Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection Article Swipe
Taehyeon Kim
,
Eric K. Lin
,
Junu Lee
,
Christian Lau
,
Vaikkunth Mugunthan
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.17097
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.17097
Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. To address these hurdles, we navigate the uncharted waters of Semi-Supervised Federated Object Detection (SSFOD). We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data. Notably, our method represents the inaugural implementation of SSFOD for clients with 0% labeled non-IID data, a stark contrast to previous studies that maintain some subset of labels at each client. We propose FedSTO, a two-stage strategy encompassing Selective Training followed by Orthogonally enhanced full-parameter training, to effectively address data shift (e.g. weather conditions) between server and clients. Our contributions include selectively refining the backbone of the detector to avert overfitting, orthogonality regularization to boost representation divergence, and local EMA-driven pseudo label assignment to yield high-quality pseudo labels. Extensive validation on prominent autonomous driving datasets (BDD100K, Cityscapes, and SODA10M) attests to the efficacy of our approach, demonstrating state-of-the-art results. Remarkably, FedSTO, using just 20-30% of labels, performs nearly as well as fully-supervised centralized training methods.
Related Topics
Concepts
Overfitting
Computer science
Unavailability
Labeled data
Object (grammar)
Representation (politics)
Artificial intelligence
Regularization (linguistics)
Federated learning
Machine learning
Orthogonality
Feature learning
Artificial neural network
Engineering
Politics
Geometry
Mathematics
Political science
Reliability engineering
Law
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.17097
- https://arxiv.org/pdf/2310.17097
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387995081
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387995081Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.17097Digital Object Identifier
- Title
-
Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object DetectionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-26Full publication date if available
- Authors
-
Taehyeon Kim, Eric K. Lin, Junu Lee, Christian Lau, Vaikkunth MugunthanList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.17097Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.17097Direct 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/2310.17097Direct OA link when available
- Concepts
-
Overfitting, Computer science, Unavailability, Labeled data, Object (grammar), Representation (politics), Artificial intelligence, Regularization (linguistics), Federated learning, Machine learning, Orthogonality, Feature learning, Artificial neural network, Engineering, Politics, Geometry, Mathematics, Political science, Reliability engineering, LawTop 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/W4387995081 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.17097 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.17097 |
| ids.openalex | https://openalex.org/W4387995081 |
| fwci | |
| type | preprint |
| title | Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10764 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9979000091552734 |
| 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 | Privacy-Preserving Technologies in Data |
| topics[1].id | https://openalex.org/T11980 |
| topics[1].field.id | https://openalex.org/fields/33 |
| topics[1].field.display_name | Social Sciences |
| topics[1].score | 0.9825000166893005 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3313 |
| topics[1].subfield.display_name | Transportation |
| topics[1].display_name | Human Mobility and Location-Based Analysis |
| topics[2].id | https://openalex.org/T12120 |
| topics[2].field.id | https://openalex.org/fields/23 |
| topics[2].field.display_name | Environmental Science |
| topics[2].score | 0.9603000283241272 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2305 |
| topics[2].subfield.display_name | Environmental Engineering |
| topics[2].display_name | Air Quality Monitoring and Forecasting |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C22019652 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8314622640609741 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q331309 |
| concepts[0].display_name | Overfitting |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7774252891540527 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2780505938 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5404106378555298 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17093282 |
| concepts[2].display_name | Unavailability |
| concepts[3].id | https://openalex.org/C2776145971 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5285769104957581 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q30673951 |
| concepts[3].display_name | Labeled data |
| concepts[4].id | https://openalex.org/C2781238097 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4965820908546448 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q175026 |
| concepts[4].display_name | Object (grammar) |
| concepts[5].id | https://openalex.org/C2776359362 |
| concepts[5].level | 3 |
| concepts[5].score | 0.48027491569519043 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[5].display_name | Representation (politics) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.4757623076438904 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C2776135515 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4632284641265869 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[7].display_name | Regularization (linguistics) |
| concepts[8].id | https://openalex.org/C2992525071 |
| concepts[8].level | 2 |
| concepts[8].score | 0.46129095554351807 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q50818671 |
| concepts[8].display_name | Federated learning |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.4544612765312195 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C17137986 |
| concepts[10].level | 2 |
| concepts[10].score | 0.44215258955955505 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q215067 |
| concepts[10].display_name | Orthogonality |
| concepts[11].id | https://openalex.org/C59404180 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4152734875679016 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[11].display_name | Feature learning |
| concepts[12].id | https://openalex.org/C50644808 |
| concepts[12].level | 2 |
| concepts[12].score | 0.11284798383712769 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[12].display_name | Artificial neural network |
| concepts[13].id | https://openalex.org/C127413603 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[13].display_name | Engineering |
| 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/C2524010 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[15].display_name | Geometry |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| concepts[17].id | https://openalex.org/C17744445 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[17].display_name | Political science |
| concepts[18].id | https://openalex.org/C200601418 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q2193887 |
| concepts[18].display_name | Reliability engineering |
| concepts[19].id | https://openalex.org/C199539241 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[19].display_name | Law |
| keywords[0].id | https://openalex.org/keywords/overfitting |
| keywords[0].score | 0.8314622640609741 |
| keywords[0].display_name | Overfitting |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7774252891540527 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/unavailability |
| keywords[2].score | 0.5404106378555298 |
| keywords[2].display_name | Unavailability |
| keywords[3].id | https://openalex.org/keywords/labeled-data |
| keywords[3].score | 0.5285769104957581 |
| keywords[3].display_name | Labeled data |
| keywords[4].id | https://openalex.org/keywords/object |
| keywords[4].score | 0.4965820908546448 |
| keywords[4].display_name | Object (grammar) |
| keywords[5].id | https://openalex.org/keywords/representation |
| keywords[5].score | 0.48027491569519043 |
| keywords[5].display_name | Representation (politics) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.4757623076438904 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/regularization |
| keywords[7].score | 0.4632284641265869 |
| keywords[7].display_name | Regularization (linguistics) |
| keywords[8].id | https://openalex.org/keywords/federated-learning |
| keywords[8].score | 0.46129095554351807 |
| keywords[8].display_name | Federated learning |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.4544612765312195 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/orthogonality |
| keywords[10].score | 0.44215258955955505 |
| keywords[10].display_name | Orthogonality |
| keywords[11].id | https://openalex.org/keywords/feature-learning |
| keywords[11].score | 0.4152734875679016 |
| keywords[11].display_name | Feature learning |
| keywords[12].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[12].score | 0.11284798383712769 |
| keywords[12].display_name | Artificial neural network |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.17097 |
| 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/2310.17097 |
| 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/2310.17097 |
| locations[1].id | doi:10.48550/arxiv.2310.17097 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2310.17097 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100774197 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5496-2625 |
| authorships[0].author.display_name | Taehyeon Kim |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Kim, Taehyeon |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5079225210 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2190-7034 |
| authorships[1].author.display_name | Eric K. Lin |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lin, Eric |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5104291243 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Junu Lee |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lee, Junu |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5113032554 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Christian Lau |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lau, Christian |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5082178110 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Vaikkunth Mugunthan |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Mugunthan, Vaikkunth |
| authorships[4].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://arxiv.org/pdf/2310.17097 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-10-28T00:00:00 |
| display_name | Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10764 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9979000091552734 |
| 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 | Privacy-Preserving Technologies in Data |
| related_works | https://openalex.org/W4237235066, https://openalex.org/W2026539069, https://openalex.org/W207884067, https://openalex.org/W3127016596, https://openalex.org/W3172418599, https://openalex.org/W4299840061, https://openalex.org/W4281705236, https://openalex.org/W4315629742, https://openalex.org/W2799180539, https://openalex.org/W2998993449 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.17097 |
| 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/2310.17097 |
| 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/2310.17097 |
| primary_location.id | pmh:oai:arXiv.org:2310.17097 |
| 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/2310.17097 |
| 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/2310.17097 |
| publication_date | 2023-10-26 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 55, 91, 109 |
| abstract_inverted_index.0% | 87 |
| abstract_inverted_index.To | 38 |
| abstract_inverted_index.We | 53, 106 |
| abstract_inverted_index.as | 5, 193, 195 |
| abstract_inverted_index.at | 67, 103 |
| abstract_inverted_index.by | 116 |
| abstract_inverted_index.in | 33 |
| abstract_inverted_index.it | 21 |
| abstract_inverted_index.of | 47, 82, 101, 140, 178, 189 |
| abstract_inverted_index.on | 165 |
| abstract_inverted_index.to | 94, 121, 143, 148, 158, 175 |
| abstract_inverted_index.we | 42 |
| abstract_inverted_index.Our | 133 |
| abstract_inverted_index.and | 28, 131, 152, 172 |
| abstract_inverted_index.for | 9, 60, 84 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.our | 76, 179 |
| abstract_inverted_index.the | 44, 68, 79, 138, 141, 176 |
| abstract_inverted_index.(FL) | 2 |
| abstract_inverted_index.data | 14, 18, 64, 124 |
| abstract_inverted_index.each | 104 |
| abstract_inverted_index.just | 187 |
| abstract_inverted_index.like | 35 |
| abstract_inverted_index.only | 66 |
| abstract_inverted_index.some | 99 |
| abstract_inverted_index.that | 97 |
| abstract_inverted_index.well | 194 |
| abstract_inverted_index.with | 24, 86 |
| abstract_inverted_index.(e.g. | 126 |
| abstract_inverted_index.SSFOD | 57, 83 |
| abstract_inverted_index.avert | 144 |
| abstract_inverted_index.boost | 149 |
| abstract_inverted_index.data, | 31, 90 |
| abstract_inverted_index.data. | 74 |
| abstract_inverted_index.faces | 22 |
| abstract_inverted_index.label | 156 |
| abstract_inverted_index.local | 153 |
| abstract_inverted_index.shift | 125 |
| abstract_inverted_index.stark | 92 |
| abstract_inverted_index.these | 40 |
| abstract_inverted_index.using | 186 |
| abstract_inverted_index.where | 62 |
| abstract_inverted_index.while | 16, 70 |
| abstract_inverted_index.yield | 159 |
| abstract_inverted_index.20-30% | 188 |
| abstract_inverted_index.Object | 50 |
| abstract_inverted_index.across | 12 |
| abstract_inverted_index.client | 30 |
| abstract_inverted_index.labels | 27, 102 |
| abstract_inverted_index.method | 77 |
| abstract_inverted_index.models | 11 |
| abstract_inverted_index.nearly | 192 |
| abstract_inverted_index.potent | 7 |
| abstract_inverted_index.pseudo | 155, 161 |
| abstract_inverted_index.reside | 65 |
| abstract_inverted_index.server | 69, 130 |
| abstract_inverted_index.subset | 100 |
| abstract_inverted_index.waters | 46 |
| abstract_inverted_index.FedSTO, | 108, 185 |
| abstract_inverted_index.address | 39, 123 |
| abstract_inverted_index.attests | 174 |
| abstract_inverted_index.between | 129 |
| abstract_inverted_index.client. | 105 |
| abstract_inverted_index.clients | 71, 85 |
| abstract_inverted_index.driving | 168 |
| abstract_inverted_index.emerged | 4 |
| abstract_inverted_index.include | 135 |
| abstract_inverted_index.labeled | 63, 88 |
| abstract_inverted_index.labels, | 190 |
| abstract_inverted_index.labels. | 162 |
| abstract_inverted_index.limited | 25 |
| abstract_inverted_index.non-IID | 29, 89 |
| abstract_inverted_index.possess | 72 |
| abstract_inverted_index.present | 54 |
| abstract_inverted_index.propose | 107 |
| abstract_inverted_index.sources | 15 |
| abstract_inverted_index.studies | 96 |
| abstract_inverted_index.weather | 127 |
| abstract_inverted_index.(SSFOD). | 52 |
| abstract_inverted_index.Learning | 1 |
| abstract_inverted_index.Notably, | 75 |
| abstract_inverted_index.SODA10M) | 173 |
| abstract_inverted_index.Training | 114 |
| abstract_inverted_index.backbone | 139 |
| abstract_inverted_index.clients. | 132 |
| abstract_inverted_index.contrast | 93 |
| abstract_inverted_index.datasets | 169 |
| abstract_inverted_index.designed | 59 |
| abstract_inverted_index.detector | 142 |
| abstract_inverted_index.driving. | 37 |
| abstract_inverted_index.efficacy | 177 |
| abstract_inverted_index.enhanced | 118 |
| abstract_inverted_index.followed | 115 |
| abstract_inverted_index.hurdles, | 41 |
| abstract_inverted_index.maintain | 98 |
| abstract_inverted_index.methods. | 199 |
| abstract_inverted_index.navigate | 43 |
| abstract_inverted_index.performs | 191 |
| abstract_inverted_index.previous | 95 |
| abstract_inverted_index.privacy. | 19 |
| abstract_inverted_index.refining | 137 |
| abstract_inverted_index.results. | 183 |
| abstract_inverted_index.strategy | 111 |
| abstract_inverted_index.training | 10, 198 |
| abstract_inverted_index.(BDD100K, | 170 |
| abstract_inverted_index.Detection | 51 |
| abstract_inverted_index.Extensive | 163 |
| abstract_inverted_index.Federated | 0, 49 |
| abstract_inverted_index.Selective | 113 |
| abstract_inverted_index.approach, | 180 |
| abstract_inverted_index.framework | 8 |
| abstract_inverted_index.inaugural | 80 |
| abstract_inverted_index.prominent | 166 |
| abstract_inverted_index.scenarios | 61 |
| abstract_inverted_index.training, | 120 |
| abstract_inverted_index.two-stage | 110 |
| abstract_inverted_index.uncharted | 45 |
| abstract_inverted_index.unlabeled | 73 |
| abstract_inverted_index.EMA-driven | 154 |
| abstract_inverted_index.assignment | 157 |
| abstract_inverted_index.autonomous | 36, 167 |
| abstract_inverted_index.challenges | 23 |
| abstract_inverted_index.framework, | 58 |
| abstract_inverted_index.pioneering | 56 |
| abstract_inverted_index.represents | 78 |
| abstract_inverted_index.validation | 164 |
| abstract_inverted_index.Cityscapes, | 171 |
| abstract_inverted_index.Remarkably, | 184 |
| abstract_inverted_index.centralized | 197 |
| abstract_inverted_index.conditions) | 128 |
| abstract_inverted_index.distributed | 13 |
| abstract_inverted_index.divergence, | 151 |
| abstract_inverted_index.effectively | 122 |
| abstract_inverted_index.maintaining | 17 |
| abstract_inverted_index.selectively | 136 |
| abstract_inverted_index.Orthogonally | 117 |
| abstract_inverted_index.applications | 34 |
| abstract_inverted_index.encompassing | 112 |
| abstract_inverted_index.high-quality | 26, 160 |
| abstract_inverted_index.overfitting, | 145 |
| abstract_inverted_index.particularly | 32 |
| abstract_inverted_index.Nevertheless, | 20 |
| abstract_inverted_index.contributions | 134 |
| abstract_inverted_index.demonstrating | 181 |
| abstract_inverted_index.orthogonality | 146 |
| abstract_inverted_index.full-parameter | 119 |
| abstract_inverted_index.implementation | 81 |
| abstract_inverted_index.regularization | 147 |
| abstract_inverted_index.representation | 150 |
| abstract_inverted_index.Semi-Supervised | 48 |
| abstract_inverted_index.fully-supervised | 196 |
| abstract_inverted_index.state-of-the-art | 182 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/11 |
| sustainable_development_goals[0].score | 0.5 |
| sustainable_development_goals[0].display_name | Sustainable cities and communities |
| citation_normalized_percentile |