Semi-supervised learning made simple with self-supervised clustering Article Swipe
Enrico Fini
,
Pietro Astolfi
,
Karteek Alahari
,
Xavier Alameda-Pineda
,
Julien Mairal
,
Moin Nabi
,
Elisa Ricci
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2306.07483
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2306.07483
Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partially available, motivating a recent line of work on semi-supervised methods inspired by self-supervised principles. In this paper, we propose a conceptually simple yet empirically powerful approach to turn clustering-based self-supervised methods such as SwAV or DINO into semi-supervised learners. More precisely, we introduce a multi-task framework merging a supervised objective using ground-truth labels and a self-supervised objective relying on clustering assignments with a single cross-entropy loss. This approach may be interpreted as imposing the cluster centroids to be class prototypes. Despite its simplicity, we provide empirical evidence that our approach is highly effective and achieves state-of-the-art performance on CIFAR100 and ImageNet.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.48550/arxiv.2306.07483
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4380687243
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4380687243Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2306.07483Digital Object Identifier
- Title
-
Semi-supervised learning made simple with self-supervised clusteringWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-06-13Full publication date if available
- Authors
-
Enrico Fini, Pietro Astolfi, Karteek Alahari, Xavier Alameda-Pineda, Julien Mairal, Moin Nabi, Elisa RicciList of authors in order
- Landing page
-
https://doi.org/10.48550/arxiv.2306.07483Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.48550/arxiv.2306.07483Direct OA link when available
- Concepts
-
Cluster analysis, Computer science, Artificial intelligence, Machine learning, Supervised learning, Semi-supervised learning, Centroid, Simple (philosophy), Entropy (arrow of time), Simplicity, Ground truth, Unsupervised learning, Artificial neural network, Epistemology, Physics, Philosophy, Quantum mechanicsTop 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/W4380687243 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2306.07483 |
| ids.doi | https://doi.org/10.48550/arxiv.2306.07483 |
| ids.openalex | https://openalex.org/W4380687243 |
| fwci | 0.0 |
| type | preprint |
| title | Semi-supervised learning made simple with self-supervised clustering |
| 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 | 0.9991999864578247 |
| 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/T10627 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9934999942779541 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Image and Video Retrieval Techniques |
| topics[2].id | https://openalex.org/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9914000034332275 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C73555534 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7262963056564331 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q622825 |
| concepts[0].display_name | Cluster analysis |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7184128761291504 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6375572085380554 |
| 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 | 0.6270682215690613 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C136389625 |
| concepts[4].level | 3 |
| concepts[4].score | 0.6208710670471191 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q334384 |
| concepts[4].display_name | Supervised learning |
| concepts[5].id | https://openalex.org/C58973888 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5909684896469116 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1041418 |
| concepts[5].display_name | Semi-supervised learning |
| concepts[6].id | https://openalex.org/C146599234 |
| concepts[6].level | 2 |
| concepts[6].score | 0.48466426134109497 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q511093 |
| concepts[6].display_name | Centroid |
| concepts[7].id | https://openalex.org/C2780586882 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4805079698562622 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7520643 |
| concepts[7].display_name | Simple (philosophy) |
| concepts[8].id | https://openalex.org/C106301342 |
| concepts[8].level | 2 |
| concepts[8].score | 0.46047890186309814 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q4117933 |
| concepts[8].display_name | Entropy (arrow of time) |
| concepts[9].id | https://openalex.org/C2776372474 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4484175443649292 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q508291 |
| concepts[9].display_name | Simplicity |
| concepts[10].id | https://openalex.org/C146849305 |
| concepts[10].level | 2 |
| concepts[10].score | 0.43642711639404297 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q370766 |
| concepts[10].display_name | Ground truth |
| concepts[11].id | https://openalex.org/C8038995 |
| concepts[11].level | 2 |
| concepts[11].score | 0.429552286863327 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1152135 |
| concepts[11].display_name | Unsupervised learning |
| concepts[12].id | https://openalex.org/C50644808 |
| concepts[12].level | 2 |
| concepts[12].score | 0.11449867486953735 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[12].display_name | Artificial neural network |
| concepts[13].id | https://openalex.org/C111472728 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[13].display_name | Epistemology |
| concepts[14].id | https://openalex.org/C121332964 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[14].display_name | Physics |
| concepts[15].id | https://openalex.org/C138885662 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[15].display_name | Philosophy |
| concepts[16].id | https://openalex.org/C62520636 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[16].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/cluster-analysis |
| keywords[0].score | 0.7262963056564331 |
| keywords[0].display_name | Cluster analysis |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7184128761291504 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6375572085380554 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.6270682215690613 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/supervised-learning |
| keywords[4].score | 0.6208710670471191 |
| keywords[4].display_name | Supervised learning |
| keywords[5].id | https://openalex.org/keywords/semi-supervised-learning |
| keywords[5].score | 0.5909684896469116 |
| keywords[5].display_name | Semi-supervised learning |
| keywords[6].id | https://openalex.org/keywords/centroid |
| keywords[6].score | 0.48466426134109497 |
| keywords[6].display_name | Centroid |
| keywords[7].id | https://openalex.org/keywords/simple |
| keywords[7].score | 0.4805079698562622 |
| keywords[7].display_name | Simple (philosophy) |
| keywords[8].id | https://openalex.org/keywords/entropy |
| keywords[8].score | 0.46047890186309814 |
| keywords[8].display_name | Entropy (arrow of time) |
| keywords[9].id | https://openalex.org/keywords/simplicity |
| keywords[9].score | 0.4484175443649292 |
| keywords[9].display_name | Simplicity |
| keywords[10].id | https://openalex.org/keywords/ground-truth |
| keywords[10].score | 0.43642711639404297 |
| keywords[10].display_name | Ground truth |
| keywords[11].id | https://openalex.org/keywords/unsupervised-learning |
| keywords[11].score | 0.429552286863327 |
| keywords[11].display_name | Unsupervised learning |
| keywords[12].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[12].score | 0.11449867486953735 |
| keywords[12].display_name | Artificial neural network |
| language | en |
| locations[0].id | doi:10.48550/arxiv.2306.07483 |
| 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 | |
| locations[0].version | |
| locations[0].raw_type | article-journal |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.48550/arxiv.2306.07483 |
| indexed_in | datacite |
| authorships[0].author.id | https://openalex.org/A5066230537 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1671-875X |
| authorships[0].author.display_name | Enrico Fini |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Fini, Enrico |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5049825997 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-5192-9608 |
| authorships[1].author.display_name | Pietro Astolfi |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Astolfi, Pietro |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5049440980 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1838-5936 |
| authorships[2].author.display_name | Karteek Alahari |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Alahari, Karteek |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5066621495 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5354-1084 |
| authorships[3].author.display_name | Xavier Alameda-Pineda |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Alameda-Pineda, Xavier |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5062817741 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6991-2110 |
| authorships[4].author.display_name | Julien Mairal |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Mairal, Julien |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5001459748 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-7559-9888 |
| authorships[5].author.display_name | Moin Nabi |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Nabi, Moin |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5065059558 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-0228-1147 |
| authorships[6].author.display_name | Elisa Ricci |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Ricci, Elisa |
| authorships[6].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.48550/arxiv.2306.07483 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Semi-supervised learning made simple with self-supervised clustering |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11307 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991999864578247 |
| 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/W3148060700, https://openalex.org/W2794908468, https://openalex.org/W2531570999, https://openalex.org/W2042184006, https://openalex.org/W4319302697, https://openalex.org/W2921630034, https://openalex.org/W4390062853, https://openalex.org/W2062926306, https://openalex.org/W4310801741, https://openalex.org/W4317542939 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.48550/arxiv.2306.07483 |
| 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 | |
| best_oa_location.version | |
| best_oa_location.raw_type | article-journal |
| 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 | https://doi.org/10.48550/arxiv.2306.07483 |
| primary_location.id | doi:10.48550/arxiv.2306.07483 |
| 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 | |
| primary_location.version | |
| primary_location.raw_type | article-journal |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.48550/arxiv.2306.07483 |
| publication_date | 2023-06-13 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 25, 42, 66, 70, 77, 85 |
| abstract_inverted_index.In | 37 |
| abstract_inverted_index.as | 55, 94 |
| abstract_inverted_index.be | 92, 100 |
| abstract_inverted_index.by | 34 |
| abstract_inverted_index.in | 16 |
| abstract_inverted_index.is | 113 |
| abstract_inverted_index.of | 28 |
| abstract_inverted_index.on | 30, 81, 120 |
| abstract_inverted_index.or | 57 |
| abstract_inverted_index.to | 6, 49, 99 |
| abstract_inverted_index.we | 40, 64, 106 |
| abstract_inverted_index.and | 76, 116, 122 |
| abstract_inverted_index.are | 21 |
| abstract_inverted_index.its | 104 |
| abstract_inverted_index.may | 91 |
| abstract_inverted_index.our | 111 |
| abstract_inverted_index.the | 96 |
| abstract_inverted_index.yet | 45 |
| abstract_inverted_index.DINO | 58 |
| abstract_inverted_index.More | 62 |
| abstract_inverted_index.SwAV | 56 |
| abstract_inverted_index.This | 89 |
| abstract_inverted_index.been | 4 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.into | 59 |
| abstract_inverted_index.line | 27 |
| abstract_inverted_index.many | 17 |
| abstract_inverted_index.rich | 8 |
| abstract_inverted_index.such | 54 |
| abstract_inverted_index.that | 110 |
| abstract_inverted_index.this | 38 |
| abstract_inverted_index.turn | 50 |
| abstract_inverted_index.with | 84 |
| abstract_inverted_index.work | 29 |
| abstract_inverted_index.class | 101 |
| abstract_inverted_index.human | 13 |
| abstract_inverted_index.learn | 7 |
| abstract_inverted_index.loss. | 88 |
| abstract_inverted_index.shown | 5 |
| abstract_inverted_index.using | 73 |
| abstract_inverted_index.highly | 114 |
| abstract_inverted_index.labels | 20, 75 |
| abstract_inverted_index.models | 2 |
| abstract_inverted_index.paper, | 39 |
| abstract_inverted_index.recent | 26 |
| abstract_inverted_index.simple | 44 |
| abstract_inverted_index.single | 86 |
| abstract_inverted_index.visual | 9 |
| abstract_inverted_index.Despite | 103 |
| abstract_inverted_index.cluster | 97 |
| abstract_inverted_index.merging | 69 |
| abstract_inverted_index.methods | 32, 53 |
| abstract_inverted_index.propose | 41 |
| abstract_inverted_index.provide | 107 |
| abstract_inverted_index.relying | 80 |
| abstract_inverted_index.without | 11 |
| abstract_inverted_index.CIFAR100 | 121 |
| abstract_inverted_index.However, | 15 |
| abstract_inverted_index.achieves | 117 |
| abstract_inverted_index.approach | 48, 90, 112 |
| abstract_inverted_index.evidence | 109 |
| abstract_inverted_index.imposing | 95 |
| abstract_inverted_index.inspired | 33 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.powerful | 47 |
| abstract_inverted_index.ImageNet. | 123 |
| abstract_inverted_index.centroids | 98 |
| abstract_inverted_index.effective | 115 |
| abstract_inverted_index.empirical | 108 |
| abstract_inverted_index.framework | 68 |
| abstract_inverted_index.introduce | 65 |
| abstract_inverted_index.learners. | 61 |
| abstract_inverted_index.objective | 72, 79 |
| abstract_inverted_index.partially | 22 |
| abstract_inverted_index.requiring | 12 |
| abstract_inverted_index.available, | 23 |
| abstract_inverted_index.clustering | 82 |
| abstract_inverted_index.motivating | 24 |
| abstract_inverted_index.multi-task | 67 |
| abstract_inverted_index.precisely, | 63 |
| abstract_inverted_index.real-world | 18 |
| abstract_inverted_index.scenarios, | 19 |
| abstract_inverted_index.supervised | 71 |
| abstract_inverted_index.assignments | 83 |
| abstract_inverted_index.empirically | 46 |
| abstract_inverted_index.interpreted | 93 |
| abstract_inverted_index.performance | 119 |
| abstract_inverted_index.principles. | 36 |
| abstract_inverted_index.prototypes. | 102 |
| abstract_inverted_index.simplicity, | 105 |
| abstract_inverted_index.annotations. | 14 |
| abstract_inverted_index.conceptually | 43 |
| abstract_inverted_index.ground-truth | 74 |
| abstract_inverted_index.cross-entropy | 87 |
| abstract_inverted_index.Self-supervised | 0 |
| abstract_inverted_index.representations | 10 |
| abstract_inverted_index.self-supervised | 35, 52, 78 |
| abstract_inverted_index.semi-supervised | 31, 60 |
| abstract_inverted_index.clustering-based | 51 |
| abstract_inverted_index.state-of-the-art | 118 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.5899999737739563 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.07103008 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |