Correlated Input-Dependent Label Noise in Large-Scale Image\n Classification Article Swipe
Mark Collier
,
Basil Mustafa
,
Efi Kokiopoulou
,
Rodolphe Jenatton
,
Jesse Berent
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2105.10305
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2105.10305
Large scale image classification datasets often contain noisy labels. We take\na principled probabilistic approach to modelling input-dependent, also known as\nheteroscedastic, label noise in these datasets. We place a multivariate Normal\ndistributed latent variable on the final hidden layer of a neural network\nclassifier. The covariance matrix of this latent variable, models the aleatoric\nuncertainty due to label noise. We demonstrate that the learned covariance\nstructure captures known sources of label noise between semantically similar\nand co-occurring classes. Compared to standard neural network training and\nother baselines, we show significantly improved accuracy on Imagenet ILSVRC\n2012 79.3% (+2.6%), Imagenet-21k 47.0% (+1.1%) and JFT 64.7% (+1.6%). We set a\nnew state-of-the-art result on WebVision 1.0 with 76.6% top-1 accuracy. These\ndatasets range from over 1M to over 300M training examples and from 1k classes\nto more than 21k classes. Our method is simple to use, and we provide an\nimplementation that is a drop-in replacement for the final fully-connected\nlayer in a deep classifier.\n
Related Topics
Concepts
Classifier (UML)
Pattern recognition (psychology)
Artificial intelligence
Computer science
Latent variable
Artificial neural network
Covariance
Covariance matrix
Contextual image classification
Deep neural networks
Probabilistic logic
Noise (video)
Machine learning
Discriminative model
Image (mathematics)
Mathematics
Statistics
Algorithm
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2105.10305
- https://arxiv.org/pdf/2105.10305
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287179911
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287179911Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2105.10305Digital Object Identifier
- Title
-
Correlated Input-Dependent Label Noise in Large-Scale Image\n ClassificationWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2021Year of publication
- Publication date
-
2021-05-19Full publication date if available
- Authors
-
Mark Collier, Basil Mustafa, Efi Kokiopoulou, Rodolphe Jenatton, Jesse BerentList of authors in order
- Landing page
-
https://arxiv.org/abs/2105.10305Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2105.10305Direct 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/2105.10305Direct OA link when available
- Concepts
-
Classifier (UML), Pattern recognition (psychology), Artificial intelligence, Computer science, Latent variable, Artificial neural network, Covariance, Covariance matrix, Contextual image classification, Deep neural networks, Probabilistic logic, Noise (video), Machine learning, Discriminative model, Image (mathematics), Mathematics, Statistics, AlgorithmTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4287179911 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2105.10305 |
| ids.openalex | https://openalex.org/W4287179911 |
| fwci | 0.0 |
| type | preprint |
| title | Correlated Input-Dependent Label Noise in Large-Scale Image\n Classification |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12535 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9965000152587891 |
| 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 | Machine Learning and Data Classification |
| topics[1].id | https://openalex.org/T12549 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9114999771118164 |
| 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 | Image and Object Detection Techniques |
| topics[2].id | https://openalex.org/T12026 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9107999801635742 |
| 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 | Explainable Artificial Intelligence (XAI) |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C95623464 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7004804015159607 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[0].display_name | Classifier (UML) |
| concepts[1].id | https://openalex.org/C153180895 |
| concepts[1].level | 2 |
| concepts[1].score | 0.664696991443634 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[1].display_name | Pattern recognition (psychology) |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6582772135734558 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5982517004013062 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C51167844 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5267961621284485 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q4422623 |
| concepts[4].display_name | Latent variable |
| concepts[5].id | https://openalex.org/C50644808 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5218074321746826 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[5].display_name | Artificial neural network |
| concepts[6].id | https://openalex.org/C178650346 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4686020612716675 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q201984 |
| concepts[6].display_name | Covariance |
| concepts[7].id | https://openalex.org/C185142706 |
| concepts[7].level | 2 |
| concepts[7].score | 0.46446484327316284 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1134404 |
| concepts[7].display_name | Covariance matrix |
| concepts[8].id | https://openalex.org/C75294576 |
| concepts[8].level | 3 |
| concepts[8].score | 0.46004346013069153 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5165192 |
| concepts[8].display_name | Contextual image classification |
| concepts[9].id | https://openalex.org/C2984842247 |
| concepts[9].level | 3 |
| concepts[9].score | 0.4569019675254822 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[9].display_name | Deep neural networks |
| concepts[10].id | https://openalex.org/C49937458 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4556695222854614 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2599292 |
| concepts[10].display_name | Probabilistic logic |
| concepts[11].id | https://openalex.org/C99498987 |
| concepts[11].level | 3 |
| concepts[11].score | 0.44378143548965454 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2210247 |
| concepts[11].display_name | Noise (video) |
| concepts[12].id | https://openalex.org/C119857082 |
| concepts[12].level | 1 |
| concepts[12].score | 0.42859819531440735 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[12].display_name | Machine learning |
| concepts[13].id | https://openalex.org/C97931131 |
| concepts[13].level | 2 |
| concepts[13].score | 0.42053312063217163 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q5282087 |
| concepts[13].display_name | Discriminative model |
| concepts[14].id | https://openalex.org/C115961682 |
| concepts[14].level | 2 |
| concepts[14].score | 0.329464852809906 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[14].display_name | Image (mathematics) |
| concepts[15].id | https://openalex.org/C33923547 |
| concepts[15].level | 0 |
| concepts[15].score | 0.20036450028419495 |
| 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 | 0.14836406707763672 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[16].display_name | Statistics |
| concepts[17].id | https://openalex.org/C11413529 |
| concepts[17].level | 1 |
| concepts[17].score | 0.1358567178249359 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[17].display_name | Algorithm |
| keywords[0].id | https://openalex.org/keywords/classifier |
| keywords[0].score | 0.7004804015159607 |
| keywords[0].display_name | Classifier (UML) |
| keywords[1].id | https://openalex.org/keywords/pattern-recognition |
| keywords[1].score | 0.664696991443634 |
| keywords[1].display_name | Pattern recognition (psychology) |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6582772135734558 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5982517004013062 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/latent-variable |
| keywords[4].score | 0.5267961621284485 |
| keywords[4].display_name | Latent variable |
| keywords[5].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[5].score | 0.5218074321746826 |
| keywords[5].display_name | Artificial neural network |
| keywords[6].id | https://openalex.org/keywords/covariance |
| keywords[6].score | 0.4686020612716675 |
| keywords[6].display_name | Covariance |
| keywords[7].id | https://openalex.org/keywords/covariance-matrix |
| keywords[7].score | 0.46446484327316284 |
| keywords[7].display_name | Covariance matrix |
| keywords[8].id | https://openalex.org/keywords/contextual-image-classification |
| keywords[8].score | 0.46004346013069153 |
| keywords[8].display_name | Contextual image classification |
| keywords[9].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[9].score | 0.4569019675254822 |
| keywords[9].display_name | Deep neural networks |
| keywords[10].id | https://openalex.org/keywords/probabilistic-logic |
| keywords[10].score | 0.4556695222854614 |
| keywords[10].display_name | Probabilistic logic |
| keywords[11].id | https://openalex.org/keywords/noise |
| keywords[11].score | 0.44378143548965454 |
| keywords[11].display_name | Noise (video) |
| keywords[12].id | https://openalex.org/keywords/machine-learning |
| keywords[12].score | 0.42859819531440735 |
| keywords[12].display_name | Machine learning |
| keywords[13].id | https://openalex.org/keywords/discriminative-model |
| keywords[13].score | 0.42053312063217163 |
| keywords[13].display_name | Discriminative model |
| keywords[14].id | https://openalex.org/keywords/image |
| keywords[14].score | 0.329464852809906 |
| keywords[14].display_name | Image (mathematics) |
| keywords[15].id | https://openalex.org/keywords/mathematics |
| keywords[15].score | 0.20036450028419495 |
| keywords[15].display_name | Mathematics |
| keywords[16].id | https://openalex.org/keywords/statistics |
| keywords[16].score | 0.14836406707763672 |
| keywords[16].display_name | Statistics |
| keywords[17].id | https://openalex.org/keywords/algorithm |
| keywords[17].score | 0.1358567178249359 |
| keywords[17].display_name | Algorithm |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2105.10305 |
| 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/2105.10305 |
| 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/2105.10305 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5058235234 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1391-9473 |
| authorships[0].author.display_name | Mark Collier |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Collier, Mark |
| 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/A5009956004 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Efi Kokiopoulou |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kokiopoulou, Efi |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5033851429 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Rodolphe Jenatton |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jenatton, Rodolphe |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5024318881 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Jesse Berent |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Berent, Jesse |
| authorships[4].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/2105.10305 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-25T00:00:00 |
| display_name | Correlated Input-Dependent Label Noise in Large-Scale Image\n Classification |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12535 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9965000152587891 |
| 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 | Machine Learning and Data Classification |
| related_works | https://openalex.org/W4389116644, https://openalex.org/W2153315159, https://openalex.org/W3103844505, https://openalex.org/W259157601, https://openalex.org/W4205463238, https://openalex.org/W1482209366, https://openalex.org/W2110523656, https://openalex.org/W2521627374, https://openalex.org/W2981954115, https://openalex.org/W2129933262 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2105.10305 |
| 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/2105.10305 |
| 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/2105.10305 |
| primary_location.id | pmh:oai:arXiv.org:2105.10305 |
| 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/2105.10305 |
| 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/2105.10305 |
| publication_date | 2021-05-19 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 27, 38, 139, 147 |
| abstract_inverted_index.1M | 113 |
| abstract_inverted_index.1k | 121 |
| abstract_inverted_index.We | 9, 25, 55, 97 |
| abstract_inverted_index.in | 22, 146 |
| abstract_inverted_index.is | 129, 138 |
| abstract_inverted_index.of | 37, 44, 64 |
| abstract_inverted_index.on | 32, 85, 102 |
| abstract_inverted_index.to | 14, 52, 73, 114, 131 |
| abstract_inverted_index.we | 80, 134 |
| abstract_inverted_index.1.0 | 104 |
| abstract_inverted_index.21k | 125 |
| abstract_inverted_index.JFT | 94 |
| abstract_inverted_index.Our | 127 |
| abstract_inverted_index.The | 41 |
| abstract_inverted_index.and | 93, 119, 133 |
| abstract_inverted_index.due | 51 |
| abstract_inverted_index.for | 142 |
| abstract_inverted_index.set | 98 |
| abstract_inverted_index.the | 33, 49, 58, 143 |
| abstract_inverted_index.300M | 116 |
| abstract_inverted_index.also | 17 |
| abstract_inverted_index.deep | 148 |
| abstract_inverted_index.from | 111, 120 |
| abstract_inverted_index.more | 123 |
| abstract_inverted_index.over | 112, 115 |
| abstract_inverted_index.show | 81 |
| abstract_inverted_index.than | 124 |
| abstract_inverted_index.that | 57, 137 |
| abstract_inverted_index.this | 45 |
| abstract_inverted_index.use, | 132 |
| abstract_inverted_index.with | 105 |
| abstract_inverted_index.47.0% | 91 |
| abstract_inverted_index.64.7% | 95 |
| abstract_inverted_index.76.6% | 106 |
| abstract_inverted_index.79.3% | 88 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.final | 34, 144 |
| abstract_inverted_index.image | 2 |
| abstract_inverted_index.known | 18, 62 |
| abstract_inverted_index.label | 20, 53, 65 |
| abstract_inverted_index.layer | 36 |
| abstract_inverted_index.noise | 21, 66 |
| abstract_inverted_index.noisy | 7 |
| abstract_inverted_index.often | 5 |
| abstract_inverted_index.place | 26 |
| abstract_inverted_index.range | 110 |
| abstract_inverted_index.scale | 1 |
| abstract_inverted_index.these | 23 |
| abstract_inverted_index.top-1 | 107 |
| abstract_inverted_index.a\nnew | 99 |
| abstract_inverted_index.hidden | 35 |
| abstract_inverted_index.latent | 30, 46 |
| abstract_inverted_index.matrix | 43 |
| abstract_inverted_index.method | 128 |
| abstract_inverted_index.models | 48 |
| abstract_inverted_index.neural | 39, 75 |
| abstract_inverted_index.noise. | 54 |
| abstract_inverted_index.result | 101 |
| abstract_inverted_index.simple | 130 |
| abstract_inverted_index.(+1.1%) | 92 |
| abstract_inverted_index.between | 67 |
| abstract_inverted_index.contain | 6 |
| abstract_inverted_index.drop-in | 140 |
| abstract_inverted_index.labels. | 8 |
| abstract_inverted_index.learned | 59 |
| abstract_inverted_index.network | 76 |
| abstract_inverted_index.provide | 135 |
| abstract_inverted_index.sources | 63 |
| abstract_inverted_index.take\na | 10 |
| abstract_inverted_index.(+1.6%). | 96 |
| abstract_inverted_index.(+2.6%), | 89 |
| abstract_inverted_index.Compared | 72 |
| abstract_inverted_index.Imagenet | 86 |
| abstract_inverted_index.accuracy | 84 |
| abstract_inverted_index.approach | 13 |
| abstract_inverted_index.captures | 61 |
| abstract_inverted_index.classes. | 71, 126 |
| abstract_inverted_index.datasets | 4 |
| abstract_inverted_index.examples | 118 |
| abstract_inverted_index.improved | 83 |
| abstract_inverted_index.standard | 74 |
| abstract_inverted_index.training | 77, 117 |
| abstract_inverted_index.variable | 31 |
| abstract_inverted_index.WebVision | 103 |
| abstract_inverted_index.accuracy. | 108 |
| abstract_inverted_index.datasets. | 24 |
| abstract_inverted_index.modelling | 15 |
| abstract_inverted_index.variable, | 47 |
| abstract_inverted_index.and\nother | 78 |
| abstract_inverted_index.baselines, | 79 |
| abstract_inverted_index.covariance | 42 |
| abstract_inverted_index.principled | 11 |
| abstract_inverted_index.classes\nto | 122 |
| abstract_inverted_index.demonstrate | 56 |
| abstract_inverted_index.replacement | 141 |
| abstract_inverted_index.ILSVRC\n2012 | 87 |
| abstract_inverted_index.Imagenet-21k | 90 |
| abstract_inverted_index.co-occurring | 70 |
| abstract_inverted_index.multivariate | 28 |
| abstract_inverted_index.semantically | 68 |
| abstract_inverted_index.similar\nand | 69 |
| abstract_inverted_index.classifier.\n | 149 |
| abstract_inverted_index.probabilistic | 12 |
| abstract_inverted_index.significantly | 82 |
| abstract_inverted_index.classification | 3 |
| abstract_inverted_index.These\ndatasets | 109 |
| abstract_inverted_index.input-dependent, | 16 |
| abstract_inverted_index.state-of-the-art | 100 |
| abstract_inverted_index.an\nimplementation | 136 |
| abstract_inverted_index.Normal\ndistributed | 29 |
| abstract_inverted_index.as\nheteroscedastic, | 19 |
| abstract_inverted_index.network\nclassifier. | 40 |
| abstract_inverted_index.covariance\nstructure | 60 |
| abstract_inverted_index.aleatoric\nuncertainty | 50 |
| abstract_inverted_index.fully-connected\nlayer | 145 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.24240471 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |