Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images Article Swipe
Shiyu Miao
,
Delong Chen
,
Fan Liu
,
Chuanyi Zhang
,
Yanhui Gu
,
Shengjie Guo
,
Jun Zhou
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.06194
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.06194
The Direct Segment Anything Model (DirectSAM) excels in class-agnostic contour extraction. In this paper, we explore its use by applying it to optical remote sensing imagery, where semantic contour extraction-such as identifying buildings, road networks, and coastlines-holds significant practical value. Those applications are currently handled via training specialized small models separately on small datasets in each domain. We introduce a foundation model derived from DirectSAM, termed DirectSAM-RS, which not only inherits the strong segmentation capability acquired from natural images, but also benefits from a large-scale dataset we created for remote sensing semantic contour extraction. This dataset comprises over 34k image-text-contour triplets, making it at least 30 times larger than individual dataset. DirectSAM-RS integrates a prompter module: a text encoder and cross-attention layers attached to the DirectSAM architecture, which allows flexible conditioning on target class labels or referring expressions. We evaluate the DirectSAM-RS in both zero-shot and fine-tuning setting, and demonstrate that it achieves state-of-the-art performance across several downstream benchmarks.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2410.06194
- https://arxiv.org/pdf/2410.06194
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403344689
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403344689Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2410.06194Digital Object Identifier
- Title
-
Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing ImagesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-08Full publication date if available
- Authors
-
Shiyu Miao, Delong Chen, Fan Liu, Chuanyi Zhang, Yanhui Gu, Shengjie Guo, Jun ZhouList of authors in order
- Landing page
-
https://arxiv.org/abs/2410.06194Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2410.06194Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2410.06194Direct OA link when available
- Concepts
-
Computer science, Extraction (chemistry), Artificial intelligence, Computer vision, Remote sensing, Pattern recognition (psychology), Geography, Chemistry, ChromatographyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403344689 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2410.06194 |
| ids.doi | https://doi.org/10.48550/arxiv.2410.06194 |
| ids.openalex | https://openalex.org/W4403344689 |
| fwci | |
| type | preprint |
| title | Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10689 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9865000247955322 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2214 |
| topics[0].subfield.display_name | Media Technology |
| topics[0].display_name | Remote-Sensing Image Classification |
| topics[1].id | https://openalex.org/T12983 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9556999802589417 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2212 |
| topics[1].subfield.display_name | Ocean Engineering |
| topics[1].display_name | Satellite Image Processing and Photogrammetry |
| topics[2].id | https://openalex.org/T10627 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9465000033378601 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Advanced Image and Video Retrieval Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6006672382354736 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C4725764 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5366321206092834 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q844704 |
| concepts[1].display_name | Extraction (chemistry) |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5062721967697144 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C31972630 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4338390529155731 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[3].display_name | Computer vision |
| concepts[4].id | https://openalex.org/C62649853 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3857535421848297 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q199687 |
| concepts[4].display_name | Remote sensing |
| concepts[5].id | https://openalex.org/C153180895 |
| concepts[5].level | 2 |
| concepts[5].score | 0.3490162193775177 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[5].display_name | Pattern recognition (psychology) |
| concepts[6].id | https://openalex.org/C205649164 |
| concepts[6].level | 0 |
| concepts[6].score | 0.2624273896217346 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[6].display_name | Geography |
| concepts[7].id | https://openalex.org/C185592680 |
| concepts[7].level | 0 |
| concepts[7].score | 0.06656131148338318 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[7].display_name | Chemistry |
| concepts[8].id | https://openalex.org/C43617362 |
| concepts[8].level | 1 |
| concepts[8].score | 0.053963810205459595 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q170050 |
| concepts[8].display_name | Chromatography |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6006672382354736 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/extraction |
| keywords[1].score | 0.5366321206092834 |
| keywords[1].display_name | Extraction (chemistry) |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5062721967697144 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-vision |
| keywords[3].score | 0.4338390529155731 |
| keywords[3].display_name | Computer vision |
| keywords[4].id | https://openalex.org/keywords/remote-sensing |
| keywords[4].score | 0.3857535421848297 |
| keywords[4].display_name | Remote sensing |
| keywords[5].id | https://openalex.org/keywords/pattern-recognition |
| keywords[5].score | 0.3490162193775177 |
| keywords[5].display_name | Pattern recognition (psychology) |
| keywords[6].id | https://openalex.org/keywords/geography |
| keywords[6].score | 0.2624273896217346 |
| keywords[6].display_name | Geography |
| keywords[7].id | https://openalex.org/keywords/chemistry |
| keywords[7].score | 0.06656131148338318 |
| keywords[7].display_name | Chemistry |
| keywords[8].id | https://openalex.org/keywords/chromatography |
| keywords[8].score | 0.053963810205459595 |
| keywords[8].display_name | Chromatography |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2410.06194 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2410.06194 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2410.06194 |
| locations[1].id | doi:10.48550/arxiv.2410.06194 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2410.06194 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5109643500 |
| authorships[0].author.orcid | https://orcid.org/0009-0006-1588-4760 |
| authorships[0].author.display_name | Shiyu Miao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Miao, Shiyu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5020620488 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-8172-2894 |
| authorships[1].author.display_name | Delong Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chen, Delong |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100960969 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Fan Liu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Liu, Fan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5101465467 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8724-5796 |
| authorships[3].author.display_name | Chuanyi Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhang, Chuanyi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100749023 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8838-3186 |
| authorships[4].author.display_name | Yanhui Gu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Gu, Yanhui |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5059221217 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-7365-5487 |
| authorships[5].author.display_name | Shengjie Guo |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Guo, Shengjie |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100781212 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-5822-8233 |
| authorships[6].author.display_name | Jun Zhou |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Zhou, Jun |
| authorships[6].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2410.06194 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-10-12T00:00:00 |
| display_name | Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10689 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9865000247955322 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2214 |
| primary_topic.subfield.display_name | Media Technology |
| primary_topic.display_name | Remote-Sensing Image Classification |
| related_works | https://openalex.org/W2058170566, https://openalex.org/W2772917594, https://openalex.org/W2755342338, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398, https://openalex.org/W2775347418 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2410.06194 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2410.06194 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2410.06194 |
| primary_location.id | pmh:oai:arXiv.org:2410.06194 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2410.06194 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2410.06194 |
| publication_date | 2024-10-08 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 59, 83, 113, 116 |
| abstract_inverted_index.30 | 105 |
| abstract_inverted_index.In | 11 |
| abstract_inverted_index.We | 57, 138 |
| abstract_inverted_index.as | 30 |
| abstract_inverted_index.at | 103 |
| abstract_inverted_index.by | 18 |
| abstract_inverted_index.in | 7, 54, 142 |
| abstract_inverted_index.it | 20, 102, 151 |
| abstract_inverted_index.on | 51, 131 |
| abstract_inverted_index.or | 135 |
| abstract_inverted_index.to | 21, 123 |
| abstract_inverted_index.we | 14, 86 |
| abstract_inverted_index.34k | 98 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 35, 119, 145, 148 |
| abstract_inverted_index.are | 42 |
| abstract_inverted_index.but | 79 |
| abstract_inverted_index.for | 88 |
| abstract_inverted_index.its | 16 |
| abstract_inverted_index.not | 68 |
| abstract_inverted_index.the | 71, 124, 140 |
| abstract_inverted_index.use | 17 |
| abstract_inverted_index.via | 45 |
| abstract_inverted_index.This | 94 |
| abstract_inverted_index.also | 80 |
| abstract_inverted_index.both | 143 |
| abstract_inverted_index.each | 55 |
| abstract_inverted_index.from | 63, 76, 82 |
| abstract_inverted_index.only | 69 |
| abstract_inverted_index.over | 97 |
| abstract_inverted_index.road | 33 |
| abstract_inverted_index.text | 117 |
| abstract_inverted_index.than | 108 |
| abstract_inverted_index.that | 150 |
| abstract_inverted_index.this | 12 |
| abstract_inverted_index.Model | 4 |
| abstract_inverted_index.Those | 40 |
| abstract_inverted_index.class | 133 |
| abstract_inverted_index.least | 104 |
| abstract_inverted_index.model | 61 |
| abstract_inverted_index.small | 48, 52 |
| abstract_inverted_index.times | 106 |
| abstract_inverted_index.where | 26 |
| abstract_inverted_index.which | 67, 127 |
| abstract_inverted_index.Direct | 1 |
| abstract_inverted_index.across | 155 |
| abstract_inverted_index.allows | 128 |
| abstract_inverted_index.excels | 6 |
| abstract_inverted_index.labels | 134 |
| abstract_inverted_index.larger | 107 |
| abstract_inverted_index.layers | 121 |
| abstract_inverted_index.making | 101 |
| abstract_inverted_index.models | 49 |
| abstract_inverted_index.paper, | 13 |
| abstract_inverted_index.remote | 23, 89 |
| abstract_inverted_index.strong | 72 |
| abstract_inverted_index.target | 132 |
| abstract_inverted_index.termed | 65 |
| abstract_inverted_index.value. | 39 |
| abstract_inverted_index.Segment | 2 |
| abstract_inverted_index.contour | 9, 28, 92 |
| abstract_inverted_index.created | 87 |
| abstract_inverted_index.dataset | 85, 95 |
| abstract_inverted_index.derived | 62 |
| abstract_inverted_index.domain. | 56 |
| abstract_inverted_index.encoder | 118 |
| abstract_inverted_index.explore | 15 |
| abstract_inverted_index.handled | 44 |
| abstract_inverted_index.images, | 78 |
| abstract_inverted_index.module: | 115 |
| abstract_inverted_index.natural | 77 |
| abstract_inverted_index.optical | 22 |
| abstract_inverted_index.sensing | 24, 90 |
| abstract_inverted_index.several | 156 |
| abstract_inverted_index.Anything | 3 |
| abstract_inverted_index.achieves | 152 |
| abstract_inverted_index.acquired | 75 |
| abstract_inverted_index.applying | 19 |
| abstract_inverted_index.attached | 122 |
| abstract_inverted_index.benefits | 81 |
| abstract_inverted_index.dataset. | 110 |
| abstract_inverted_index.datasets | 53 |
| abstract_inverted_index.evaluate | 139 |
| abstract_inverted_index.flexible | 129 |
| abstract_inverted_index.imagery, | 25 |
| abstract_inverted_index.inherits | 70 |
| abstract_inverted_index.prompter | 114 |
| abstract_inverted_index.semantic | 27, 91 |
| abstract_inverted_index.setting, | 147 |
| abstract_inverted_index.training | 46 |
| abstract_inverted_index.DirectSAM | 125 |
| abstract_inverted_index.comprises | 96 |
| abstract_inverted_index.currently | 43 |
| abstract_inverted_index.introduce | 58 |
| abstract_inverted_index.networks, | 34 |
| abstract_inverted_index.practical | 38 |
| abstract_inverted_index.referring | 136 |
| abstract_inverted_index.triplets, | 100 |
| abstract_inverted_index.zero-shot | 144 |
| abstract_inverted_index.DirectSAM, | 64 |
| abstract_inverted_index.buildings, | 32 |
| abstract_inverted_index.capability | 74 |
| abstract_inverted_index.downstream | 157 |
| abstract_inverted_index.foundation | 60 |
| abstract_inverted_index.individual | 109 |
| abstract_inverted_index.integrates | 112 |
| abstract_inverted_index.separately | 50 |
| abstract_inverted_index.(DirectSAM) | 5 |
| abstract_inverted_index.benchmarks. | 158 |
| abstract_inverted_index.demonstrate | 149 |
| abstract_inverted_index.extraction. | 10, 93 |
| abstract_inverted_index.fine-tuning | 146 |
| abstract_inverted_index.identifying | 31 |
| abstract_inverted_index.large-scale | 84 |
| abstract_inverted_index.performance | 154 |
| abstract_inverted_index.significant | 37 |
| abstract_inverted_index.specialized | 47 |
| abstract_inverted_index.DirectSAM-RS | 111, 141 |
| abstract_inverted_index.applications | 41 |
| abstract_inverted_index.conditioning | 130 |
| abstract_inverted_index.expressions. | 137 |
| abstract_inverted_index.segmentation | 73 |
| abstract_inverted_index.DirectSAM-RS, | 66 |
| abstract_inverted_index.architecture, | 126 |
| abstract_inverted_index.class-agnostic | 8 |
| abstract_inverted_index.cross-attention | 120 |
| abstract_inverted_index.extraction-such | 29 |
| abstract_inverted_index.coastlines-holds | 36 |
| abstract_inverted_index.state-of-the-art | 153 |
| abstract_inverted_index.image-text-contour | 99 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |