Distilling Representations from GAN Generator via Squeeze and Span Article Swipe
Yang Yu
,
Xiaotian Cheng
,
Chang Liu
,
Hakan Bilen
,
Xiangyang Ji
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2211.03000
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2211.03000
In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains. The controllable synthesis ability of GAN generators suggests that they maintain informative, disentangled, and explainable image representations, but leveraging and transferring their representations to downstream tasks is largely unexplored. In this paper, we propose to distill knowledge from GAN generators by squeezing and spanning their representations. We squeeze the generator features into representations that are invariant to semantic-preserving transformations through a network before they are distilled into the student network. We span the distilled representation of the synthetic domain to the real domain by also using real training data to remedy the mode collapse of GANs and boost the student network performance in a real domain. Experiments justify the efficacy of our method and reveal its great significance in self-supervised representation learning. Code is available at https://github.com/yangyu12/squeeze-and-span.
Related Topics
Concepts
Generator (circuit theory)
Computer science
Representation (politics)
Generative adversarial network
Span (engineering)
Generative grammar
Invariant (physics)
Domain (mathematical analysis)
Code (set theory)
Artificial intelligence
Theoretical computer science
Natural language processing
Algorithm
Computer engineering
Image (mathematics)
Programming language
Mathematics
Power (physics)
Engineering
Set (abstract data type)
Mathematical analysis
Mathematical physics
Law
Physics
Politics
Civil engineering
Political science
Quantum mechanics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2211.03000
- https://arxiv.org/pdf/2211.03000
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4308612980
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4308612980Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2211.03000Digital Object Identifier
- Title
-
Distilling Representations from GAN Generator via Squeeze and SpanWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-11-06Full publication date if available
- Authors
-
Yang Yu, Xiaotian Cheng, Chang Liu, Hakan Bilen, Xiangyang JiList of authors in order
- Landing page
-
https://arxiv.org/abs/2211.03000Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2211.03000Direct 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/2211.03000Direct OA link when available
- Concepts
-
Generator (circuit theory), Computer science, Representation (politics), Generative adversarial network, Span (engineering), Generative grammar, Invariant (physics), Domain (mathematical analysis), Code (set theory), Artificial intelligence, Theoretical computer science, Natural language processing, Algorithm, Computer engineering, Image (mathematics), Programming language, Mathematics, Power (physics), Engineering, Set (abstract data type), Mathematical analysis, Mathematical physics, Law, Physics, Politics, Civil engineering, Political science, 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/W4308612980 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2211.03000 |
| ids.doi | https://doi.org/10.48550/arxiv.2211.03000 |
| ids.openalex | https://openalex.org/W4308612980 |
| fwci | |
| type | preprint |
| title | Distilling Representations from GAN Generator via Squeeze and Span |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10775 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9970999956130981 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780992000 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7811136841773987 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q17016113 |
| concepts[0].display_name | Generator (circuit theory) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7137205004692078 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2776359362 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6536411643028259 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[2].display_name | Representation (politics) |
| concepts[3].id | https://openalex.org/C2988773926 |
| concepts[3].level | 3 |
| concepts[3].score | 0.6250362992286682 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q25104379 |
| concepts[3].display_name | Generative adversarial network |
| concepts[4].id | https://openalex.org/C2778753569 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5728490352630615 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1960395 |
| concepts[4].display_name | Span (engineering) |
| concepts[5].id | https://openalex.org/C39890363 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5596849322319031 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[5].display_name | Generative grammar |
| concepts[6].id | https://openalex.org/C190470478 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5257214903831482 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2370229 |
| concepts[6].display_name | Invariant (physics) |
| concepts[7].id | https://openalex.org/C36503486 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5235878229141235 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[7].display_name | Domain (mathematical analysis) |
| concepts[8].id | https://openalex.org/C2776760102 |
| concepts[8].level | 3 |
| concepts[8].score | 0.5135583877563477 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[8].display_name | Code (set theory) |
| concepts[9].id | https://openalex.org/C154945302 |
| concepts[9].level | 1 |
| concepts[9].score | 0.49499887228012085 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[9].display_name | Artificial intelligence |
| concepts[10].id | https://openalex.org/C80444323 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4077352285385132 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[10].display_name | Theoretical computer science |
| concepts[11].id | https://openalex.org/C204321447 |
| concepts[11].level | 1 |
| concepts[11].score | 0.36942994594573975 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[11].display_name | Natural language processing |
| concepts[12].id | https://openalex.org/C11413529 |
| concepts[12].level | 1 |
| concepts[12].score | 0.3448505699634552 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[12].display_name | Algorithm |
| concepts[13].id | https://openalex.org/C113775141 |
| concepts[13].level | 1 |
| concepts[13].score | 0.3202712833881378 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[13].display_name | Computer engineering |
| concepts[14].id | https://openalex.org/C115961682 |
| concepts[14].level | 2 |
| concepts[14].score | 0.30936819314956665 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[14].display_name | Image (mathematics) |
| concepts[15].id | https://openalex.org/C199360897 |
| concepts[15].level | 1 |
| concepts[15].score | 0.21521735191345215 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[15].display_name | Programming language |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.13583186268806458 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| concepts[17].id | https://openalex.org/C163258240 |
| concepts[17].level | 2 |
| concepts[17].score | 0.08971241116523743 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q25342 |
| concepts[17].display_name | Power (physics) |
| concepts[18].id | https://openalex.org/C127413603 |
| concepts[18].level | 0 |
| concepts[18].score | 0.07085102796554565 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[18].display_name | Engineering |
| concepts[19].id | https://openalex.org/C177264268 |
| concepts[19].level | 2 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[19].display_name | Set (abstract data type) |
| concepts[20].id | https://openalex.org/C134306372 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[20].display_name | Mathematical analysis |
| concepts[21].id | https://openalex.org/C37914503 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q156495 |
| concepts[21].display_name | Mathematical physics |
| concepts[22].id | https://openalex.org/C199539241 |
| concepts[22].level | 1 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[22].display_name | Law |
| concepts[23].id | https://openalex.org/C121332964 |
| concepts[23].level | 0 |
| concepts[23].score | 0.0 |
| concepts[23].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[23].display_name | Physics |
| concepts[24].id | https://openalex.org/C94625758 |
| concepts[24].level | 2 |
| concepts[24].score | 0.0 |
| concepts[24].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[24].display_name | Politics |
| concepts[25].id | https://openalex.org/C147176958 |
| concepts[25].level | 1 |
| concepts[25].score | 0.0 |
| concepts[25].wikidata | https://www.wikidata.org/wiki/Q77590 |
| concepts[25].display_name | Civil engineering |
| concepts[26].id | https://openalex.org/C17744445 |
| concepts[26].level | 0 |
| concepts[26].score | 0.0 |
| concepts[26].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[26].display_name | Political science |
| concepts[27].id | https://openalex.org/C62520636 |
| concepts[27].level | 1 |
| concepts[27].score | 0.0 |
| concepts[27].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[27].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/generator |
| keywords[0].score | 0.7811136841773987 |
| keywords[0].display_name | Generator (circuit theory) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7137205004692078 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/representation |
| keywords[2].score | 0.6536411643028259 |
| keywords[2].display_name | Representation (politics) |
| keywords[3].id | https://openalex.org/keywords/generative-adversarial-network |
| keywords[3].score | 0.6250362992286682 |
| keywords[3].display_name | Generative adversarial network |
| keywords[4].id | https://openalex.org/keywords/span |
| keywords[4].score | 0.5728490352630615 |
| keywords[4].display_name | Span (engineering) |
| keywords[5].id | https://openalex.org/keywords/generative-grammar |
| keywords[5].score | 0.5596849322319031 |
| keywords[5].display_name | Generative grammar |
| keywords[6].id | https://openalex.org/keywords/invariant |
| keywords[6].score | 0.5257214903831482 |
| keywords[6].display_name | Invariant (physics) |
| keywords[7].id | https://openalex.org/keywords/domain |
| keywords[7].score | 0.5235878229141235 |
| keywords[7].display_name | Domain (mathematical analysis) |
| keywords[8].id | https://openalex.org/keywords/code |
| keywords[8].score | 0.5135583877563477 |
| keywords[8].display_name | Code (set theory) |
| keywords[9].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[9].score | 0.49499887228012085 |
| keywords[9].display_name | Artificial intelligence |
| keywords[10].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[10].score | 0.4077352285385132 |
| keywords[10].display_name | Theoretical computer science |
| keywords[11].id | https://openalex.org/keywords/natural-language-processing |
| keywords[11].score | 0.36942994594573975 |
| keywords[11].display_name | Natural language processing |
| keywords[12].id | https://openalex.org/keywords/algorithm |
| keywords[12].score | 0.3448505699634552 |
| keywords[12].display_name | Algorithm |
| keywords[13].id | https://openalex.org/keywords/computer-engineering |
| keywords[13].score | 0.3202712833881378 |
| keywords[13].display_name | Computer engineering |
| keywords[14].id | https://openalex.org/keywords/image |
| keywords[14].score | 0.30936819314956665 |
| keywords[14].display_name | Image (mathematics) |
| keywords[15].id | https://openalex.org/keywords/programming-language |
| keywords[15].score | 0.21521735191345215 |
| keywords[15].display_name | Programming language |
| keywords[16].id | https://openalex.org/keywords/mathematics |
| keywords[16].score | 0.13583186268806458 |
| keywords[16].display_name | Mathematics |
| keywords[17].id | https://openalex.org/keywords/power |
| keywords[17].score | 0.08971241116523743 |
| keywords[17].display_name | Power (physics) |
| keywords[18].id | https://openalex.org/keywords/engineering |
| keywords[18].score | 0.07085102796554565 |
| keywords[18].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2211.03000 |
| 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/2211.03000 |
| 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/2211.03000 |
| locations[1].id | doi:10.48550/arxiv.2211.03000 |
| 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.2211.03000 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100458535 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1972-6496 |
| authorships[0].author.display_name | Yang Yu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yang, Yu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5112876866 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Xiaotian Cheng |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cheng, Xiaotian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5114889359 |
| authorships[2].author.orcid | https://orcid.org/0009-0003-1751-6206 |
| authorships[2].author.display_name | Chang Liu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Liu, Chang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5056977175 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6947-6918 |
| authorships[3].author.display_name | Hakan Bilen |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Bilen, Hakan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5024401174 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-7333-9975 |
| authorships[4].author.display_name | Xiangyang Ji |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Ji, Xiangyang |
| 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/2211.03000 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Distilling Representations from GAN Generator via Squeeze and Span |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10775 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9970999956130981 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| related_works | https://openalex.org/W4386984417, https://openalex.org/W2888032422, https://openalex.org/W3156763702, https://openalex.org/W4377980832, https://openalex.org/W3005996785, https://openalex.org/W2897769091, https://openalex.org/W4297411772, https://openalex.org/W2845413374, https://openalex.org/W4226298148, https://openalex.org/W4235873501 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2211.03000 |
| 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/2211.03000 |
| 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/2211.03000 |
| primary_location.id | pmh:oai:arXiv.org:2211.03000 |
| 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/2211.03000 |
| 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/2211.03000 |
| publication_date | 2022-11-06 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 84, 127 |
| abstract_inverted_index.In | 0, 53 |
| abstract_inverted_index.We | 70, 94 |
| abstract_inverted_index.an | 9 |
| abstract_inverted_index.at | 149 |
| abstract_inverted_index.by | 64, 107 |
| abstract_inverted_index.in | 21, 126, 142 |
| abstract_inverted_index.is | 50, 147 |
| abstract_inverted_index.of | 28, 99, 118, 134 |
| abstract_inverted_index.to | 15, 47, 58, 80, 103, 113 |
| abstract_inverted_index.we | 56 |
| abstract_inverted_index.GAN | 29, 62 |
| abstract_inverted_index.The | 24 |
| abstract_inverted_index.and | 13, 37, 43, 66, 120, 137 |
| abstract_inverted_index.are | 78, 88 |
| abstract_inverted_index.but | 41 |
| abstract_inverted_index.its | 139 |
| abstract_inverted_index.our | 135 |
| abstract_inverted_index.the | 72, 91, 96, 100, 104, 115, 122, 132 |
| abstract_inverted_index.Code | 146 |
| abstract_inverted_index.GANs | 119 |
| abstract_inverted_index.also | 108 |
| abstract_inverted_index.been | 8 |
| abstract_inverted_index.data | 112 |
| abstract_inverted_index.from | 61 |
| abstract_inverted_index.have | 7 |
| abstract_inverted_index.into | 75, 90 |
| abstract_inverted_index.mode | 116 |
| abstract_inverted_index.real | 105, 110, 128 |
| abstract_inverted_index.span | 95 |
| abstract_inverted_index.that | 32, 77 |
| abstract_inverted_index.they | 33, 87 |
| abstract_inverted_index.this | 54 |
| abstract_inverted_index.boost | 121 |
| abstract_inverted_index.great | 140 |
| abstract_inverted_index.image | 39 |
| abstract_inverted_index.shown | 14 |
| abstract_inverted_index.tasks | 49 |
| abstract_inverted_index.their | 45, 68 |
| abstract_inverted_index.topic | 12 |
| abstract_inverted_index.using | 109 |
| abstract_inverted_index.(GANs) | 6 |
| abstract_inverted_index.before | 86 |
| abstract_inverted_index.domain | 102, 106 |
| abstract_inverted_index.images | 20 |
| abstract_inverted_index.method | 136 |
| abstract_inverted_index.paper, | 55 |
| abstract_inverted_index.recent | 1 |
| abstract_inverted_index.remedy | 114 |
| abstract_inverted_index.reveal | 138 |
| abstract_inverted_index.years, | 2 |
| abstract_inverted_index.ability | 27 |
| abstract_inverted_index.distill | 59 |
| abstract_inverted_index.domain. | 129 |
| abstract_inverted_index.justify | 131 |
| abstract_inverted_index.largely | 51 |
| abstract_inverted_index.network | 85, 124 |
| abstract_inverted_index.produce | 17 |
| abstract_inverted_index.propose | 57 |
| abstract_inverted_index.squeeze | 71 |
| abstract_inverted_index.student | 92, 123 |
| abstract_inverted_index.studied | 11 |
| abstract_inverted_index.through | 83 |
| abstract_inverted_index.various | 22 |
| abstract_inverted_index.actively | 10 |
| abstract_inverted_index.collapse | 117 |
| abstract_inverted_index.domains. | 23 |
| abstract_inverted_index.efficacy | 133 |
| abstract_inverted_index.features | 74 |
| abstract_inverted_index.maintain | 34 |
| abstract_inverted_index.network. | 93 |
| abstract_inverted_index.networks | 5 |
| abstract_inverted_index.spanning | 67 |
| abstract_inverted_index.suggests | 31 |
| abstract_inverted_index.training | 111 |
| abstract_inverted_index.available | 148 |
| abstract_inverted_index.distilled | 89, 97 |
| abstract_inverted_index.generator | 73 |
| abstract_inverted_index.invariant | 79 |
| abstract_inverted_index.knowledge | 60 |
| abstract_inverted_index.learning. | 145 |
| abstract_inverted_index.realistic | 19 |
| abstract_inverted_index.squeezing | 65 |
| abstract_inverted_index.synthesis | 26 |
| abstract_inverted_index.synthetic | 101 |
| abstract_inverted_index.downstream | 48 |
| abstract_inverted_index.generative | 3 |
| abstract_inverted_index.generators | 30, 63 |
| abstract_inverted_index.leveraging | 42 |
| abstract_inverted_index.Experiments | 130 |
| abstract_inverted_index.adversarial | 4 |
| abstract_inverted_index.explainable | 38 |
| abstract_inverted_index.performance | 125 |
| abstract_inverted_index.unexplored. | 52 |
| abstract_inverted_index.controllable | 25 |
| abstract_inverted_index.high-quality | 18 |
| abstract_inverted_index.informative, | 35 |
| abstract_inverted_index.significance | 141 |
| abstract_inverted_index.successfully | 16 |
| abstract_inverted_index.transferring | 44 |
| abstract_inverted_index.disentangled, | 36 |
| abstract_inverted_index.representation | 98, 144 |
| abstract_inverted_index.representations | 46, 76 |
| abstract_inverted_index.self-supervised | 143 |
| abstract_inverted_index.transformations | 82 |
| abstract_inverted_index.representations, | 40 |
| abstract_inverted_index.representations. | 69 |
| abstract_inverted_index.semantic-preserving | 81 |
| abstract_inverted_index.https://github.com/yangyu12/squeeze-and-span. | 150 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |