Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models Article Swipe

PDF

Sifan Long , Zhen Zhao , Junkun Yuan , Zichang Tan , Jiangjiang Liu , Luping Zhou , Shengsheng Wang , Jingdong Wang ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2303.17169

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropriate prompt for each specific task. Recent CoCoOp further boosts the base-to-new generalization performance via an image-conditional prompt. However, it directly fuses identical image semantics to prompts of different labels and significantly weakens the discrimination among different classes as shown in our experiments. Motivated by this observation, we first propose a class-aware text prompt (CTP) to enrich generated prompts with label-related image information. Unlike CoCoOp, CTP can effectively involve image semantics and avoid introducing extra ambiguities into different prompts. On the other hand, instead of reserving the complete image representations, we propose text-guided feature tuning (TFT) to make the image branch attend to class-related representation. A contrastive loss is employed to align such augmented text and image representations on downstream tasks. In this way, the image-to-text CTP and text-to-image TFT can be mutually promoted to enhance the adaptation of VLMs for downstream tasks. Extensive experiments demonstrate that our method outperforms the existing methods by a significant margin. Especially, compared to CoCoOp, we achieve an average improvement of 4.03% on new classes and 3.19% on harmonic-mean over eleven classification benchmarks.

Related Topics

Computer Science

Artificial Intelligence

Mathematical Analysis

Concepts

Computer science Task (project management) Artificial intelligence Semantics (computer science) Image (mathematics) Class (philosophy) Representation (politics) Margin (machine learning) Feature (linguistics) Generalization Modal Natural language processing Pattern recognition (psychology) Machine learning Law Polymer chemistry Mathematics Mathematical analysis Linguistics Programming language Political science Economics Management Chemistry Philosophy Politics

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2303.17169
PDF: https://arxiv.org/pdf/2303.17169
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4361865825

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4361865825

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2303.17169

Digital Object Identifier
Title: Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-03-30

Full publication date if available
Authors: Sifan Long, Zhen Zhao, Junkun Yuan, Zichang Tan, Jiangjiang Liu, Luping Zhou, Shengsheng Wang, Jingdong Wang

List of authors in order
Landing page: https://arxiv.org/abs/2303.17169

Publisher landing page
PDF URL: https://arxiv.org/pdf/2303.17169

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2303.17169

Direct OA link when available
Concepts: Computer science, Task (project management), Artificial intelligence, Semantics (computer science), Image (mathematics), Class (philosophy), Representation (politics), Margin (machine learning), Feature (linguistics), Generalization, Modal, Natural language processing, Pattern recognition (psychology), Machine learning, Law, Polymer chemistry, Mathematics, Mathematical analysis, Linguistics, Programming language, Political science, Economics, Management, Chemistry, Philosophy, Politics

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4361865825
doi	https://doi.org/10.48550/arxiv.2303.17169
ids.doi	https://doi.org/10.48550/arxiv.2303.17169
ids.openalex	https://openalex.org/W4361865825
fwci
type	preprint
title	Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
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	0.9994999766349792
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	0.9965000152587891
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/T10627
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9603999853134155
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	0.7913802862167358
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C2780451532
concepts[1].level	2
concepts[1].score	0.6037497520446777
concepts[1].wikidata	https://www.wikidata.org/wiki/Q759676
concepts[1].display_name	Task (project management)
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.5737022161483765
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C184337299
concepts[3].level	2
concepts[3].score	0.5627158284187317
concepts[3].wikidata	https://www.wikidata.org/wiki/Q1437428
concepts[3].display_name	Semantics (computer science)
concepts[4].id	https://openalex.org/C115961682
concepts[4].level	2
concepts[4].score	0.5517263412475586
concepts[4].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[4].display_name	Image (mathematics)
concepts[5].id	https://openalex.org/C2777212361
concepts[5].level	2
concepts[5].score	0.5464845299720764
concepts[5].wikidata	https://www.wikidata.org/wiki/Q5127848
concepts[5].display_name	Class (philosophy)
concepts[6].id	https://openalex.org/C2776359362
concepts[6].level	3
concepts[6].score	0.5450272560119629
concepts[6].wikidata	https://www.wikidata.org/wiki/Q2145286
concepts[6].display_name	Representation (politics)
concepts[7].id	https://openalex.org/C774472
concepts[7].level	2
concepts[7].score	0.535449743270874
concepts[7].wikidata	https://www.wikidata.org/wiki/Q6760393
concepts[7].display_name	Margin (machine learning)
concepts[8].id	https://openalex.org/C2776401178
concepts[8].level	2
concepts[8].score	0.526861310005188
concepts[8].wikidata	https://www.wikidata.org/wiki/Q12050496
concepts[8].display_name	Feature (linguistics)
concepts[9].id	https://openalex.org/C177148314
concepts[9].level	2
concepts[9].score	0.489479660987854
concepts[9].wikidata	https://www.wikidata.org/wiki/Q170084
concepts[9].display_name	Generalization
concepts[10].id	https://openalex.org/C71139939
concepts[10].level	2
concepts[10].score	0.4612402617931366
concepts[10].wikidata	https://www.wikidata.org/wiki/Q910194
concepts[10].display_name	Modal
concepts[11].id	https://openalex.org/C204321447
concepts[11].level	1
concepts[11].score	0.4581202268600464
concepts[11].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[11].display_name	Natural language processing
concepts[12].id	https://openalex.org/C153180895
concepts[12].level	2
concepts[12].score	0.39483359456062317
concepts[12].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[12].display_name	Pattern recognition (psychology)
concepts[13].id	https://openalex.org/C119857082
concepts[13].level	1
concepts[13].score	0.32918447256088257
concepts[13].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[13].display_name	Machine learning
concepts[14].id	https://openalex.org/C199539241
concepts[14].level	1
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q7748
concepts[14].display_name	Law
concepts[15].id	https://openalex.org/C188027245
concepts[15].level	1
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q750446
concepts[15].display_name	Polymer chemistry
concepts[16].id	https://openalex.org/C33923547
concepts[16].level	0
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q395
concepts[16].display_name	Mathematics
concepts[17].id	https://openalex.org/C134306372
concepts[17].level	1
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q7754
concepts[17].display_name	Mathematical analysis
concepts[18].id	https://openalex.org/C41895202
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[18].display_name	Linguistics
concepts[19].id	https://openalex.org/C199360897
concepts[19].level	1
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[19].display_name	Programming language
concepts[20].id	https://openalex.org/C17744445
concepts[20].level	0
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q36442
concepts[20].display_name	Political science
concepts[21].id	https://openalex.org/C162324750
concepts[21].level	0
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q8134
concepts[21].display_name	Economics
concepts[22].id	https://openalex.org/C187736073
concepts[22].level	1
concepts[22].score	0.0
concepts[22].wikidata	https://www.wikidata.org/wiki/Q2920921
concepts[22].display_name	Management
concepts[23].id	https://openalex.org/C185592680
concepts[23].level	0
concepts[23].score	0.0
concepts[23].wikidata	https://www.wikidata.org/wiki/Q2329
concepts[23].display_name	Chemistry
concepts[24].id	https://openalex.org/C138885662
concepts[24].level	0
concepts[24].score	0.0
concepts[24].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[24].display_name	Philosophy
concepts[25].id	https://openalex.org/C94625758
concepts[25].level	2
concepts[25].score	0.0
concepts[25].wikidata	https://www.wikidata.org/wiki/Q7163
concepts[25].display_name	Politics
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.7913802862167358
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/task
keywords[1].score	0.6037497520446777
keywords[1].display_name	Task (project management)
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.5737022161483765
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/semantics
keywords[3].score	0.5627158284187317
keywords[3].display_name	Semantics (computer science)
keywords[4].id	https://openalex.org/keywords/image
keywords[4].score	0.5517263412475586
keywords[4].display_name	Image (mathematics)
keywords[5].id	https://openalex.org/keywords/class
keywords[5].score	0.5464845299720764
keywords[5].display_name	Class (philosophy)
keywords[6].id	https://openalex.org/keywords/representation
keywords[6].score	0.5450272560119629
keywords[6].display_name	Representation (politics)
keywords[7].id	https://openalex.org/keywords/margin
keywords[7].score	0.535449743270874
keywords[7].display_name	Margin (machine learning)
keywords[8].id	https://openalex.org/keywords/feature
keywords[8].score	0.526861310005188
keywords[8].display_name	Feature (linguistics)
keywords[9].id	https://openalex.org/keywords/generalization
keywords[9].score	0.489479660987854
keywords[9].display_name	Generalization
keywords[10].id	https://openalex.org/keywords/modal
keywords[10].score	0.4612402617931366
keywords[10].display_name	Modal
keywords[11].id	https://openalex.org/keywords/natural-language-processing
keywords[11].score	0.4581202268600464
keywords[11].display_name	Natural language processing
keywords[12].id	https://openalex.org/keywords/pattern-recognition
keywords[12].score	0.39483359456062317
keywords[12].display_name	Pattern recognition (psychology)
keywords[13].id	https://openalex.org/keywords/machine-learning
keywords[13].score	0.32918447256088257
keywords[13].display_name	Machine learning
language	en
locations[0].id	pmh:oai:arXiv.org:2303.17169
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/2303.17169
locations[0].version	submittedVersion
locations[0].raw_type
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/2303.17169
locations[1].id	doi:10.48550/arxiv.2303.17169
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.2303.17169
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5102874282
authorships[0].author.orcid	https://orcid.org/0000-0001-7060-1133
authorships[0].author.display_name	Sifan Long
authorships[0].author_position	first
authorships[0].raw_author_name	Long, Sifan
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5072694516
authorships[1].author.orcid	https://orcid.org/0000-0002-0796-4078
authorships[1].author.display_name	Zhen Zhao
authorships[1].author_position	middle
authorships[1].raw_author_name	Zhao, Zhen
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5049344673
authorships[2].author.orcid	https://orcid.org/0000-0003-0012-7397
authorships[2].author.display_name	Junkun Yuan
authorships[2].author_position	middle
authorships[2].raw_author_name	Yuan, Junkun
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5040257967
authorships[3].author.orcid	https://orcid.org/0000-0002-8501-4123
authorships[3].author.display_name	Zichang Tan
authorships[3].author_position	middle
authorships[3].raw_author_name	Tan, Zichang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5059524537
authorships[4].author.orcid	https://orcid.org/0000-0002-1341-2763
authorships[4].author.display_name	Jiangjiang Liu
authorships[4].author_position	middle
authorships[4].raw_author_name	Liu, Jiangjiang
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5100643784
authorships[5].author.orcid	https://orcid.org/0000-0001-8762-2424
authorships[5].author.display_name	Luping Zhou
authorships[5].author_position	middle
authorships[5].raw_author_name	Zhou, Luping
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5086280684
authorships[6].author.orcid	https://orcid.org/0000-0002-8503-8061
authorships[6].author.display_name	Shengsheng Wang
authorships[6].author_position	middle
authorships[6].raw_author_name	Wang, Shengsheng
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5075880303
authorships[7].author.orcid	https://orcid.org/0000-0002-4888-4445
authorships[7].author.display_name	Jingdong Wang
authorships[7].author_position	last
authorships[7].raw_author_name	Wang, Jingdong
authorships[7].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/2303.17169
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
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	0.9994999766349792
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/W3125011624, https://openalex.org/W1508631387, https://openalex.org/W2370917603, https://openalex.org/W2017776670, https://openalex.org/W2952760143, https://openalex.org/W3162204513, https://openalex.org/W2347897961, https://openalex.org/W2979236518, https://openalex.org/W2358318464, https://openalex.org/W2340870721
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2303.17169
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/2303.17169
best_oa_location.version	submittedVersion
best_oa_location.raw_type
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/2303.17169
primary_location.id	pmh:oai:arXiv.org:2303.17169
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/2303.17169
primary_location.version	submittedVersion
primary_location.raw_type
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/2303.17169
publication_date	2023-03-30
publication_year	2023
referenced_works_count	0
abstract_inverted_index.A	139
abstract_inverted_index.a	84, 188
abstract_inverted_index.In	155
abstract_inverted_index.On	113
abstract_inverted_index.an	33, 49, 197
abstract_inverted_index.as	72
abstract_inverted_index.be	165
abstract_inverted_index.by	78, 187
abstract_inverted_index.in	74
abstract_inverted_index.is	142
abstract_inverted_index.it	53
abstract_inverted_index.of	5, 61, 118, 172, 200
abstract_inverted_index.on	152, 202, 207
abstract_inverted_index.to	16, 27, 31, 59, 89, 130, 136, 144, 168, 193
abstract_inverted_index.we	81, 124, 195
abstract_inverted_index.CTP	99, 160
abstract_inverted_index.TFT	163
abstract_inverted_index.and	24, 64, 105, 149, 161, 205
abstract_inverted_index.can	100, 164
abstract_inverted_index.for	10, 36, 174
abstract_inverted_index.has	2
abstract_inverted_index.new	203
abstract_inverted_index.one	4
abstract_inverted_index.our	75, 181
abstract_inverted_index.the	6, 44, 67, 114, 120, 132, 158, 170, 184
abstract_inverted_index.via	48
abstract_inverted_index.CoOp	23
abstract_inverted_index.VLMs	173
abstract_inverted_index.each	37
abstract_inverted_index.into	110
abstract_inverted_index.like	22
abstract_inverted_index.loss	141
abstract_inverted_index.make	131
abstract_inverted_index.most	7
abstract_inverted_index.over	209
abstract_inverted_index.soft	29
abstract_inverted_index.such	146
abstract_inverted_index.tend	26
abstract_inverted_index.text	86, 148
abstract_inverted_index.that	180
abstract_inverted_index.this	79, 156
abstract_inverted_index.way,	157
abstract_inverted_index.with	93
abstract_inverted_index.(CTP)	88
abstract_inverted_index.(TFT)	129
abstract_inverted_index.3.19%	206
abstract_inverted_index.4.03%	201
abstract_inverted_index.adopt	28
abstract_inverted_index.align	145
abstract_inverted_index.among	69
abstract_inverted_index.avoid	106
abstract_inverted_index.extra	108
abstract_inverted_index.first	82
abstract_inverted_index.fuses	55
abstract_inverted_index.hand,	116
abstract_inverted_index.image	57, 95, 103, 122, 133, 150
abstract_inverted_index.large	12
abstract_inverted_index.learn	32
abstract_inverted_index.other	115
abstract_inverted_index.shown	73
abstract_inverted_index.task.	39
abstract_inverted_index.CoCoOp	41
abstract_inverted_index.ProDA,	25
abstract_inverted_index.Prompt	0
abstract_inverted_index.Recent	40
abstract_inverted_index.Unlike	97
abstract_inverted_index.attend	135
abstract_inverted_index.become	3
abstract_inverted_index.boosts	43
abstract_inverted_index.branch	134
abstract_inverted_index.eleven	210
abstract_inverted_index.enrich	90
abstract_inverted_index.labels	63
abstract_inverted_index.method	182
abstract_inverted_index.models	15
abstract_inverted_index.prompt	35, 87
abstract_inverted_index.tasks.	18, 154, 176
abstract_inverted_index.tuning	128
abstract_inverted_index.CoCoOp,	98, 194
abstract_inverted_index.Current	19
abstract_inverted_index.achieve	196
abstract_inverted_index.average	198
abstract_inverted_index.classes	71, 204
abstract_inverted_index.enhance	169
abstract_inverted_index.feature	127
abstract_inverted_index.further	42
abstract_inverted_index.instead	117
abstract_inverted_index.involve	102
abstract_inverted_index.margin.	190
abstract_inverted_index.methods	186
abstract_inverted_index.prompt.	51
abstract_inverted_index.prompts	30, 60, 92
abstract_inverted_index.propose	83, 125
abstract_inverted_index.weakens	66
abstract_inverted_index.However,	52
abstract_inverted_index.adapting	11
abstract_inverted_index.compared	192
abstract_inverted_index.complete	121
abstract_inverted_index.directly	54
abstract_inverted_index.employed	143
abstract_inverted_index.existing	185
abstract_inverted_index.learning	1
abstract_inverted_index.methods,	21
abstract_inverted_index.mutually	166
abstract_inverted_index.promoted	167
abstract_inverted_index.prompts.	112
abstract_inverted_index.specific	38
abstract_inverted_index.Extensive	177
abstract_inverted_index.Motivated	77
abstract_inverted_index.augmented	147
abstract_inverted_index.different	62, 70, 111
abstract_inverted_index.efficient	8
abstract_inverted_index.generated	91
abstract_inverted_index.identical	56
abstract_inverted_index.paradigms	9
abstract_inverted_index.reserving	119
abstract_inverted_index.semantics	58, 104
abstract_inverted_index.adaptation	171
abstract_inverted_index.downstream	17, 153, 175
abstract_inverted_index.Especially,	191
abstract_inverted_index.ambiguities	109
abstract_inverted_index.appropriate	34
abstract_inverted_index.base-to-new	45
abstract_inverted_index.benchmarks.	212
abstract_inverted_index.class-aware	85
abstract_inverted_index.contrastive	140
abstract_inverted_index.demonstrate	179
abstract_inverted_index.effectively	101
abstract_inverted_index.experiments	178
abstract_inverted_index.improvement	199
abstract_inverted_index.introducing	107
abstract_inverted_index.outperforms	183
abstract_inverted_index.performance	47
abstract_inverted_index.pre-trained	13
abstract_inverted_index.significant	189
abstract_inverted_index.text-guided	126
abstract_inverted_index.experiments.	76
abstract_inverted_index.information.	96
abstract_inverted_index.observation,	80
abstract_inverted_index.class-related	137
abstract_inverted_index.harmonic-mean	208
abstract_inverted_index.image-to-text	159
abstract_inverted_index.label-related	94
abstract_inverted_index.significantly	65
abstract_inverted_index.text-to-image	162
abstract_inverted_index.classification	211
abstract_inverted_index.discrimination	68
abstract_inverted_index.generalization	46
abstract_inverted_index.representation.	138
abstract_inverted_index.representations	151
abstract_inverted_index.vision-language	14
abstract_inverted_index.representations,	123
abstract_inverted_index.state-of-the-art	20
abstract_inverted_index.image-conditional	50
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	8
sustainable_development_goals[0].id	https://metadata.un.org/sdg/16
sustainable_development_goals[0].score	0.5
sustainable_development_goals[0].display_name	Peace, Justice and strong institutions
sustainable_development_goals[1].id	https://metadata.un.org/sdg/10
sustainable_development_goals[1].score	0.5
sustainable_development_goals[1].display_name	Reduced inequalities
citation_normalized_percentile