A soft nearest-neighbor framework for continual semi-supervised learning Article Swipe
Zhiqi Kang
,
Enrico Fini
,
Moin Nabi
,
Elisa Ricci
,
Karteek Alahari
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1109/iccv51070.2023.01090
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1109/iccv51070.2023.01090
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised learning--a setting where not all the data samples are labeled. A primary issue in this scenario is the model forgetting representations of unlabeled data and overfitting the labeled samples. We leverage the power of nearest-neighbor classifiers to nonlinearly partition the feature space and flexibly model the underlying data distribution thanks to its non-parametric nature. This enables the model to learn a strong representation for the current task, and distill relevant information from previous tasks. We perform a thorough experimental evaluation and show that our method outperforms all the existing approaches by large margins, setting a solid state of the art on the continual semi-supervised learning paradigm. For example, on CIFAR-100 we surpass several others even when using at least 30 times less supervision (0.8% vs. 25% of annotations). Finally, our method works well on both low and high resolution images and scales seamlessly to more complex datasets such as ImageNet-100. The code is publicly available on https://github.com/kangzhiq/NNCSL
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1109/iccv51070.2023.01090
- OA Status
- green
- Cited By
- 6
- References
- 90
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4311426782
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4311426782Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/iccv51070.2023.01090Digital Object Identifier
- Title
-
A soft nearest-neighbor framework for continual semi-supervised learningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-01Full publication date if available
- Authors
-
Zhiqi Kang, Enrico Fini, Moin Nabi, Elisa Ricci, Karteek AlahariList of authors in order
- Landing page
-
https://doi.org/10.1109/iccv51070.2023.01090Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2212.05102Direct OA link when available
- Concepts
-
Computer science, k-nearest neighbors algorithm, Artificial intelligence, Machine learning, Pattern recognition (psychology)Top concepts (fields/topics) attached by OpenAlex
- Cited by
-
6Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2024: 4Per-year citation counts (last 5 years)
- References (count)
-
90Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4311426782 |
|---|---|
| doi | https://doi.org/10.1109/iccv51070.2023.01090 |
| ids.doi | https://doi.org/10.48550/arxiv.2212.05102 |
| ids.openalex | https://openalex.org/W4311426782 |
| fwci | 1.53265733 |
| type | preprint |
| title | A soft nearest-neighbor framework for continual semi-supervised learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 11843 |
| biblio.first_page | 11834 |
| 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 | 0.9997000098228455 |
| 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/T11714 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9866999983787537 |
| 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 | Multimodal Machine Learning Applications |
| topics[2].id | https://openalex.org/T10812 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.984000027179718 |
| 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 | Human Pose and Action Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7376732230186462 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C113238511 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6810994744300842 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1071612 |
| concepts[1].display_name | k-nearest neighbors algorithm |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5947234034538269 |
| 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 | 0.41301584243774414 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C153180895 |
| concepts[4].level | 2 |
| concepts[4].score | 0.3535365164279938 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[4].display_name | Pattern recognition (psychology) |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7376732230186462 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/k-nearest-neighbors-algorithm |
| keywords[1].score | 0.6810994744300842 |
| keywords[1].display_name | k-nearest neighbors algorithm |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5947234034538269 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.41301584243774414 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/pattern-recognition |
| keywords[4].score | 0.3535365164279938 |
| keywords[4].display_name | Pattern recognition (psychology) |
| language | en |
| locations[0].id | doi:10.1109/iccv51070.2023.01090 |
| locations[0].is_oa | False |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | 2023 IEEE/CVF International Conference on Computer Vision (ICCV) |
| locations[0].landing_page_url | https://doi.org/10.1109/iccv51070.2023.01090 |
| locations[1].id | pmh:oai:arXiv.org:2212.05102 |
| 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 | |
| locations[1].pdf_url | https://arxiv.org/pdf/2212.05102 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2212.05102 |
| locations[2].id | pmh:oai:HAL:hal-03893056v3 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306402512 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | HAL (Le Centre pour la Communication Scientifique Directe) |
| locations[2].source.host_organization | https://openalex.org/I1294671590 |
| locations[2].source.host_organization_name | Centre National de la Recherche Scientifique |
| locations[2].source.host_organization_lineage | https://openalex.org/I1294671590 |
| locations[2].license | cc-by |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | Conference papers |
| locations[2].license_id | https://openalex.org/licenses/cc-by |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | ICCV 2023 - IEEE/CVF International Conference on Computer Vision, Oct 2023, Paris, France. pp.11834-11843, ⟨10.1109/ICCV51070.2023.01090⟩ |
| locations[2].landing_page_url | https://hal.science/hal-03893056 |
| locations[3].id | doi:10.48550/arxiv.2212.05102 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400194 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | arXiv (Cornell University) |
| locations[3].source.host_organization | https://openalex.org/I205783295 |
| locations[3].source.host_organization_name | Cornell University |
| locations[3].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[3].license | |
| locations[3].pdf_url | |
| locations[3].version | |
| locations[3].raw_type | article |
| locations[3].license_id | |
| locations[3].is_accepted | False |
| locations[3].is_published | |
| locations[3].raw_source_name | |
| locations[3].landing_page_url | https://doi.org/10.48550/arxiv.2212.05102 |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5044584521 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zhiqi Kang |
| authorships[0].countries | FR |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1326498283 |
| authorships[0].affiliations[0].raw_affiliation_string | Inria |
| authorships[0].institutions[0].id | https://openalex.org/I1326498283 |
| authorships[0].institutions[0].ror | https://ror.org/02kvxyf05 |
| authorships[0].institutions[0].type | government |
| authorships[0].institutions[0].lineage | https://openalex.org/I1326498283 |
| authorships[0].institutions[0].country_code | FR |
| authorships[0].institutions[0].display_name | Institut national de recherche en sciences et technologies du numérique |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhiqi Kang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Inria |
| authorships[1].author.id | https://openalex.org/A5066230537 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1671-875X |
| authorships[1].author.display_name | Enrico Fini |
| authorships[1].countries | IT |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I193223587 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Trento |
| authorships[1].institutions[0].id | https://openalex.org/I193223587 |
| authorships[1].institutions[0].ror | https://ror.org/05trd4x28 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I193223587 |
| authorships[1].institutions[0].country_code | IT |
| authorships[1].institutions[0].display_name | University of Trento |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Enrico Fini |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Trento |
| authorships[2].author.id | https://openalex.org/A5001459748 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7559-9888 |
| authorships[2].author.display_name | Moin Nabi |
| authorships[2].countries | GB |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210133614 |
| authorships[2].affiliations[0].raw_affiliation_string | SAP AI Research |
| authorships[2].institutions[0].id | https://openalex.org/I4210133614 |
| authorships[2].institutions[0].ror | https://ror.org/04k7gd586 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I4210132444, https://openalex.org/I4210133614 |
| authorships[2].institutions[0].country_code | GB |
| authorships[2].institutions[0].display_name | Systems, Applications & Products in Data Processing (United Kingdom) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Moin Nabi |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | SAP AI Research |
| authorships[3].author.id | https://openalex.org/A5065059558 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0228-1147 |
| authorships[3].author.display_name | Elisa Ricci |
| authorships[3].countries | IT |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I2277624104 |
| authorships[3].affiliations[0].raw_affiliation_string | Fondazione Bruno Kessler |
| authorships[3].affiliations[1].institution_ids | https://openalex.org/I193223587 |
| authorships[3].affiliations[1].raw_affiliation_string | University of Trento |
| authorships[3].institutions[0].id | https://openalex.org/I2277624104 |
| authorships[3].institutions[0].ror | https://ror.org/01j33xk10 |
| authorships[3].institutions[0].type | facility |
| authorships[3].institutions[0].lineage | https://openalex.org/I2277624104 |
| authorships[3].institutions[0].country_code | IT |
| authorships[3].institutions[0].display_name | Fondazione Bruno Kessler |
| authorships[3].institutions[1].id | https://openalex.org/I193223587 |
| authorships[3].institutions[1].ror | https://ror.org/05trd4x28 |
| authorships[3].institutions[1].type | education |
| authorships[3].institutions[1].lineage | https://openalex.org/I193223587 |
| authorships[3].institutions[1].country_code | IT |
| authorships[3].institutions[1].display_name | University of Trento |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Elisa Ricci |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Fondazione Bruno Kessler, University of Trento |
| authorships[4].author.id | https://openalex.org/A5049440980 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-1838-5936 |
| authorships[4].author.display_name | Karteek Alahari |
| authorships[4].countries | FR |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1326498283 |
| authorships[4].affiliations[0].raw_affiliation_string | Inria |
| authorships[4].institutions[0].id | https://openalex.org/I1326498283 |
| authorships[4].institutions[0].ror | https://ror.org/02kvxyf05 |
| authorships[4].institutions[0].type | government |
| authorships[4].institutions[0].lineage | https://openalex.org/I1326498283 |
| authorships[4].institutions[0].country_code | FR |
| authorships[4].institutions[0].display_name | Institut national de recherche en sciences et technologies du numérique |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Karteek Alahari |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Inria |
| 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/2212.05102 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-12-26T00:00:00 |
| display_name | A soft nearest-neighbor framework for continual semi-supervised 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 | 0.9997000098228455 |
| 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/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W2033914206 |
| cited_by_count | 6 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 4 |
| locations_count | 4 |
| best_oa_location.id | pmh:oai:arXiv.org:2212.05102 |
| 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/2212.05102 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2212.05102 |
| primary_location.id | doi:10.1109/iccv51070.2023.01090 |
| primary_location.is_oa | False |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | 2023 IEEE/CVF International Conference on Computer Vision (ICCV) |
| primary_location.landing_page_url | https://doi.org/10.1109/iccv51070.2023.01090 |
| publication_date | 2023-10-01 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W6753859023, https://openalex.org/W3091002423, https://openalex.org/W3158278463, https://openalex.org/W6757712183, https://openalex.org/W6770578729, https://openalex.org/W6762913911, https://openalex.org/W4295789386, https://openalex.org/W4293066019, https://openalex.org/W6776188292, https://openalex.org/W3091958244, https://openalex.org/W2884282566, https://openalex.org/W4214662032, https://openalex.org/W2786446225, https://openalex.org/W6757384668, https://openalex.org/W6810458260, https://openalex.org/W6774314701, https://openalex.org/W4293057377, https://openalex.org/W3030364939, https://openalex.org/W3107810305, https://openalex.org/W4225484930, https://openalex.org/W4225777901, https://openalex.org/W3107137534, https://openalex.org/W6638523607, https://openalex.org/W2948734064, https://openalex.org/W2560647685, https://openalex.org/W6787972765, https://openalex.org/W6764051988, https://openalex.org/W3160103175, https://openalex.org/W2473930607, https://openalex.org/W6741087337, https://openalex.org/W6622262455, https://openalex.org/W2982410595, https://openalex.org/W2963080758, https://openalex.org/W2962804657, https://openalex.org/W6767099637, https://openalex.org/W2964189064, https://openalex.org/W6756754374, https://openalex.org/W6849896277, https://openalex.org/W6717772578, https://openalex.org/W6747837551, https://openalex.org/W6738602802, https://openalex.org/W3203131677, https://openalex.org/W3189641358, https://openalex.org/W6773005947, https://openalex.org/W6733814495, https://openalex.org/W3108655343, https://openalex.org/W3209458476, https://openalex.org/W4313028293, https://openalex.org/W3181161034, https://openalex.org/W6849414221, https://openalex.org/W2954929116, https://openalex.org/W3035160371, https://openalex.org/W6797119129, https://openalex.org/W6744513255, https://openalex.org/W2981952041, https://openalex.org/W6802864417, https://openalex.org/W3034989734, https://openalex.org/W2963813679, https://openalex.org/W4392173735, https://openalex.org/W3118608800, https://openalex.org/W3098511564, https://openalex.org/W4287392045, https://openalex.org/W4287814827, https://openalex.org/W4319988532, https://openalex.org/W2978426779, https://openalex.org/W4226096664, https://openalex.org/W2953070460, https://openalex.org/W3001197829, https://openalex.org/W4319049883, https://openalex.org/W2982593362, https://openalex.org/W4288376233, https://openalex.org/W3005680577, https://openalex.org/W2757910899, https://openalex.org/W4287936108, https://openalex.org/W4288020585, https://openalex.org/W4295883599, https://openalex.org/W2951970475, https://openalex.org/W2963559848, https://openalex.org/W4226188892, https://openalex.org/W2187089797, https://openalex.org/W769612788, https://openalex.org/W3205500251, https://openalex.org/W1821462560, https://openalex.org/W2885949783, https://openalex.org/W4287394940, https://openalex.org/W4287112127, https://openalex.org/W2431080869, https://openalex.org/W2902456977, https://openalex.org/W3171608926, https://openalex.org/W2949985837 |
| referenced_works_count | 90 |
| abstract_inverted_index.A | 43 |
| abstract_inverted_index.a | 93, 109, 127 |
| abstract_inverted_index.30 | 152 |
| abstract_inverted_index.In | 19 |
| abstract_inverted_index.We | 62, 107 |
| abstract_inverted_index.an | 28 |
| abstract_inverted_index.as | 181 |
| abstract_inverted_index.at | 150 |
| abstract_inverted_index.by | 123 |
| abstract_inverted_index.in | 46 |
| abstract_inverted_index.is | 49, 185 |
| abstract_inverted_index.of | 5, 15, 54, 66, 130, 159 |
| abstract_inverted_index.on | 11, 133, 141, 166, 188 |
| abstract_inverted_index.to | 69, 83, 91, 176 |
| abstract_inverted_index.we | 22, 143 |
| abstract_inverted_index.25% | 158 |
| abstract_inverted_index.For | 139 |
| abstract_inverted_index.The | 183 |
| abstract_inverted_index.all | 37, 119 |
| abstract_inverted_index.and | 26, 57, 75, 100, 113, 169, 173 |
| abstract_inverted_index.are | 41 |
| abstract_inverted_index.art | 132 |
| abstract_inverted_index.for | 30, 96 |
| abstract_inverted_index.its | 84 |
| abstract_inverted_index.low | 168 |
| abstract_inverted_index.not | 36 |
| abstract_inverted_index.our | 116, 162 |
| abstract_inverted_index.the | 3, 12, 38, 50, 59, 64, 72, 78, 89, 97, 120, 131, 134 |
| abstract_inverted_index.vs. | 157 |
| abstract_inverted_index.This | 87 |
| abstract_inverted_index.both | 167 |
| abstract_inverted_index.code | 184 |
| abstract_inverted_index.data | 39, 56, 80 |
| abstract_inverted_index.even | 147 |
| abstract_inverted_index.from | 104 |
| abstract_inverted_index.high | 170 |
| abstract_inverted_index.less | 154 |
| abstract_inverted_index.more | 177 |
| abstract_inverted_index.show | 114 |
| abstract_inverted_index.such | 180 |
| abstract_inverted_index.that | 115 |
| abstract_inverted_index.this | 20, 24, 47 |
| abstract_inverted_index.well | 165 |
| abstract_inverted_index.when | 148 |
| abstract_inverted_index.(0.8% | 156 |
| abstract_inverted_index.data. | 18 |
| abstract_inverted_index.fully | 16 |
| abstract_inverted_index.issue | 45 |
| abstract_inverted_index.large | 124 |
| abstract_inverted_index.learn | 92 |
| abstract_inverted_index.least | 151 |
| abstract_inverted_index.model | 51, 77, 90 |
| abstract_inverted_index.power | 65 |
| abstract_inverted_index.solid | 128 |
| abstract_inverted_index.space | 74 |
| abstract_inverted_index.state | 129 |
| abstract_inverted_index.task, | 99 |
| abstract_inverted_index.times | 153 |
| abstract_inverted_index.using | 149 |
| abstract_inverted_index.where | 35 |
| abstract_inverted_index.works | 164 |
| abstract_inverted_index.hinges | 10 |
| abstract_inverted_index.images | 172 |
| abstract_inverted_index.method | 117, 163 |
| abstract_inverted_index.others | 146 |
| abstract_inverted_index.paper, | 21 |
| abstract_inverted_index.scales | 174 |
| abstract_inverted_index.strong | 94 |
| abstract_inverted_index.tackle | 23 |
| abstract_inverted_index.tasks. | 106 |
| abstract_inverted_index.thanks | 82 |
| abstract_inverted_index.Despite | 0 |
| abstract_inverted_index.complex | 178 |
| abstract_inverted_index.current | 98 |
| abstract_inverted_index.distill | 101 |
| abstract_inverted_index.enables | 88 |
| abstract_inverted_index.feature | 73 |
| abstract_inverted_index.labeled | 17, 60 |
| abstract_inverted_index.nature. | 86 |
| abstract_inverted_index.perform | 108 |
| abstract_inverted_index.primary | 44 |
| abstract_inverted_index.propose | 27 |
| abstract_inverted_index.samples | 40 |
| abstract_inverted_index.setting | 34, 126 |
| abstract_inverted_index.several | 145 |
| abstract_inverted_index.surpass | 144 |
| abstract_inverted_index.Finally, | 161 |
| abstract_inverted_index.approach | 29 |
| abstract_inverted_index.datasets | 179 |
| abstract_inverted_index.example, | 140 |
| abstract_inverted_index.existing | 121 |
| abstract_inverted_index.flexibly | 76 |
| abstract_inverted_index.labeled. | 42 |
| abstract_inverted_index.learning | 8, 137 |
| abstract_inverted_index.leverage | 63 |
| abstract_inverted_index.margins, | 125 |
| abstract_inverted_index.previous | 105 |
| abstract_inverted_index.publicly | 186 |
| abstract_inverted_index.relevant | 102 |
| abstract_inverted_index.samples. | 61 |
| abstract_inverted_index.scenario | 14, 48 |
| abstract_inverted_index.thorough | 110 |
| abstract_inverted_index.CIFAR-100 | 142 |
| abstract_inverted_index.advances, | 2 |
| abstract_inverted_index.available | 187 |
| abstract_inverted_index.challenge | 25 |
| abstract_inverted_index.continual | 7, 31, 135 |
| abstract_inverted_index.paradigm. | 138 |
| abstract_inverted_index.partition | 71 |
| abstract_inverted_index.unlabeled | 55 |
| abstract_inverted_index.approaches | 9, 122 |
| abstract_inverted_index.evaluation | 112 |
| abstract_inverted_index.forgetting | 52 |
| abstract_inverted_index.resolution | 171 |
| abstract_inverted_index.seamlessly | 175 |
| abstract_inverted_index.underlying | 79 |
| abstract_inverted_index.classifiers | 68 |
| abstract_inverted_index.information | 103 |
| abstract_inverted_index.learning--a | 33 |
| abstract_inverted_index.nonlinearly | 70 |
| abstract_inverted_index.outperforms | 118 |
| abstract_inverted_index.overfitting | 58 |
| abstract_inverted_index.performance | 4 |
| abstract_inverted_index.significant | 1 |
| abstract_inverted_index.supervision | 155 |
| abstract_inverted_index.unrealistic | 13 |
| abstract_inverted_index.distribution | 81 |
| abstract_inverted_index.experimental | 111 |
| abstract_inverted_index.ImageNet-100. | 182 |
| abstract_inverted_index.annotations). | 160 |
| abstract_inverted_index.non-parametric | 85 |
| abstract_inverted_index.representation | 95 |
| abstract_inverted_index.representations | 53 |
| abstract_inverted_index.semi-supervised | 32, 136 |
| abstract_inverted_index.nearest-neighbor | 67 |
| abstract_inverted_index.state-of-the-art | 6 |
| abstract_inverted_index.https://github.com/kangzhiq/NNCSL | 189 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 95 |
| countries_distinct_count | 3 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.82285223 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |