DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial\n Estimation Article Swipe
Alexandre Ramé
,
Matthieu Cord
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2101.05544
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2101.05544
Deep ensembles perform better than a single network thanks to the diversity\namong their members. Recent approaches regularize predictions to increase\ndiversity; however, they also drastically decrease individual members'\nperformances. In this paper, we argue that learning strategies for deep\nensembles need to tackle the trade-off between ensemble diversity and\nindividual accuracies. Motivated by arguments from information theory and\nleveraging recent advances in neural estimation of conditional mutual\ninformation, we introduce a novel training criterion called DICE: it increases\ndiversity by reducing spurious correlations among features. The main idea is\nthat features extracted from pairs of members should only share information\nuseful for target class prediction without being conditionally redundant.\nTherefore, besides the classification loss with information bottleneck, we\nadversarially prevent features from being conditionally predictable from each\nother. We manage to reduce simultaneous errors while protecting class\ninformation. We obtain state-of-the-art accuracy results on CIFAR-10/100: for\nexample, an ensemble of 5 networks trained with DICE matches an ensemble of 7\nnetworks trained independently. We further analyze the consequences on\ncalibration, uncertainty estimation, out-of-distribution detection and online\nco-distillation.\n
Related Topics
Concepts
Information bottleneck method
Computer science
Bottleneck
Dice
Artificial intelligence
Spurious relationship
Machine learning
Mutual information
Redundancy (engineering)
Class (philosophy)
Deep neural networks
Diversity (politics)
Deep learning
Mathematics
Statistics
Sociology
Embedded system
Anthropology
Operating system
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2101.05544
- https://arxiv.org/pdf/2101.05544
- OA Status
- green
- Cited By
- 23
- References
- 134
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3132452637
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3132452637Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2101.05544Digital Object Identifier
- Title
-
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial\n EstimationWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2021Year of publication
- Publication date
-
2021-01-14Full publication date if available
- Authors
-
Alexandre Ramé, Matthieu CordList of authors in order
- Landing page
-
https://arxiv.org/abs/2101.05544Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2101.05544Direct 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/2101.05544Direct OA link when available
- Concepts
-
Information bottleneck method, Computer science, Bottleneck, Dice, Artificial intelligence, Spurious relationship, Machine learning, Mutual information, Redundancy (engineering), Class (philosophy), Deep neural networks, Diversity (politics), Deep learning, Mathematics, Statistics, Sociology, Embedded system, Anthropology, Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
23Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 6, 2023: 9, 2022: 3, 2021: 3Per-year citation counts (last 5 years)
- References (count)
-
134Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3132452637 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2101.05544 |
| ids.mag | 3132452637 |
| ids.openalex | https://openalex.org/W3132452637 |
| fwci | 2.96317508 |
| type | preprint |
| title | DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial\n Estimation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11689 |
| 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 | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9991000294685364 |
| 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 | Anomaly Detection Techniques and Applications |
| 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 | 0.9958999752998352 |
| 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/C60008888 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8622912168502808 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q6031013 |
| concepts[0].display_name | Information bottleneck method |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.712142825126648 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2780513914 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7114230394363403 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q18210350 |
| concepts[2].display_name | Bottleneck |
| concepts[3].id | https://openalex.org/C22029948 |
| concepts[3].level | 2 |
| concepts[3].score | 0.7070640325546265 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q45089 |
| concepts[3].display_name | Dice |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.638145387172699 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C97256817 |
| concepts[5].level | 2 |
| concepts[5].score | 0.6211987137794495 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1462316 |
| concepts[5].display_name | Spurious relationship |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5776886940002441 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C152139883 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5177651643753052 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q252973 |
| concepts[7].display_name | Mutual information |
| concepts[8].id | https://openalex.org/C152124472 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4952467978000641 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1204361 |
| concepts[8].display_name | Redundancy (engineering) |
| concepts[9].id | https://openalex.org/C2777212361 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4848266839981079 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[9].display_name | Class (philosophy) |
| concepts[10].id | https://openalex.org/C2984842247 |
| concepts[10].level | 3 |
| concepts[10].score | 0.44368797540664673 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[10].display_name | Deep neural networks |
| concepts[11].id | https://openalex.org/C2781316041 |
| concepts[11].level | 2 |
| concepts[11].score | 0.41241946816444397 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1230584 |
| concepts[11].display_name | Diversity (politics) |
| concepts[12].id | https://openalex.org/C108583219 |
| concepts[12].level | 2 |
| concepts[12].score | 0.39787811040878296 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[12].display_name | Deep learning |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.1607157588005066 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C105795698 |
| concepts[14].level | 1 |
| concepts[14].score | 0.09566688537597656 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[14].display_name | Statistics |
| concepts[15].id | https://openalex.org/C144024400 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[15].display_name | Sociology |
| concepts[16].id | https://openalex.org/C149635348 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q193040 |
| concepts[16].display_name | Embedded system |
| concepts[17].id | https://openalex.org/C19165224 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q23404 |
| concepts[17].display_name | Anthropology |
| concepts[18].id | https://openalex.org/C111919701 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[18].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/information-bottleneck-method |
| keywords[0].score | 0.8622912168502808 |
| keywords[0].display_name | Information bottleneck method |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.712142825126648 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/bottleneck |
| keywords[2].score | 0.7114230394363403 |
| keywords[2].display_name | Bottleneck |
| keywords[3].id | https://openalex.org/keywords/dice |
| keywords[3].score | 0.7070640325546265 |
| keywords[3].display_name | Dice |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.638145387172699 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/spurious-relationship |
| keywords[5].score | 0.6211987137794495 |
| keywords[5].display_name | Spurious relationship |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.5776886940002441 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/mutual-information |
| keywords[7].score | 0.5177651643753052 |
| keywords[7].display_name | Mutual information |
| keywords[8].id | https://openalex.org/keywords/redundancy |
| keywords[8].score | 0.4952467978000641 |
| keywords[8].display_name | Redundancy (engineering) |
| keywords[9].id | https://openalex.org/keywords/class |
| keywords[9].score | 0.4848266839981079 |
| keywords[9].display_name | Class (philosophy) |
| keywords[10].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[10].score | 0.44368797540664673 |
| keywords[10].display_name | Deep neural networks |
| keywords[11].id | https://openalex.org/keywords/diversity |
| keywords[11].score | 0.41241946816444397 |
| keywords[11].display_name | Diversity (politics) |
| keywords[12].id | https://openalex.org/keywords/deep-learning |
| keywords[12].score | 0.39787811040878296 |
| keywords[12].display_name | Deep learning |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.1607157588005066 |
| keywords[13].display_name | Mathematics |
| keywords[14].id | https://openalex.org/keywords/statistics |
| keywords[14].score | 0.09566688537597656 |
| keywords[14].display_name | Statistics |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2101.05544 |
| 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/2101.05544 |
| 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/2101.05544 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5057217987 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Alexandre Ramé |
| authorships[0].affiliations[0].raw_affiliation_string | Machine Learning and Information Access |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Alexandre Ramé |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Machine Learning and Information Access |
| authorships[1].author.id | https://openalex.org/A5108118084 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0627-5844 |
| authorships[1].author.display_name | Matthieu Cord |
| authorships[1].affiliations[0].raw_affiliation_string | Machine Learning and Information Access |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Matthieu Cord |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Machine Learning and Information Access |
| 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/2101.05544 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2021-03-01T00:00:00 |
| display_name | DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial\n Estimation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-10-24T21:50:52.558619 |
| primary_topic.id | https://openalex.org/T11689 |
| 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 | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W3104750253, https://openalex.org/W3021239166, https://openalex.org/W2783047733, https://openalex.org/W3189092450, https://openalex.org/W4287238667, https://openalex.org/W3149287595, https://openalex.org/W3173203577, https://openalex.org/W4225670787, https://openalex.org/W3035096847, https://openalex.org/W4283805326 |
| cited_by_count | 23 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 6 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 9 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 3 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 3 |
| counts_by_year[5].year | 2020 |
| counts_by_year[5].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2101.05544 |
| 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/2101.05544 |
| 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/2101.05544 |
| primary_location.id | pmh:oai:arXiv.org:2101.05544 |
| 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/2101.05544 |
| 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/2101.05544 |
| publication_date | 2021-01-14 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2962723992, https://openalex.org/W2135293965, https://openalex.org/W2108384452, https://openalex.org/W2996750072, https://openalex.org/W2149454242, https://openalex.org/W2963800509, https://openalex.org/W2620998106, https://openalex.org/W2950560720, https://openalex.org/W3026092005, https://openalex.org/W2979585146, https://openalex.org/W2305495461, https://openalex.org/W2949517790, https://openalex.org/W3035321581, https://openalex.org/W2980611702, https://openalex.org/W2810676804, https://openalex.org/W2789700415, https://openalex.org/W2073241381, https://openalex.org/W1821462560, https://openalex.org/W2149772057, https://openalex.org/W3118608800, https://openalex.org/W2988205463, https://openalex.org/W2797563284, https://openalex.org/W2164411961, https://openalex.org/W2788453699, https://openalex.org/W2194775991, https://openalex.org/W3024340622, https://openalex.org/W2963384892, https://openalex.org/W2997224071, https://openalex.org/W2913465221, https://openalex.org/W2907020378, https://openalex.org/W1869142786, https://openalex.org/W2890638503, https://openalex.org/W2970859221, https://openalex.org/W2123838014, https://openalex.org/W2116374865, https://openalex.org/W3012436946, https://openalex.org/W3106428938, https://openalex.org/W2912934387, https://openalex.org/W1959608418, https://openalex.org/W3088546530, https://openalex.org/W2964160479, https://openalex.org/W3013360361, https://openalex.org/W2995464762, https://openalex.org/W2964059111, https://openalex.org/W1515456194, https://openalex.org/W2994658979, https://openalex.org/W2122925692, https://openalex.org/W1995945562, https://openalex.org/W2061119986, https://openalex.org/W2963077256, https://openalex.org/W2842511635, https://openalex.org/W2146705998, https://openalex.org/W3034696486, https://openalex.org/W3000217983, https://openalex.org/W2978968642, https://openalex.org/W2965302384, https://openalex.org/W2997973660, https://openalex.org/W2966201455, https://openalex.org/W2115629999, https://openalex.org/W1995875735, https://openalex.org/W1534477342, https://openalex.org/W3106195168, https://openalex.org/W2154457314, https://openalex.org/W2089943482, https://openalex.org/W3041809491, https://openalex.org/W2964137095, https://openalex.org/W2161914416, https://openalex.org/W2099111195, https://openalex.org/W2969515171, https://openalex.org/W1994618660, https://openalex.org/W2145073242, https://openalex.org/W2023935830, https://openalex.org/W2964220233, https://openalex.org/W2963693742, https://openalex.org/W2887997457, https://openalex.org/W2996970889, https://openalex.org/W2964072591, https://openalex.org/W2964093539, https://openalex.org/W2899771611, https://openalex.org/W2099741732, https://openalex.org/W1970954633, https://openalex.org/W3035337271, https://openalex.org/W2115247131, https://openalex.org/W2172734211, https://openalex.org/W2803832867, https://openalex.org/W2971155163, https://openalex.org/W2964212410, https://openalex.org/W3034760359, https://openalex.org/W2933254221, https://openalex.org/W2996369242, https://openalex.org/W2786712888, https://openalex.org/W2254249950, https://openalex.org/W3035294798, https://openalex.org/W2996959377, https://openalex.org/W2786857698, https://openalex.org/W2963373431, https://openalex.org/W2100128988, https://openalex.org/W2128073546, https://openalex.org/W2951696358, https://openalex.org/W2099471712, https://openalex.org/W2154053567, https://openalex.org/W3034407868, https://openalex.org/W2531327146, https://openalex.org/W2963104724, https://openalex.org/W2188155116, https://openalex.org/W2990064463, https://openalex.org/W2963238274, https://openalex.org/W2158875652, https://openalex.org/W2796283979, https://openalex.org/W3035748723, https://openalex.org/W1516193414, https://openalex.org/W2092939357, https://openalex.org/W2969338701, https://openalex.org/W1581426664, https://openalex.org/W1980567103, https://openalex.org/W2155806188, https://openalex.org/W3083978735, https://openalex.org/W3034169498, https://openalex.org/W2979454998, https://openalex.org/W2962945412, https://openalex.org/W2971130081, https://openalex.org/W2911510572, https://openalex.org/W2025720061, https://openalex.org/W1831674524, https://openalex.org/W2108598243, https://openalex.org/W2938998646, https://openalex.org/W2148520070, https://openalex.org/W2912070915, https://openalex.org/W2996603747, https://openalex.org/W967544008, https://openalex.org/W1881190771, https://openalex.org/W2136144249, https://openalex.org/W2913343212, https://openalex.org/W2124951716 |
| referenced_works_count | 134 |
| abstract_inverted_index.5 | 136 |
| abstract_inverted_index.a | 5, 64 |
| abstract_inverted_index.In | 27 |
| abstract_inverted_index.We | 116, 125, 148 |
| abstract_inverted_index.an | 133, 142 |
| abstract_inverted_index.by | 48, 72 |
| abstract_inverted_index.in | 56 |
| abstract_inverted_index.it | 70 |
| abstract_inverted_index.of | 59, 86, 135, 144 |
| abstract_inverted_index.on | 130 |
| abstract_inverted_index.to | 9, 18, 38, 118 |
| abstract_inverted_index.we | 30, 62 |
| abstract_inverted_index.The | 78 |
| abstract_inverted_index.and | 158 |
| abstract_inverted_index.for | 35, 92 |
| abstract_inverted_index.the | 10, 40, 101, 151 |
| abstract_inverted_index.DICE | 140 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.also | 22 |
| abstract_inverted_index.from | 50, 84, 110, 114 |
| abstract_inverted_index.idea | 80 |
| abstract_inverted_index.loss | 103 |
| abstract_inverted_index.main | 79 |
| abstract_inverted_index.need | 37 |
| abstract_inverted_index.only | 89 |
| abstract_inverted_index.than | 4 |
| abstract_inverted_index.that | 32 |
| abstract_inverted_index.they | 21 |
| abstract_inverted_index.this | 28 |
| abstract_inverted_index.with | 104, 139 |
| abstract_inverted_index.DICE: | 69 |
| abstract_inverted_index.among | 76 |
| abstract_inverted_index.argue | 31 |
| abstract_inverted_index.being | 97, 111 |
| abstract_inverted_index.class | 94 |
| abstract_inverted_index.novel | 65 |
| abstract_inverted_index.pairs | 85 |
| abstract_inverted_index.share | 90 |
| abstract_inverted_index.their | 12 |
| abstract_inverted_index.while | 122 |
| abstract_inverted_index.Recent | 14 |
| abstract_inverted_index.better | 3 |
| abstract_inverted_index.called | 68 |
| abstract_inverted_index.errors | 121 |
| abstract_inverted_index.manage | 117 |
| abstract_inverted_index.neural | 57 |
| abstract_inverted_index.obtain | 126 |
| abstract_inverted_index.paper, | 29 |
| abstract_inverted_index.recent | 54 |
| abstract_inverted_index.reduce | 119 |
| abstract_inverted_index.should | 88 |
| abstract_inverted_index.single | 6 |
| abstract_inverted_index.tackle | 39 |
| abstract_inverted_index.target | 93 |
| abstract_inverted_index.thanks | 8 |
| abstract_inverted_index.theory | 52 |
| abstract_inverted_index.analyze | 150 |
| abstract_inverted_index.besides | 100 |
| abstract_inverted_index.between | 42 |
| abstract_inverted_index.further | 149 |
| abstract_inverted_index.matches | 141 |
| abstract_inverted_index.members | 87 |
| abstract_inverted_index.network | 7 |
| abstract_inverted_index.perform | 2 |
| abstract_inverted_index.prevent | 108 |
| abstract_inverted_index.results | 129 |
| abstract_inverted_index.trained | 138, 146 |
| abstract_inverted_index.without | 96 |
| abstract_inverted_index.accuracy | 128 |
| abstract_inverted_index.advances | 55 |
| abstract_inverted_index.decrease | 24 |
| abstract_inverted_index.ensemble | 43, 134, 143 |
| abstract_inverted_index.features | 82, 109 |
| abstract_inverted_index.however, | 20 |
| abstract_inverted_index.is\nthat | 81 |
| abstract_inverted_index.learning | 33 |
| abstract_inverted_index.members. | 13 |
| abstract_inverted_index.networks | 137 |
| abstract_inverted_index.reducing | 73 |
| abstract_inverted_index.spurious | 74 |
| abstract_inverted_index.training | 66 |
| abstract_inverted_index.Motivated | 47 |
| abstract_inverted_index.arguments | 49 |
| abstract_inverted_index.criterion | 67 |
| abstract_inverted_index.detection | 157 |
| abstract_inverted_index.diversity | 44 |
| abstract_inverted_index.ensembles | 1 |
| abstract_inverted_index.extracted | 83 |
| abstract_inverted_index.features. | 77 |
| abstract_inverted_index.introduce | 63 |
| abstract_inverted_index.trade-off | 41 |
| abstract_inverted_index.approaches | 15 |
| abstract_inverted_index.estimation | 58 |
| abstract_inverted_index.individual | 25 |
| abstract_inverted_index.prediction | 95 |
| abstract_inverted_index.protecting | 123 |
| abstract_inverted_index.regularize | 16 |
| abstract_inverted_index.strategies | 34 |
| abstract_inverted_index.7\nnetworks | 145 |
| abstract_inverted_index.accuracies. | 46 |
| abstract_inverted_index.bottleneck, | 106 |
| abstract_inverted_index.conditional | 60 |
| abstract_inverted_index.drastically | 23 |
| abstract_inverted_index.estimation, | 155 |
| abstract_inverted_index.information | 51, 105 |
| abstract_inverted_index.predictable | 113 |
| abstract_inverted_index.predictions | 17 |
| abstract_inverted_index.uncertainty | 154 |
| abstract_inverted_index.consequences | 152 |
| abstract_inverted_index.correlations | 75 |
| abstract_inverted_index.each\nother. | 115 |
| abstract_inverted_index.simultaneous | 120 |
| abstract_inverted_index.CIFAR-10/100: | 131 |
| abstract_inverted_index.conditionally | 98, 112 |
| abstract_inverted_index.for\nexample, | 132 |
| abstract_inverted_index.classification | 102 |
| abstract_inverted_index.independently. | 147 |
| abstract_inverted_index.and\nindividual | 45 |
| abstract_inverted_index.and\nleveraging | 53 |
| abstract_inverted_index.deep\nensembles | 36 |
| abstract_inverted_index.diversity\namong | 11 |
| abstract_inverted_index.on\ncalibration, | 153 |
| abstract_inverted_index.state-of-the-art | 127 |
| abstract_inverted_index.we\nadversarially | 107 |
| abstract_inverted_index.class\ninformation. | 124 |
| abstract_inverted_index.information\nuseful | 91 |
| abstract_inverted_index.out-of-distribution | 156 |
| abstract_inverted_index.increase\ndiversity; | 19 |
| abstract_inverted_index.increases\ndiversity | 71 |
| abstract_inverted_index.mutual\ninformation, | 61 |
| abstract_inverted_index.redundant.\nTherefore, | 99 |
| abstract_inverted_index.members'\nperformances. | 26 |
| abstract_inverted_index.online\nco-distillation.\n | 159 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile.value | 0.92424726 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |