossref_primary_10_1109_JPROC_2023_3338272 crossref_primary_10_1016_j_eswa_2024_126027 crossref_primary_10_1109_JSTSP_2022_3170227 crossref_primary_10_1109_TMM_2023_3324490 crossref_primary_10_3390_s23052563 crossref_primary_10_1109_ACCESS_2025_3527756 crossref_primary_10_1007_s11042_020_09907_1 crossref_primary_10_1007_s11042_024_18724_9 crossref_primary_10_1016_j_image_2024_117153 crossref_primary_10_3390_electronics12010030 crossref_primary_10_1109_ACCESS_2021_3091971 crossref_primary_10_1007_s11263_023_01765_2 crossref_primary_10_3390_s20195666 crossref_primary_10_1109_TIP_2023_3274967 crossref_primary_10_1016_j_knosys_2023_110681 crossref_primary_10_1016_j_knosys_2024_111659 crossref_primary_10_3390_s24248085 crossref_primary_10_1038_s41598_024_79466_0 crossref_primary_10_1016_j_dsp_2025_105002 crossref_primary_10_1109_TIP_2023_3318946 crossref_primary_10_1109_TPDS_2024_3453607 crossref_primary_10_3390_e24060775 crossref_primary_10_3390_e25121579 crossref_primary_10_26599_AIR_2022_9150004 crossref_primary_10_1109_JPHOT_2024_3434972 crossref_primary_10_1145_3649441 crossref_primary_10_1016_j_sysarc_2022_102760 crossref_primary_10_3390_info15120773 crossref_primary_10_1109_TMM_2023_3321424 crossref_primary_10_1007_s00371_022_02585_0 crossref_primary_10_1016_j_jvcir_2024_104071 crossref_primary_10_1109_TCI_2024_3354423 |
| Cites_doi | 10.1109/TIP.2014.2323127 10.1109/CVPR.2019.01257 10.1016/j.sigpro.2013.09.025 10.1109/CVPR.2016.55 10.1109/MMSP.2017.8122281 10.1109/CVPR.2014.349 10.1109/CVPR.2015.7299156 10.1109/TIP.2009.2022459 10.1109/CVPR.2016.207 10.1109/TBME.2012.2226175 10.1109/ICCV.2001.937655 10.1109/ALLERTON.2015.7447163 10.1109/ICCPhot.2012.6215212 10.1109/COMST.2016.2524443 10.1016/j.acha.2009.04.002 10.1109/CVPR.2018.00196 10.1109/TIP.2003.819861 10.1109/TCI.2016.2637079 10.1002/mrm.21391 10.1109/CVPR.2017.300 10.1109/ICCV.2015.50 10.1016/j.sigpro.2018.05.021 10.1109/DCC.2010.90 10.1109/ICASSP.2017.7952561 10.1109/TCSVT.2016.2580399 10.1109/TCI.2018.2846413 10.1109/ACCESS.2018.2882990 10.1109/ICCV.2017.627 10.1007/s10589-013-9576-1 10.1038/srep05552 10.1109/TSP.2017.2708040 10.1016/j.sigpro.2018.04.020 10.1109/CVPR.2015.7299163 10.1109/TIT.2016.2556683 10.1016/j.dsp.2017.09.010 10.1109/ALLERTON.2017.8262812 10.1109/LSP.2016.2548245 10.1109/TIP.2014.2329449 10.1109/ICIP.2010.5652744 10.1016/j.neucom.2018.04.084 10.1109/ICME.2017.8019428 10.1109/TSP.2009.2022003 10.1109/JETCAS.2012.2220391 10.1109/TCSVT.2016.2527181 10.1109/TIP.2006.881969 10.1109/MSP.2007.914730 10.1109/TIT.2006.885507 10.1109/TSP.2015.2399864 10.1016/j.crma.2008.03.014 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| DBID | 97E RIA RIE AAYXX CITATION 7SP 8FD H8D L7M |
| DOI | 10.1109/JSTSP.2020.2977507 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Aerospace Database Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Aerospace Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1941-0484 |
| EndPage | 774 |
| ExternalDocumentID | 10_1109_JSTSP_2020_2977507 9019857 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61902009 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of Guangdong Province grantid: 2017A030310576 funderid: 10.13039/501100003453 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL RIA RIE RNS AAYXX CITATION RIG 7SP 8FD H8D L7M |
| ID | FETCH-LOGICAL-c361t-a5364fe7ed23e235efd5a2cf1e7ca22888faf6e3654fdffdb81172c0bacc10ad3 |
| IEDL.DBID | RIE |
| ISSN | 1932-4553 |
| IngestDate | Mon Jun 30 10:16:00 EDT 2025 Tue Jul 01 02:54:56 EDT 2025 Thu Apr 24 23:10:04 EDT 2025 Wed Aug 27 02:32:37 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c361t-a5364fe7ed23e235efd5a2cf1e7ca22888faf6e3654fdffdb81172c0bacc10ad3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-5486-3125 |
| PQID | 2434126677 |
| PQPubID | 75721 |
| PageCount | 10 |
| ParticipantIDs | crossref_citationtrail_10_1109_JSTSP_2020_2977507 ieee_primary_9019857 crossref_primary_10_1109_JSTSP_2020_2977507 proquest_journals_2434126677 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2020-05-01 |
| PublicationDateYYYYMMDD | 2020-05-01 |
| PublicationDate_xml | – month: 05 year: 2020 text: 2020-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE journal of selected topics in signal processing |
| PublicationTitleAbbrev | JSTSP |
| PublicationYear | 2020 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref15 ref14 ref52 ref11 ref10 ref17 ref16 he (ref24) 2009; 57 ref19 ref18 ref51 ref50 ref46 ref45 ref47 ref41 ref44 ref49 ref8 kingma (ref48) 0 ref7 ref9 ref3 ref6 ref5 ref40 ref35 ref34 yang (ref42) 0 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 metzler (ref43) 0 ref23 ref26 ref25 ref20 ref22 ref21 liutkus (ref4) 2014; 4 ref28 ref27 ref29 |
| References_xml | – ident: ref27 doi: 10.1109/TIP.2014.2323127 – start-page: 10 year: 0 ident: ref42 article-title: Deep ADMM-net for compressive sensing MRI publication-title: Proc Adv Neural Inf Process Syst – ident: ref46 doi: 10.1109/CVPR.2019.01257 – ident: ref10 doi: 10.1016/j.sigpro.2013.09.025 – ident: ref35 doi: 10.1109/CVPR.2016.55 – ident: ref17 doi: 10.1109/MMSP.2017.8122281 – ident: ref38 doi: 10.1109/CVPR.2014.349 – ident: ref50 doi: 10.1109/CVPR.2015.7299156 – ident: ref13 doi: 10.1109/TIP.2009.2022459 – ident: ref47 doi: 10.1109/CVPR.2016.207 – start-page: 1772 year: 0 ident: ref43 article-title: Learned D-AMP: Principled neural network based compressive image recovery publication-title: Proc Adv Neural Inf Process Syst – ident: ref7 doi: 10.1109/TBME.2012.2226175 – ident: ref49 doi: 10.1109/ICCV.2001.937655 – ident: ref33 doi: 10.1109/ALLERTON.2015.7447163 – ident: ref3 doi: 10.1109/ICCPhot.2012.6215212 – ident: ref8 doi: 10.1109/COMST.2016.2524443 – ident: ref28 doi: 10.1016/j.acha.2009.04.002 – ident: ref44 doi: 10.1109/CVPR.2018.00196 – ident: ref51 doi: 10.1109/TIP.2003.819861 – ident: ref5 doi: 10.1109/TCI.2016.2637079 – ident: ref6 doi: 10.1002/mrm.21391 – ident: ref30 doi: 10.1109/CVPR.2017.300 – start-page: 1 year: 0 ident: ref48 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Representations – ident: ref41 doi: 10.1109/ICCV.2015.50 – ident: ref16 doi: 10.1016/j.sigpro.2018.05.021 – ident: ref21 doi: 10.1109/DCC.2010.90 – ident: ref36 doi: 10.1109/ICASSP.2017.7952561 – ident: ref12 doi: 10.1109/TCSVT.2016.2580399 – ident: ref20 doi: 10.1109/TCI.2018.2846413 – ident: ref32 doi: 10.1109/ACCESS.2018.2882990 – ident: ref31 doi: 10.1109/ICCV.2017.627 – ident: ref22 doi: 10.1007/s10589-013-9576-1 – volume: 4 year: 2014 ident: ref4 article-title: Imaging with nature: Compressive imaging using a multiply scattering medium publication-title: Scientific Reports doi: 10.1038/srep05552 – ident: ref37 doi: 10.1109/TSP.2017.2708040 – ident: ref15 doi: 10.1016/j.sigpro.2018.04.020 – ident: ref39 doi: 10.1109/CVPR.2015.7299163 – ident: ref29 doi: 10.1109/TIT.2016.2556683 – ident: ref34 doi: 10.1016/j.dsp.2017.09.010 – ident: ref45 doi: 10.1109/ALLERTON.2017.8262812 – ident: ref40 doi: 10.1109/LSP.2016.2548245 – ident: ref26 doi: 10.1109/TIP.2014.2329449 – ident: ref23 doi: 10.1109/ICIP.2010.5652744 – ident: ref18 doi: 10.1016/j.neucom.2018.04.084 – ident: ref19 doi: 10.1109/ICME.2017.8019428 – volume: 57 start-page: 3488 year: 2009 ident: ref24 article-title: Exploiting structure in wavelet-based bayesian compressive sensing publication-title: IEEE Trans Signal Process doi: 10.1109/TSP.2009.2022003 – ident: ref25 doi: 10.1109/JETCAS.2012.2220391 – ident: ref11 doi: 10.1109/TCSVT.2016.2527181 – ident: ref9 doi: 10.1109/TIP.2006.881969 – ident: ref2 doi: 10.1109/MSP.2007.914730 – ident: ref1 doi: 10.1109/TIT.2006.885507 – ident: ref14 doi: 10.1109/TSP.2015.2399864 – ident: ref52 doi: 10.1016/j.crma.2008.03.014 |
| SSID | ssj0057614 |
| Score | 2.6032667 |
| Snippet | In order to improve CS performance of natural images, in this paper, we propose a novel framework to design an OPtimization-INspired Explicable deep Network,... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 765 |
| SubjectTerms | Adaptive sampling Adaptive systems compressive sensing Convolution Design optimization Dictionaries Image enhancement Image reconstruction interpretable networks neural networks Optimization Parameters Recovery Training Transforms |
| Title | Optimization-Inspired Compact Deep Compressive Sensing |
| URI | https://ieeexplore.ieee.org/document/9019857 https://www.proquest.com/docview/2434126677 |
| Volume | 14 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8QwEB52PenBt7i-6MGbZm3z6vYoPliFVUEFbyVNJh7U7qJdD_56k7RdREW8tZCUMDOZR-fxAexnzKJFkRKpFRJuqCKDQmREcyNiY5ROAkrE6EoO7_nlg3jowOGsFwYRQ_EZ9v1jyOWbsZ76X2VHznZlA5F2oesCt7pXq9W6zm1OmgwyJVwI1jbIxNmRE_HbGxcK0rhPnbsjPHTsFyMUUFV-qOJgX86XYNSerC4reepPq6KvP74Nbfzv0ZdhsXE0o-NaMlagg-UqLHwZP7gG8trpi5emEZNclD7pjiYKKkJX0SniJLyEUtl3jG59sXv5uA7352d3J0PS4CgQzWRSESWY5BZTNJQhZQKtEYpqm2CqFaUuBrbKSmRScGusNYVvPqU6LpTWSawM24C5clziJkS-odsFeFRQm3KtPFjMAJUteKykjjnrQdISNtfNkHGPdfGch2AjzvLAjNwzI2-Y0YOD2Z5JPWLjz9VrnrqzlQ1he7DT8i9vbuFbTrmz0c4DSdOt33dtw7z_dl3AuANz1esUd52TURV7Qbo-AX61zk8 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED7xGICBN6JQIAMbuCR-JM2IeKgFCkiAxBY59pkBSBGkDPx6bCepECDElii2Yt1d7pF7fAC7KTNoUCQkVhIJ11SSbi5SorgWodZSRR4lYnAZ9-742b24n4D9cS8MIvriM-y4S5_L10M1cr_KDqztSrsimYRpa_dFVHVrNXrXOs5RnUOmxD5mTYtMmB5YIb-5tsEgDTvUOjzCgcd-MUMeV-WHMvYW5nQBBs3ZqsKSx86ozDvq49vYxv8efhHma1czOKxkYwkmsFiGuS8DCFcgvrIa47luxST9wqXdUQdeSagyOEZ88Te-WPYdgxtX7l48rMLd6cntUY_USApEsTgqiRQs5gYT1JQhZQKNFpIqE2GiJKU2CjbSxMhiwY02Rueu_ZSqMJdKRaHUbA2mimGB6xC4lm4b4lFBTcKVdHAxXZQm56GMVchZC6KGsJmqx4w7tIunzIcbYZp5ZmSOGVnNjBbsjfe8VEM2_ly94qg7XlkTtgXthn9Z_R2-ZZRbK219kCTZ-H3XDsz0bgcX2UX_8nwTZt17qnLGNkyVryPcsi5HmW97SfsEbw7RmA |
| 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=Optimization-Inspired+Compact+Deep+Compressive+Sensing&rft.jtitle=IEEE+journal+of+selected+topics+in+signal+processing&rft.au=Zhang%2C+Jian&rft.au=Zhao%2C+Chen&rft.au=Gao%2C+Wen&rft.date=2020-05-01&rft.issn=1932-4553&rft.eissn=1941-0484&rft.volume=14&rft.issue=4&rft.spage=765&rft.epage=774&rft_id=info:doi/10.1109%2FJSTSP.2020.2977507&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSTSP_2020_2977507 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4553&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4553&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4553&client=summon |