Masked Autoencoders Are Scalable Vision Learners Article Swipe
Kaiming He
,
Xinlei Chen
,
Saining Xie
,
Yanghao Li
,
Piotr Dollár
,
Ross Girshick
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2111.06377
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2111.06377
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs. First, we develop an asymmetric encoder-decoder architecture, with an encoder that operates only on the visible subset of patches (without mask tokens), along with a lightweight decoder that reconstructs the original image from the latent representation and mask tokens. Second, we find that masking a high proportion of the input image, e.g., 75%, yields a nontrivial and meaningful self-supervisory task. Coupling these two designs enables us to train large models efficiently and effectively: we accelerate training (by 3x or more) and improve accuracy. Our scalable approach allows for learning high-capacity models that generalize well: e.g., a vanilla ViT-Huge model achieves the best accuracy (87.8%) among methods that use only ImageNet-1K data. Transfer performance in downstream tasks outperforms supervised pre-training and shows promising scaling behavior.
Related Topics
Concepts
Computer science
Scalability
Encoder
Artificial intelligence
Masking (illustration)
Representation (politics)
Image (mathematics)
Feature learning
Pattern recognition (psychology)
Pixel
Scaling
Machine learning
Computer vision
Mathematics
Art
Operating system
Geometry
Politics
Visual arts
Law
Database
Political science
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2111.06377
- https://arxiv.org/pdf/2111.06377
- OA Status
- green
- Cited By
- 179
- References
- 59
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3211983881
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3211983881Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2111.06377Digital Object Identifier
- Title
-
Masked Autoencoders Are Scalable Vision LearnersWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-11-11Full publication date if available
- Authors
-
Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross GirshickList of authors in order
- Landing page
-
https://arxiv.org/abs/2111.06377Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2111.06377Direct 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/2111.06377Direct OA link when available
- Concepts
-
Computer science, Scalability, Encoder, Artificial intelligence, Masking (illustration), Representation (politics), Image (mathematics), Feature learning, Pattern recognition (psychology), Pixel, Scaling, Machine learning, Computer vision, Mathematics, Art, Operating system, Geometry, Politics, Visual arts, Law, Database, Political scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
179Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 47, 2024: 56, 2023: 54, 2022: 13, 2021: 9Per-year citation counts (last 5 years)
- References (count)
-
59Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3211983881 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2111.06377 |
| ids.doi | https://doi.org/10.48550/arxiv.2111.06377 |
| ids.mag | 3211983881 |
| ids.openalex | https://openalex.org/W3211983881 |
| fwci | |
| type | preprint |
| title | Masked Autoencoders Are Scalable Vision Learners |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11307 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 1.0 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Domain Adaptation and Few-Shot Learning |
| 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 | 0.9998000264167786 |
| 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/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9990000128746033 |
| 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 | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.843129575252533 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C48044578 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7173157334327698 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q727490 |
| concepts[1].display_name | Scalability |
| concepts[2].id | https://openalex.org/C118505674 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6238670945167542 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[2].display_name | Encoder |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6172170639038086 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C2777402240 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5815168619155884 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q6783436 |
| concepts[4].display_name | Masking (illustration) |
| concepts[5].id | https://openalex.org/C2776359362 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5280255675315857 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[5].display_name | Representation (politics) |
| concepts[6].id | https://openalex.org/C115961682 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5108096599578857 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[6].display_name | Image (mathematics) |
| concepts[7].id | https://openalex.org/C59404180 |
| concepts[7].level | 2 |
| concepts[7].score | 0.43822774291038513 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[7].display_name | Feature learning |
| concepts[8].id | https://openalex.org/C153180895 |
| concepts[8].level | 2 |
| concepts[8].score | 0.42926347255706787 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[8].display_name | Pattern recognition (psychology) |
| concepts[9].id | https://openalex.org/C160633673 |
| concepts[9].level | 2 |
| concepts[9].score | 0.423355370759964 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q355198 |
| concepts[9].display_name | Pixel |
| concepts[10].id | https://openalex.org/C99844830 |
| concepts[10].level | 2 |
| concepts[10].score | 0.42012882232666016 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q102441924 |
| concepts[10].display_name | Scaling |
| concepts[11].id | https://openalex.org/C119857082 |
| concepts[11].level | 1 |
| concepts[11].score | 0.35246381163597107 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[11].display_name | Machine learning |
| concepts[12].id | https://openalex.org/C31972630 |
| concepts[12].level | 1 |
| concepts[12].score | 0.3461090922355652 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[12].display_name | Computer vision |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C142362112 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[14].display_name | Art |
| concepts[15].id | https://openalex.org/C111919701 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[15].display_name | Operating system |
| concepts[16].id | https://openalex.org/C2524010 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[16].display_name | Geometry |
| concepts[17].id | https://openalex.org/C94625758 |
| concepts[17].level | 2 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[17].display_name | Politics |
| concepts[18].id | https://openalex.org/C153349607 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q36649 |
| concepts[18].display_name | Visual arts |
| concepts[19].id | https://openalex.org/C199539241 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[19].display_name | Law |
| concepts[20].id | https://openalex.org/C77088390 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[20].display_name | Database |
| concepts[21].id | https://openalex.org/C17744445 |
| concepts[21].level | 0 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[21].display_name | Political science |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.843129575252533 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/scalability |
| keywords[1].score | 0.7173157334327698 |
| keywords[1].display_name | Scalability |
| keywords[2].id | https://openalex.org/keywords/encoder |
| keywords[2].score | 0.6238670945167542 |
| keywords[2].display_name | Encoder |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.6172170639038086 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/masking |
| keywords[4].score | 0.5815168619155884 |
| keywords[4].display_name | Masking (illustration) |
| keywords[5].id | https://openalex.org/keywords/representation |
| keywords[5].score | 0.5280255675315857 |
| keywords[5].display_name | Representation (politics) |
| keywords[6].id | https://openalex.org/keywords/image |
| keywords[6].score | 0.5108096599578857 |
| keywords[6].display_name | Image (mathematics) |
| keywords[7].id | https://openalex.org/keywords/feature-learning |
| keywords[7].score | 0.43822774291038513 |
| keywords[7].display_name | Feature learning |
| keywords[8].id | https://openalex.org/keywords/pattern-recognition |
| keywords[8].score | 0.42926347255706787 |
| keywords[8].display_name | Pattern recognition (psychology) |
| keywords[9].id | https://openalex.org/keywords/pixel |
| keywords[9].score | 0.423355370759964 |
| keywords[9].display_name | Pixel |
| keywords[10].id | https://openalex.org/keywords/scaling |
| keywords[10].score | 0.42012882232666016 |
| keywords[10].display_name | Scaling |
| keywords[11].id | https://openalex.org/keywords/machine-learning |
| keywords[11].score | 0.35246381163597107 |
| keywords[11].display_name | Machine learning |
| keywords[12].id | https://openalex.org/keywords/computer-vision |
| keywords[12].score | 0.3461090922355652 |
| keywords[12].display_name | Computer vision |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2111.06377 |
| 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 | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2111.06377 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2111.06377 |
| locations[1].id | doi:10.48550/arxiv.2111.06377 |
| 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.2111.06377 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100700361 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7318-9658 |
| authorships[0].author.display_name | Kaiming He |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Kaiming He |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101507596 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5233-8335 |
| authorships[1].author.display_name | Xinlei Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xinlei Chen |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102416863 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Saining Xie |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Saining Xie |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5029760000 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5274-1367 |
| authorships[3].author.display_name | Yanghao Li |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yanghao Li |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5057866698 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Piotr Dollár |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Piotr Dollár |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5049246408 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Ross Girshick |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Ross B. Girshick |
| authorships[5].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2111.06377 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Masked Autoencoders Are Scalable Vision Learners |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11307 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 1.0 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Domain Adaptation and Few-Shot Learning |
| related_works | https://openalex.org/W4390516098, https://openalex.org/W3081694532, https://openalex.org/W2085033728, https://openalex.org/W4285411112, https://openalex.org/W141820298, https://openalex.org/W2171299904, https://openalex.org/W2181948922, https://openalex.org/W2384362569, https://openalex.org/W2049584446, https://openalex.org/W1647606319 |
| cited_by_count | 179 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 47 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 56 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 54 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 13 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 9 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2111.06377 |
| 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 | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2111.06377 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| 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/2111.06377 |
| primary_location.id | pmh:oai:arXiv.org:2111.06377 |
| 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 | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2111.06377 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2111.06377 |
| publication_date | 2021-11-11 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2321533354, https://openalex.org/W343636949, https://openalex.org/W219040644, https://openalex.org/W2799269579, https://openalex.org/W2565639579, https://openalex.org/W2138621090, https://openalex.org/W1836465849, https://openalex.org/W2063971957, https://openalex.org/W3195108980, https://openalex.org/W3212756788, https://openalex.org/W3035524453, https://openalex.org/W3216272314, https://openalex.org/W3170016573, https://openalex.org/W2996035354, https://openalex.org/W2102409316, https://openalex.org/W2342877626, https://openalex.org/W3171007011, https://openalex.org/W2884822772, https://openalex.org/W2908510526, https://openalex.org/W2183341477, https://openalex.org/W3173631098, https://openalex.org/W2149933564, https://openalex.org/W2331143823, https://openalex.org/W3135715136, https://openalex.org/W3101821705, https://openalex.org/W2163605009, https://openalex.org/W3170874841, https://openalex.org/W2134670479, https://openalex.org/W2944223741, https://openalex.org/W3170863103, https://openalex.org/W2108598243, https://openalex.org/W2963399829, https://openalex.org/W1533861849, https://openalex.org/W2025768430, https://openalex.org/W2507296351, https://openalex.org/W3034978746, https://openalex.org/W2147800946, https://openalex.org/W2962835968, https://openalex.org/W3204619080, https://openalex.org/W2622263826, https://openalex.org/W3034445277, https://openalex.org/W2575671312, https://openalex.org/W2963263347, https://openalex.org/W2963403868, https://openalex.org/W3098903812, https://openalex.org/W2326925005, https://openalex.org/W3119786062, https://openalex.org/W2145094598, https://openalex.org/W2194775991, https://openalex.org/W2963341956, https://openalex.org/W2798991696, https://openalex.org/W2962742544, https://openalex.org/W2842511635, https://openalex.org/W3102631365, https://openalex.org/W1861492603, https://openalex.org/W2963799213, https://openalex.org/W3082274269, https://openalex.org/W2971315489, https://openalex.org/W2757910899 |
| referenced_works_count | 59 |
| abstract_inverted_index.a | 63, 83, 93, 134 |
| abstract_inverted_index.3x | 116 |
| abstract_inverted_index.It | 32 |
| abstract_inverted_index.an | 42, 47 |
| abstract_inverted_index.in | 152 |
| abstract_inverted_index.is | 17, 33 |
| abstract_inverted_index.of | 23, 56, 86 |
| abstract_inverted_index.on | 35, 52 |
| abstract_inverted_index.or | 117 |
| abstract_inverted_index.to | 105 |
| abstract_inverted_index.us | 104 |
| abstract_inverted_index.we | 19, 40, 79, 112 |
| abstract_inverted_index.(by | 115 |
| abstract_inverted_index.MAE | 15 |
| abstract_inverted_index.Our | 14, 122 |
| abstract_inverted_index.and | 27, 75, 95, 110, 119, 158 |
| abstract_inverted_index.are | 7 |
| abstract_inverted_index.for | 11, 126 |
| abstract_inverted_index.the | 24, 29, 53, 68, 72, 87, 139 |
| abstract_inverted_index.two | 36, 101 |
| abstract_inverted_index.use | 146 |
| abstract_inverted_index.75%, | 91 |
| abstract_inverted_index.This | 0 |
| abstract_inverted_index.best | 140 |
| abstract_inverted_index.core | 37 |
| abstract_inverted_index.find | 80 |
| abstract_inverted_index.from | 71 |
| abstract_inverted_index.high | 84 |
| abstract_inverted_index.mask | 20, 59, 76 |
| abstract_inverted_index.only | 51, 147 |
| abstract_inverted_index.that | 3, 49, 66, 81, 130, 145 |
| abstract_inverted_index.with | 46, 62 |
| abstract_inverted_index.(MAE) | 6 |
| abstract_inverted_index.along | 61 |
| abstract_inverted_index.among | 143 |
| abstract_inverted_index.based | 34 |
| abstract_inverted_index.data. | 149 |
| abstract_inverted_index.e.g., | 90, 133 |
| abstract_inverted_index.image | 26, 70 |
| abstract_inverted_index.input | 25, 88 |
| abstract_inverted_index.large | 107 |
| abstract_inverted_index.model | 137 |
| abstract_inverted_index.more) | 118 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.shows | 2, 159 |
| abstract_inverted_index.task. | 98 |
| abstract_inverted_index.tasks | 154 |
| abstract_inverted_index.these | 100 |
| abstract_inverted_index.train | 106 |
| abstract_inverted_index.well: | 132 |
| abstract_inverted_index.First, | 39 |
| abstract_inverted_index.allows | 125 |
| abstract_inverted_index.image, | 89 |
| abstract_inverted_index.latent | 73 |
| abstract_inverted_index.masked | 4 |
| abstract_inverted_index.models | 108, 129 |
| abstract_inverted_index.random | 21 |
| abstract_inverted_index.subset | 55 |
| abstract_inverted_index.yields | 92 |
| abstract_inverted_index.(87.8%) | 142 |
| abstract_inverted_index.Second, | 78 |
| abstract_inverted_index.decoder | 65 |
| abstract_inverted_index.designs | 102 |
| abstract_inverted_index.develop | 41 |
| abstract_inverted_index.enables | 103 |
| abstract_inverted_index.encoder | 48 |
| abstract_inverted_index.improve | 120 |
| abstract_inverted_index.masking | 82 |
| abstract_inverted_index.methods | 144 |
| abstract_inverted_index.missing | 30 |
| abstract_inverted_index.patches | 22, 57 |
| abstract_inverted_index.pixels. | 31 |
| abstract_inverted_index.scaling | 161 |
| abstract_inverted_index.simple: | 18 |
| abstract_inverted_index.tokens. | 77 |
| abstract_inverted_index.vanilla | 135 |
| abstract_inverted_index.visible | 54 |
| abstract_inverted_index.vision. | 13 |
| abstract_inverted_index.(without | 58 |
| abstract_inverted_index.Coupling | 99 |
| abstract_inverted_index.Transfer | 150 |
| abstract_inverted_index.ViT-Huge | 136 |
| abstract_inverted_index.accuracy | 141 |
| abstract_inverted_index.achieves | 138 |
| abstract_inverted_index.approach | 16, 124 |
| abstract_inverted_index.computer | 12 |
| abstract_inverted_index.designs. | 38 |
| abstract_inverted_index.learners | 10 |
| abstract_inverted_index.learning | 127 |
| abstract_inverted_index.operates | 50 |
| abstract_inverted_index.original | 69 |
| abstract_inverted_index.scalable | 8, 123 |
| abstract_inverted_index.tokens), | 60 |
| abstract_inverted_index.training | 114 |
| abstract_inverted_index.accuracy. | 121 |
| abstract_inverted_index.behavior. | 162 |
| abstract_inverted_index.promising | 160 |
| abstract_inverted_index.accelerate | 113 |
| abstract_inverted_index.asymmetric | 43 |
| abstract_inverted_index.downstream | 153 |
| abstract_inverted_index.generalize | 131 |
| abstract_inverted_index.meaningful | 96 |
| abstract_inverted_index.nontrivial | 94 |
| abstract_inverted_index.proportion | 85 |
| abstract_inverted_index.supervised | 156 |
| abstract_inverted_index.ImageNet-1K | 148 |
| abstract_inverted_index.efficiently | 109 |
| abstract_inverted_index.lightweight | 64 |
| abstract_inverted_index.outperforms | 155 |
| abstract_inverted_index.performance | 151 |
| abstract_inverted_index.reconstruct | 28 |
| abstract_inverted_index.autoencoders | 5 |
| abstract_inverted_index.effectively: | 111 |
| abstract_inverted_index.pre-training | 157 |
| abstract_inverted_index.reconstructs | 67 |
| abstract_inverted_index.architecture, | 45 |
| abstract_inverted_index.high-capacity | 128 |
| abstract_inverted_index.representation | 74 |
| abstract_inverted_index.encoder-decoder | 44 |
| abstract_inverted_index.self-supervised | 9 |
| abstract_inverted_index.self-supervisory | 97 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |