SILC: Improving Vision Language Pretraining with Self-Distillation Article Swipe
Muhammad Ferjad Naeem
,
Yongqin Xian
,
Xiaohua Zhai
,
Lukas Hoyer
,
Luc Van Gool
,
Federico Tombari
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.13355
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.13355
Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation, while also providing improvements on image-level tasks such as classification and retrieval. SILC models sets a new state of the art for zero-shot classification, few shot classification, image and text retrieval, zero-shot segmentation, and open vocabulary segmentation. We further show that SILC features greatly benefit open vocabulary detection, captioning and visual question answering.
Related Topics
Concepts
Closed captioning
Computer science
Artificial intelligence
Vocabulary
Feature (linguistics)
Image (mathematics)
Segmentation
Set (abstract data type)
Language model
Contextual image classification
Matching (statistics)
Feature extraction
Natural language processing
Pattern recognition (psychology)
Machine learning
Mathematics
Statistics
Programming language
Philosophy
Linguistics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.13355
- https://arxiv.org/pdf/2310.13355
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387891890
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387891890Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.13355Digital Object Identifier
- Title
-
SILC: Improving Vision Language Pretraining with Self-DistillationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-20Full publication date if available
- Authors
-
Muhammad Ferjad Naeem, Yongqin Xian, Xiaohua Zhai, Lukas Hoyer, Luc Van Gool, Federico TombariList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.13355Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.13355Direct 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/2310.13355Direct OA link when available
- Concepts
-
Closed captioning, Computer science, Artificial intelligence, Vocabulary, Feature (linguistics), Image (mathematics), Segmentation, Set (abstract data type), Language model, Contextual image classification, Matching (statistics), Feature extraction, Natural language processing, Pattern recognition (psychology), Machine learning, Mathematics, Statistics, Programming language, Philosophy, LinguisticsTop 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/W4387891890 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.13355 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.13355 |
| ids.openalex | https://openalex.org/W4387891890 |
| fwci | |
| type | preprint |
| title | SILC: Improving Vision Language Pretraining with Self-Distillation |
| 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 | 0.9995999932289124 |
| 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 | 0.9697999954223633 |
| 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/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9506999850273132 |
| 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 | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C157657479 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7909376621246338 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q2367247 |
| concepts[0].display_name | Closed captioning |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7837022542953491 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6636314392089844 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C2777601683 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5965683460235596 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q6499736 |
| concepts[3].display_name | Vocabulary |
| concepts[4].id | https://openalex.org/C2776401178 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5762534737586975 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[4].display_name | Feature (linguistics) |
| concepts[5].id | https://openalex.org/C115961682 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5729260444641113 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[5].display_name | Image (mathematics) |
| concepts[6].id | https://openalex.org/C89600930 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5713436603546143 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[6].display_name | Segmentation |
| concepts[7].id | https://openalex.org/C177264268 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4948970675468445 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[7].display_name | Set (abstract data type) |
| concepts[8].id | https://openalex.org/C137293760 |
| concepts[8].level | 2 |
| concepts[8].score | 0.48018231987953186 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[8].display_name | Language model |
| concepts[9].id | https://openalex.org/C75294576 |
| concepts[9].level | 3 |
| concepts[9].score | 0.4472009539604187 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5165192 |
| concepts[9].display_name | Contextual image classification |
| concepts[10].id | https://openalex.org/C165064840 |
| concepts[10].level | 2 |
| concepts[10].score | 0.442632257938385 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1321061 |
| concepts[10].display_name | Matching (statistics) |
| concepts[11].id | https://openalex.org/C52622490 |
| concepts[11].level | 2 |
| concepts[11].score | 0.41427159309387207 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1026626 |
| concepts[11].display_name | Feature extraction |
| concepts[12].id | https://openalex.org/C204321447 |
| concepts[12].level | 1 |
| concepts[12].score | 0.40512463450431824 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[12].display_name | Natural language processing |
| concepts[13].id | https://openalex.org/C153180895 |
| concepts[13].level | 2 |
| concepts[13].score | 0.4024888873100281 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[13].display_name | Pattern recognition (psychology) |
| concepts[14].id | https://openalex.org/C119857082 |
| concepts[14].level | 1 |
| concepts[14].score | 0.36771607398986816 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[14].display_name | Machine learning |
| concepts[15].id | https://openalex.org/C33923547 |
| concepts[15].level | 0 |
| concepts[15].score | 0.10324326157569885 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[15].display_name | Mathematics |
| concepts[16].id | https://openalex.org/C105795698 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[16].display_name | Statistics |
| concepts[17].id | https://openalex.org/C199360897 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[17].display_name | Programming language |
| concepts[18].id | https://openalex.org/C138885662 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[18].display_name | Philosophy |
| concepts[19].id | https://openalex.org/C41895202 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[19].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/closed-captioning |
| keywords[0].score | 0.7909376621246338 |
| keywords[0].display_name | Closed captioning |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7837022542953491 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6636314392089844 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/vocabulary |
| keywords[3].score | 0.5965683460235596 |
| keywords[3].display_name | Vocabulary |
| keywords[4].id | https://openalex.org/keywords/feature |
| keywords[4].score | 0.5762534737586975 |
| keywords[4].display_name | Feature (linguistics) |
| keywords[5].id | https://openalex.org/keywords/image |
| keywords[5].score | 0.5729260444641113 |
| keywords[5].display_name | Image (mathematics) |
| keywords[6].id | https://openalex.org/keywords/segmentation |
| keywords[6].score | 0.5713436603546143 |
| keywords[6].display_name | Segmentation |
| keywords[7].id | https://openalex.org/keywords/set |
| keywords[7].score | 0.4948970675468445 |
| keywords[7].display_name | Set (abstract data type) |
| keywords[8].id | https://openalex.org/keywords/language-model |
| keywords[8].score | 0.48018231987953186 |
| keywords[8].display_name | Language model |
| keywords[9].id | https://openalex.org/keywords/contextual-image-classification |
| keywords[9].score | 0.4472009539604187 |
| keywords[9].display_name | Contextual image classification |
| keywords[10].id | https://openalex.org/keywords/matching |
| keywords[10].score | 0.442632257938385 |
| keywords[10].display_name | Matching (statistics) |
| keywords[11].id | https://openalex.org/keywords/feature-extraction |
| keywords[11].score | 0.41427159309387207 |
| keywords[11].display_name | Feature extraction |
| keywords[12].id | https://openalex.org/keywords/natural-language-processing |
| keywords[12].score | 0.40512463450431824 |
| keywords[12].display_name | Natural language processing |
| keywords[13].id | https://openalex.org/keywords/pattern-recognition |
| keywords[13].score | 0.4024888873100281 |
| keywords[13].display_name | Pattern recognition (psychology) |
| keywords[14].id | https://openalex.org/keywords/machine-learning |
| keywords[14].score | 0.36771607398986816 |
| keywords[14].display_name | Machine learning |
| keywords[15].id | https://openalex.org/keywords/mathematics |
| keywords[15].score | 0.10324326157569885 |
| keywords[15].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.13355 |
| 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/2310.13355 |
| 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/2310.13355 |
| locations[1].id | doi:10.48550/arxiv.2310.13355 |
| 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.2310.13355 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5103091877 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7455-7280 |
| authorships[0].author.display_name | Muhammad Ferjad Naeem |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Naeem, Muhammad Ferjad |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5012209802 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7186-1295 |
| authorships[1].author.display_name | Yongqin Xian |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xian, Yongqin |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5071668416 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Xiaohua Zhai |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhai, Xiaohua |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5053328232 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7391-0676 |
| authorships[3].author.display_name | Lukas Hoyer |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hoyer, Lukas |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5001254143 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-3445-5711 |
| authorships[4].author.display_name | Luc Van Gool |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Van Gool, Luc |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5041092666 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-5598-5212 |
| authorships[5].author.display_name | Federico Tombari |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Tombari, Federico |
| 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/2310.13355 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | SILC: Improving Vision Language Pretraining with Self-Distillation |
| 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 | 0.9995999932289124 |
| 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/W4210416330, https://openalex.org/W2775506363, https://openalex.org/W3088136942, https://openalex.org/W2949362007, https://openalex.org/W4290852288, https://openalex.org/W4388893791, https://openalex.org/W4283207562, https://openalex.org/W2963177403, https://openalex.org/W2330246314, https://openalex.org/W2565656575 |
| 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:2310.13355 |
| 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/2310.13355 |
| 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/2310.13355 |
| primary_location.id | pmh:oai:arXiv.org:2310.13355 |
| 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/2310.13355 |
| 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/2310.13355 |
| publication_date | 2023-10-20 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 77, 141 |
| abstract_inverted_index.In | 71 |
| abstract_inverted_index.We | 99, 163 |
| abstract_inverted_index.an | 107 |
| abstract_inverted_index.as | 134 |
| abstract_inverted_index.by | 52, 97 |
| abstract_inverted_index.of | 23, 44, 93, 144 |
| abstract_inverted_index.on | 2, 57, 118, 130 |
| abstract_inverted_index.to | 20 |
| abstract_inverted_index.we | 74 |
| abstract_inverted_index.and | 16, 25, 39, 60, 124, 136, 154, 159, 175 |
| abstract_inverted_index.art | 146 |
| abstract_inverted_index.few | 150 |
| abstract_inverted_index.for | 12, 35, 67, 80, 147 |
| abstract_inverted_index.has | 7 |
| abstract_inverted_index.its | 26 |
| abstract_inverted_index.new | 142 |
| abstract_inverted_index.not | 62 |
| abstract_inverted_index.the | 9, 21, 42, 48, 90, 145 |
| abstract_inverted_index.CLIP | 24, 33 |
| abstract_inverted_index.SILC | 84, 138, 167 |
| abstract_inverted_index.also | 31, 127 |
| abstract_inverted_index.does | 61 |
| abstract_inverted_index.from | 106 |
| abstract_inverted_index.have | 30, 40 |
| abstract_inverted_index.like | 122 |
| abstract_inverted_index.only | 55 |
| abstract_inverted_index.open | 13, 160, 171 |
| abstract_inverted_index.sets | 140 |
| abstract_inverted_index.shot | 151 |
| abstract_inverted_index.show | 100, 165 |
| abstract_inverted_index.such | 133 |
| abstract_inverted_index.text | 155 |
| abstract_inverted_index.that | 101, 166 |
| abstract_inverted_index.this | 72 |
| abstract_inverted_index.used | 32, 51 |
| abstract_inverted_index.with | 89 |
| abstract_inverted_index.(EMA) | 111 |
| abstract_inverted_index.SILC, | 76 |
| abstract_inverted_index.dense | 36, 68, 119 |
| abstract_inverted_index.image | 4, 64, 104, 153 |
| abstract_inverted_index.local | 103 |
| abstract_inverted_index.model | 113, 116 |
| abstract_inverted_index.novel | 78 |
| abstract_inverted_index.shown | 41 |
| abstract_inverted_index.state | 143 |
| abstract_inverted_index.tasks | 38, 121, 132 |
| abstract_inverted_index.these | 53 |
| abstract_inverted_index.while | 126 |
| abstract_inverted_index.work, | 73 |
| abstract_inverted_index.works | 29 |
| abstract_inverted_index.become | 8 |
| abstract_inverted_index.models | 18, 54, 139 |
| abstract_inverted_index.moving | 109 |
| abstract_inverted_index.recipe | 11 |
| abstract_inverted_index.simple | 91 |
| abstract_inverted_index.tasks. | 70 |
| abstract_inverted_index.thanks | 19 |
| abstract_inverted_index.vision | 81 |
| abstract_inverted_index.visual | 176 |
| abstract_inverted_index.Several | 28 |
| abstract_inverted_index.average | 110 |
| abstract_inverted_index.benefit | 170 |
| abstract_inverted_index.caption | 5 |
| abstract_inverted_index.default | 10 |
| abstract_inverted_index.feature | 65 |
| abstract_inverted_index.focuses | 56 |
| abstract_inverted_index.further | 164 |
| abstract_inverted_index.greatly | 169 |
| abstract_inverted_index.success | 22 |
| abstract_inverted_index.teacher | 112 |
| abstract_inverted_index.However, | 47 |
| abstract_inverted_index.addition | 92 |
| abstract_inverted_index.datasets | 6 |
| abstract_inverted_index.features | 34, 105, 168 |
| abstract_inverted_index.improves | 85, 115 |
| abstract_inverted_index.language | 82 |
| abstract_inverted_index.learning | 66, 88, 96 |
| abstract_inverted_index.open-set | 45 |
| abstract_inverted_index.question | 177 |
| abstract_inverted_index.alignment | 59 |
| abstract_inverted_index.detection | 123 |
| abstract_inverted_index.emergence | 43 |
| abstract_inverted_index.framework | 79 |
| abstract_inverted_index.introduce | 75 |
| abstract_inverted_index.objective | 50 |
| abstract_inverted_index.providing | 128 |
| abstract_inverted_index.retrieval | 17 |
| abstract_inverted_index.variants. | 27 |
| abstract_inverted_index.web-scale | 3 |
| abstract_inverted_index.zero-shot | 148, 157 |
| abstract_inverted_index.Image-Text | 0 |
| abstract_inverted_index.abilities. | 46 |
| abstract_inverted_index.answering. | 178 |
| abstract_inverted_index.captioning | 174 |
| abstract_inverted_index.detection, | 173 |
| abstract_inverted_index.distilling | 102 |
| abstract_inverted_index.image-text | 58, 86 |
| abstract_inverted_index.prediction | 37, 69 |
| abstract_inverted_index.retrieval, | 156 |
| abstract_inverted_index.retrieval. | 137 |
| abstract_inverted_index.vocabulary | 14, 161, 172 |
| abstract_inverted_index.contrastive | 49, 87 |
| abstract_inverted_index.exponential | 108 |
| abstract_inverted_index.image-level | 131 |
| abstract_inverted_index.incentivise | 63 |
| abstract_inverted_index.performance | 117 |
| abstract_inverted_index.predictions | 120 |
| abstract_inverted_index.pretraining | 1 |
| abstract_inverted_index.improvements | 129 |
| abstract_inverted_index.pretraining. | 83 |
| abstract_inverted_index.segmentation, | 125, 158 |
| abstract_inverted_index.segmentation. | 162 |
| abstract_inverted_index.significantly | 114 |
| abstract_inverted_index.classification | 15, 135 |
| abstract_inverted_index.correspondence | 95 |
| abstract_inverted_index.classification, | 149, 152 |
| abstract_inverted_index.local-to-global | 94 |
| abstract_inverted_index.self-distillation. | 98 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8399999737739563 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |