YOLO-Count: Differentiable Object Counting for Text-to-Image Generation Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2508.00728
We propose YOLO-Count, a differentiable open-vocabulary object counting model that tackles both general counting challenges and enables precise quantity control for text-to-image (T2I) generation. A core contribution is the 'cardinality' map, a novel regression target that accounts for variations in object size and spatial distribution. Leveraging representation alignment and a hybrid strong-weak supervision scheme, YOLO-Count bridges the gap between open-vocabulary counting and T2I generation control. Its fully differentiable architecture facilitates gradient-based optimization, enabling accurate object count estimation and fine-grained guidance for generative models. Extensive experiments demonstrate that YOLO-Count achieves state-of-the-art counting accuracy while providing robust and effective quantity control for T2I systems.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2508.00728
- https://arxiv.org/pdf/2508.00728
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416551917
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416551917Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2508.00728Digital Object Identifier
- Title
-
YOLO-Count: Differentiable Object Counting for Text-to-Image GenerationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-08-01Full publication date if available
- Authors
-
Guanning Zeng, Xiang Zhang, Zirui Wang, Zeyuan Chen, Bingnan Li, Zhuowen TuList of authors in order
- Landing page
-
https://arxiv.org/abs/2508.00728Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2508.00728Direct 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/2508.00728Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416551917 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2508.00728 |
| ids.doi | https://doi.org/10.48550/arxiv.2508.00728 |
| ids.openalex | https://openalex.org/W4416551917 |
| fwci | |
| type | preprint |
| title | YOLO-Count: Differentiable Object Counting for Text-to-Image Generation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2508.00728 |
| 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/2508.00728 |
| 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/2508.00728 |
| locations[1].id | doi:10.48550/arxiv.2508.00728 |
| 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.2508.00728 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5111068871 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Guanning Zeng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zeng, Guanning |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100651136 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1017-742X |
| authorships[1].author.display_name | Xiang Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhang, Xiang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100687845 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5927-6322 |
| authorships[2].author.display_name | Zirui Wang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wang, Zirui |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5104236856 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Zeyuan Chen |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Chen, Zeyuan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5078314744 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Bingnan Li |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Li, Bingnan |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5001760915 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-1900-2124 |
| authorships[5].author.display_name | Zhuowen Tu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Tu, Zhuowen |
| 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/2508.00728 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | YOLO-Count: Differentiable Object Counting for Text-to-Image Generation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T17:10:14.772475 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2508.00728 |
| 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/2508.00728 |
| 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/2508.00728 |
| primary_location.id | pmh:oai:arXiv.org:2508.00728 |
| 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/2508.00728 |
| 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/2508.00728 |
| publication_date | 2025-08-01 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.A | 24 |
| abstract_inverted_index.a | 3, 31, 49 |
| abstract_inverted_index.We | 0 |
| abstract_inverted_index.in | 39 |
| abstract_inverted_index.is | 27 |
| abstract_inverted_index.Its | 65 |
| abstract_inverted_index.T2I | 62, 100 |
| abstract_inverted_index.and | 15, 42, 48, 61, 77, 95 |
| abstract_inverted_index.for | 20, 37, 80, 99 |
| abstract_inverted_index.gap | 57 |
| abstract_inverted_index.the | 28, 56 |
| abstract_inverted_index.both | 11 |
| abstract_inverted_index.core | 25 |
| abstract_inverted_index.map, | 30 |
| abstract_inverted_index.size | 41 |
| abstract_inverted_index.that | 9, 35, 86 |
| abstract_inverted_index.(T2I) | 22 |
| abstract_inverted_index.count | 75 |
| abstract_inverted_index.fully | 66 |
| abstract_inverted_index.model | 8 |
| abstract_inverted_index.novel | 32 |
| abstract_inverted_index.while | 92 |
| abstract_inverted_index.hybrid | 50 |
| abstract_inverted_index.object | 6, 40, 74 |
| abstract_inverted_index.robust | 94 |
| abstract_inverted_index.target | 34 |
| abstract_inverted_index.between | 58 |
| abstract_inverted_index.bridges | 55 |
| abstract_inverted_index.control | 19, 98 |
| abstract_inverted_index.enables | 16 |
| abstract_inverted_index.general | 12 |
| abstract_inverted_index.models. | 82 |
| abstract_inverted_index.precise | 17 |
| abstract_inverted_index.propose | 1 |
| abstract_inverted_index.scheme, | 53 |
| abstract_inverted_index.spatial | 43 |
| abstract_inverted_index.tackles | 10 |
| abstract_inverted_index.accounts | 36 |
| abstract_inverted_index.accuracy | 91 |
| abstract_inverted_index.accurate | 73 |
| abstract_inverted_index.achieves | 88 |
| abstract_inverted_index.control. | 64 |
| abstract_inverted_index.counting | 7, 13, 60, 90 |
| abstract_inverted_index.enabling | 72 |
| abstract_inverted_index.guidance | 79 |
| abstract_inverted_index.quantity | 18, 97 |
| abstract_inverted_index.systems. | 101 |
| abstract_inverted_index.Extensive | 83 |
| abstract_inverted_index.alignment | 47 |
| abstract_inverted_index.effective | 96 |
| abstract_inverted_index.providing | 93 |
| abstract_inverted_index.Leveraging | 45 |
| abstract_inverted_index.YOLO-Count | 54, 87 |
| abstract_inverted_index.challenges | 14 |
| abstract_inverted_index.estimation | 76 |
| abstract_inverted_index.generation | 63 |
| abstract_inverted_index.generative | 81 |
| abstract_inverted_index.regression | 33 |
| abstract_inverted_index.variations | 38 |
| abstract_inverted_index.YOLO-Count, | 2 |
| abstract_inverted_index.demonstrate | 85 |
| abstract_inverted_index.experiments | 84 |
| abstract_inverted_index.facilitates | 69 |
| abstract_inverted_index.generation. | 23 |
| abstract_inverted_index.strong-weak | 51 |
| abstract_inverted_index.supervision | 52 |
| abstract_inverted_index.architecture | 68 |
| abstract_inverted_index.contribution | 26 |
| abstract_inverted_index.fine-grained | 78 |
| abstract_inverted_index.'cardinality' | 29 |
| abstract_inverted_index.distribution. | 44 |
| abstract_inverted_index.optimization, | 71 |
| abstract_inverted_index.text-to-image | 21 |
| abstract_inverted_index.differentiable | 4, 67 |
| abstract_inverted_index.gradient-based | 70 |
| abstract_inverted_index.representation | 46 |
| abstract_inverted_index.open-vocabulary | 5, 59 |
| abstract_inverted_index.state-of-the-art | 89 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |