ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer Article Swipe
Wen Yao
,
Li Chen
,
Minjun Xiong
,
Wenbo Dong
,
Hao Chen
,
Xiong Xiao
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.17688
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.17688
This paper presents Contourformer, a real-time contour-based instance segmentation algorithm. The method is fully based on the DETR paradigm and achieves end-to-end inference through iterative and progressive mechanisms to optimize contours. To improve efficiency and accuracy, we develop two novel techniques: sub-contour decoupling mechanisms and contour fine-grained distribution refinement. In the sub-contour decoupling mechanism, we propose a deformable attention-based module that adaptively selects sampling regions based on the current predicted contour, enabling more effective capturing of object boundary information. Additionally, we design a multi-stage optimization process to enhance segmentation precision by progressively refining sub-contours. The contour fine-grained distribution refinement technique aims to further improve the ability to express fine details of contours. These innovations enable Contourformer to achieve stable and precise segmentation for each instance while maintaining real-time performance. Extensive experiments demonstrate the superior performance of Contourformer on multiple benchmark datasets, including SBD, COCO, and KINS. We conduct comprehensive evaluations and comparisons with existing state-of-the-art methods, showing significant improvements in both accuracy and inference speed. This work provides a new solution for contour-based instance segmentation tasks and lays a foundation for future research, with the potential to become a strong baseline method in this field.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2501.17688
- https://arxiv.org/pdf/2501.17688
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406975639
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406975639Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2501.17688Digital Object Identifier
- Title
-
ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation TransformerWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-29Full publication date if available
- Authors
-
Wen Yao, Li Chen, Minjun Xiong, Wenbo Dong, Hao Chen, Xiong XiaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2501.17688Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2501.17688Direct 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/2501.17688Direct OA link when available
- Concepts
-
End-to-end principle, Computer science, Transformer, Segmentation, Artificial intelligence, Computer vision, Engineering, Electrical engineering, VoltageTop 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/W4406975639 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2501.17688 |
| ids.doi | https://doi.org/10.48550/arxiv.2501.17688 |
| ids.openalex | https://openalex.org/W4406975639 |
| fwci | |
| type | preprint |
| title | ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12111 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9837999939918518 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2209 |
| topics[0].subfield.display_name | Industrial and Manufacturing Engineering |
| topics[0].display_name | Industrial Vision Systems and Defect Detection |
| topics[1].id | https://openalex.org/T10531 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9538000226020813 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Vision and Imaging |
| topics[2].id | https://openalex.org/T10481 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9514999985694885 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1704 |
| topics[2].subfield.display_name | Computer Graphics and Computer-Aided Design |
| topics[2].display_name | Computer Graphics and Visualization Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C74296488 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7285412549972534 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q2527392 |
| concepts[0].display_name | End-to-end principle |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5547595024108887 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C66322947 |
| concepts[2].level | 3 |
| concepts[2].score | 0.5175958871841431 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[2].display_name | Transformer |
| concepts[3].id | https://openalex.org/C89600930 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4414825439453125 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[3].display_name | Segmentation |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4076002836227417 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C31972630 |
| concepts[5].level | 1 |
| concepts[5].score | 0.35823795199394226 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[5].display_name | Computer vision |
| concepts[6].id | https://openalex.org/C127413603 |
| concepts[6].level | 0 |
| concepts[6].score | 0.15803015232086182 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[6].display_name | Engineering |
| concepts[7].id | https://openalex.org/C119599485 |
| concepts[7].level | 1 |
| concepts[7].score | 0.13053807616233826 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[7].display_name | Electrical engineering |
| concepts[8].id | https://openalex.org/C165801399 |
| concepts[8].level | 2 |
| concepts[8].score | 0.049402087926864624 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[8].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/end-to-end-principle |
| keywords[0].score | 0.7285412549972534 |
| keywords[0].display_name | End-to-end principle |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5547595024108887 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/transformer |
| keywords[2].score | 0.5175958871841431 |
| keywords[2].display_name | Transformer |
| keywords[3].id | https://openalex.org/keywords/segmentation |
| keywords[3].score | 0.4414825439453125 |
| keywords[3].display_name | Segmentation |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4076002836227417 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/computer-vision |
| keywords[5].score | 0.35823795199394226 |
| keywords[5].display_name | Computer vision |
| keywords[6].id | https://openalex.org/keywords/engineering |
| keywords[6].score | 0.15803015232086182 |
| keywords[6].display_name | Engineering |
| keywords[7].id | https://openalex.org/keywords/electrical-engineering |
| keywords[7].score | 0.13053807616233826 |
| keywords[7].display_name | Electrical engineering |
| keywords[8].id | https://openalex.org/keywords/voltage |
| keywords[8].score | 0.049402087926864624 |
| keywords[8].display_name | Voltage |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2501.17688 |
| 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/2501.17688 |
| 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/2501.17688 |
| locations[1].id | doi:10.48550/arxiv.2501.17688 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2501.17688 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5089866078 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5224-9834 |
| authorships[0].author.display_name | Wen Yao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | yao, Weiwei |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100379252 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4907-9720 |
| authorships[1].author.display_name | Li Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Li, Chen |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5084017457 |
| authorships[2].author.orcid | https://orcid.org/0009-0006-9914-7169 |
| authorships[2].author.display_name | Minjun Xiong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xiong, Minjun |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5113632510 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-2318-5928 |
| authorships[3].author.display_name | Wenbo Dong |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Dong, Wenbo |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5082764553 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6849-9413 |
| authorships[4].author.display_name | Hao Chen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Chen, Hao |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5057945477 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4471-7946 |
| authorships[5].author.display_name | Xiong Xiao |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Xiao, Xiong |
| authorships[5].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2501.17688 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12111 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9837999939918518 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2209 |
| primary_topic.subfield.display_name | Industrial and Manufacturing Engineering |
| primary_topic.display_name | Industrial Vision Systems and Defect Detection |
| related_works | https://openalex.org/W2772917594, https://openalex.org/W2036807459, https://openalex.org/W2058170566, 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 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2501.17688 |
| 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/2501.17688 |
| 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/2501.17688 |
| primary_location.id | pmh:oai:arXiv.org:2501.17688 |
| 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/2501.17688 |
| 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/2501.17688 |
| publication_date | 2025-01-29 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 56, 82, 168, 178, 188 |
| abstract_inverted_index.In | 49 |
| abstract_inverted_index.To | 31 |
| abstract_inverted_index.We | 146 |
| abstract_inverted_index.by | 90 |
| abstract_inverted_index.in | 159, 192 |
| abstract_inverted_index.is | 12 |
| abstract_inverted_index.of | 75, 110, 135 |
| abstract_inverted_index.on | 15, 66, 137 |
| abstract_inverted_index.to | 28, 86, 101, 106, 116, 186 |
| abstract_inverted_index.we | 36, 54, 80 |
| abstract_inverted_index.The | 10, 94 |
| abstract_inverted_index.and | 19, 25, 34, 44, 119, 144, 150, 162, 176 |
| abstract_inverted_index.for | 122, 171, 180 |
| abstract_inverted_index.new | 169 |
| abstract_inverted_index.the | 16, 50, 67, 104, 132, 184 |
| abstract_inverted_index.two | 38 |
| abstract_inverted_index.DETR | 17 |
| abstract_inverted_index.SBD, | 142 |
| abstract_inverted_index.This | 0, 165 |
| abstract_inverted_index.aims | 100 |
| abstract_inverted_index.both | 160 |
| abstract_inverted_index.each | 123 |
| abstract_inverted_index.fine | 108 |
| abstract_inverted_index.lays | 177 |
| abstract_inverted_index.more | 72 |
| abstract_inverted_index.that | 60 |
| abstract_inverted_index.this | 193 |
| abstract_inverted_index.with | 152, 183 |
| abstract_inverted_index.work | 166 |
| abstract_inverted_index.COCO, | 143 |
| abstract_inverted_index.KINS. | 145 |
| abstract_inverted_index.These | 112 |
| abstract_inverted_index.based | 14, 65 |
| abstract_inverted_index.fully | 13 |
| abstract_inverted_index.novel | 39 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.tasks | 175 |
| abstract_inverted_index.while | 125 |
| abstract_inverted_index.become | 187 |
| abstract_inverted_index.design | 81 |
| abstract_inverted_index.enable | 114 |
| abstract_inverted_index.field. | 194 |
| abstract_inverted_index.future | 181 |
| abstract_inverted_index.method | 11, 191 |
| abstract_inverted_index.module | 59 |
| abstract_inverted_index.object | 76 |
| abstract_inverted_index.speed. | 164 |
| abstract_inverted_index.stable | 118 |
| abstract_inverted_index.strong | 189 |
| abstract_inverted_index.ability | 105 |
| abstract_inverted_index.achieve | 117 |
| abstract_inverted_index.conduct | 147 |
| abstract_inverted_index.contour | 45, 95 |
| abstract_inverted_index.current | 68 |
| abstract_inverted_index.details | 109 |
| abstract_inverted_index.develop | 37 |
| abstract_inverted_index.enhance | 87 |
| abstract_inverted_index.express | 107 |
| abstract_inverted_index.further | 102 |
| abstract_inverted_index.improve | 32, 103 |
| abstract_inverted_index.precise | 120 |
| abstract_inverted_index.process | 85 |
| abstract_inverted_index.propose | 55 |
| abstract_inverted_index.regions | 64 |
| abstract_inverted_index.selects | 62 |
| abstract_inverted_index.showing | 156 |
| abstract_inverted_index.through | 23 |
| abstract_inverted_index.accuracy | 161 |
| abstract_inverted_index.achieves | 20 |
| abstract_inverted_index.baseline | 190 |
| abstract_inverted_index.boundary | 77 |
| abstract_inverted_index.contour, | 70 |
| abstract_inverted_index.enabling | 71 |
| abstract_inverted_index.existing | 153 |
| abstract_inverted_index.instance | 7, 124, 173 |
| abstract_inverted_index.methods, | 155 |
| abstract_inverted_index.multiple | 138 |
| abstract_inverted_index.optimize | 29 |
| abstract_inverted_index.paradigm | 18 |
| abstract_inverted_index.presents | 2 |
| abstract_inverted_index.provides | 167 |
| abstract_inverted_index.refining | 92 |
| abstract_inverted_index.sampling | 63 |
| abstract_inverted_index.solution | 170 |
| abstract_inverted_index.superior | 133 |
| abstract_inverted_index.Extensive | 129 |
| abstract_inverted_index.accuracy, | 35 |
| abstract_inverted_index.benchmark | 139 |
| abstract_inverted_index.capturing | 74 |
| abstract_inverted_index.contours. | 30, 111 |
| abstract_inverted_index.datasets, | 140 |
| abstract_inverted_index.effective | 73 |
| abstract_inverted_index.including | 141 |
| abstract_inverted_index.inference | 22, 163 |
| abstract_inverted_index.iterative | 24 |
| abstract_inverted_index.potential | 185 |
| abstract_inverted_index.precision | 89 |
| abstract_inverted_index.predicted | 69 |
| abstract_inverted_index.real-time | 5, 127 |
| abstract_inverted_index.research, | 182 |
| abstract_inverted_index.technique | 99 |
| abstract_inverted_index.adaptively | 61 |
| abstract_inverted_index.algorithm. | 9 |
| abstract_inverted_index.decoupling | 42, 52 |
| abstract_inverted_index.deformable | 57 |
| abstract_inverted_index.efficiency | 33 |
| abstract_inverted_index.end-to-end | 21 |
| abstract_inverted_index.foundation | 179 |
| abstract_inverted_index.mechanism, | 53 |
| abstract_inverted_index.mechanisms | 27, 43 |
| abstract_inverted_index.refinement | 98 |
| abstract_inverted_index.comparisons | 151 |
| abstract_inverted_index.demonstrate | 131 |
| abstract_inverted_index.evaluations | 149 |
| abstract_inverted_index.experiments | 130 |
| abstract_inverted_index.innovations | 113 |
| abstract_inverted_index.maintaining | 126 |
| abstract_inverted_index.multi-stage | 83 |
| abstract_inverted_index.performance | 134 |
| abstract_inverted_index.progressive | 26 |
| abstract_inverted_index.refinement. | 48 |
| abstract_inverted_index.significant | 157 |
| abstract_inverted_index.sub-contour | 41, 51 |
| abstract_inverted_index.techniques: | 40 |
| abstract_inverted_index.distribution | 47, 97 |
| abstract_inverted_index.fine-grained | 46, 96 |
| abstract_inverted_index.improvements | 158 |
| abstract_inverted_index.information. | 78 |
| abstract_inverted_index.optimization | 84 |
| abstract_inverted_index.performance. | 128 |
| abstract_inverted_index.segmentation | 8, 88, 121, 174 |
| abstract_inverted_index.Additionally, | 79 |
| abstract_inverted_index.Contourformer | 115, 136 |
| abstract_inverted_index.comprehensive | 148 |
| abstract_inverted_index.contour-based | 6, 172 |
| abstract_inverted_index.progressively | 91 |
| abstract_inverted_index.sub-contours. | 93 |
| abstract_inverted_index.Contourformer, | 3 |
| abstract_inverted_index.attention-based | 58 |
| abstract_inverted_index.state-of-the-art | 154 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |