DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval Article Swipe
Yating Liu
,
Zimo Liu
,
Xiangyuan Lan
,
Wenming Yang
,
Yaowei Li
,
Qingmin Liao
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i6.32608
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i6.32608
Text-based person retrieval (TPR) has gained significant attention as a fine-grained and challenging task that closely aligns with practical applications. Tailoring CLIP to person domain is now a emerging research topic due to the abundant knowledge of vision-language pretraining, but challenges still remain during fine-tuning: (i) Previous full-model fine-tuning in TPR is computationally expensive and prone to overfitting.(ii) Existing parameter-efficient transfer learning (PETL) for TPR lacks of fine-grained feature extraction. To address these issues, we propose Domain-Aware Mixture-of-Adapters (DM-Adapter), which unifies Mixture-of-Experts (MOE) and PETL to enhance fine-grained feature representations while maintaining efficiency. Specifically, Sparse Mixture-of-Adapters is designed in parallel to MLP layers in both vision and language branches, where different experts specialize in distinct aspects of person knowledge to handle features more finely. To promote the router to exploit domain information effectively and alleviate the routing imbalance, Domain-Aware Router is then developed by building a novel gating function and injecting learnable domain-aware prompts. Extensive experiments show that our DM-Adapter achieves state-of-the-art performance, outperforming previous methods by a significant margin.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i6.32608
- https://ojs.aaai.org/index.php/AAAI/article/download/32608/34763
- OA Status
- diamond
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409367909
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409367909Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i6.32608Digital Object Identifier
- Title
-
DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person RetrievalWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Yating Liu, Zimo Liu, Xiangyuan Lan, Wenming Yang, Yaowei Li, Qingmin LiaoList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i6.32608Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/32608/34763Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/32608/34763Direct OA link when available
- Concepts
-
Adapter (computing), Computer science, Domain (mathematical analysis), Information retrieval, Operating system, Mathematics, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4409367909 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i6.32608 |
| ids.doi | https://doi.org/10.1609/aaai.v39i6.32608 |
| ids.openalex | https://openalex.org/W4409367909 |
| fwci | 8.33333333 |
| type | article |
| title | DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval |
| biblio.issue | 6 |
| biblio.volume | 39 |
| biblio.last_page | 5711 |
| biblio.first_page | 5703 |
| topics[0].id | https://openalex.org/T11980 |
| topics[0].field.id | https://openalex.org/fields/33 |
| topics[0].field.display_name | Social Sciences |
| topics[0].score | 0.958299994468689 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3313 |
| topics[0].subfield.display_name | Transportation |
| topics[0].display_name | Human Mobility and Location-Based Analysis |
| topics[1].id | https://openalex.org/T11819 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.932699978351593 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2713 |
| topics[1].subfield.display_name | Epidemiology |
| topics[1].display_name | Data-Driven Disease Surveillance |
| topics[2].id | https://openalex.org/T11719 |
| topics[2].field.id | https://openalex.org/fields/18 |
| topics[2].field.display_name | Decision Sciences |
| topics[2].score | 0.9185000061988831 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1803 |
| topics[2].subfield.display_name | Management Science and Operations Research |
| topics[2].display_name | Data Quality and Management |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C177284502 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9213699102401733 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1005390 |
| concepts[0].display_name | Adapter (computing) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5885658264160156 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C36503486 |
| concepts[2].level | 2 |
| concepts[2].score | 0.44143056869506836 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[2].display_name | Domain (mathematical analysis) |
| concepts[3].id | https://openalex.org/C23123220 |
| concepts[3].level | 1 |
| concepts[3].score | 0.35493817925453186 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[3].display_name | Information retrieval |
| concepts[4].id | https://openalex.org/C111919701 |
| concepts[4].level | 1 |
| concepts[4].score | 0.20201686024665833 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[4].display_name | Operating system |
| concepts[5].id | https://openalex.org/C33923547 |
| concepts[5].level | 0 |
| concepts[5].score | 0.08983656764030457 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[5].display_name | Mathematics |
| concepts[6].id | https://openalex.org/C134306372 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[6].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/adapter |
| keywords[0].score | 0.9213699102401733 |
| keywords[0].display_name | Adapter (computing) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5885658264160156 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/domain |
| keywords[2].score | 0.44143056869506836 |
| keywords[2].display_name | Domain (mathematical analysis) |
| keywords[3].id | https://openalex.org/keywords/information-retrieval |
| keywords[3].score | 0.35493817925453186 |
| keywords[3].display_name | Information retrieval |
| keywords[4].id | https://openalex.org/keywords/operating-system |
| keywords[4].score | 0.20201686024665833 |
| keywords[4].display_name | Operating system |
| keywords[5].id | https://openalex.org/keywords/mathematics |
| keywords[5].score | 0.08983656764030457 |
| keywords[5].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i6.32608 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/32608/34763 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v39i6.32608 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5100727177 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5256-1331 |
| authorships[0].author.display_name | Yating Liu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yating Liu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5008507010 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3469-0532 |
| authorships[1].author.display_name | Zimo Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zimo Liu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5055543314 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-8564-0346 |
| authorships[2].author.display_name | Xiangyuan Lan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xiangyuan Lan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5026184280 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-2506-1286 |
| authorships[3].author.display_name | Wenming Yang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wenming Yang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5024538926 |
| authorships[4].author.orcid | https://orcid.org/0009-0006-7325-6439 |
| authorships[4].author.display_name | Yaowei Li |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Yaowei Li |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5009239895 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7509-3964 |
| authorships[5].author.display_name | Qingmin Liao |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Qingmin Liao |
| authorships[5].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://ojs.aaai.org/index.php/AAAI/article/download/32608/34763 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11980 |
| primary_topic.field.id | https://openalex.org/fields/33 |
| primary_topic.field.display_name | Social Sciences |
| primary_topic.score | 0.958299994468689 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3313 |
| primary_topic.subfield.display_name | Transportation |
| primary_topic.display_name | Human Mobility and Location-Based Analysis |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2133028525, https://openalex.org/W4229060448, https://openalex.org/W4306381730, https://openalex.org/W2981692913, https://openalex.org/W3044188621, https://openalex.org/W3184035966, https://openalex.org/W2485605994 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i6.32608 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/32608/34763 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v39i6.32608 |
| primary_location.id | doi:10.1609/aaai.v39i6.32608 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/32608/34763 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v39i6.32608 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 9, 27, 145, 167 |
| abstract_inverted_index.To | 70, 124 |
| abstract_inverted_index.as | 8 |
| abstract_inverted_index.by | 143, 166 |
| abstract_inverted_index.in | 49, 98, 103, 113 |
| abstract_inverted_index.is | 25, 51, 96, 140 |
| abstract_inverted_index.of | 36, 66, 116 |
| abstract_inverted_index.to | 22, 32, 56, 85, 100, 119, 128 |
| abstract_inverted_index.we | 74 |
| abstract_inverted_index.(i) | 45 |
| abstract_inverted_index.MLP | 101 |
| abstract_inverted_index.TPR | 50, 64 |
| abstract_inverted_index.and | 11, 54, 83, 106, 133, 149 |
| abstract_inverted_index.but | 39 |
| abstract_inverted_index.due | 31 |
| abstract_inverted_index.for | 63 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.now | 26 |
| abstract_inverted_index.our | 158 |
| abstract_inverted_index.the | 33, 126, 135 |
| abstract_inverted_index.CLIP | 21 |
| abstract_inverted_index.PETL | 84 |
| abstract_inverted_index.both | 104 |
| abstract_inverted_index.more | 122 |
| abstract_inverted_index.show | 156 |
| abstract_inverted_index.task | 13 |
| abstract_inverted_index.that | 14, 157 |
| abstract_inverted_index.then | 141 |
| abstract_inverted_index.with | 17 |
| abstract_inverted_index.(MOE) | 82 |
| abstract_inverted_index.(TPR) | 3 |
| abstract_inverted_index.lacks | 65 |
| abstract_inverted_index.novel | 146 |
| abstract_inverted_index.prone | 55 |
| abstract_inverted_index.still | 41 |
| abstract_inverted_index.these | 72 |
| abstract_inverted_index.topic | 30 |
| abstract_inverted_index.where | 109 |
| abstract_inverted_index.which | 79 |
| abstract_inverted_index.while | 90 |
| abstract_inverted_index.(PETL) | 62 |
| abstract_inverted_index.Router | 139 |
| abstract_inverted_index.Sparse | 94 |
| abstract_inverted_index.aligns | 16 |
| abstract_inverted_index.domain | 24, 130 |
| abstract_inverted_index.during | 43 |
| abstract_inverted_index.gained | 5 |
| abstract_inverted_index.gating | 147 |
| abstract_inverted_index.handle | 120 |
| abstract_inverted_index.layers | 102 |
| abstract_inverted_index.person | 1, 23, 117 |
| abstract_inverted_index.remain | 42 |
| abstract_inverted_index.router | 127 |
| abstract_inverted_index.vision | 105 |
| abstract_inverted_index.address | 71 |
| abstract_inverted_index.aspects | 115 |
| abstract_inverted_index.closely | 15 |
| abstract_inverted_index.enhance | 86 |
| abstract_inverted_index.experts | 111 |
| abstract_inverted_index.exploit | 129 |
| abstract_inverted_index.feature | 68, 88 |
| abstract_inverted_index.finely. | 123 |
| abstract_inverted_index.issues, | 73 |
| abstract_inverted_index.margin. | 169 |
| abstract_inverted_index.methods | 165 |
| abstract_inverted_index.promote | 125 |
| abstract_inverted_index.propose | 75 |
| abstract_inverted_index.routing | 136 |
| abstract_inverted_index.unifies | 80 |
| abstract_inverted_index.Existing | 58 |
| abstract_inverted_index.Previous | 46 |
| abstract_inverted_index.abundant | 34 |
| abstract_inverted_index.achieves | 160 |
| abstract_inverted_index.building | 144 |
| abstract_inverted_index.designed | 97 |
| abstract_inverted_index.distinct | 114 |
| abstract_inverted_index.emerging | 28 |
| abstract_inverted_index.features | 121 |
| abstract_inverted_index.function | 148 |
| abstract_inverted_index.language | 107 |
| abstract_inverted_index.learning | 61 |
| abstract_inverted_index.parallel | 99 |
| abstract_inverted_index.previous | 164 |
| abstract_inverted_index.prompts. | 153 |
| abstract_inverted_index.research | 29 |
| abstract_inverted_index.transfer | 60 |
| abstract_inverted_index.Extensive | 154 |
| abstract_inverted_index.Tailoring | 20 |
| abstract_inverted_index.alleviate | 134 |
| abstract_inverted_index.attention | 7 |
| abstract_inverted_index.branches, | 108 |
| abstract_inverted_index.developed | 142 |
| abstract_inverted_index.different | 110 |
| abstract_inverted_index.expensive | 53 |
| abstract_inverted_index.injecting | 150 |
| abstract_inverted_index.knowledge | 35, 118 |
| abstract_inverted_index.learnable | 151 |
| abstract_inverted_index.practical | 18 |
| abstract_inverted_index.retrieval | 2 |
| abstract_inverted_index.DM-Adapter | 159 |
| abstract_inverted_index.Text-based | 0 |
| abstract_inverted_index.challenges | 40 |
| abstract_inverted_index.full-model | 47 |
| abstract_inverted_index.imbalance, | 137 |
| abstract_inverted_index.specialize | 112 |
| abstract_inverted_index.challenging | 12 |
| abstract_inverted_index.effectively | 132 |
| abstract_inverted_index.efficiency. | 92 |
| abstract_inverted_index.experiments | 155 |
| abstract_inverted_index.extraction. | 69 |
| abstract_inverted_index.fine-tuning | 48 |
| abstract_inverted_index.information | 131 |
| abstract_inverted_index.maintaining | 91 |
| abstract_inverted_index.significant | 6, 168 |
| abstract_inverted_index.Domain-Aware | 76, 138 |
| abstract_inverted_index.domain-aware | 152 |
| abstract_inverted_index.fine-grained | 10, 67, 87 |
| abstract_inverted_index.fine-tuning: | 44 |
| abstract_inverted_index.performance, | 162 |
| abstract_inverted_index.pretraining, | 38 |
| abstract_inverted_index.(DM-Adapter), | 78 |
| abstract_inverted_index.Specifically, | 93 |
| abstract_inverted_index.applications. | 19 |
| abstract_inverted_index.outperforming | 163 |
| abstract_inverted_index.computationally | 52 |
| abstract_inverted_index.representations | 89 |
| abstract_inverted_index.vision-language | 37 |
| abstract_inverted_index.overfitting.(ii) | 57 |
| abstract_inverted_index.state-of-the-art | 161 |
| abstract_inverted_index.Mixture-of-Experts | 81 |
| abstract_inverted_index.Mixture-of-Adapters | 77, 95 |
| abstract_inverted_index.parameter-efficient | 59 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.93103448 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |