Concurrent Discrimination and Alignment for Self-Supervised Feature\n Learning Article Swipe
Anjan Dutta
,
Massimiliano Mancini
,
Zeynep Akata
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2108.08562
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2108.08562
Existing self-supervised learning methods learn representation by means of\npretext tasks which are either (1) discriminating that explicitly specify which\nfeatures should be separated or (2) aligning that precisely indicate which\nfeatures should be closed together, but ignore the fact how to jointly and\nprincipally define which features to be repelled and which ones to be\nattracted. In this work, we combine the positive aspects of the discriminating\nand aligning methods, and design a hybrid method that addresses the above\nissue. Our method explicitly specifies the repulsion and attraction mechanism\nrespectively by discriminative predictive task and concurrently maximizing\nmutual information between paired views sharing redundant information. We\nqualitatively and quantitatively show that our proposed model learns better\nfeatures that are more effective for the diverse downstream tasks ranging from\nclassification to semantic segmentation. Our experiments on nine established\nbenchmarks show that the proposed model consistently outperforms the existing\nstate-of-the-art results of self-supervised and transfer learning protocol.\n
Related Topics
Concepts
Computer science
Discriminative model
Artificial intelligence
Machine learning
Task (project management)
Representation (politics)
Feature (linguistics)
Segmentation
Pretext
Feature learning
Mutual information
Pattern recognition (psychology)
Political science
Philosophy
Politics
Economics
Law
Linguistics
Management
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2108.08562
- https://arxiv.org/pdf/2108.08562
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287023139
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287023139Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2108.08562Digital Object Identifier
- Title
-
Concurrent Discrimination and Alignment for Self-Supervised Feature\n LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-08-19Full publication date if available
- Authors
-
Anjan Dutta, Massimiliano Mancini, Zeynep AkataList of authors in order
- Landing page
-
https://arxiv.org/abs/2108.08562Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2108.08562Direct 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/2108.08562Direct OA link when available
- Concepts
-
Computer science, Discriminative model, Artificial intelligence, Machine learning, Task (project management), Representation (politics), Feature (linguistics), Segmentation, Pretext, Feature learning, Mutual information, Pattern recognition (psychology), Political science, Philosophy, Politics, Economics, Law, Linguistics, ManagementTop 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/W4287023139 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2108.08562 |
| ids.openalex | https://openalex.org/W4287023139 |
| fwci | 0.0 |
| type | preprint |
| title | Concurrent Discrimination and Alignment for Self-Supervised Feature\n Learning |
| 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 | 0.9926999807357788 |
| 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/T11550 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9905999898910522 |
| 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 | Text and Document Classification Technologies |
| topics[2].id | https://openalex.org/T12535 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9664999842643738 |
| 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 | Machine Learning and Data Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8082231879234314 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C97931131 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7396938800811768 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5282087 |
| concepts[1].display_name | Discriminative model |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6883452534675598 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6163634061813354 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C2780451532 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5887501239776611 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[4].display_name | Task (project management) |
| concepts[5].id | https://openalex.org/C2776359362 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5331366062164307 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[5].display_name | Representation (politics) |
| concepts[6].id | https://openalex.org/C2776401178 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5012915134429932 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[6].display_name | Feature (linguistics) |
| concepts[7].id | https://openalex.org/C89600930 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4814452528953552 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[7].display_name | Segmentation |
| concepts[8].id | https://openalex.org/C2779627259 |
| concepts[8].level | 3 |
| concepts[8].score | 0.4780188798904419 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q779763 |
| concepts[8].display_name | Pretext |
| concepts[9].id | https://openalex.org/C59404180 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4722922444343567 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[9].display_name | Feature learning |
| concepts[10].id | https://openalex.org/C152139883 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4256138801574707 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q252973 |
| concepts[10].display_name | Mutual information |
| concepts[11].id | https://openalex.org/C153180895 |
| concepts[11].level | 2 |
| concepts[11].score | 0.3428248167037964 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[11].display_name | Pattern recognition (psychology) |
| concepts[12].id | https://openalex.org/C17744445 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[12].display_name | Political science |
| concepts[13].id | https://openalex.org/C138885662 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[13].display_name | Philosophy |
| concepts[14].id | https://openalex.org/C94625758 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[14].display_name | Politics |
| concepts[15].id | https://openalex.org/C162324750 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[15].display_name | Economics |
| concepts[16].id | https://openalex.org/C199539241 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[16].display_name | Law |
| concepts[17].id | https://openalex.org/C41895202 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[17].display_name | Linguistics |
| concepts[18].id | https://openalex.org/C187736073 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[18].display_name | Management |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8082231879234314 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/discriminative-model |
| keywords[1].score | 0.7396938800811768 |
| keywords[1].display_name | Discriminative model |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6883452534675598 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.6163634061813354 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/task |
| keywords[4].score | 0.5887501239776611 |
| keywords[4].display_name | Task (project management) |
| keywords[5].id | https://openalex.org/keywords/representation |
| keywords[5].score | 0.5331366062164307 |
| keywords[5].display_name | Representation (politics) |
| keywords[6].id | https://openalex.org/keywords/feature |
| keywords[6].score | 0.5012915134429932 |
| keywords[6].display_name | Feature (linguistics) |
| keywords[7].id | https://openalex.org/keywords/segmentation |
| keywords[7].score | 0.4814452528953552 |
| keywords[7].display_name | Segmentation |
| keywords[8].id | https://openalex.org/keywords/pretext |
| keywords[8].score | 0.4780188798904419 |
| keywords[8].display_name | Pretext |
| keywords[9].id | https://openalex.org/keywords/feature-learning |
| keywords[9].score | 0.4722922444343567 |
| keywords[9].display_name | Feature learning |
| keywords[10].id | https://openalex.org/keywords/mutual-information |
| keywords[10].score | 0.4256138801574707 |
| keywords[10].display_name | Mutual information |
| keywords[11].id | https://openalex.org/keywords/pattern-recognition |
| keywords[11].score | 0.3428248167037964 |
| keywords[11].display_name | Pattern recognition (psychology) |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2108.08562 |
| 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/2108.08562 |
| 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/2108.08562 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5008386240 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1667-2245 |
| authorships[0].author.display_name | Anjan Dutta |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dutta, Anjan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5017971549 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8595-9955 |
| authorships[1].author.display_name | Massimiliano Mancini |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mancini, Massimiliano |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5040372929 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Zeynep Akata |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Akata, Zeynep |
| authorships[2].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/2108.08562 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Concurrent Discrimination and Alignment for Self-Supervised Feature\n Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9926999807357788 |
| 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/W161456234, https://openalex.org/W3123043866, https://openalex.org/W2765162471, https://openalex.org/W2367130511, https://openalex.org/W3208297503, https://openalex.org/W3119773509, https://openalex.org/W2889153461, https://openalex.org/W2964117661, https://openalex.org/W4388405611, https://openalex.org/W2619127353 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2108.08562 |
| 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/2108.08562 |
| 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/2108.08562 |
| primary_location.id | pmh:oai:arXiv.org:2108.08562 |
| 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/2108.08562 |
| 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/2108.08562 |
| publication_date | 2021-08-19 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 67 |
| abstract_inverted_index.In | 52 |
| abstract_inverted_index.be | 20, 30, 45 |
| abstract_inverted_index.by | 6, 83 |
| abstract_inverted_index.of | 60, 136 |
| abstract_inverted_index.on | 123 |
| abstract_inverted_index.or | 22 |
| abstract_inverted_index.to | 38, 44, 50, 118 |
| abstract_inverted_index.we | 55 |
| abstract_inverted_index.(1) | 13 |
| abstract_inverted_index.(2) | 23 |
| abstract_inverted_index.Our | 74, 121 |
| abstract_inverted_index.and | 47, 65, 80, 87, 98, 138 |
| abstract_inverted_index.are | 11, 108 |
| abstract_inverted_index.but | 33 |
| abstract_inverted_index.for | 111 |
| abstract_inverted_index.how | 37 |
| abstract_inverted_index.our | 102 |
| abstract_inverted_index.the | 35, 57, 61, 72, 78, 112, 128, 133 |
| abstract_inverted_index.fact | 36 |
| abstract_inverted_index.more | 109 |
| abstract_inverted_index.nine | 124 |
| abstract_inverted_index.ones | 49 |
| abstract_inverted_index.show | 100, 126 |
| abstract_inverted_index.task | 86 |
| abstract_inverted_index.that | 15, 25, 70, 101, 107, 127 |
| abstract_inverted_index.this | 53 |
| abstract_inverted_index.learn | 4 |
| abstract_inverted_index.means | 7 |
| abstract_inverted_index.model | 104, 130 |
| abstract_inverted_index.tasks | 9, 115 |
| abstract_inverted_index.views | 93 |
| abstract_inverted_index.which | 10, 42, 48 |
| abstract_inverted_index.work, | 54 |
| abstract_inverted_index.closed | 31 |
| abstract_inverted_index.define | 41 |
| abstract_inverted_index.design | 66 |
| abstract_inverted_index.either | 12 |
| abstract_inverted_index.hybrid | 68 |
| abstract_inverted_index.ignore | 34 |
| abstract_inverted_index.learns | 105 |
| abstract_inverted_index.method | 69, 75 |
| abstract_inverted_index.paired | 92 |
| abstract_inverted_index.should | 19, 29 |
| abstract_inverted_index.aspects | 59 |
| abstract_inverted_index.between | 91 |
| abstract_inverted_index.combine | 56 |
| abstract_inverted_index.diverse | 113 |
| abstract_inverted_index.jointly | 39 |
| abstract_inverted_index.methods | 3 |
| abstract_inverted_index.ranging | 116 |
| abstract_inverted_index.results | 135 |
| abstract_inverted_index.sharing | 94 |
| abstract_inverted_index.specify | 17 |
| abstract_inverted_index.Existing | 0 |
| abstract_inverted_index.aligning | 24, 63 |
| abstract_inverted_index.features | 43 |
| abstract_inverted_index.indicate | 27 |
| abstract_inverted_index.learning | 2, 140 |
| abstract_inverted_index.methods, | 64 |
| abstract_inverted_index.positive | 58 |
| abstract_inverted_index.proposed | 103, 129 |
| abstract_inverted_index.repelled | 46 |
| abstract_inverted_index.semantic | 119 |
| abstract_inverted_index.transfer | 139 |
| abstract_inverted_index.addresses | 71 |
| abstract_inverted_index.effective | 110 |
| abstract_inverted_index.precisely | 26 |
| abstract_inverted_index.redundant | 95 |
| abstract_inverted_index.repulsion | 79 |
| abstract_inverted_index.separated | 21 |
| abstract_inverted_index.specifies | 77 |
| abstract_inverted_index.together, | 32 |
| abstract_inverted_index.attraction | 81 |
| abstract_inverted_index.downstream | 114 |
| abstract_inverted_index.explicitly | 16, 76 |
| abstract_inverted_index.predictive | 85 |
| abstract_inverted_index.experiments | 122 |
| abstract_inverted_index.information | 90 |
| abstract_inverted_index.of\npretext | 8 |
| abstract_inverted_index.outperforms | 132 |
| abstract_inverted_index.protocol.\n | 141 |
| abstract_inverted_index.concurrently | 88 |
| abstract_inverted_index.consistently | 131 |
| abstract_inverted_index.information. | 96 |
| abstract_inverted_index.above\nissue. | 73 |
| abstract_inverted_index.segmentation. | 120 |
| abstract_inverted_index.be\nattracted. | 51 |
| abstract_inverted_index.discriminating | 14 |
| abstract_inverted_index.discriminative | 84 |
| abstract_inverted_index.quantitatively | 99 |
| abstract_inverted_index.representation | 5 |
| abstract_inverted_index.self-supervised | 1, 137 |
| abstract_inverted_index.which\nfeatures | 18, 28 |
| abstract_inverted_index.and\nprincipally | 40 |
| abstract_inverted_index.better\nfeatures | 106 |
| abstract_inverted_index.We\nqualitatively | 97 |
| abstract_inverted_index.maximizing\nmutual | 89 |
| abstract_inverted_index.discriminating\nand | 62 |
| abstract_inverted_index.from\nclassification | 117 |
| abstract_inverted_index.established\nbenchmarks | 125 |
| abstract_inverted_index.mechanism\nrespectively | 82 |
| abstract_inverted_index.existing\nstate-of-the-art | 134 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.7300000190734863 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.23827878 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |