Text as Image: Learning Transferable Adapter for Multi-Label Classification Article Swipe
Xuelin Zhu
,
Jiuxin Cao
,
Jian Liu
,
Dongqi Tang
,
F. R. Xu
,
Weijia Liu
,
Jiawei Ge
,
Bo Liu
,
Qingpei Guo
,
Tianyi Zhang
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2312.04160
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2312.04160
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to discover novel labels in an open-vocabulary manner. However, this paradigm suffers from non-trivial training costs, and becomes computationally prohibitive for a large number of candidate labels. To address this issue, we note that vision-language pre-training aligns images and texts in a unified embedding space, making it potential for an adapter network to identify labels in visual modality while be trained in text modality. To enhance such cross-modal transfer ability, a simple yet effective method termed random perturbation is proposed, which enables the adapter to search for potential visual embeddings by perturbing text embeddings with noise during training, resulting in better performance in visual modality. Furthermore, we introduce an effective approach to employ large language models for multi-label instruction-following text generation. In this way, a fully automated pipeline for visual label recognition is developed without relying on any manual data. Extensive experiments on public benchmarks show the superiority of our method in various multi-label classification tasks.
Related Topics
Concepts
Computer science
Artificial intelligence
Embedding
Pipeline (software)
Discriminative model
Vocabulary
Adapter (computing)
Machine learning
Modality (human–computer interaction)
Contextual image classification
Natural language processing
Speech recognition
Pattern recognition (psychology)
Image (mathematics)
Programming language
Philosophy
Operating system
Linguistics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2312.04160
- https://arxiv.org/pdf/2312.04160
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4389501146
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4389501146Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2312.04160Digital Object Identifier
- Title
-
Text as Image: Learning Transferable Adapter for Multi-Label ClassificationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-12-07Full publication date if available
- Authors
-
Xuelin Zhu, Jiuxin Cao, Jian Liu, Dongqi Tang, F. R. Xu, Weijia Liu, Jiawei Ge, Bo Liu, Qingpei Guo, Tianyi ZhangList of authors in order
- Landing page
-
https://arxiv.org/abs/2312.04160Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2312.04160Direct 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/2312.04160Direct OA link when available
- Concepts
-
Computer science, Artificial intelligence, Embedding, Pipeline (software), Discriminative model, Vocabulary, Adapter (computing), Machine learning, Modality (human–computer interaction), Contextual image classification, Natural language processing, Speech recognition, Pattern recognition (psychology), Image (mathematics), Programming language, Philosophy, Operating system, LinguisticsTop 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/W4389501146 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2312.04160 |
| ids.doi | https://doi.org/10.48550/arxiv.2312.04160 |
| ids.openalex | https://openalex.org/W4389501146 |
| fwci | |
| type | preprint |
| title | Text as Image: Learning Transferable Adapter for Multi-Label Classification |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11714 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9958000183105469 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Multimodal Machine Learning Applications |
| topics[1].id | https://openalex.org/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9943000078201294 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T11550 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.993399977684021 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Text and Document Classification Technologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8136637210845947 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.6311166286468506 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C41608201 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5755453705787659 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[2].display_name | Embedding |
| concepts[3].id | https://openalex.org/C43521106 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5287503600120544 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2165493 |
| concepts[3].display_name | Pipeline (software) |
| concepts[4].id | https://openalex.org/C97931131 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5205401182174683 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q5282087 |
| concepts[4].display_name | Discriminative model |
| concepts[5].id | https://openalex.org/C2777601683 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5128576755523682 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q6499736 |
| concepts[5].display_name | Vocabulary |
| concepts[6].id | https://openalex.org/C177284502 |
| concepts[6].level | 2 |
| concepts[6].score | 0.509547233581543 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1005390 |
| concepts[6].display_name | Adapter (computing) |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4560132622718811 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C2780226545 |
| concepts[8].level | 2 |
| concepts[8].score | 0.44441571831703186 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q6888030 |
| concepts[8].display_name | Modality (human–computer interaction) |
| concepts[9].id | https://openalex.org/C75294576 |
| concepts[9].level | 3 |
| concepts[9].score | 0.4297757148742676 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5165192 |
| concepts[9].display_name | Contextual image classification |
| concepts[10].id | https://openalex.org/C204321447 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4212779104709625 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[10].display_name | Natural language processing |
| concepts[11].id | https://openalex.org/C28490314 |
| concepts[11].level | 1 |
| concepts[11].score | 0.39705565571784973 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[11].display_name | Speech recognition |
| concepts[12].id | https://openalex.org/C153180895 |
| concepts[12].level | 2 |
| concepts[12].score | 0.39577874541282654 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[12].display_name | Pattern recognition (psychology) |
| concepts[13].id | https://openalex.org/C115961682 |
| concepts[13].level | 2 |
| concepts[13].score | 0.36843588948249817 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[13].display_name | Image (mathematics) |
| concepts[14].id | https://openalex.org/C199360897 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[14].display_name | Programming language |
| concepts[15].id | https://openalex.org/C138885662 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[15].display_name | Philosophy |
| concepts[16].id | https://openalex.org/C111919701 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[16].display_name | Operating system |
| concepts[17].id | https://openalex.org/C41895202 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[17].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8136637210845947 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.6311166286468506 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/embedding |
| keywords[2].score | 0.5755453705787659 |
| keywords[2].display_name | Embedding |
| keywords[3].id | https://openalex.org/keywords/pipeline |
| keywords[3].score | 0.5287503600120544 |
| keywords[3].display_name | Pipeline (software) |
| keywords[4].id | https://openalex.org/keywords/discriminative-model |
| keywords[4].score | 0.5205401182174683 |
| keywords[4].display_name | Discriminative model |
| keywords[5].id | https://openalex.org/keywords/vocabulary |
| keywords[5].score | 0.5128576755523682 |
| keywords[5].display_name | Vocabulary |
| keywords[6].id | https://openalex.org/keywords/adapter |
| keywords[6].score | 0.509547233581543 |
| keywords[6].display_name | Adapter (computing) |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.4560132622718811 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/modality |
| keywords[8].score | 0.44441571831703186 |
| keywords[8].display_name | Modality (human–computer interaction) |
| keywords[9].id | https://openalex.org/keywords/contextual-image-classification |
| keywords[9].score | 0.4297757148742676 |
| keywords[9].display_name | Contextual image classification |
| keywords[10].id | https://openalex.org/keywords/natural-language-processing |
| keywords[10].score | 0.4212779104709625 |
| keywords[10].display_name | Natural language processing |
| keywords[11].id | https://openalex.org/keywords/speech-recognition |
| keywords[11].score | 0.39705565571784973 |
| keywords[11].display_name | Speech recognition |
| keywords[12].id | https://openalex.org/keywords/pattern-recognition |
| keywords[12].score | 0.39577874541282654 |
| keywords[12].display_name | Pattern recognition (psychology) |
| keywords[13].id | https://openalex.org/keywords/image |
| keywords[13].score | 0.36843588948249817 |
| keywords[13].display_name | Image (mathematics) |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2312.04160 |
| 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/2312.04160 |
| 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/2312.04160 |
| locations[1].id | doi:10.48550/arxiv.2312.04160 |
| 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.2312.04160 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5076214561 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7676-2843 |
| authorships[0].author.display_name | Xuelin Zhu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhu, Xuelin |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5012384188 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2448-6717 |
| authorships[1].author.display_name | Jiuxin Cao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cao, Jiuxin |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5070319114 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-9003-8042 |
| authorships[2].author.display_name | Jian Liu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | liu, Jian |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5070291038 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6311-2550 |
| authorships[3].author.display_name | Dongqi Tang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Tang, Dongqi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5076909902 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6699-0965 |
| authorships[4].author.display_name | F. R. Xu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Xu, Furong |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100747522 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2634-7283 |
| authorships[5].author.display_name | Weijia Liu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Liu, Weijia |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5018527272 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-7268-7815 |
| authorships[6].author.display_name | Jiawei Ge |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Ge, Jiawei |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5100727812 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-5426-515X |
| authorships[7].author.display_name | Bo Liu |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Liu, Bo |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5086923590 |
| authorships[8].author.orcid | https://orcid.org/0009-0001-0521-9664 |
| authorships[8].author.display_name | Qingpei Guo |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Guo, Qingpei |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5100437453 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-5468-9347 |
| authorships[9].author.display_name | Tianyi Zhang |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Zhang, Tianyi |
| authorships[9].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/2312.04160 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Text as Image: Learning Transferable Adapter for Multi-Label Classification |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11714 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9958000183105469 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Multimodal Machine Learning Applications |
| related_works | https://openalex.org/W2133028525, https://openalex.org/W4306381730, https://openalex.org/W4229060448, https://openalex.org/W2981692913, https://openalex.org/W3044188621, https://openalex.org/W3184035966, https://openalex.org/W2160602540, https://openalex.org/W4389116644, https://openalex.org/W2153315159, https://openalex.org/W2129933262 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2312.04160 |
| 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/2312.04160 |
| 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/2312.04160 |
| primary_location.id | pmh:oai:arXiv.org:2312.04160 |
| 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/2312.04160 |
| 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/2312.04160 |
| publication_date | 2023-12-07 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 48, 68, 97, 151 |
| abstract_inverted_index.In | 148 |
| abstract_inverted_index.To | 54, 91 |
| abstract_inverted_index.an | 32, 76, 135 |
| abstract_inverted_index.be | 86 |
| abstract_inverted_index.by | 117 |
| abstract_inverted_index.in | 31, 67, 82, 88, 126, 129, 178 |
| abstract_inverted_index.is | 105, 159 |
| abstract_inverted_index.it | 73 |
| abstract_inverted_index.of | 7, 51, 175 |
| abstract_inverted_index.on | 163, 169 |
| abstract_inverted_index.to | 19, 27, 79, 111, 138 |
| abstract_inverted_index.we | 58, 133 |
| abstract_inverted_index.and | 43, 65 |
| abstract_inverted_index.any | 164 |
| abstract_inverted_index.for | 47, 75, 113, 143, 155 |
| abstract_inverted_index.has | 15 |
| abstract_inverted_index.our | 176 |
| abstract_inverted_index.the | 109, 173 |
| abstract_inverted_index.via | 23 |
| abstract_inverted_index.yet | 99 |
| abstract_inverted_index.been | 17 |
| abstract_inverted_index.from | 39 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.note | 59 |
| abstract_inverted_index.show | 172 |
| abstract_inverted_index.such | 93 |
| abstract_inverted_index.text | 89, 119, 146 |
| abstract_inverted_index.that | 60 |
| abstract_inverted_index.this | 36, 56, 149 |
| abstract_inverted_index.way, | 150 |
| abstract_inverted_index.with | 121 |
| abstract_inverted_index.Their | 11 |
| abstract_inverted_index.data. | 166 |
| abstract_inverted_index.fully | 152 |
| abstract_inverted_index.image | 21 |
| abstract_inverted_index.label | 157 |
| abstract_inverted_index.large | 49, 140 |
| abstract_inverted_index.noise | 122 |
| abstract_inverted_index.novel | 29 |
| abstract_inverted_index.texts | 66 |
| abstract_inverted_index.which | 107 |
| abstract_inverted_index.while | 85 |
| abstract_inverted_index.aligns | 63 |
| abstract_inverted_index.better | 127 |
| abstract_inverted_index.costs, | 42 |
| abstract_inverted_index.during | 123 |
| abstract_inverted_index.employ | 139 |
| abstract_inverted_index.images | 64 |
| abstract_inverted_index.issue, | 57 |
| abstract_inverted_index.labels | 30, 81 |
| abstract_inverted_index.making | 72 |
| abstract_inverted_index.manual | 165 |
| abstract_inverted_index.method | 101, 177 |
| abstract_inverted_index.models | 2, 142 |
| abstract_inverted_index.number | 50 |
| abstract_inverted_index.prompt | 24 |
| abstract_inverted_index.public | 170 |
| abstract_inverted_index.random | 103 |
| abstract_inverted_index.search | 112 |
| abstract_inverted_index.simple | 98 |
| abstract_inverted_index.space, | 71 |
| abstract_inverted_index.tasks. | 182 |
| abstract_inverted_index.termed | 102 |
| abstract_inverted_index.visual | 83, 115, 130, 156 |
| abstract_inverted_index.ability | 14 |
| abstract_inverted_index.adapter | 77, 110 |
| abstract_inverted_index.address | 55 |
| abstract_inverted_index.becomes | 44 |
| abstract_inverted_index.concept | 9 |
| abstract_inverted_index.enables | 108 |
| abstract_inverted_index.enhance | 92 |
| abstract_inverted_index.labels. | 53 |
| abstract_inverted_index.manner. | 34 |
| abstract_inverted_index.network | 78 |
| abstract_inverted_index.notably | 4 |
| abstract_inverted_index.relying | 162 |
| abstract_inverted_index.suffers | 38 |
| abstract_inverted_index.trained | 87 |
| abstract_inverted_index.tuning, | 25 |
| abstract_inverted_index.unified | 69 |
| abstract_inverted_index.various | 179 |
| abstract_inverted_index.without | 161 |
| abstract_inverted_index.However, | 35 |
| abstract_inverted_index.ability, | 96 |
| abstract_inverted_index.approach | 137 |
| abstract_inverted_index.discover | 28 |
| abstract_inverted_index.enabling | 26 |
| abstract_inverted_index.identify | 80 |
| abstract_inverted_index.language | 141 |
| abstract_inverted_index.modality | 84 |
| abstract_inverted_index.paradigm | 37 |
| abstract_inverted_index.pipeline | 154 |
| abstract_inverted_index.progress | 6 |
| abstract_inverted_index.recently | 16 |
| abstract_inverted_index.training | 41 |
| abstract_inverted_index.transfer | 95 |
| abstract_inverted_index.Extensive | 167 |
| abstract_inverted_index.automated | 153 |
| abstract_inverted_index.candidate | 52 |
| abstract_inverted_index.developed | 160 |
| abstract_inverted_index.effective | 100, 136 |
| abstract_inverted_index.embedding | 70 |
| abstract_inverted_index.introduce | 134 |
| abstract_inverted_index.modality. | 90, 131 |
| abstract_inverted_index.potential | 74, 114 |
| abstract_inverted_index.proposed, | 106 |
| abstract_inverted_index.resulting | 125 |
| abstract_inverted_index.training, | 124 |
| abstract_inverted_index.zero-shot | 13 |
| abstract_inverted_index.benchmarks | 171 |
| abstract_inverted_index.embeddings | 116, 120 |
| abstract_inverted_index.impressive | 12 |
| abstract_inverted_index.open-world | 8 |
| abstract_inverted_index.perturbing | 118 |
| abstract_inverted_index.Pre-trained | 0 |
| abstract_inverted_index.accelerated | 5 |
| abstract_inverted_index.cross-modal | 94 |
| abstract_inverted_index.experiments | 168 |
| abstract_inverted_index.generation. | 147 |
| abstract_inverted_index.multi-label | 20, 144, 180 |
| abstract_inverted_index.non-trivial | 40 |
| abstract_inverted_index.performance | 128 |
| abstract_inverted_index.prohibitive | 46 |
| abstract_inverted_index.recognition | 158 |
| abstract_inverted_index.superiority | 174 |
| abstract_inverted_index.transferred | 18 |
| abstract_inverted_index.Furthermore, | 132 |
| abstract_inverted_index.perturbation | 104 |
| abstract_inverted_index.pre-training | 62 |
| abstract_inverted_index.recognition. | 10 |
| abstract_inverted_index.classification | 22, 181 |
| abstract_inverted_index.computationally | 45 |
| abstract_inverted_index.open-vocabulary | 33 |
| abstract_inverted_index.vision-language | 1, 61 |
| abstract_inverted_index.instruction-following | 145 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.7799999713897705 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |