DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation Article Swipe
Alexandre Ramé
,
Kévin Bailly
·
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 among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members' performances. In this paper, we argue that learning strategies for deep ensembles need to tackle the trade-off between ensemble diversity and individual accuracies. Motivated by arguments from information theory and leveraging recent advances in neural estimation of conditional mutual information, we introduce a novel training criterion called DICE: it increases diversity by reducing spurious correlations among features. The main idea is that features extracted from pairs of members should only share information useful for target class prediction without being conditionally redundant. Therefore, besides the classification loss with information bottleneck, we adversarially prevent features from being conditionally predictable from each other. We manage to reduce simultaneous errors while protecting class information. We obtain state-of-the-art accuracy results on CIFAR-10/100: for example, an ensemble of 5 networks trained with DICE matches an ensemble of 7 networks trained independently. We further analyze the consequences on calibration, uncertainty estimation, out-of-distribution detection and online co-distillation.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2101.05544
- https://arxiv.org/pdf/2101.05544
- OA Status
- green
- Cited By
- 6
- References
- 128
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3119420068
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3119420068Canonical 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 EstimationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-01-14Full publication date if available
- Authors
-
Alexandre Ramé, Kévin BaillyList 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
-
Adversarial system, Redundancy (engineering), Dice, Computer science, Artificial intelligence, Diversity (politics), Machine learning, Mathematics, Statistics, Operating system, Sociology, AnthropologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
6Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 3, 2023: 2, 2021: 1Per-year citation counts (last 5 years)
- References (count)
-
128Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3119420068 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2101.05544 |
| ids.doi | https://doi.org/10.48550/arxiv.2101.05544 |
| ids.mag | 3119420068 |
| ids.openalex | https://openalex.org/W3119420068 |
| fwci | |
| type | preprint |
| title | DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial 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/C37736160 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7795695662498474 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[0].display_name | Adversarial system |
| concepts[1].id | https://openalex.org/C152124472 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7098391056060791 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1204361 |
| concepts[1].display_name | Redundancy (engineering) |
| concepts[2].id | https://openalex.org/C22029948 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6731664538383484 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q45089 |
| concepts[2].display_name | Dice |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.6697380542755127 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5780874490737915 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C2781316041 |
| concepts[5].level | 2 |
| concepts[5].score | 0.48259198665618896 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1230584 |
| concepts[5].display_name | Diversity (politics) |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.36011844873428345 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.17444637417793274 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C105795698 |
| concepts[8].level | 1 |
| concepts[8].score | 0.11440438032150269 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[8].display_name | Statistics |
| concepts[9].id | https://openalex.org/C111919701 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[9].display_name | Operating system |
| concepts[10].id | https://openalex.org/C144024400 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[10].display_name | Sociology |
| concepts[11].id | https://openalex.org/C19165224 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q23404 |
| concepts[11].display_name | Anthropology |
| keywords[0].id | https://openalex.org/keywords/adversarial-system |
| keywords[0].score | 0.7795695662498474 |
| keywords[0].display_name | Adversarial system |
| keywords[1].id | https://openalex.org/keywords/redundancy |
| keywords[1].score | 0.7098391056060791 |
| keywords[1].display_name | Redundancy (engineering) |
| keywords[2].id | https://openalex.org/keywords/dice |
| keywords[2].score | 0.6731664538383484 |
| keywords[2].display_name | Dice |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.6697380542755127 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5780874490737915 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/diversity |
| keywords[5].score | 0.48259198665618896 |
| keywords[5].display_name | Diversity (politics) |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.36011844873428345 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.17444637417793274 |
| keywords[7].display_name | Mathematics |
| keywords[8].id | https://openalex.org/keywords/statistics |
| keywords[8].score | 0.11440438032150269 |
| keywords[8].display_name | Statistics |
| language | en |
| 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 | 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/2101.05544 |
| locations[1].id | pmh:oai:HAL:hal-03483364v1 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306402512 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | HAL (Le Centre pour la Communication Scientifique Directe) |
| locations[1].source.host_organization | https://openalex.org/I1294671590 |
| locations[1].source.host_organization_name | Centre National de la Recherche Scientifique |
| locations[1].source.host_organization_lineage | https://openalex.org/I1294671590 |
| locations[1].license | other-oa |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | info:eu-repo/semantics/conferenceObject |
| locations[1].license_id | https://openalex.org/licenses/other-oa |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | ICLR 2021 - 9th International Conference on Learning Representations |
| locations[1].landing_page_url | https://hal.science/hal-03483364 |
| locations[2].id | doi:10.48550/arxiv.2101.05544 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | cc-by |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | https://openalex.org/licenses/cc-by |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.2101.05544 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5057217987 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Alexandre Ramé |
| authorships[0].countries | DE |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210121009 |
| authorships[0].affiliations[0].raw_affiliation_string | Machine Learning and Information Access |
| authorships[0].institutions[0].id | https://openalex.org/I4210121009 |
| authorships[0].institutions[0].ror | https://ror.org/02gwe8432 |
| authorships[0].institutions[0].type | facility |
| authorships[0].institutions[0].lineage | https://openalex.org/I4210121009, https://openalex.org/I887968799 |
| authorships[0].institutions[0].country_code | DE |
| authorships[0].institutions[0].display_name | Access |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Alexandre Rame |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Machine Learning and Information Access |
| authorships[1].author.id | https://openalex.org/A5022871131 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7802-3673 |
| authorships[1].author.display_name | Kévin Bailly |
| authorships[1].countries | DE |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I4210121009 |
| authorships[1].affiliations[0].raw_affiliation_string | Machine Learning and Information Access |
| authorships[1].institutions[0].id | https://openalex.org/I4210121009 |
| authorships[1].institutions[0].ror | https://ror.org/02gwe8432 |
| authorships[1].institutions[0].type | facility |
| authorships[1].institutions[0].lineage | https://openalex.org/I4210121009, https://openalex.org/I887968799 |
| authorships[1].institutions[0].country_code | DE |
| authorships[1].institutions[0].display_name | 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 | 2025-10-10T00:00:00 |
| display_name | DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| 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/W2475857072, https://openalex.org/W4366341510, https://openalex.org/W3021239166, https://openalex.org/W2390936256, https://openalex.org/W2483429559, https://openalex.org/W2016385589, https://openalex.org/W2009559548, https://openalex.org/W2906397153, https://openalex.org/W2385445039 |
| cited_by_count | 6 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 3 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 2 |
| counts_by_year[2].year | 2021 |
| counts_by_year[2].cited_by_count | 1 |
| locations_count | 3 |
| 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 | 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/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 | 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/2101.05544 |
| publication_date | 2021-01-14 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2912070915, https://openalex.org/W2188155116, https://openalex.org/W2965302384, https://openalex.org/W2964059111, https://openalex.org/W2964160479, https://openalex.org/W3035748723, https://openalex.org/W2964093539, https://openalex.org/W3034169498, https://openalex.org/W2194775991, https://openalex.org/W967544008, https://openalex.org/W2148520070, https://openalex.org/W3013360361, https://openalex.org/W2115629999, https://openalex.org/W2913465221, https://openalex.org/W2966201455, https://openalex.org/W1995945562, https://openalex.org/W2988205463, https://openalex.org/W2996970889, https://openalex.org/W2099471712, https://openalex.org/W2155806188, https://openalex.org/W2996603747, https://openalex.org/W2254249950, https://openalex.org/W1970954633, https://openalex.org/W2158875652, https://openalex.org/W3034696486, https://openalex.org/W2135293965, https://openalex.org/W3118608800, https://openalex.org/W3012436946, https://openalex.org/W2969515171, https://openalex.org/W2949517790, https://openalex.org/W2023935830, https://openalex.org/W2963373431, https://openalex.org/W2154457314, https://openalex.org/W2996959377, https://openalex.org/W2969338701, https://openalex.org/W2145073242, https://openalex.org/W2887997457, https://openalex.org/W2996369242, https://openalex.org/W1821462560, https://openalex.org/W2128073546, https://openalex.org/W2099111195, https://openalex.org/W2963104724, https://openalex.org/W2154053567, https://openalex.org/W2962723992, https://openalex.org/W1995875735, https://openalex.org/W2786857698, https://openalex.org/W3026092005, https://openalex.org/W2164411961, https://openalex.org/W1831674524, https://openalex.org/W2061119986, https://openalex.org/W3034407868, https://openalex.org/W2978968642, https://openalex.org/W2796283979, https://openalex.org/W1581426664, https://openalex.org/W2073241381, https://openalex.org/W2810676804, https://openalex.org/W2911510572, https://openalex.org/W2116374865, https://openalex.org/W1959608418, https://openalex.org/W2979454998, https://openalex.org/W2789700415, https://openalex.org/W2149772057, https://openalex.org/W2305495461, https://openalex.org/W1881190771, https://openalex.org/W1534477342, https://openalex.org/W3034760359, https://openalex.org/W2803832867, https://openalex.org/W2788453699, https://openalex.org/W2161914416, https://openalex.org/W1516193414, https://openalex.org/W2995464762, https://openalex.org/W2996750072, https://openalex.org/W2964220233, https://openalex.org/W2115247131, https://openalex.org/W2890638503, https://openalex.org/W2964137095, https://openalex.org/W3035321581, https://openalex.org/W2964212410, https://openalex.org/W3035337271, https://openalex.org/W2100128988, https://openalex.org/W2963384892, https://openalex.org/W2950560720, https://openalex.org/W2997224071, https://openalex.org/W2970859221, https://openalex.org/W3035294798, https://openalex.org/W2907020378, https://openalex.org/W2123838014, https://openalex.org/W2997973660, https://openalex.org/W2963238274, https://openalex.org/W1994618660, https://openalex.org/W2913343212, https://openalex.org/W2938998646, https://openalex.org/W3106195168, https://openalex.org/W2620998106, https://openalex.org/W2122925692, https://openalex.org/W2971155163, https://openalex.org/W2994658979, https://openalex.org/W2963800509, https://openalex.org/W2786712888, https://openalex.org/W2089943482, https://openalex.org/W2099741732, https://openalex.org/W2963077256, https://openalex.org/W2108598243, https://openalex.org/W3041809491, https://openalex.org/W2933254221, https://openalex.org/W2951696358, https://openalex.org/W1980567103, https://openalex.org/W2963693742, https://openalex.org/W2149454242, https://openalex.org/W2990064463, https://openalex.org/W2092939357, https://openalex.org/W2172734211, https://openalex.org/W3024340622, https://openalex.org/W2912934387, https://openalex.org/W3000217983, https://openalex.org/W2136144249, https://openalex.org/W2124951716, https://openalex.org/W2964072591, https://openalex.org/W2025720061, https://openalex.org/W2962945412, https://openalex.org/W2842511635, https://openalex.org/W2531327146, https://openalex.org/W2108384452, https://openalex.org/W2971130081, https://openalex.org/W1869142786, https://openalex.org/W2146705998, https://openalex.org/W1515456194, https://openalex.org/W2797563284 |
| referenced_works_count | 128 |
| abstract_inverted_index.5 | 151 |
| abstract_inverted_index.7 | 160 |
| abstract_inverted_index.a | 5, 71 |
| abstract_inverted_index.In | 30 |
| abstract_inverted_index.We | 129, 139, 164 |
| abstract_inverted_index.an | 148, 157 |
| abstract_inverted_index.by | 53, 80 |
| abstract_inverted_index.in | 62 |
| abstract_inverted_index.is | 89 |
| abstract_inverted_index.it | 77 |
| abstract_inverted_index.of | 65, 95, 150, 159 |
| abstract_inverted_index.on | 144, 169 |
| abstract_inverted_index.to | 9, 19, 42, 131 |
| abstract_inverted_index.we | 33, 69, 118 |
| abstract_inverted_index.The | 86 |
| abstract_inverted_index.and | 49, 58, 175 |
| abstract_inverted_index.for | 38, 102, 146 |
| abstract_inverted_index.the | 10, 44, 112, 167 |
| abstract_inverted_index.DICE | 155 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.also | 24 |
| abstract_inverted_index.deep | 39 |
| abstract_inverted_index.each | 127 |
| abstract_inverted_index.from | 55, 93, 122, 126 |
| abstract_inverted_index.idea | 88 |
| abstract_inverted_index.loss | 114 |
| abstract_inverted_index.main | 87 |
| abstract_inverted_index.need | 41 |
| abstract_inverted_index.only | 98 |
| abstract_inverted_index.than | 4 |
| abstract_inverted_index.that | 35, 90 |
| abstract_inverted_index.they | 23 |
| abstract_inverted_index.this | 31 |
| abstract_inverted_index.with | 115, 154 |
| abstract_inverted_index.DICE: | 76 |
| abstract_inverted_index.among | 12, 84 |
| abstract_inverted_index.argue | 34 |
| abstract_inverted_index.being | 107, 123 |
| abstract_inverted_index.class | 104, 137 |
| abstract_inverted_index.novel | 72 |
| abstract_inverted_index.pairs | 94 |
| abstract_inverted_index.share | 99 |
| abstract_inverted_index.their | 13 |
| abstract_inverted_index.while | 135 |
| abstract_inverted_index.Recent | 15 |
| abstract_inverted_index.better | 3 |
| abstract_inverted_index.called | 75 |
| abstract_inverted_index.errors | 134 |
| abstract_inverted_index.manage | 130 |
| abstract_inverted_index.mutual | 67 |
| abstract_inverted_index.neural | 63 |
| abstract_inverted_index.obtain | 140 |
| abstract_inverted_index.online | 176 |
| abstract_inverted_index.other. | 128 |
| abstract_inverted_index.paper, | 32 |
| abstract_inverted_index.recent | 60 |
| abstract_inverted_index.reduce | 132 |
| abstract_inverted_index.should | 97 |
| abstract_inverted_index.single | 6 |
| abstract_inverted_index.tackle | 43 |
| abstract_inverted_index.target | 103 |
| abstract_inverted_index.thanks | 8 |
| abstract_inverted_index.theory | 57 |
| abstract_inverted_index.useful | 101 |
| abstract_inverted_index.analyze | 166 |
| abstract_inverted_index.besides | 111 |
| abstract_inverted_index.between | 46 |
| abstract_inverted_index.further | 165 |
| abstract_inverted_index.matches | 156 |
| abstract_inverted_index.members | 96 |
| abstract_inverted_index.network | 7 |
| abstract_inverted_index.perform | 2 |
| abstract_inverted_index.prevent | 120 |
| abstract_inverted_index.results | 143 |
| abstract_inverted_index.trained | 153, 162 |
| abstract_inverted_index.without | 106 |
| abstract_inverted_index.accuracy | 142 |
| abstract_inverted_index.advances | 61 |
| abstract_inverted_index.decrease | 26 |
| abstract_inverted_index.ensemble | 47, 149, 158 |
| abstract_inverted_index.example, | 147 |
| abstract_inverted_index.features | 91, 121 |
| abstract_inverted_index.however, | 22 |
| abstract_inverted_index.increase | 20 |
| abstract_inverted_index.learning | 36 |
| abstract_inverted_index.members' | 28 |
| abstract_inverted_index.members. | 14 |
| abstract_inverted_index.networks | 152, 161 |
| abstract_inverted_index.reducing | 81 |
| abstract_inverted_index.spurious | 82 |
| abstract_inverted_index.training | 73 |
| abstract_inverted_index.Motivated | 52 |
| abstract_inverted_index.arguments | 54 |
| abstract_inverted_index.criterion | 74 |
| abstract_inverted_index.detection | 174 |
| abstract_inverted_index.diversity | 11, 48, 79 |
| abstract_inverted_index.ensembles | 1, 40 |
| abstract_inverted_index.extracted | 92 |
| abstract_inverted_index.features. | 85 |
| abstract_inverted_index.increases | 78 |
| abstract_inverted_index.introduce | 70 |
| abstract_inverted_index.trade-off | 45 |
| abstract_inverted_index.Therefore, | 110 |
| abstract_inverted_index.approaches | 16 |
| abstract_inverted_index.diversity; | 21 |
| abstract_inverted_index.estimation | 64 |
| abstract_inverted_index.individual | 27, 50 |
| abstract_inverted_index.leveraging | 59 |
| abstract_inverted_index.prediction | 105 |
| abstract_inverted_index.protecting | 136 |
| abstract_inverted_index.redundant. | 109 |
| abstract_inverted_index.regularize | 17 |
| abstract_inverted_index.strategies | 37 |
| abstract_inverted_index.accuracies. | 51 |
| abstract_inverted_index.bottleneck, | 117 |
| abstract_inverted_index.conditional | 66 |
| abstract_inverted_index.drastically | 25 |
| abstract_inverted_index.estimation, | 172 |
| abstract_inverted_index.information | 56, 100, 116 |
| abstract_inverted_index.predictable | 125 |
| abstract_inverted_index.predictions | 18 |
| abstract_inverted_index.uncertainty | 171 |
| abstract_inverted_index.calibration, | 170 |
| abstract_inverted_index.consequences | 168 |
| abstract_inverted_index.correlations | 83 |
| abstract_inverted_index.information, | 68 |
| abstract_inverted_index.information. | 138 |
| abstract_inverted_index.simultaneous | 133 |
| abstract_inverted_index.CIFAR-10/100: | 145 |
| abstract_inverted_index.adversarially | 119 |
| abstract_inverted_index.conditionally | 108, 124 |
| abstract_inverted_index.performances. | 29 |
| abstract_inverted_index.classification | 113 |
| abstract_inverted_index.independently. | 163 |
| abstract_inverted_index.co-distillation. | 177 |
| abstract_inverted_index.state-of-the-art | 141 |
| abstract_inverted_index.out-of-distribution | 173 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile |