Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation Article Swipe
Zhen Zhao
,
Ye Liu
,
Meng Zhao
,
Di Yin
,
Yixuan Yuan
,
Luping Zhou
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2308.11903
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2308.11903
Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently. Due to the limited labelled data, SSMIS methods mainly focus on effectively leveraging unlabeled data to enhance the segmentation performance. However, despite their promising performance, current state-of-the-art methods often prioritize integrating complex techniques and loss terms rather than addressing the core challenges of semi-supervised scenarios directly. We argue that the key to SSMIS lies in generating substantial and appropriate prediction disagreement on unlabeled data. To this end, we emphasize the crutiality of data perturbation and model stabilization in semi-supervised segmentation, and propose a simple yet effective approach to boost SSMIS performance significantly, dubbed DPMS. Specifically, we first revisit SSMIS from three distinct perspectives: the data, the model, and the loss, and conduct a comprehensive study of corresponding strategies to examine their effectiveness. Based on these examinations, we then propose DPMS, which adopts a plain teacher-student framework with a standard supervised loss and unsupervised consistency loss. To produce appropriate prediction disagreements, DPMS perturbs the unlabeled data via strong augmentations to enlarge prediction disagreements considerably. On the other hand, using EMA teacher when strong augmentation is applied does not necessarily improve performance. DPMS further utilizes a forwarding-twice and momentum updating strategies for normalization statistics to stabilize the training on unlabeled data effectively. Despite its simplicity, DPMS can obtain new state-of-the-art performance on the public 2D ACDC and 3D LA datasets across various semi-supervised settings, e.g. obtaining a remarkable 22.62% improvement against previous SOTA on ACDC with 5% labels.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2308.11903
- https://arxiv.org/pdf/2308.11903
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4386148109
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4386148109Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2308.11903Digital Object Identifier
- Title
-
Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image SegmentationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-08-23Full publication date if available
- Authors
-
Zhen Zhao, Ye Liu, Meng Zhao, Di Yin, Yixuan Yuan, Luping ZhouList of authors in order
- Landing page
-
https://arxiv.org/abs/2308.11903Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2308.11903Direct 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/2308.11903Direct OA link when available
- Concepts
-
Computer science, Segmentation, Labeled data, Artificial intelligence, Machine learning, Normalization (sociology), Consistency (knowledge bases), Training set, Synthetic data, Sociology, AnthropologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4386148109 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2308.11903 |
| ids.doi | https://doi.org/10.48550/arxiv.2308.11903 |
| ids.openalex | https://openalex.org/W4386148109 |
| fwci | |
| type | preprint |
| title | Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Neural Network Applications |
| topics[1].id | https://openalex.org/T12702 |
| topics[1].field.id | https://openalex.org/fields/28 |
| topics[1].field.display_name | Neuroscience |
| topics[1].score | 0.9902999997138977 |
| topics[1].domain.id | https://openalex.org/domains/1 |
| topics[1].domain.display_name | Life Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2808 |
| topics[1].subfield.display_name | Neurology |
| topics[1].display_name | Brain Tumor Detection and Classification |
| topics[2].id | https://openalex.org/T14510 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9866999983787537 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2204 |
| topics[2].subfield.display_name | Biomedical Engineering |
| topics[2].display_name | Medical Imaging and Analysis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.693875789642334 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C89600930 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6818186044692993 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[1].display_name | Segmentation |
| concepts[2].id | https://openalex.org/C2776145971 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5522895455360413 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30673951 |
| concepts[2].display_name | Labeled data |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.543718695640564 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5174501538276672 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C136886441 |
| concepts[5].level | 2 |
| concepts[5].score | 0.49727538228034973 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q926129 |
| concepts[5].display_name | Normalization (sociology) |
| concepts[6].id | https://openalex.org/C2776436953 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4473792016506195 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5163215 |
| concepts[6].display_name | Consistency (knowledge bases) |
| concepts[7].id | https://openalex.org/C51632099 |
| concepts[7].level | 2 |
| concepts[7].score | 0.42594239115715027 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q3985153 |
| concepts[7].display_name | Training set |
| concepts[8].id | https://openalex.org/C160920958 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4197738766670227 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7662746 |
| concepts[8].display_name | Synthetic data |
| concepts[9].id | https://openalex.org/C144024400 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[9].display_name | Sociology |
| concepts[10].id | https://openalex.org/C19165224 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q23404 |
| concepts[10].display_name | Anthropology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.693875789642334 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/segmentation |
| keywords[1].score | 0.6818186044692993 |
| keywords[1].display_name | Segmentation |
| keywords[2].id | https://openalex.org/keywords/labeled-data |
| keywords[2].score | 0.5522895455360413 |
| keywords[2].display_name | Labeled data |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.543718695640564 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.5174501538276672 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/normalization |
| keywords[5].score | 0.49727538228034973 |
| keywords[5].display_name | Normalization (sociology) |
| keywords[6].id | https://openalex.org/keywords/consistency |
| keywords[6].score | 0.4473792016506195 |
| keywords[6].display_name | Consistency (knowledge bases) |
| keywords[7].id | https://openalex.org/keywords/training-set |
| keywords[7].score | 0.42594239115715027 |
| keywords[7].display_name | Training set |
| keywords[8].id | https://openalex.org/keywords/synthetic-data |
| keywords[8].score | 0.4197738766670227 |
| keywords[8].display_name | Synthetic data |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2308.11903 |
| 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/2308.11903 |
| 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/2308.11903 |
| locations[1].id | doi:10.48550/arxiv.2308.11903 |
| 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 | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2308.11903 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5072694516 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0796-4078 |
| authorships[0].author.display_name | Zhen Zhao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhao, Zhen |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101489668 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6190-1855 |
| authorships[1].author.display_name | Ye Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Liu, Ye |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101803407 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5575-7962 |
| authorships[2].author.display_name | Meng Zhao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhao, Meng |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100567807 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Di Yin |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yin, Di |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5073968803 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-0853-6948 |
| authorships[4].author.display_name | Yixuan Yuan |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Yuan, Yixuan |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100643784 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-8762-2424 |
| authorships[5].author.display_name | Luping Zhou |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Zhou, Luping |
| authorships[5].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/2308.11903 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-08-25T00:00:00 |
| display_name | Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Neural Network Applications |
| related_works | https://openalex.org/W2130553454, https://openalex.org/W3022007134, https://openalex.org/W4317548404, https://openalex.org/W4312659495, https://openalex.org/W2087783760, https://openalex.org/W4385366257, https://openalex.org/W3101007570, https://openalex.org/W4387910575, https://openalex.org/W3104108945, https://openalex.org/W2033364610 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2308.11903 |
| 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/2308.11903 |
| 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/2308.11903 |
| primary_location.id | pmh:oai:arXiv.org:2308.11903 |
| 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/2308.11903 |
| 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/2308.11903 |
| publication_date | 2023-08-23 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 94, 124, 144, 149, 195, 236 |
| abstract_inverted_index.2D | 224 |
| abstract_inverted_index.3D | 227 |
| abstract_inverted_index.5% | 246 |
| abstract_inverted_index.LA | 228 |
| abstract_inverted_index.On | 175 |
| abstract_inverted_index.To | 76, 157 |
| abstract_inverted_index.We | 58 |
| abstract_inverted_index.in | 66, 89 |
| abstract_inverted_index.is | 185 |
| abstract_inverted_index.of | 54, 83, 127 |
| abstract_inverted_index.on | 1, 22, 73, 135, 208, 221, 243 |
| abstract_inverted_index.to | 13, 27, 63, 99, 130, 170, 204 |
| abstract_inverted_index.we | 79, 107, 138 |
| abstract_inverted_index.Due | 12 |
| abstract_inverted_index.EMA | 180 |
| abstract_inverted_index.and | 45, 69, 86, 92, 119, 122, 153, 197, 226 |
| abstract_inverted_index.can | 216 |
| abstract_inverted_index.for | 201 |
| abstract_inverted_index.its | 213 |
| abstract_inverted_index.key | 62 |
| abstract_inverted_index.new | 218 |
| abstract_inverted_index.not | 188 |
| abstract_inverted_index.the | 14, 29, 51, 61, 81, 115, 117, 120, 164, 176, 206, 222 |
| abstract_inverted_index.via | 167 |
| abstract_inverted_index.yet | 96 |
| abstract_inverted_index.ACDC | 225, 244 |
| abstract_inverted_index.DPMS | 162, 192, 215 |
| abstract_inverted_index.SOTA | 242 |
| abstract_inverted_index.core | 52 |
| abstract_inverted_index.data | 26, 84, 166, 210 |
| abstract_inverted_index.does | 187 |
| abstract_inverted_index.e.g. | 234 |
| abstract_inverted_index.end, | 78 |
| abstract_inverted_index.fast | 9 |
| abstract_inverted_index.from | 111 |
| abstract_inverted_index.have | 7 |
| abstract_inverted_index.lies | 65 |
| abstract_inverted_index.loss | 46, 152 |
| abstract_inverted_index.seen | 8 |
| abstract_inverted_index.than | 49 |
| abstract_inverted_index.that | 60 |
| abstract_inverted_index.then | 139 |
| abstract_inverted_index.this | 77 |
| abstract_inverted_index.when | 182 |
| abstract_inverted_index.with | 148, 245 |
| abstract_inverted_index.Based | 134 |
| abstract_inverted_index.DPMS, | 141 |
| abstract_inverted_index.DPMS. | 105 |
| abstract_inverted_index.SSMIS | 18, 64, 101, 110 |
| abstract_inverted_index.argue | 59 |
| abstract_inverted_index.boost | 100 |
| abstract_inverted_index.data, | 17, 116 |
| abstract_inverted_index.data. | 75 |
| abstract_inverted_index.first | 108 |
| abstract_inverted_index.focus | 21 |
| abstract_inverted_index.hand, | 178 |
| abstract_inverted_index.image | 4 |
| abstract_inverted_index.loss, | 121 |
| abstract_inverted_index.loss. | 156 |
| abstract_inverted_index.model | 87 |
| abstract_inverted_index.often | 40 |
| abstract_inverted_index.other | 177 |
| abstract_inverted_index.plain | 145 |
| abstract_inverted_index.study | 126 |
| abstract_inverted_index.terms | 47 |
| abstract_inverted_index.their | 34, 132 |
| abstract_inverted_index.these | 136 |
| abstract_inverted_index.three | 112 |
| abstract_inverted_index.using | 179 |
| abstract_inverted_index.which | 142 |
| abstract_inverted_index.22.62% | 238 |
| abstract_inverted_index.across | 230 |
| abstract_inverted_index.adopts | 143 |
| abstract_inverted_index.dubbed | 104 |
| abstract_inverted_index.mainly | 20 |
| abstract_inverted_index.model, | 118 |
| abstract_inverted_index.obtain | 217 |
| abstract_inverted_index.public | 223 |
| abstract_inverted_index.rather | 48 |
| abstract_inverted_index.simple | 95 |
| abstract_inverted_index.strong | 168, 183 |
| abstract_inverted_index.(SSMIS) | 6 |
| abstract_inverted_index.Despite | 212 |
| abstract_inverted_index.Studies | 0 |
| abstract_inverted_index.against | 240 |
| abstract_inverted_index.applied | 186 |
| abstract_inverted_index.complex | 43 |
| abstract_inverted_index.conduct | 123 |
| abstract_inverted_index.current | 37 |
| abstract_inverted_index.despite | 33 |
| abstract_inverted_index.enhance | 28 |
| abstract_inverted_index.enlarge | 171 |
| abstract_inverted_index.examine | 131 |
| abstract_inverted_index.further | 193 |
| abstract_inverted_index.improve | 190 |
| abstract_inverted_index.labels. | 247 |
| abstract_inverted_index.limited | 15 |
| abstract_inverted_index.medical | 3 |
| abstract_inverted_index.methods | 19, 39 |
| abstract_inverted_index.produce | 158 |
| abstract_inverted_index.propose | 93, 140 |
| abstract_inverted_index.revisit | 109 |
| abstract_inverted_index.teacher | 181 |
| abstract_inverted_index.various | 231 |
| abstract_inverted_index.However, | 32 |
| abstract_inverted_index.approach | 98 |
| abstract_inverted_index.datasets | 229 |
| abstract_inverted_index.distinct | 113 |
| abstract_inverted_index.labelled | 16 |
| abstract_inverted_index.momentum | 198 |
| abstract_inverted_index.perturbs | 163 |
| abstract_inverted_index.previous | 241 |
| abstract_inverted_index.progress | 10 |
| abstract_inverted_index.standard | 150 |
| abstract_inverted_index.training | 207 |
| abstract_inverted_index.updating | 199 |
| abstract_inverted_index.utilizes | 194 |
| abstract_inverted_index.directly. | 57 |
| abstract_inverted_index.effective | 97 |
| abstract_inverted_index.emphasize | 80 |
| abstract_inverted_index.framework | 147 |
| abstract_inverted_index.obtaining | 235 |
| abstract_inverted_index.promising | 35 |
| abstract_inverted_index.recently. | 11 |
| abstract_inverted_index.scenarios | 56 |
| abstract_inverted_index.settings, | 233 |
| abstract_inverted_index.stabilize | 205 |
| abstract_inverted_index.unlabeled | 25, 74, 165, 209 |
| abstract_inverted_index.addressing | 50 |
| abstract_inverted_index.challenges | 53 |
| abstract_inverted_index.crutiality | 82 |
| abstract_inverted_index.generating | 67 |
| abstract_inverted_index.leveraging | 24 |
| abstract_inverted_index.prediction | 71, 160, 172 |
| abstract_inverted_index.prioritize | 41 |
| abstract_inverted_index.remarkable | 237 |
| abstract_inverted_index.statistics | 203 |
| abstract_inverted_index.strategies | 129, 200 |
| abstract_inverted_index.supervised | 151 |
| abstract_inverted_index.techniques | 44 |
| abstract_inverted_index.appropriate | 70, 159 |
| abstract_inverted_index.consistency | 155 |
| abstract_inverted_index.effectively | 23 |
| abstract_inverted_index.improvement | 239 |
| abstract_inverted_index.integrating | 42 |
| abstract_inverted_index.necessarily | 189 |
| abstract_inverted_index.performance | 102, 220 |
| abstract_inverted_index.simplicity, | 214 |
| abstract_inverted_index.substantial | 68 |
| abstract_inverted_index.augmentation | 184 |
| abstract_inverted_index.disagreement | 72 |
| abstract_inverted_index.effectively. | 211 |
| abstract_inverted_index.performance, | 36 |
| abstract_inverted_index.performance. | 31, 191 |
| abstract_inverted_index.perturbation | 85 |
| abstract_inverted_index.segmentation | 5, 30 |
| abstract_inverted_index.unsupervised | 154 |
| abstract_inverted_index.Specifically, | 106 |
| abstract_inverted_index.augmentations | 169 |
| abstract_inverted_index.comprehensive | 125 |
| abstract_inverted_index.considerably. | 174 |
| abstract_inverted_index.corresponding | 128 |
| abstract_inverted_index.disagreements | 173 |
| abstract_inverted_index.examinations, | 137 |
| abstract_inverted_index.normalization | 202 |
| abstract_inverted_index.perspectives: | 114 |
| abstract_inverted_index.segmentation, | 91 |
| abstract_inverted_index.stabilization | 88 |
| abstract_inverted_index.disagreements, | 161 |
| abstract_inverted_index.effectiveness. | 133 |
| abstract_inverted_index.significantly, | 103 |
| abstract_inverted_index.semi-supervised | 2, 55, 90, 232 |
| abstract_inverted_index.teacher-student | 146 |
| abstract_inverted_index.forwarding-twice | 196 |
| abstract_inverted_index.state-of-the-art | 38, 219 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.7300000190734863 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |