RingMo-SAM: A Foundation Model for Segment Anything in Multimodal Remote-Sensing Images
The proposal of the segment anything model (SAM) has created a new paradigm for the deep-learning-based semantic segmentation field and has shown amazing generalization performance. However, we find it may fail or perform poorly on multimodal remote-sensing scenarios, especially synthetic aperture r...
Saved in:
| Published in | IEEE transactions on geoscience and remote sensing Vol. 61; pp. 1 - 16 |
|---|---|
| Main Authors | , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0196-2892 1558-0644 |
| DOI | 10.1109/TGRS.2023.3332219 |
Cover
Loading…
| Abstract | The proposal of the segment anything model (SAM) has created a new paradigm for the deep-learning-based semantic segmentation field and has shown amazing generalization performance. However, we find it may fail or perform poorly on multimodal remote-sensing scenarios, especially synthetic aperture radar (SAR) images. Besides, SAM does not provide category information for objects. In this article, we propose a foundation model for multimodal remote-sensing image segmentation called RingMo-SAM, which can not only segment anything in optical and SAR remote-sensing data, but also identify object categories. First, a large-scale dataset containing millions of segmentation instances is constructed by collecting multiple open-source datasets in this field to train the model. Then, by constructing an instance-type and terrain-type category-decoupling mask decoder (CDMDecoder), the categorywise segmentation of various objects is achieved. In addition, a prompt encoder embedded with the characteristics of multimodal remote-sensing data is designed. It not only supports multibox prompts to improve the segmentation accuracy of multiobjects in complicated remote-sensing scenes, but also supports SAR characteristics prompts to improve the segmentation performance on SAR images. Extensive experimental results on several datasets including iSAID, ISPRS Vaihingen, ISPRS Potsdam, AIR-PolSAR-Seg, and so on have demonstrated the effectiveness of our method. |
|---|---|
| AbstractList | The proposal of the segment anything model (SAM) has created a new paradigm for the deep-learning-based semantic segmentation field and has shown amazing generalization performance. However, we find it may fail or perform poorly on multimodal remote-sensing scenarios, especially synthetic aperture radar (SAR) images. Besides, SAM does not provide category information for objects. In this article, we propose a foundation model for multimodal remote-sensing image segmentation called RingMo-SAM, which can not only segment anything in optical and SAR remote-sensing data, but also identify object categories. First, a large-scale dataset containing millions of segmentation instances is constructed by collecting multiple open-source datasets in this field to train the model. Then, by constructing an instance-type and terrain-type category-decoupling mask decoder (CDMDecoder), the categorywise segmentation of various objects is achieved. In addition, a prompt encoder embedded with the characteristics of multimodal remote-sensing data is designed. It not only supports multibox prompts to improve the segmentation accuracy of multiobjects in complicated remote-sensing scenes, but also supports SAR characteristics prompts to improve the segmentation performance on SAR images. Extensive experimental results on several datasets including iSAID, ISPRS Vaihingen, ISPRS Potsdam, AIR-PolSAR-Seg, and so on have demonstrated the effectiveness of our method. |
| Author | Yan, Zhiyuan Li, Junxi Diao, Wenhui Li, Xuexue Sun, Xian Fu, Kun Feng, Yingchao Zhou, Ruixue Zhang, Wenkai |
| Author_xml | – sequence: 1 givenname: Zhiyuan orcidid: 0000-0002-4264-6868 surname: Yan fullname: Yan, Zhiyuan email: yanzy@aircas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 2 givenname: Junxi orcidid: 0000-0002-9428-9751 surname: Li fullname: Li, Junxi email: lijunxi191@mails.ucas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 3 givenname: Xuexue orcidid: 0000-0002-0177-7001 surname: Li fullname: Li, Xuexue email: lixuexue20@mails.ucas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 4 givenname: Ruixue surname: Zhou fullname: Zhou, Ruixue email: zhouruixue18@mails.ucas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 5 givenname: Wenkai orcidid: 0000-0002-8903-2708 surname: Zhang fullname: Zhang, Wenkai email: zhangwk@aircas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 6 givenname: Yingchao orcidid: 0000-0003-4017-8885 surname: Feng fullname: Feng, Yingchao email: fengyc@aircas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 7 givenname: Wenhui orcidid: 0000-0002-3931-3974 surname: Diao fullname: Diao, Wenhui email: zhangwk@aircas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 8 givenname: Kun orcidid: 0000-0002-8647-9627 surname: Fu fullname: Fu, Kun email: kunfuiecas@gmail.com organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China – sequence: 9 givenname: Xian orcidid: 0000-0002-0038-9816 surname: Sun fullname: Sun, Xian email: sunxian@aircas.ac.cn organization: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China |
| BookMark | eNp9kL1OwzAUhS1UJNrCAyAxRGJO8U_sxGxRRUulVkhNEaPlJE5JldjFcYa-PQ7tgBiY7nDOufeebwJG2mgFwD2CM4Qgf9ott9kMQ0xmhBCMEb8CY0RpEkIWRSMwhoizECcc34BJ1x0gRBFF8Rh8bGu935gwSzfPQRosTK9L6Wqjg40pVRNUxgaZ2rdKuyDVJ_fp7UHt1b5xdWtK2QRb1RqnwkzpbhBXrdyr7hZcV7Lp1N1lTsH74mU3fw3Xb8vVPF2HBeaRCxknJS4UpBCVSikuI5hApnIMGS1knpCclTiqmMwRYmVOClrFMPHGijKWYEqm4PG892jNV686Jw6mt9qfFL4thZBTGnsXOrsKa7rOqkocbd1KexIIioGfGPiJgZ-48POZ-E-mqN0PGmdl3fybfDgna1_p1yWCKPfPfANfy367 |
| CODEN | IGRSD2 |
| CitedBy_id | crossref_primary_10_1080_17538947_2024_2447347 crossref_primary_10_1109_TGRS_2024_3407884 crossref_primary_10_1109_LGRS_2024_3422805 crossref_primary_10_1109_TGRS_2024_3517878 crossref_primary_10_1080_22797254_2024_2447344 crossref_primary_10_3390_jimaging10090220 crossref_primary_10_1117_1_JRS_18_036503 crossref_primary_10_1109_JSTARS_2024_3525072 crossref_primary_10_1109_TGRS_2024_3519891 crossref_primary_10_3389_fenvs_2024_1395337 crossref_primary_10_1109_JSTARS_2025_3542255 crossref_primary_10_1109_JSTARS_2024_3434448 crossref_primary_10_1109_TGRS_2024_3443420 crossref_primary_10_1109_TGRS_2024_3446950 crossref_primary_10_1080_13658816_2024_2397441 crossref_primary_10_1109_TIP_2024_3424335 crossref_primary_10_3390_rs17020179 crossref_primary_10_1080_10095020_2024_2446307 crossref_primary_10_1109_ACCESS_2024_3516519 crossref_primary_10_1109_JSTARS_2024_3504409 crossref_primary_10_1109_TGRS_2025_3531930 crossref_primary_10_1109_TGRS_2025_3529031 crossref_primary_10_3390_rs16193620 crossref_primary_10_1109_JSTARS_2025_3532690 |
| Cites_doi | 10.1145/3560815 10.1007/978-3-030-01228-1_26 10.1016/j.isprsjprs.2017.11.011 10.1109/JSTARS.2021.3119654 10.1007/s11432-022-3663-1 10.1016/j.isprsjprs.2023.04.009 10.1109/JSTARS.2021.3106941 10.1109/LGRS.2021.3063799 10.1162/neco_a_00990 10.1016/j.isprsjprs.2021.12.004 10.1109/TGRS.2022.3176603 10.1109/ICCV48922.2021.00986 10.1109/CVPR.2015.7298965 10.1109/ICCV.2019.00069 10.48550/arXiv.2102.04306 10.1016/j.jag.2021.102638 10.1109/CVPR52688.2022.00135 10.1109/CVPR46437.2021.01625 10.1007/s11263-022-01653-1 10.1109/JSTARS.2018.2873417 10.48550/arXiv.1909.11065 10.1109/TGRS.2023.3317016 10.1007/978-3-031-19827-4_41 10.1109/CVPR52688.2022.01170 10.1109/CVPR.2018.00813 10.1016/j.rse.2019.04.014 10.1007/s11432-022-3599-y 10.1007/978-3-319-24574-4_28 10.1109/CVPR.2019.00584 10.1007/s11432-022-3610-5 10.1109/JSTARS.2020.3032672 10.1109/CVPR52729.2023.01398 10.1109/TGRS.2020.2976658 10.1109/CVPR52729.2023.00682 10.1109/TGRS.2021.3130174 10.1109/CVPR.2017.660 10.1007/s11432-022-3588-0 10.1109/iccv51070.2023.00110 10.1007/978-3-031-19833-5_7 10.1109/CVPR.2016.90 10.48550/arXiv.1802.02611 10.1109/CVPR46437.2021.00681 10.1109/CVPR52688.2022.01369 10.5555/3524938.3525087 10.1109/ICCV48922.2021.00928 10.1109/ICCV51070.2023.00371 10.1109/CVPR52688.2022.01179 10.1109/tnnls.2023.3327962 10.1109/JSTARS.2022.3170326 10.1109/TGRS.2023.3290411 10.1109/TGRS.2016.2554563 10.1109/CVPRW.2016.90 10.1109/CVPR.2019.00326 10.18653/v1/2021.emnlp-main.243 10.1109/TGRS.2022.3194732 |
| 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 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
| DOI | 10.1109/TGRS.2023.3332219 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management |
| 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 Physics |
| EISSN | 1558-0644 |
| EndPage | 16 |
| ExternalDocumentID | 10_1109_TGRS_2023_3332219 10315957 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Key Research and Development Program of China grantid: 2021YFB3900504 funderid: 10.13039/501100012166 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYOK AAYXX CITATION RIG 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
| ID | FETCH-LOGICAL-c294t-693d2ce0501deee9a40806eb2065cab83b6d24f6ab116db3c5f708ee9f5668253 |
| IEDL.DBID | RIE |
| ISSN | 0196-2892 |
| IngestDate | Mon Jun 30 08:22:19 EDT 2025 Tue Jul 01 02:15:16 EDT 2025 Thu Apr 24 23:07:12 EDT 2025 Wed Aug 27 02:25:26 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| 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-c294t-693d2ce0501deee9a40806eb2065cab83b6d24f6ab116db3c5f708ee9f5668253 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-3931-3974 0000-0002-8647-9627 0000-0002-8903-2708 0000-0002-0038-9816 0000-0002-4264-6868 0000-0002-9428-9751 0000-0003-4017-8885 0000-0002-0177-7001 |
| PQID | 2895009557 |
| PQPubID | 85465 |
| PageCount | 16 |
| ParticipantIDs | crossref_primary_10_1109_TGRS_2023_3332219 crossref_citationtrail_10_1109_TGRS_2023_3332219 proquest_journals_2895009557 ieee_primary_10315957 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 20230000 2023-00-00 20230101 |
| PublicationDateYYYYMMDD | 2023-01-01 |
| PublicationDate_xml | – year: 2023 text: 20230000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on geoscience and remote sensing |
| PublicationTitleAbbrev | TGRS |
| 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 | ref13 ref57 ref12 Jain (ref22) 2022 ref56 ref15 ref59 ref14 Dehghani (ref33) 2023 ref58 ref52 Lin (ref71) 2019 Krizhevsky (ref5); 25 ref54 (ref6) 2023 Chen (ref53) 2023 ref17 ref16 ref18 Zamir (ref10) ref50 ref46 ref45 Lisa Li (ref43) 2021 ref48 ref42 Han (ref69); 34 ref8 ref7 ref4 Brown (ref30); 33 ref3 ref40 Yao (ref47) 2021 Jiang (ref49) 2019 ref80 ref35 ref34 ref78 ref37 ref36 Zou (ref9) 2023 ref75 ref74 ref77 ref32 ref76 (ref31) 2023 ref1 (ref11) 2020 Liang (ref38) 2022 Alayrac (ref44); 35 Xu (ref55) 2021 ref70 ref73 ref72 Chen (ref41) 2023 Couprie (ref26) 2013 Liu (ref39) 2023 ref24 ref68 Wang (ref79); 1 ref23 ref67 Bahng (ref51) 2022 ref25 ref20 ref64 ref63 ref66 ref21 ref65 ref28 ref27 Chen (ref2) 2014 ref29 ref60 Chen (ref19) 2017 ref62 ref61 |
| References_xml | – ident: ref36 doi: 10.1145/3560815 – ident: ref4 doi: 10.1007/978-3-030-01228-1_26 – ident: ref27 doi: 10.1016/j.isprsjprs.2017.11.011 – start-page: 28 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. ident: ref10 article-title: iSAID: A large-scale dataset for instance segmentation in aerial images – year: 2022 ident: ref38 article-title: Open-vocabulary semantic segmentation with mask-adapted CLIP publication-title: arXiv:2210.04150 – year: 2021 ident: ref43 article-title: Prefix-tuning: Optimizing continuous prompts for generation publication-title: arXiv:2101.00190 – ident: ref73 doi: 10.1109/JSTARS.2021.3119654 – ident: ref15 doi: 10.1007/s11432-022-3663-1 – ident: ref57 doi: 10.1016/j.isprsjprs.2023.04.009 – volume: 34 start-page: 15908 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref69 article-title: Transformer in transformer – year: 2023 ident: ref39 article-title: Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection publication-title: arXiv:2303.05499 – ident: ref59 doi: 10.1109/JSTARS.2021.3106941 – ident: ref75 doi: 10.1109/LGRS.2021.3063799 – ident: ref14 doi: 10.1162/neco_a_00990 – ident: ref80 doi: 10.1016/j.isprsjprs.2021.12.004 – ident: ref67 doi: 10.1109/TGRS.2022.3176603 – ident: ref78 doi: 10.1109/ICCV48922.2021.00986 – ident: ref61 doi: 10.1109/CVPR.2015.7298965 – ident: ref3 doi: 10.1109/ICCV.2019.00069 – ident: ref70 doi: 10.48550/arXiv.2102.04306 – ident: ref12 doi: 10.1016/j.jag.2021.102638 – ident: ref40 doi: 10.1109/CVPR52688.2022.00135 – ident: ref72 doi: 10.1109/CVPR46437.2021.01625 – volume: 33 start-page: 1877 volume-title: Proc. Adv. Neur. Inf. Process. Sys. ident: ref30 article-title: Language models are few-shot learners – ident: ref45 doi: 10.1007/s11263-022-01653-1 – year: 2023 ident: ref53 article-title: RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model publication-title: arXiv:2306.16269 – year: 2021 ident: ref47 article-title: CPT: Colorful prompt tuning for pre-trained vision-language models publication-title: arXiv:2109.11797 – ident: ref58 doi: 10.1109/JSTARS.2018.2873417 – ident: ref76 doi: 10.48550/arXiv.1909.11065 – ident: ref17 doi: 10.1109/TGRS.2023.3317016 – ident: ref50 doi: 10.1007/978-3-031-19827-4_41 – ident: ref34 doi: 10.1109/CVPR52688.2022.01170 – ident: ref63 doi: 10.1109/CVPR.2018.00813 – ident: ref28 doi: 10.1016/j.rse.2019.04.014 – volume-title: GPT-4 year: 2023 ident: ref6 – ident: ref16 doi: 10.1007/s11432-022-3599-y – year: 2019 ident: ref71 article-title: SAN: Scale-aware network for semantic segmentation of high-resolution aerial images publication-title: arXiv:1907.03089 – year: 2019 ident: ref49 article-title: How can we know what language models know? publication-title: arXiv:1911.12543 – ident: ref60 doi: 10.1007/978-3-319-24574-4_28 – ident: ref66 doi: 10.1109/CVPR.2019.00584 – ident: ref23 doi: 10.1007/s11432-022-3610-5 – ident: ref68 doi: 10.1109/JSTARS.2020.3032672 – ident: ref35 doi: 10.1109/CVPR52729.2023.01398 – ident: ref74 doi: 10.1109/TGRS.2020.2976658 – ident: ref52 doi: 10.1109/CVPR52729.2023.00682 – ident: ref56 doi: 10.1109/TGRS.2021.3130174 – year: 2014 ident: ref2 article-title: Semantic image segmentation with deep convolutional nets and fully connected CRFs publication-title: arXiv:1412.7062 – volume: 35 start-page: 23716 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref44 article-title: Flamingo: A visual language model for few-shot learning – ident: ref1 doi: 10.1109/CVPR.2017.660 – ident: ref24 doi: 10.1007/s11432-022-3588-0 – year: 2022 ident: ref51 article-title: Exploring visual prompts for adapting large-scale models publication-title: arXiv:2203.17274 – ident: ref8 doi: 10.1109/iccv51070.2023.00110 – volume: 1 volume-title: Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks ident: ref79 article-title: LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation – year: 2023 ident: ref41 article-title: SAM fails to segment anything?—SAM-adapter: Adapting SAM in underperformed scenes: Camouflage, shadow, medical image segmentation, and more publication-title: arXiv:2304.09148 – ident: ref46 doi: 10.1007/978-3-031-19833-5_7 – ident: ref77 doi: 10.1109/CVPR.2016.90 – volume: 25 start-page: 1097 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref5 article-title: ImageNet classification with deep convolutional neural networks – year: 2023 ident: ref9 article-title: Segment everything everywhere all at once publication-title: arXiv:2304.06718 – ident: ref20 doi: 10.48550/arXiv.1802.02611 – ident: ref65 doi: 10.1109/CVPR46437.2021.00681 – ident: ref54 doi: 10.1109/CVPR52688.2022.01369 – year: 2022 ident: ref22 article-title: Multimodal contrastive learning for remote sensing tasks publication-title: arXiv:2209.02329 – year: 2017 ident: ref19 article-title: Rethinking atrous convolution for semantic image segmentation publication-title: arXiv:1706.05587 – year: 2013 ident: ref26 article-title: Indoor semantic segmentation using depth information publication-title: arXiv:1301.3572 – ident: ref29 doi: 10.5555/3524938.3525087 – ident: ref62 doi: 10.1109/ICCV48922.2021.00928 – ident: ref7 doi: 10.1109/ICCV51070.2023.00371 – ident: ref32 doi: 10.1109/CVPR52688.2022.01179 – ident: ref48 doi: 10.1109/tnnls.2023.3327962 – volume-title: ISPRS 2D Semantic Labeling Contest Vaihingen year: 2020 ident: ref11 – year: 2021 ident: ref55 article-title: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model publication-title: arXiv:2112. 14757 – ident: ref13 doi: 10.1109/JSTARS.2022.3170326 – volume-title: Introducing Chatgpt year: 2023 ident: ref31 – ident: ref18 doi: 10.1109/TGRS.2023.3290411 – ident: ref21 doi: 10.1109/TGRS.2016.2554563 – ident: ref25 doi: 10.1109/CVPRW.2016.90 – ident: ref64 doi: 10.1109/CVPR.2019.00326 – ident: ref42 doi: 10.18653/v1/2021.emnlp-main.243 – year: 2023 ident: ref33 article-title: Scaling vision transformers to 22 billion parameters publication-title: arXiv:2302.05442 – ident: ref37 doi: 10.1109/TGRS.2022.3194732 |
| SSID | ssj0014517 |
| Score | 2.6073673 |
| Snippet | The proposal of the segment anything model (SAM) has created a new paradigm for the deep-learning-based semantic segmentation field and has shown amazing... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Adaptation models Datasets Decoupling Feature extraction Image processing Image segmentation Multimodal remote-sensing images prompt learning Radar imaging Radar polarimetry Remote sensing SAR (radar) segment anything model (SAM) Semantic segmentation Synthetic aperture radar Task analysis Training |
| Title | RingMo-SAM: A Foundation Model for Segment Anything in Multimodal Remote-Sensing Images |
| URI | https://ieeexplore.ieee.org/document/10315957 https://www.proquest.com/docview/2895009557 |
| Volume | 61 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFH84QdCD3-J0Sg6ehNZ-JW28DVGnMA_rht5K81ER5yauO-hf70vazaEo3tomaVJ-r8n7Je8D4MQXHGmPQqYayxwJitKOyIvQwbUkoYnUHre2Od071hlEtw_0oXZWt74wWmtrfKZdc2nP8tVYTs1W2ZlNScBp3IAGMrfKWWt-ZBBRv_aNZg6yiKA-wvQ9fta_7qWuyRPuhiEKsImqs7AI2awqP6Ziu75cbcDdbGSVWcmzOy2FKz--BW3899A3Yb3WNEm7Eo0tWNKjbVhbiD-4DSvW_lNOduC-hw-6Yydtd89Jm3wlWyImWdqQoGpLUv1oOiHt0Xtp9q3IE5Yae8SXscKOehpR105qLOKx8OYFZ6rJLgyuLvsXHafOueDIgEelw3ioAoSIer7Cj-B5hColQ_qNqorMRRIKpoKoYLnwfaZEKGkRewlWLFAvRLYZ7sHyaDzS-0CCUAeKBYWKsYWPa6DiEcUbTyifSU2b4M1AyGQdkNzkxRhmlph4PDO4ZQa3rMatCafzJq9VNI6_Ku8aHBYqVhA0oTWDOqt_2EmGEkNtOL744Jdmh7Bq3l5tv7RguXyb6iNUSEpxbAXxEz1w2e8 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3JTsMwEB1BEQIOrEWU1QdOSAnZ7NTcKgS0QHtoi-AWxUsQAlpE0wN8PWMnhQoE4pbEtuzoTTLz7FkADn3BkfYoZKqxTJGgKO2INAsd1CV1Wpfa49Y3p91hzZvo8o7elcHqNhZGa22dz7RrLu1ZvhrKsdkqO7YlCTiNZ2GOmmjcIlzr89Agon4ZHc0c5BFBeYjpe_y4f9HtuaZSuBuGKMImr86UGrJ1VX78jK2GOV-BzmRthWPJozvOhSvfv6Vt_PfiV2G5tDVJoxCONZjRg3VYmspAuA7z1gNUjjbgtosP2kOn12ifkAb5KrdETLm0J4LGLenpezMJaQzecrNzRR6w1XgkPg8VTtTViLt2esYnHhtbz_ivGlXh5vysf9p0yqoLjgx4lDuMhypAkKjnK3wJnkZoVDIk4GisyFTUQ8FUEGUsFb7PlAglzWKvjh0ztAyRb4abUBkMB3oLSBDqQLEgUzGO8FELKh5RvPGE8pnUtAbeBIRElinJTWWMp8RSE48nBrfE4JaUuNXg6HPIS5GP46_OVYPDVMcCghrsTqBOyk92lKDEUJuQL97-ZdgBLDT77evkutW52oFFM1OxGbMLlfx1rPfQPMnFvhXKD8Uy3Tc |
| 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=RingMo-SAM%3A+A+Foundation+Model+for+Segment+Anything+in+Multimodal+Remote-Sensing+Images&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Yan%2C+Zhiyuan&rft.au=Li%2C+Junxi&rft.au=Li%2C+Xuexue&rft.au=Zhou%2C+Ruixue&rft.date=2023&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=61&rft.spage=1&rft.epage=16&rft_id=info:doi/10.1109%2FTGRS.2023.3332219&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2023_3332219 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon |