Continual Image Deraining With Hypergraph Convolutional Networks
Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep learning-based methods mainly construct the deraining networks by stacking vanilla convolutional layers with local relations, and can only handl...
Saved in:
| Published in: | IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 8; pp. 9534 - 9551 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep learning-based methods mainly construct the deraining networks by stacking vanilla convolutional layers with local relations, and can only handle a single dataset due to catastrophic forgetting, resulting in a limited performance and insufficient adaptability. To address these issues, we propose a new image deraining framework to effectively explore nonlocal similarity, and to continuously learn on multiple datasets. Specifically, we first design a patchwise hypergraph convolutional module, which aims to better extract the nonlocal properties with higher-order constraints on the data, to construct a new backbone and to improve the deraining performance. Then, to achieve better generalizability and adaptability in real-world scenarios, we propose a biological brain-inspired continual learning algorithm. By imitating the plasticity mechanism of brain synapses during the learning and memory process, our continual learning process allows the network to achieve a subtle stability-plasticity tradeoff. This it can effectively alleviate catastrophic forgetting and enables a single network to handle multiple datasets. Compared with the competitors, our new deraining network with unified parameters attains a state-of-the-art performance on seen synthetic datasets and has a significantly improved generalizability on unseen real rainy images. |
|---|---|
| AbstractList | Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep learning-based methods mainly construct the deraining networks by stacking vanilla convolutional layers with local relations, and can only handle a single dataset due to catastrophic forgetting, resulting in a limited performance and insufficient adaptability. To address these issues, we propose a new image deraining framework to effectively explore nonlocal similarity, and to continuously learn on multiple datasets. Specifically, we first design a patchwise hypergraph convolutional module, which aims to better extract the nonlocal properties with higher-order constraints on the data, to construct a new backbone and to improve the deraining performance. Then, to achieve better generalizability and adaptability in real-world scenarios, we propose a biological brain-inspired continual learning algorithm. By imitating the plasticity mechanism of brain synapses during the learning and memory process, our continual learning process allows the network to achieve a subtle stability-plasticity tradeoff. This it can effectively alleviate catastrophic forgetting and enables a single network to handle multiple datasets. Compared with the competitors, our new deraining network with unified parameters attains a state-of-the-art performance on seen synthetic datasets and has a significantly improved generalizability on unseen real rainy images. Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep learning-based methods mainly construct the deraining networks by stacking vanilla convolutional layers with local relations, and can only handle a single dataset due to catastrophic forgetting, resulting in a limited performance and insufficient adaptability. To address these issues, we propose a new image deraining framework to effectively explore nonlocal similarity, and to continuously learn on multiple datasets. Specifically, we first design a patchwise hypergraph convolutional module, which aims to better extract the nonlocal properties with higher-order constraints on the data, to construct a new backbone and to improve the deraining performance. Then, to achieve better generalizability and adaptability in real-world scenarios, we propose a biological brain-inspired continual learning algorithm. By imitating the plasticity mechanism of brain synapses during the learning and memory process, our continual learning process allows the network to achieve a subtle stability-plasticity tradeoff. This it can effectively alleviate catastrophic forgetting and enables a single network to handle multiple datasets. Compared with the competitors, our new deraining network with unified parameters attains a state-of-the-art performance on seen synthetic datasets and has a significantly improved generalizability on unseen real rainy images.Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep learning-based methods mainly construct the deraining networks by stacking vanilla convolutional layers with local relations, and can only handle a single dataset due to catastrophic forgetting, resulting in a limited performance and insufficient adaptability. To address these issues, we propose a new image deraining framework to effectively explore nonlocal similarity, and to continuously learn on multiple datasets. Specifically, we first design a patchwise hypergraph convolutional module, which aims to better extract the nonlocal properties with higher-order constraints on the data, to construct a new backbone and to improve the deraining performance. Then, to achieve better generalizability and adaptability in real-world scenarios, we propose a biological brain-inspired continual learning algorithm. By imitating the plasticity mechanism of brain synapses during the learning and memory process, our continual learning process allows the network to achieve a subtle stability-plasticity tradeoff. This it can effectively alleviate catastrophic forgetting and enables a single network to handle multiple datasets. Compared with the competitors, our new deraining network with unified parameters attains a state-of-the-art performance on seen synthetic datasets and has a significantly improved generalizability on unseen real rainy images. |
| Author | Xiao, Jie Wu, Feng Fu, Xueyang Liu, Aiping Zha, Zheng-Jun Zhu, Yurui |
| Author_xml | – sequence: 1 givenname: Xueyang orcidid: 0000-0001-8036-4071 surname: Fu fullname: Fu, Xueyang email: xyfu@ustc.edu.cn organization: University of Science and Technology of China, Hefei, China – sequence: 2 givenname: Jie surname: Xiao fullname: Xiao, Jie email: ustchbxj@mail.ustc.edu.cn organization: University of Science and Technology of China, Hefei, China – sequence: 3 givenname: Yurui surname: Zhu fullname: Zhu, Yurui email: zry@mail.ustc.edu.cn organization: University of Science and Technology of China, Hefei, China – sequence: 4 givenname: Aiping orcidid: 0000-0001-8849-5228 surname: Liu fullname: Liu, Aiping email: aipingl@ustc.edu.cn organization: University of Science and Technology of China, Hefei, China – sequence: 5 givenname: Feng surname: Wu fullname: Wu, Feng email: fengwu@ustc.edu.cn organization: University of Science and Technology of China, Hefei, China – sequence: 6 givenname: Zheng-Jun orcidid: 0000-0003-2510-8993 surname: Zha fullname: Zha, Zheng-Jun email: zhazj@ustc.edu.cn organization: University of Science and Technology of China, Hefei, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37022385$$D View this record in MEDLINE/PubMed |
| BookMark | eNp90U9v0zAYBnALDbFu8AUQQpG4cEn3-rXjPzemDlilDTgMcYyc9E3nkcbFTob27XFpQWgHTr78Htt6nhN2NISBGHvJYc452LObL-fXyzkCirlAyXWlnrAZcgWlRYtHbAZcYWkMmmN2ktIdAJcViGfsWGhAFKaasXeLMIx-mFxfLDduTcUFRecHP6yLb368LS4fthTX0W1viyzvQz-NPgxZf6LxZ4jf03P2tHN9oheH85R9_fD-ZnFZXn3-uFycX5WtqHAsO92gcabTAEYIaqRdGelAQtUa1SkUZEXTGuSNAu1AG4tCNZV15FaklBSn7O3-3m0MPyZKY73xqaW-dwOFKdWorebSaGsyffOI3oUp5k9nZQSvQCtjs3p9UFOzoVW9jX7j4kP9p5sMcA_aGFKK1P0lHOrdAPXvAerdAPVhgBwyj0KtH92uszH32v8_-mof9UT0z1sgKim1-AVFN5Eg |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1016_j_neucom_2025_130161 crossref_primary_10_1109_TPAMI_2025_3586712 crossref_primary_10_1038_s41598_024_53360_1 crossref_primary_10_1016_j_sigpro_2024_109718 crossref_primary_10_1109_TGRS_2024_3451471 crossref_primary_10_1109_TCSVT_2024_3411655 crossref_primary_10_1016_j_engappai_2024_109067 crossref_primary_10_1109_TMM_2024_3382873 crossref_primary_10_1016_j_engappai_2025_111373 crossref_primary_10_1016_j_eswa_2023_121339 crossref_primary_10_3390_pr13061628 crossref_primary_10_1109_TPAMI_2024_3416731 crossref_primary_10_1016_j_knosys_2025_114086 crossref_primary_10_1049_csy2_12115 crossref_primary_10_1007_s00371_024_03659_x crossref_primary_10_1109_TCSVT_2025_3559624 crossref_primary_10_1016_j_jvcir_2024_104060 crossref_primary_10_1109_TPAMI_2025_3556133 crossref_primary_10_3390_sym15081571 crossref_primary_10_1049_ipr2_13258 crossref_primary_10_3390_wevj16020072 crossref_primary_10_1016_j_inffus_2025_103016 crossref_primary_10_1016_j_engappai_2024_109207 crossref_primary_10_1109_LSP_2023_3330129 crossref_primary_10_1007_s00371_023_03252_8 crossref_primary_10_1109_TCSVT_2025_3543622 crossref_primary_10_1109_TCSVT_2023_3337884 crossref_primary_10_1002_adma_202310704 |
| Cites_doi | 10.1007/978-3-030-01246-5_21 10.1109/CVPR.2019.00821 10.1109/TPAMI.2021.3095064 10.1109/CVPR46437.2021.01212 10.1007/978-3-030-58520-4_22 10.1109/CVPR.2018.00079 10.1109/TIP.2018.2867951 10.1109/CVPR42600.2020.00179 10.1109/CVPR.2016.90 10.1109/CVPR.2017.186 10.1109/CVPR.2018.00324 10.1145/3240508.3240636 10.1109/TIP.2020.3013166 10.1038/nature01276 10.1007/s11263-020-01428-6 10.1109/CVPR42600.2020.00897 10.1109/CVPR42600.2020.00297 10.1109/CVPR.2017.183 10.1007/s11263-020-01425-9 10.1109/CVPR.2018.00133 10.1109/ICCV.2015.388 10.1109/CVPR.2018.00810 10.1109/CVPR42600.2020.01459 10.1109/TIP.2017.2691802 10.1109/CVPR42600.2020.01457 10.1109/TPAMI.2021.3061604 10.1007/978-3-030-01234-2_16 10.1109/CVPR.2018.00813 10.1073/pnas.1611835114 10.1109/CVPR.2019.00400 10.1109/TCSVT.2019.2920407 10.1109/TPAMI.2019.2938758 10.1038/nature08577 10.1109/TPAMI.2020.2968521 10.1109/TPAMI.2019.2918284 10.1109/CVPR.2016.299 10.1109/TPAMI.2018.2873610 10.1007/s13042-020-01061-2 10.1016/j.neunet.2019.01.012 10.1109/TIP.2011.2179057 10.1109/CVPR46437.2021.00025 10.1609/aaai.v33i01.33013558 10.1109/ICCV48922.2021.00495 10.1109/TIP.2020.2993406 10.1016/j.cviu.2019.05.003 10.1109/TNNLS.2019.2921597 10.1109/TIP.2021.3074804 10.1109/TPAMI.2020.2969348 10.1007/s11263-020-01416-w 10.1109/TIP.2017.2662206 10.1007/s11263-006-0028-6 10.1109/TIP.2020.2973802 10.1109/CVPR42600.2020.00280 10.1109/TPAMI.2019.2895793 10.1109/CVPR.2019.00406 10.1109/CVPR.2011.5995401 10.1109/TPAMI.2020.2995190 10.1073/pnas.0605184103 10.1109/TMM.2013.2284759 10.1609/aaai.v34i07.6954 10.1109/CVPR42600.2020.00317 10.1109/ICCV48922.2021.00420 10.1109/CVPR42600.2020.00837 10.1109/CVPR.2018.00745 10.1109/ICCV.2017.275 10.1109/TPAMI.2017.2773081 10.1109/CVPR.2019.01255 10.1109/ICCV.2017.191 10.1109/CVPR46437.2021.00487 10.1109/TIP.2020.2990606 10.1109/ICCV48922.2021.00494 10.1109/ICCV.2017.189 10.1109/ICCV48922.2021.00475 10.1109/CVPR.2017.301 10.1007/s11263-020-01421-z 10.1109/CVPR.2018.00695 10.1109/CVPR.2017.587 10.1109/WACV.2017.145 10.1109/ICCV.2013.247 10.1109/TPAMI.2021.3088914 10.1109/ICCV.2017.368 10.1007/978-3-030-58621-8_23 10.1109/AVSS.2019.8909828 10.1109/CVPR.2019.00396 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TPAMI.2023.3241756 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | Technology Research Database PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 9551 |
| ExternalDocumentID | 37022385 10_1109_TPAMI_2023_3241756 10035447 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: National Key R&D Program of China grantid: 2020AAA0105702 – fundername: National Natural Science Foundation of China grantid: 62225207; 62276243; U19B2038 funderid: 10.13039/501100001809 – fundername: University Synergy Innovation Program of Anhui Province grantid: GXXT-2019-025 |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION NPM RIG 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c352t-f7b28a8f700833eb49d84a0405c86f623e93bc821b607a0789236b59aeade6643 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 35 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001022958600017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Sun Sep 28 03:27:12 EDT 2025 Sun Nov 09 07:21:54 EST 2025 Mon Jul 21 05:27:55 EDT 2025 Sat Nov 29 02:58:22 EST 2025 Tue Nov 18 22:43:54 EST 2025 Wed Aug 27 02:25:48 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| 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-c352t-f7b28a8f700833eb49d84a0405c86f623e93bc821b607a0789236b59aeade6643 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0001-8849-5228 0000-0003-2510-8993 0000-0001-8036-4071 |
| PMID | 37022385 |
| PQID | 2831507689 |
| PQPubID | 85458 |
| PageCount | 18 |
| ParticipantIDs | ieee_primary_10035447 crossref_citationtrail_10_1109_TPAMI_2023_3241756 pubmed_primary_37022385 crossref_primary_10_1109_TPAMI_2023_3241756 proquest_miscellaneous_2797148798 proquest_journals_2831507689 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-08-01 |
| PublicationDateYYYYMMDD | 2023-08-01 |
| PublicationDate_xml | – month: 08 year: 2023 text: 2023-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2023 |
| 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 | ref57 ref56 ref59 ref58 ref53 ref52 ref55 zhou (ref84) 2006 chaudhry (ref78) 2019 ref51 ref50 yang (ref10) 2022; 44 hinton (ref90) 2015 ref46 ref45 ref48 ref47 ref41 ref44 ref43 kirkpatrick (ref77) 2017; 114 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref100 ref40 waqas zamir (ref93) 2021 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref39 ref38 aljundi (ref99) 2018 ref24 ref23 ref26 ref25 ref20 defferrard (ref85) 2016 ref22 ref28 ref27 ref29 dosovitskiy (ref96) 2020 ref13 ref12 ref15 ref14 ref97 ref11 ref98 ref17 ref16 ref19 ref18 kingma (ref95) 2015 ref92 zhu (ref42) 2017 ref89 tarvainen (ref91) 2017 ref86 ref88 ref87 krizhevsky (ref94) 2012 ref82 ref81 ref83 ref79 yoon (ref80) 2018 ref75 ref74 ref76 ref2 ref1 ref71 ref70 ref73 ref72 kipf (ref62) 2017 ref68 ref67 ref69 ref64 ref63 ref66 ref65 goodfellow (ref54) 2014 ref60 ref61 zhang (ref21) 2019 |
| References_xml | – ident: ref64 doi: 10.1007/978-3-030-01246-5_21 – ident: ref56 doi: 10.1109/CVPR.2019.00821 – ident: ref81 doi: 10.1109/TPAMI.2021.3095064 – ident: ref97 doi: 10.1109/CVPR46437.2021.01212 – start-page: 1 year: 2020 ident: ref96 article-title: An image is worth 16x16 words: Transformers for image recognition at scale publication-title: Proc Int Conf Learn Representations – ident: ref49 doi: 10.1007/978-3-030-58520-4_22 – ident: ref55 doi: 10.1109/CVPR.2018.00079 – ident: ref98 doi: 10.1109/TIP.2018.2867951 – ident: ref9 doi: 10.1109/CVPR42600.2020.00179 – ident: ref15 doi: 10.1109/CVPR.2016.90 – ident: ref51 doi: 10.1109/CVPR.2017.186 – ident: ref19 doi: 10.1109/CVPR.2018.00324 – ident: ref67 doi: 10.1145/3240508.3240636 – ident: ref65 doi: 10.1109/TIP.2020.3013166 – start-page: 2526 year: 2017 ident: ref42 article-title: Joint bi-layer optimization for single-image rain streak removal publication-title: Proc IEEE Int Conf Comput Vis – ident: ref89 doi: 10.1038/nature01276 – ident: ref68 doi: 10.1007/s11263-020-01428-6 – ident: ref66 doi: 10.1109/CVPR42600.2020.00897 – ident: ref71 doi: 10.1109/CVPR42600.2020.00297 – ident: ref28 doi: 10.1109/CVPR.2017.183 – ident: ref34 doi: 10.1007/s11263-020-01425-9 – ident: ref63 doi: 10.1109/CVPR.2018.00133 – ident: ref40 doi: 10.1109/ICCV.2015.388 – ident: ref79 doi: 10.1109/CVPR.2018.00810 – start-page: 1 year: 2019 ident: ref78 article-title: Efficient lifelong learning with A-GEM publication-title: Proc Int Conf Learn Representations – year: 2015 ident: ref90 article-title: Distilling the knowledge in a neural network – ident: ref70 doi: 10.1109/CVPR42600.2020.01459 – ident: ref50 doi: 10.1109/TIP.2017.2691802 – ident: ref59 doi: 10.1109/CVPR42600.2020.01457 – ident: ref26 doi: 10.1109/TPAMI.2021.3061604 – ident: ref52 doi: 10.1007/978-3-030-01234-2_16 – start-page: 139 year: 2018 ident: ref99 article-title: Memory aware synapses: Learning what (not) to forget publication-title: Proc Eur Conf Comput Vis – start-page: 14816 year: 2021 ident: ref93 article-title: Multi-stage progressive image restoration publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref86 doi: 10.1109/CVPR.2018.00813 – volume: 114 start-page: 3521 year: 2017 ident: ref77 article-title: Overcoming catastrophic forgetting in neural networks publication-title: Proc Nat Acad Sci doi: 10.1073/pnas.1611835114 – ident: ref61 doi: 10.1109/CVPR.2019.00400 – ident: ref29 doi: 10.1109/TCSVT.2019.2920407 – ident: ref17 doi: 10.1109/TPAMI.2019.2938758 – ident: ref88 doi: 10.1038/nature08577 – ident: ref23 doi: 10.1109/TPAMI.2020.2968521 – ident: ref16 doi: 10.1109/TPAMI.2019.2918284 – start-page: 1097 year: 2012 ident: ref94 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc Int Conf Neural Inf Process – ident: ref14 doi: 10.1109/CVPR.2016.299 – ident: ref20 doi: 10.1109/TPAMI.2018.2873610 – ident: ref3 doi: 10.1007/s13042-020-01061-2 – ident: ref72 doi: 10.1016/j.neunet.2019.01.012 – ident: ref12 doi: 10.1109/TIP.2011.2179057 – ident: ref100 doi: 10.1109/CVPR46437.2021.00025 – ident: ref35 doi: 10.1609/aaai.v33i01.33013558 – ident: ref27 doi: 10.1109/ICCV48922.2021.00495 – ident: ref58 doi: 10.1109/TIP.2020.2993406 – ident: ref44 doi: 10.1016/j.cviu.2019.05.003 – ident: ref43 doi: 10.1109/TNNLS.2019.2921597 – ident: ref47 doi: 10.1109/TIP.2021.3074804 – ident: ref22 doi: 10.1109/TPAMI.2020.2969348 – ident: ref4 doi: 10.1007/s11263-020-01416-w – start-page: 3844 year: 2016 ident: ref85 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Proc 30th Int Conf Neural Inf Process Syst – volume: 44 start-page: 8569 year: 2022 ident: ref10 article-title: Recurrent multi-frame deraining: Combining physics guidance and adversarial learning publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref18 doi: 10.1109/TIP.2017.2662206 – ident: ref5 doi: 10.1007/s11263-006-0028-6 – ident: ref48 doi: 10.1109/TIP.2020.2973802 – ident: ref11 doi: 10.1109/CVPR42600.2020.00280 – ident: ref30 doi: 10.1109/TPAMI.2019.2895793 – ident: ref31 doi: 10.1109/CVPR.2019.00406 – ident: ref69 doi: 10.1109/CVPR.2011.5995401 – start-page: 1 year: 2018 ident: ref80 article-title: Lifelong learning with dynamically expandable networks publication-title: Proc Int Conf Learn Representations – ident: ref2 doi: 10.1109/TPAMI.2020.2995190 – ident: ref87 doi: 10.1073/pnas.0605184103 – ident: ref39 doi: 10.1109/TMM.2013.2284759 – ident: ref92 doi: 10.1609/aaai.v34i07.6954 – start-page: 1195 year: 2017 ident: ref91 article-title: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results publication-title: Proc Int Conf Neural Inf Process – ident: ref32 doi: 10.1109/CVPR42600.2020.00317 – ident: ref60 doi: 10.1109/ICCV48922.2021.00420 – ident: ref45 doi: 10.1109/CVPR42600.2020.00837 – ident: ref53 doi: 10.1109/CVPR.2018.00745 – start-page: 1601 year: 2006 ident: ref84 article-title: Learning with hypergraphs: Clustering, classification, and embedding publication-title: Proc Adv Neural Inf Process Syst – ident: ref7 doi: 10.1109/ICCV.2017.275 – ident: ref76 doi: 10.1109/TPAMI.2017.2773081 – ident: ref57 doi: 10.1109/CVPR.2019.01255 – start-page: 1 year: 2019 ident: ref21 article-title: Residual non-local attention networks for image restoration publication-title: Proc Int Conf Learn Representations – ident: ref37 doi: 10.1109/ICCV.2017.191 – ident: ref83 doi: 10.1109/CVPR46437.2021.00487 – start-page: 2672 year: 2014 ident: ref54 article-title: Generative adversarial nets publication-title: Proc Adv Neural Inf Process Syst – ident: ref46 doi: 10.1109/TIP.2020.2990606 – ident: ref36 doi: 10.1109/ICCV48922.2021.00494 – ident: ref41 doi: 10.1109/ICCV.2017.189 – ident: ref25 doi: 10.1109/ICCV48922.2021.00475 – start-page: 1 year: 2017 ident: ref62 article-title: Semi-supervised classification with graph convolutional networks publication-title: Proc Int Conf Learn Representations – ident: ref6 doi: 10.1109/CVPR.2017.301 – ident: ref33 doi: 10.1007/s11263-020-01421-z – ident: ref8 doi: 10.1109/CVPR.2018.00695 – ident: ref73 doi: 10.1109/CVPR.2017.587 – ident: ref38 doi: 10.1109/WACV.2017.145 – ident: ref13 doi: 10.1109/ICCV.2013.247 – start-page: 1 year: 2015 ident: ref95 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Representations – ident: ref24 doi: 10.1109/TPAMI.2021.3088914 – ident: ref74 doi: 10.1109/ICCV.2017.368 – ident: ref82 doi: 10.1007/978-3-030-58621-8_23 – ident: ref75 doi: 10.1109/AVSS.2019.8909828 – ident: ref1 doi: 10.1109/CVPR.2019.00396 |
| SSID | ssj0014503 |
| Score | 2.6157742 |
| Snippet | Image deraining is a challenging task since rain streaks have the characteristics of a spatially long structure and have a complex diversity. Existing deep... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 9534 |
| SubjectTerms | Algorithms Brain Continual learning Convolution Convolutional codes Datasets Deep learning Graph theory Graphs hypergraph convolution image deraining image restoration Machine learning Memory Optimization Plastic properties Rain Synapses Synthetic data Task analysis Training |
| Title | Continual Image Deraining With Hypergraph Convolutional Networks |
| URI | https://ieeexplore.ieee.org/document/10035447 https://www.ncbi.nlm.nih.gov/pubmed/37022385 https://www.proquest.com/docview/2831507689 https://www.proquest.com/docview/2797148798 |
| Volume | 45 |
| WOSCitedRecordID | wos001022958600017&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLYAcYAD70d5qUjcUEfXpnncQMA0DkwcQOxWpW0iJsGG9vr92Gk67QISt0p12yi24y-N7Q_gKsU1rop1EcVJYSPGdBZpXQm8UpXlmY11XDmyCdHryX5fvfhidVcLY4xxyWemRZfuLL8alTP6VYYeHqcZY2IVVoXgdbHW4siAZY4GGSEMujjuI5oKmVjdvL7cPT-1iCi8hfgBAyYRF6UCw1dKHMpLAckxrPwONl3Q6Wz_c7g7sOXRZXhXm8MurJjhHmw3zA2hd-Q92FxqQ7gPt9SiakC9ScOnL1xfwgfjiSPC98H0I-ziXnXsOluHKDn3xorSvTqHfHIAb53H1_tu5JkVohIB1zSyokikllYQAktNgYqRTKM_Z6XkFhGRUWlRyqRd8Fho6kifpLzIlKb0ao4g5hDWhqOhOYaQlanmJrOs4opRO_uKy6RCoMGstW2eBdBupjcvfdtxYr_4zN32I1a5005O2sm9dgK4XjzzXTfd-FP6gOZ-SbKe9gDOGjXm3jEnOaIpgsBcqgAuF7fRpeicRA_NaIYyQgncJQolAziq1b94eWM1J7989BQ2aGx1iuAZrE3HM3MO6-V8OpiML9Bu-_LC2e0PFVTksA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4VikQ5lJZnyqNB4oayeBPHj1sRLdpVYcVhEdwiJ7HVlcputQ9-PzOOs9oLSD3FUiaJ5ZnxfBPb8wGcZzjH1cyUCUtLl3Bu8sSYWmJL107kjhlWe7IJORiopyd9Hw6r-7Mw1lq_-cx2qOnX8utJtaBfZejhLMs5l2vwES8pa45rLRcNeO6JkBHEoJNjJtGekWH6cnh_ddfvEFV4BxEEhkyiLsokBrCMWJRXQpLnWHkbbvqwc7P9nx3-Ap8DvoyvGoP4Ch_seAe2W-6GOLjyDmytFCLchR9UpGpE1Unj_jPOMPFPG6gj4sfR_E_cw2x16mtbxyj5EswVpQfNLvLZHjzc_Bpe95LArZBUCLnmiZNlqoxykjBYZktUjeIGPTqvlHCIiazOykql3VIwaagmfZqJMteGNlgLhDH7sD6ejO0hxLzKjLC547XQnAra10KlNUIN7pzrijyCbju8RRUKjxP_xd_CJyBMF147BWmnCNqJ4GL5zL-m7Ma70ns09iuSzbBHcNyqsQiuOSsQTxEIFkpHcLa8jU5FKyVmbCcLlJFaYp4otYrgoFH_8uWt1Xx746PfYbM3vLstbvuD30fwifrZbBg8hvX5dGFPYKN6mY9m01Nvva_AW-cP |
| 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=Continual+Image+Deraining+With+Hypergraph+Convolutional+Networks&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Fu%2C+Xueyang&rft.au=Xiao%2C+Jie&rft.au=Zhu%2C+Yurui&rft.au=Liu%2C+Aiping&rft.date=2023-08-01&rft.pub=IEEE&rft.issn=0162-8828&rft.volume=45&rft.issue=8&rft.spage=9534&rft.epage=9551&rft_id=info:doi/10.1109%2FTPAMI.2023.3241756&rft_id=info%3Apmid%2F37022385&rft.externalDocID=10035447 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |