Overcoming Catastrophic Forgetting with Detail-Degradation Decoupling Networks for Super-Resolution
Abstract Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing methods are fine-tuned based on the application target during their usage, which enables them to be applied to new data domains. Neverthel...
Saved in:
Published in | Journal of physics. Conference series Vol. 2637; no. 1; pp. 12023 - 12029 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Bristol
IOP Publishing
01.11.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Abstract
Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing methods are fine-tuned based on the application target during their usage, which enables them to be applied to new data domains. Nevertheless, the extent to which the fine-tuned model can generalize to the original data domain remains unclear, and therefore, additional research is warranted in this particular aspect. To solve the above problems, we analyzed the forgetting phenomenon of super-resolution methods under different degradation kernels, scenarios, and modalities. Then, we introduced Detail-Degradation Decoupling Networks, which separate the inverse process of degradation and the process of recovering high-frequency details in super-resolution. During the incremental learning process, the network parameters can be adjusted based on the task’s characteristics. Our experimental results demonstrate that our approach can significantly reduce catastrophic forgetting in super-resolution reconstruction and enhance the network’s ability to generalize and remain robust. |
---|---|
AbstractList | Abstract
Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing methods are fine-tuned based on the application target during their usage, which enables them to be applied to new data domains. Nevertheless, the extent to which the fine-tuned model can generalize to the original data domain remains unclear, and therefore, additional research is warranted in this particular aspect. To solve the above problems, we analyzed the forgetting phenomenon of super-resolution methods under different degradation kernels, scenarios, and modalities. Then, we introduced Detail-Degradation Decoupling Networks, which separate the inverse process of degradation and the process of recovering high-frequency details in super-resolution. During the incremental learning process, the network parameters can be adjusted based on the task’s characteristics. Our experimental results demonstrate that our approach can significantly reduce catastrophic forgetting in super-resolution reconstruction and enhance the network’s ability to generalize and remain robust. Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing methods are fine-tuned based on the application target during their usage, which enables them to be applied to new data domains. Nevertheless, the extent to which the fine-tuned model can generalize to the original data domain remains unclear, and therefore, additional research is warranted in this particular aspect. To solve the above problems, we analyzed the forgetting phenomenon of super-resolution methods under different degradation kernels, scenarios, and modalities. Then, we introduced Detail-Degradation Decoupling Networks, which separate the inverse process of degradation and the process of recovering high-frequency details in super-resolution. During the incremental learning process, the network parameters can be adjusted based on the task’s characteristics. Our experimental results demonstrate that our approach can significantly reduce catastrophic forgetting in super-resolution reconstruction and enhance the network’s ability to generalize and remain robust. |
Author | Jiang, Yichun Zhan, Weida Liu, Yunqing |
Author_xml | – sequence: 1 givenname: Yichun surname: Jiang fullname: Jiang, Yichun organization: School of Electronic and Information Engineering, Changchun University of Science and Technology , China – sequence: 2 givenname: Yunqing surname: Liu fullname: Liu, Yunqing organization: School of Electronic and Information Engineering, Changchun University of Science and Technology , China – sequence: 3 givenname: Weida surname: Zhan fullname: Zhan, Weida organization: School of Electronic and Information Engineering, Changchun University of Science and Technology , China |
BookMark | eNqFkF1LwzAUhoNMcJv-BgveCbVpkjbtpWzOD4YTp9chzdKts2tqkjr89yZUJoJgbnI453nPxzsCg0Y1EoDzGF7FMMuimBIUpkmeRijFNIojGCOI8BEYHiqDQ5xlJ2BkzBZC7B4dArH4kFqoXdWsgwm33Fit2k0lgpnSa2mtz-8ruwmm0vKqDqdyrfmK20o1LiVU19YeeZR2r_SbCUqlg2XXSh0-S6PqzoOn4LjktZFn3_8YvM5uXiZ34Xxxez-5nocCUYJDzgssZZ4nKM8FLVZFQiSBVEqYYcIp4TmiJU1I6s52ABSli0iBBCG0QHmJx-Ci79tq9d5JY9lWdbpxIxnKnBgmhCaOoj0ltDJGy5K1utpx_cliyLyjzHvFvG_MO8pi1jvqlJe9slLtT-uHp8nyN8jalV8G_wH_N-ILk5WISw |
Cites_doi | 10.1016/j.irbm.2020.08.004 10.1109/CVPR.2016.182 10.1007/978-3-030-11021-5_5 10.1007/978-3-319-10593-2_13 10.1109/ICCVW54120.2021.00217 10.1109/CVPR.2017.19 10.1007/s00521-020-04893-9 10.1109/CVPRW.2017.15 10.1109/CVPR.2018.00262 10.1109/ICCV48922.2021.00475 |
ContentType | Journal Article |
Copyright | Published under licence by IOP Publishing Ltd Published under licence by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: Published under licence by IOP Publishing Ltd – notice: Published under licence by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | O3W TSCCA AAYXX CITATION 8FD 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO H8D HCIFZ L7M P5Z P62 PIMPY PQEST PQQKQ PQUKI PRINS |
DOI | 10.1088/1742-6596/2637/1/012023 |
DatabaseName | IOP_英国物理学会OA刊 IOPscience (Open Access) CrossRef Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni Edition) ProQuest Central UK/Ireland Advanced Technologies & Aerospace Database (1962 - current) ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Aerospace Database SciTech Premium Collection Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Publicly Available Content (ProQuest) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China |
DatabaseTitle | CrossRef Publicly Available Content Database Advanced Technologies & Aerospace Collection Technology Collection Technology Research Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central Advanced Technologies & Aerospace Database Aerospace Database ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest One Academic Advanced Technologies Database with Aerospace |
DatabaseTitleList | CrossRef Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: O3W name: IOP_英国物理学会OA刊 url: http://iopscience.iop.org/ sourceTypes: Enrichment Source Publisher – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 1742-6596 |
ExternalDocumentID | 10_1088_1742_6596_2637_1_012023 JPCS_2637_1_012023 |
GroupedDBID | 1JI 29L 2WC 4.4 5B3 5GY 5PX 5VS 7.Q AAJIO AAJKP ABHWH ACAFW ACHIP AEFHF AEJGL AFKRA AFYNE AIYBF AKPSB ALMA_UNASSIGNED_HOLDINGS ARAPS ASPBG ATQHT AVWKF AZFZN BENPR BGLVJ CCPQU CEBXE CJUJL CRLBU CS3 DU5 E3Z EBS EDWGO EQZZN F5P FRP GROUPED_DOAJ GX1 HCIFZ HH5 IJHAN IOP IZVLO J9A KNG KQ8 LAP N5L N9A O3W OK1 P2P PIMPY PJBAE RIN RNS RO9 ROL SY9 T37 TR2 TSCCA UCJ W28 XSB ~02 AAYXX CITATION 8FD 8FE 8FG ABUWG AZQEC DWQXO H8D L7M P62 PQEST PQQKQ PQUKI PRINS |
ID | FETCH-LOGICAL-c2743-aab3ee995299c7bdb54e407ee0834a74a927f75461089c70cf6104b2c447b29f3 |
IEDL.DBID | IOP |
ISSN | 1742-6588 |
IngestDate | Fri Sep 13 02:09:49 EDT 2024 Fri Aug 23 21:12:02 EDT 2024 Sun Aug 18 14:50:26 EDT 2024 Tue Aug 20 22:15:36 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Language | English |
License | Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c2743-aab3ee995299c7bdb54e407ee0834a74a927f75461089c70cf6104b2c447b29f3 |
OpenAccessLink | https://proxy.k.utb.cz/login?url=https://iopscience.iop.org/article/10.1088/1742-6596/2637/1/012023 |
PQID | 2892705475 |
PQPubID | 4998668 |
PageCount | 7 |
ParticipantIDs | proquest_journals_2892705475 crossref_primary_10_1088_1742_6596_2637_1_012023 iop_journals_10_1088_1742_6596_2637_1_012023 |
PublicationCentury | 2000 |
PublicationDate | 20231101 |
PublicationDateYYYYMMDD | 2023-11-01 |
PublicationDate_xml | – month: 11 year: 2023 text: 20231101 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Bristol |
PublicationPlace_xml | – name: Bristol |
PublicationTitle | Journal of physics. Conference series |
PublicationTitleAlternate | J. Phys.: Conf. Ser |
PublicationYear | 2023 |
Publisher | IOP Publishing |
Publisher_xml | – name: IOP Publishing |
References | Ledig (JPCS_2637_1_012023bib7) 2017 Zhang (JPCS_2637_1_012023bib10) 2021 Kim (JPCS_2637_1_012023bib4) 2016 Zhang (JPCS_2637_1_012023bib6) 2018 Dong (JPCS_2637_1_012023bib3) 2014 Lim (JPCS_2637_1_012023bib5) 2017 Zou (JPCS_2637_1_012023bib1) 2020; 32 Wang (JPCS_2637_1_012023bib9) 2021 Li (JPCS_2637_1_012023bib2) 2021; 42 Wang (JPCS_2637_1_012023bib8) 2018 |
References_xml | – volume: 42 start-page: 120 year: 2021 ident: JPCS_2637_1_012023bib2 article-title: A review of the deep learning methods for medical images super resolution problems publication-title: Irbm doi: 10.1016/j.irbm.2020.08.004 contributor: fullname: Li – start-page: 1646 year: 2016 ident: JPCS_2637_1_012023bib4 doi: 10.1109/CVPR.2016.182 contributor: fullname: Kim – start-page: 0 year: 2018 ident: JPCS_2637_1_012023bib8 doi: 10.1007/978-3-030-11021-5_5 contributor: fullname: Wang – start-page: 184 year: 2014 ident: JPCS_2637_1_012023bib3 doi: 10.1007/978-3-319-10593-2_13 contributor: fullname: Dong – start-page: 1905 year: 2021 ident: JPCS_2637_1_012023bib9 doi: 10.1109/ICCVW54120.2021.00217 contributor: fullname: Wang – start-page: 4681 year: 2017 ident: JPCS_2637_1_012023bib7 doi: 10.1109/CVPR.2017.19 contributor: fullname: Ledig – volume: 32 start-page: 14549 year: 2020 ident: JPCS_2637_1_012023bib1 article-title: Arbitrary-oriented object detection via dense feature fusion and attention model for remote sensing super-resolution image publication-title: Neural Computing and Applications doi: 10.1007/s00521-020-04893-9 contributor: fullname: Zou – start-page: 136 year: 2017 ident: JPCS_2637_1_012023bib5 doi: 10.1109/CVPRW.2017.15 contributor: fullname: Lim – start-page: 2472 year: 2018 ident: JPCS_2637_1_012023bib6 doi: 10.1109/CVPR.2018.00262 contributor: fullname: Zhang – start-page: 4791 year: 2021 ident: JPCS_2637_1_012023bib10 doi: 10.1109/ICCV48922.2021.00475 contributor: fullname: Zhang |
SSID | ssj0033337 |
Score | 2.3840933 |
Snippet | Abstract
Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details.... Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing... |
SourceID | proquest crossref iop |
SourceType | Aggregation Database Enrichment Source Publisher |
StartPage | 12023 |
SubjectTerms | Decoupling Degradation Image enhancement Image reconstruction Image resolution Physics |
SummonAdditionalLinks | – databaseName: ProQuest Technology Collection dbid: 8FG link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhR1Na9swVKQdhV5Gu640W1sE27HCtiRb8mmMpGkoNBt0hdyEJEtrL7HbJP9_7_mDEgatT0Z-NvbT8_v-IOR7TINzhbMs00owmTnBdKErlsMNuXVR8Dbl_25RzB_k7TJfjsh8qIXBtMqBJ7aMuqo9-sgTMAy4Av1C5Yl16AXwm-RH88xwfhTGWfthGnvkQ4Y98bBmfHYz8GQBh-pKIzkDmauHTC8w__q1skh4IVSSJVhOysWOnNp7qpv_mHUrgWZH5GOvOtKf3V4fk1FYfSIHbQqnX58Q_wuoEr4FZBGd2I2Ft6-bxydPZ63XG9ObKXpd6bTNGmVTbBPRTVSCJV9vsTb3L110eeFrCtosvd824YWhi78j0M_kYXb9ZzJn_QgF5jk2H7XWiRDKMgep45WrXC4DmHAhgOYlrZIWkBpVjk3XNQCkPsKZdNxLqRwvozgl-6t6Fc4IDWCZOGl1rIoouU1L0M3TGKzGwKHw-ZikA8JM03XKMG2EW2uDODaIY4M4NpnpcDwmV4BY0_816_fBv-2A3_6e3O9CmKaKY3I-7NMr6Cv1fHn78ldyiA_qqg3Pyf7mZRsuQO3YuMuWov4BrBHQQA priority: 102 providerName: ProQuest |
Title | Overcoming Catastrophic Forgetting with Detail-Degradation Decoupling Networks for Super-Resolution |
URI | https://iopscience.iop.org/article/10.1088/1742-6596/2637/1/012023 https://www.proquest.com/docview/2892705475/abstract/ |
Volume | 2637 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED_RTUi88I0ojMoSPJI29UfsPLJuZUyirRgTe7Ns12YTUhu16Qt_Pec4ESsIIUQeEis6J87lfHe2f3cGeBNyb21hTTZWkmV8bFmmCrXMBFYQxgZGG8j_x1lxdsnPr8TV7ViYddWq_iEWU6LgxMIWEKdG6EPTrBBlMaIFk6PxKMZ_UtaDQzS-edy-4cN80WljhodMQZGxklIdxuvPD9qzUD1sxW9qurE90wfgulYnyMm34a62Q_f9l4SO__dZD-F-65qSd6nGI7jjV4_hbgMRddsn4OYo9SifaOvIxNRmW2_W1fWNI9NmVj3Cp0mc1SUnDSo1O4lpKNKOTXjLrXcx9vcrmSXc-Zagt0wudpXfZHEJIXWAp3A5Pf08OcvaLRoyR2NyU2Ms874sBVo1J-3SCu5xiOg9enbcSG5KKoMUMam7QoLcBSxxSx3n0tIysGdwsFqv_HMgHkc-lhsVlkXg1OQl-v558EbFhUnmRB_y7rfoKmXi0M0KulI68k5H3unIOz3WiXd9eIvc1m2v3P6d_PUe-flicrFPoatl6MNRJw0_SXHYSiV6v1K8-Ld3voR78ZKiG4_goN7s_Ct0c2o7gJ6avh_A4fHpbPFp0Eg1nufsyw-ZUfAv |
link.rule.ids | 315,786,790,12792,21416,27957,27958,33408,33779,38900,38925,43635,43840,53877,53903 |
linkProvider | IOP Publishing |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV3da9swEBdrx2hfxj5Zuq4VbI8TcSTZkp9GSZtmWZsN2kLfhCRLa15iN07-_935gxAKq5-MfTb4dL4v_e6OkG8xCc5lzrKRVoLJkRNMZ7pgKTyQWhcFbyD_1_Nseidn9-l9l3CrO1hlrxMbRV2UHnPkQwgMuAL_QqU_qkeGU6Nwd7UbobFHXkoBphMrxSeXvSYWcKi2IJIzsLS6x3dB0Nddy7Mhz4QajoZYRMrFjnXaW5TVExXd2J3JG_K6cxjpWbvCb8mLsHxHXjXATV-_J_43yCJ8AVggOrZrW69XZfWw8HTS5LoR1Ewx10rPG6woO8fmEO0cJbjkyw1W5P6l8xYNXlPwYenNpgorhon9Viw_kLvJxe14yrrBCcxzbDlqrRMh5HkKtsYrV7hUBgjcQgB_S1olLbAyqhRbrWsgSHyEM-m4l1I5nkfxkewvy2X4RGiAeMRJq2ORRcltkoNHnsRgNW4XCp8OSNIzzFRtfwzT7GtrbZDHBnlskMdmZFoeD8h3YKzp_pX6efKvO-SzP-ObXQpTFXFAjvt12pJuZebo_7dPycH09vrKXP2c__pMDvGlbb3hMdlfrzbhCzgea3fSSNc_ExTPbg |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED9tQyBe-EYUBliCR9ykthM7j6gl2gZ0lcakvVm2aw-E1EZt-sJfzzlOQAUhhMiTZZ0T53z23dm_OwO8Drm3trSGTpTkVEwsp6pUS1pgg8LYwFkH-f84L08uxdlVcXUA9Y9YmHXTL_1jLKZEwYmFPSBOZWhDM1oWVZmxkstsksX4T8azZhkO4QZOYBmdsNPzxbAic3xkCoyMDZUacF5_ftmeljrEnvy2VHf6p74L10PPE-zk63jX2rH79ktSx___tXtwpzdRydvU6j4c-NUDuNlBRd32IbhzlH6UU9R5ZGpas2036-bzF0fqbnc9wqhJ3N0lsw6dSmcxHUW6uQmr3HoXY4CvyTzhz7cErWZysWv8hsajhDQRHsFl_e7T9IT2VzVQx2KSU2Ms976qCtRuTtqlLYRHV9F7tPCEkcJUTAZZxOTuCglyF7AkLHNCSMuqwB_D0Wq98k-AePSArDAqLMsgmMkr9AHy4I2KB5TcFSPIh6HRTcrIobuTdKV05J-O_NORf3qiE_9G8AY5rvvZuf07-as98rPF9GKfQuOAjOB4kIifpOi-MolWsCye_ts3X8KtxazWH07n75_B7ViTAh6P4ajd7PxztHxa-6IT6-9H2PIn |
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=Overcoming+Catastrophic+Forgetting+with+Detail-Degradation+Decoupling+Networks+for+Super-Resolution&rft.jtitle=Journal+of+physics.+Conference+series&rft.au=Jiang%2C+Yichun&rft.au=Liu%2C+Yunqing&rft.au=Zhan%2C+Weida&rft.date=2023-11-01&rft.issn=1742-6588&rft.eissn=1742-6596&rft.volume=2637&rft.issue=1&rft.spage=12023&rft_id=info:doi/10.1088%2F1742-6596%2F2637%2F1%2F012023&rft.externalDBID=n%2Fa&rft.externalDocID=10_1088_1742_6596_2637_1_012023 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1742-6588&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1742-6588&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1742-6588&client=summon |