Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution Article Swipe
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2307.06304
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT) offer flexible sequence-based modeling, and hence varying input sequence lengths. We take advantage of this with NaViT (Native Resolution ViT) which uses sequence packing during training to process inputs of arbitrary resolutions and aspect ratios. Alongside flexible model usage, we demonstrate improved training efficiency for large-scale supervised and contrastive image-text pretraining. NaViT can be efficiently transferred to standard tasks such as image and video classification, object detection, and semantic segmentation and leads to improved results on robustness and fairness benchmarks. At inference time, the input resolution flexibility can be used to smoothly navigate the test-time cost-performance trade-off. We believe that NaViT marks a departure from the standard, CNN-designed, input and modelling pipeline used by most computer vision models, and represents a promising direction for ViTs.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2307.06304
- https://arxiv.org/pdf/2307.06304
- OA Status
- green
- Cited By
- 15
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4384268586
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4384268586Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2307.06304Digital Object Identifier
- Title
-
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and ResolutionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-07-12Full publication date if available
- Authors
-
Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim Alabdulmohsin, Avital Oliver, Piotr Padlewski, Alexey A. Gritsenko, Mario Lučić, Neil HoulsbyList of authors in order
- Landing page
-
https://arxiv.org/abs/2307.06304Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2307.06304Direct 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/2307.06304Direct OA link when available
- Concepts
-
Computer science, Artificial intelligence, Robustness (evolution), Inference, Segmentation, Transformer, Computer vision, Engineering, Biochemistry, Electrical engineering, Chemistry, Voltage, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
15Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 7, 2024: 8Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4384268586 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2307.06304 |
| ids.doi | https://doi.org/10.48550/arxiv.2307.06304 |
| ids.openalex | https://openalex.org/W4384268586 |
| fwci | |
| type | preprint |
| title | Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10627 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998000264167786 |
| 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 | Advanced Image and Video Retrieval Techniques |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9994999766349792 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T11307 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9987999796867371 |
| 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 | Domain Adaptation and Few-Shot Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7673527598381042 |
| 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 | 0.6251357793807983 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C63479239 |
| concepts[2].level | 3 |
| concepts[2].score | 0.5800178050994873 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[2].display_name | Robustness (evolution) |
| concepts[3].id | https://openalex.org/C2776214188 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5740326642990112 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[3].display_name | Inference |
| concepts[4].id | https://openalex.org/C89600930 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5632737874984741 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[4].display_name | Segmentation |
| concepts[5].id | https://openalex.org/C66322947 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5367146134376526 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[5].display_name | Transformer |
| concepts[6].id | https://openalex.org/C31972630 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5027430057525635 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[6].display_name | Computer vision |
| concepts[7].id | https://openalex.org/C127413603 |
| concepts[7].level | 0 |
| concepts[7].score | 0.09026956558227539 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[7].display_name | Engineering |
| concepts[8].id | https://openalex.org/C55493867 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[8].display_name | Biochemistry |
| concepts[9].id | https://openalex.org/C119599485 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[9].display_name | Electrical engineering |
| concepts[10].id | https://openalex.org/C185592680 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[10].display_name | Chemistry |
| concepts[11].id | https://openalex.org/C165801399 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[11].display_name | Voltage |
| concepts[12].id | https://openalex.org/C104317684 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[12].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7673527598381042 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.6251357793807983 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/robustness |
| keywords[2].score | 0.5800178050994873 |
| keywords[2].display_name | Robustness (evolution) |
| keywords[3].id | https://openalex.org/keywords/inference |
| keywords[3].score | 0.5740326642990112 |
| keywords[3].display_name | Inference |
| keywords[4].id | https://openalex.org/keywords/segmentation |
| keywords[4].score | 0.5632737874984741 |
| keywords[4].display_name | Segmentation |
| keywords[5].id | https://openalex.org/keywords/transformer |
| keywords[5].score | 0.5367146134376526 |
| keywords[5].display_name | Transformer |
| keywords[6].id | https://openalex.org/keywords/computer-vision |
| keywords[6].score | 0.5027430057525635 |
| keywords[6].display_name | Computer vision |
| keywords[7].id | https://openalex.org/keywords/engineering |
| keywords[7].score | 0.09026956558227539 |
| keywords[7].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2307.06304 |
| 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/2307.06304 |
| 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/2307.06304 |
| locations[1].id | doi:10.48550/arxiv.2307.06304 |
| 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.2307.06304 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102906366 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9772-1095 |
| authorships[0].author.display_name | Mostafa Dehghani |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dehghani, Mostafa |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5072796087 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7305-7890 |
| authorships[1].author.display_name | Basil Mustafa |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mustafa, Basil |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5010814788 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Josip Djolonga |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Djolonga, Josip |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5086404363 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Jonathan Heek |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Heek, Jonathan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5088239541 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6428-8256 |
| authorships[4].author.display_name | Matthias Minderer |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Minderer, Matthias |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5071626315 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-6594-6698 |
| authorships[5].author.display_name | Mathilde Caron |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Caron, Mathilde |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5053094006 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-9272-3262 |
| authorships[6].author.display_name | Andreas Steiner |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Steiner, Andreas |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5001091279 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-1926-2233 |
| authorships[7].author.display_name | Joan Puigcerver |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Puigcerver, Joan |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5043113119 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-7698-3187 |
| authorships[8].author.display_name | Robert Geirhos |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Geirhos, Robert |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5029133361 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-9387-5820 |
| authorships[9].author.display_name | Ibrahim Alabdulmohsin |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Alabdulmohsin, Ibrahim |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5104143329 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Avital Oliver |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Oliver, Avital |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5086683431 |
| authorships[11].author.orcid | https://orcid.org/0000-0001-5107-0824 |
| authorships[11].author.display_name | Piotr Padlewski |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Padlewski, Piotr |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5083585691 |
| authorships[12].author.orcid | https://orcid.org/0000-0003-1799-2301 |
| authorships[12].author.display_name | Alexey A. Gritsenko |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Gritsenko, Alexey |
| authorships[12].is_corresponding | False |
| authorships[13].author.id | https://openalex.org/A5044677020 |
| authorships[13].author.orcid | |
| authorships[13].author.display_name | Mario Lučić |
| authorships[13].author_position | middle |
| authorships[13].raw_author_name | Lučić, Mario |
| authorships[13].is_corresponding | False |
| authorships[14].author.id | https://openalex.org/A5068878643 |
| authorships[14].author.orcid | |
| authorships[14].author.display_name | Neil Houlsby |
| authorships[14].author_position | last |
| authorships[14].raw_author_name | Houlsby, Neil |
| authorships[14].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/2307.06304 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-07-14T00:00:00 |
| display_name | Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10627 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998000264167786 |
| 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 | Advanced Image and Video Retrieval Techniques |
| related_works | https://openalex.org/W2055243143, https://openalex.org/W2770593030, https://openalex.org/W3154990682, https://openalex.org/W4281727072, https://openalex.org/W2560201613, https://openalex.org/W2171975302, https://openalex.org/W4206178588, https://openalex.org/W4287635093, https://openalex.org/W3094491777, https://openalex.org/W3214715529 |
| cited_by_count | 15 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 7 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 8 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2307.06304 |
| 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/2307.06304 |
| 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/2307.06304 |
| primary_location.id | pmh:oai:arXiv.org:2307.06304 |
| 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/2307.06304 |
| 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/2307.06304 |
| publication_date | 2023-07-12 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 10, 136, 154 |
| abstract_inverted_index.At | 114 |
| abstract_inverted_index.We | 44, 131 |
| abstract_inverted_index.as | 29, 94 |
| abstract_inverted_index.be | 87, 122 |
| abstract_inverted_index.by | 147 |
| abstract_inverted_index.of | 6, 47, 63 |
| abstract_inverted_index.on | 109 |
| abstract_inverted_index.to | 9, 60, 90, 106, 124 |
| abstract_inverted_index.we | 73 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 2, 38, 66, 81, 96, 101, 104, 111, 143, 152 |
| abstract_inverted_index.can | 86, 121 |
| abstract_inverted_index.for | 78, 157 |
| abstract_inverted_index.has | 20 |
| abstract_inverted_index.not | 21 |
| abstract_inverted_index.the | 30, 117, 127, 139 |
| abstract_inverted_index.yet | 22 |
| abstract_inverted_index.ViT) | 53 |
| abstract_inverted_index.been | 23 |
| abstract_inverted_index.from | 138 |
| abstract_inverted_index.most | 148 |
| abstract_inverted_index.such | 28, 93 |
| abstract_inverted_index.take | 45 |
| abstract_inverted_index.that | 133 |
| abstract_inverted_index.them | 15 |
| abstract_inverted_index.this | 48 |
| abstract_inverted_index.used | 123, 146 |
| abstract_inverted_index.uses | 55 |
| abstract_inverted_index.with | 16, 49 |
| abstract_inverted_index.(ViT) | 33 |
| abstract_inverted_index.NaViT | 50, 85, 134 |
| abstract_inverted_index.ViTs. | 158 |
| abstract_inverted_index.fixed | 11 |
| abstract_inverted_index.hence | 39 |
| abstract_inverted_index.image | 95 |
| abstract_inverted_index.input | 41, 118, 142 |
| abstract_inverted_index.leads | 105 |
| abstract_inverted_index.marks | 135 |
| abstract_inverted_index.model | 71 |
| abstract_inverted_index.offer | 34 |
| abstract_inverted_index.tasks | 92 |
| abstract_inverted_index.time, | 116 |
| abstract_inverted_index.video | 97 |
| abstract_inverted_index.which | 54 |
| abstract_inverted_index.Vision | 31 |
| abstract_inverted_index.aspect | 67 |
| abstract_inverted_index.before | 13 |
| abstract_inverted_index.choice | 5 |
| abstract_inverted_index.during | 58 |
| abstract_inverted_index.images | 8 |
| abstract_inverted_index.inputs | 62 |
| abstract_inverted_index.models | 19, 27 |
| abstract_inverted_index.object | 99 |
| abstract_inverted_index.usage, | 72 |
| abstract_inverted_index.vision | 18, 150 |
| abstract_inverted_index.(Native | 51 |
| abstract_inverted_index.believe | 132 |
| abstract_inverted_index.models, | 151 |
| abstract_inverted_index.packing | 57 |
| abstract_inverted_index.process | 61 |
| abstract_inverted_index.ratios. | 68 |
| abstract_inverted_index.results | 108 |
| abstract_inverted_index.varying | 40 |
| abstract_inverted_index.However, | 26 |
| abstract_inverted_index.computer | 17, 149 |
| abstract_inverted_index.fairness | 112 |
| abstract_inverted_index.flexible | 35, 70 |
| abstract_inverted_index.improved | 75, 107 |
| abstract_inverted_index.lengths. | 43 |
| abstract_inverted_index.navigate | 126 |
| abstract_inverted_index.pipeline | 145 |
| abstract_inverted_index.resizing | 7 |
| abstract_inverted_index.semantic | 102 |
| abstract_inverted_index.sequence | 42, 56 |
| abstract_inverted_index.smoothly | 125 |
| abstract_inverted_index.standard | 91 |
| abstract_inverted_index.training | 59, 76 |
| abstract_inverted_index.Alongside | 69 |
| abstract_inverted_index.advantage | 46 |
| abstract_inverted_index.arbitrary | 64 |
| abstract_inverted_index.departure | 137 |
| abstract_inverted_index.direction | 156 |
| abstract_inverted_index.inference | 115 |
| abstract_inverted_index.modeling, | 37 |
| abstract_inverted_index.modelling | 144 |
| abstract_inverted_index.promising | 155 |
| abstract_inverted_index.standard, | 140 |
| abstract_inverted_index.test-time | 128 |
| abstract_inverted_index.Resolution | 52 |
| abstract_inverted_index.detection, | 100 |
| abstract_inverted_index.efficiency | 77 |
| abstract_inverted_index.image-text | 83 |
| abstract_inverted_index.processing | 14 |
| abstract_inverted_index.represents | 153 |
| abstract_inverted_index.resolution | 12, 119 |
| abstract_inverted_index.robustness | 110 |
| abstract_inverted_index.suboptimal | 4 |
| abstract_inverted_index.supervised | 80 |
| abstract_inverted_index.trade-off. | 130 |
| abstract_inverted_index.ubiquitous | 1 |
| abstract_inverted_index.Transformer | 32 |
| abstract_inverted_index.benchmarks. | 113 |
| abstract_inverted_index.challenged. | 25 |
| abstract_inverted_index.contrastive | 82 |
| abstract_inverted_index.demonstrate | 74 |
| abstract_inverted_index.efficiently | 88 |
| abstract_inverted_index.flexibility | 120 |
| abstract_inverted_index.large-scale | 79 |
| abstract_inverted_index.resolutions | 65 |
| abstract_inverted_index.transferred | 89 |
| abstract_inverted_index.demonstrably | 3 |
| abstract_inverted_index.pretraining. | 84 |
| abstract_inverted_index.segmentation | 103 |
| abstract_inverted_index.successfully | 24 |
| abstract_inverted_index.CNN-designed, | 141 |
| abstract_inverted_index.sequence-based | 36 |
| abstract_inverted_index.classification, | 98 |
| abstract_inverted_index.cost-performance | 129 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 15 |
| citation_normalized_percentile |