Generalized Depthwise-Separable Convolutions for Adversarially Robust\n and Efficient Neural Networks Article Swipe
Hassan Dbouk
,
Naresh R. Shanbhag
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.14871
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.14871
Despite their tremendous successes, convolutional neural networks (CNNs)\nincur high computational/storage costs and are vulnerable to adversarial\nperturbations. Recent works on robust model compression address these\nchallenges by combining model compression techniques with adversarial training.\nBut these methods are unable to improve throughput (frames-per-second) on\nreal-life hardware while simultaneously preserving robustness to adversarial\nperturbations. To overcome this problem, we propose the method of Generalized\nDepthwise-Separable (GDWS) convolution -- an efficient, universal,\npost-training approximation of a standard 2D convolution. GDWS dramatically\nimproves the throughput of a standard pre-trained network on real-life hardware\nwhile preserving its robustness. Lastly, GDWS is scalable to large problem\nsizes since it operates on pre-trained models and doesn't require any\nadditional training. We establish the optimality of GDWS as a 2D convolution\napproximator and present exact algorithms for constructing optimal GDWS\nconvolutions under complexity and error constraints. We demonstrate the\neffectiveness of GDWS via extensive experiments on CIFAR-10, SVHN, and ImageNet\ndatasets. Our code can be found at https://github.com/hsndbk4/GDWS.\n
Related Topics
Concepts
Computer science
Robustness (evolution)
Scalability
Convolution (computer science)
Convolutional neural network
Separable space
Computational complexity theory
Code (set theory)
Artificial intelligence
Artificial neural network
Adversarial system
Mathematical optimization
Algorithm
Machine learning
Mathematics
Chemistry
Biochemistry
Set (abstract data type)
Gene
Database
Programming language
Mathematical analysis
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2110.14871
- https://arxiv.org/pdf/2110.14871
- OA Status
- green
- Cited By
- 3
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4286892346
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4286892346Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2110.14871Digital Object Identifier
- Title
-
Generalized Depthwise-Separable Convolutions for Adversarially Robust\n and Efficient Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2021Year of publication
- Publication date
-
2021-10-27Full publication date if available
- Authors
-
Hassan Dbouk, Naresh R. ShanbhagList of authors in order
- Landing page
-
https://arxiv.org/abs/2110.14871Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2110.14871Direct 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/2110.14871Direct OA link when available
- Concepts
-
Computer science, Robustness (evolution), Scalability, Convolution (computer science), Convolutional neural network, Separable space, Computational complexity theory, Code (set theory), Artificial intelligence, Artificial neural network, Adversarial system, Mathematical optimization, Algorithm, Machine learning, Mathematics, Chemistry, Biochemistry, Set (abstract data type), Gene, Database, Programming language, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2023: 2Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4286892346 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2110.14871 |
| ids.openalex | https://openalex.org/W4286892346 |
| fwci | 0.28220715 |
| type | preprint |
| title | Generalized Depthwise-Separable Convolutions for Adversarially Robust\n and Efficient Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11689 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9991999864578247 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9905999898910522 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Anomaly Detection Techniques and Applications |
| topics[2].id | https://openalex.org/T10036 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9822999835014343 |
| 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 | Advanced Neural Network Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8328288793563843 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C63479239 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7776905298233032 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[1].display_name | Robustness (evolution) |
| concepts[2].id | https://openalex.org/C48044578 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6686381101608276 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q727490 |
| concepts[2].display_name | Scalability |
| concepts[3].id | https://openalex.org/C45347329 |
| concepts[3].level | 3 |
| concepts[3].score | 0.6213048696517944 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q5166604 |
| concepts[3].display_name | Convolution (computer science) |
| concepts[4].id | https://openalex.org/C81363708 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5987411737442017 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[4].display_name | Convolutional neural network |
| concepts[5].id | https://openalex.org/C70710897 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5778127312660217 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q680081 |
| concepts[5].display_name | Separable space |
| concepts[6].id | https://openalex.org/C179799912 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4701896905899048 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q205084 |
| concepts[6].display_name | Computational complexity theory |
| concepts[7].id | https://openalex.org/C2776760102 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4209277927875519 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[7].display_name | Code (set theory) |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.4193479120731354 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C50644808 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4149456322193146 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[9].display_name | Artificial neural network |
| concepts[10].id | https://openalex.org/C37736160 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4123117923736572 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[10].display_name | Adversarial system |
| concepts[11].id | https://openalex.org/C126255220 |
| concepts[11].level | 1 |
| concepts[11].score | 0.40684980154037476 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[11].display_name | Mathematical optimization |
| concepts[12].id | https://openalex.org/C11413529 |
| concepts[12].level | 1 |
| concepts[12].score | 0.35576093196868896 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[12].display_name | Algorithm |
| concepts[13].id | https://openalex.org/C119857082 |
| concepts[13].level | 1 |
| concepts[13].score | 0.33697807788848877 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[13].display_name | Machine learning |
| concepts[14].id | https://openalex.org/C33923547 |
| concepts[14].level | 0 |
| concepts[14].score | 0.12500309944152832 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[14].display_name | Mathematics |
| concepts[15].id | https://openalex.org/C185592680 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[15].display_name | Chemistry |
| concepts[16].id | https://openalex.org/C55493867 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[16].display_name | Biochemistry |
| concepts[17].id | https://openalex.org/C177264268 |
| concepts[17].level | 2 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[17].display_name | Set (abstract data type) |
| concepts[18].id | https://openalex.org/C104317684 |
| concepts[18].level | 2 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[18].display_name | Gene |
| concepts[19].id | https://openalex.org/C77088390 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[19].display_name | Database |
| concepts[20].id | https://openalex.org/C199360897 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[20].display_name | Programming language |
| concepts[21].id | https://openalex.org/C134306372 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[21].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8328288793563843 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/robustness |
| keywords[1].score | 0.7776905298233032 |
| keywords[1].display_name | Robustness (evolution) |
| keywords[2].id | https://openalex.org/keywords/scalability |
| keywords[2].score | 0.6686381101608276 |
| keywords[2].display_name | Scalability |
| keywords[3].id | https://openalex.org/keywords/convolution |
| keywords[3].score | 0.6213048696517944 |
| keywords[3].display_name | Convolution (computer science) |
| keywords[4].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[4].score | 0.5987411737442017 |
| keywords[4].display_name | Convolutional neural network |
| keywords[5].id | https://openalex.org/keywords/separable-space |
| keywords[5].score | 0.5778127312660217 |
| keywords[5].display_name | Separable space |
| keywords[6].id | https://openalex.org/keywords/computational-complexity-theory |
| keywords[6].score | 0.4701896905899048 |
| keywords[6].display_name | Computational complexity theory |
| keywords[7].id | https://openalex.org/keywords/code |
| keywords[7].score | 0.4209277927875519 |
| keywords[7].display_name | Code (set theory) |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.4193479120731354 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[9].score | 0.4149456322193146 |
| keywords[9].display_name | Artificial neural network |
| keywords[10].id | https://openalex.org/keywords/adversarial-system |
| keywords[10].score | 0.4123117923736572 |
| keywords[10].display_name | Adversarial system |
| keywords[11].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[11].score | 0.40684980154037476 |
| keywords[11].display_name | Mathematical optimization |
| keywords[12].id | https://openalex.org/keywords/algorithm |
| keywords[12].score | 0.35576093196868896 |
| keywords[12].display_name | Algorithm |
| keywords[13].id | https://openalex.org/keywords/machine-learning |
| keywords[13].score | 0.33697807788848877 |
| keywords[13].display_name | Machine learning |
| keywords[14].id | https://openalex.org/keywords/mathematics |
| keywords[14].score | 0.12500309944152832 |
| keywords[14].display_name | Mathematics |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2110.14871 |
| 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/2110.14871 |
| 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/2110.14871 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5036439422 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8597-2121 |
| authorships[0].author.display_name | Hassan Dbouk |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dbouk, Hassan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5057014407 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4323-9164 |
| authorships[1].author.display_name | Naresh R. Shanbhag |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Shanbhag, Naresh R. |
| authorships[1].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/2110.14871 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-25T00:00:00 |
| display_name | Generalized Depthwise-Separable Convolutions for Adversarially Robust\n and Efficient Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11689 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991999864578247 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W2502115930, https://openalex.org/W2482350142, https://openalex.org/W2530952058, https://openalex.org/W2582836483, https://openalex.org/W4299366318, https://openalex.org/W3158431807, https://openalex.org/W2964954556, https://openalex.org/W4297580547, https://openalex.org/W2951583185, https://openalex.org/W4308155352 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 2 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2110.14871 |
| 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/2110.14871 |
| 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/2110.14871 |
| primary_location.id | pmh:oai:arXiv.org:2110.14871 |
| 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/2110.14871 |
| 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/2110.14871 |
| publication_date | 2021-10-27 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 66, 75, 110 |
| abstract_inverted_index.-- | 60 |
| abstract_inverted_index.2D | 68, 111 |
| abstract_inverted_index.To | 48 |
| abstract_inverted_index.We | 103, 126 |
| abstract_inverted_index.an | 61 |
| abstract_inverted_index.as | 109 |
| abstract_inverted_index.at | 144 |
| abstract_inverted_index.be | 142 |
| abstract_inverted_index.by | 24 |
| abstract_inverted_index.is | 87 |
| abstract_inverted_index.it | 93 |
| abstract_inverted_index.of | 56, 65, 74, 107, 129 |
| abstract_inverted_index.on | 18, 79, 95, 134 |
| abstract_inverted_index.to | 14, 36, 46, 89 |
| abstract_inverted_index.we | 52 |
| abstract_inverted_index.Our | 139 |
| abstract_inverted_index.and | 11, 98, 113, 123, 137 |
| abstract_inverted_index.are | 12, 34 |
| abstract_inverted_index.can | 141 |
| abstract_inverted_index.for | 117 |
| abstract_inverted_index.its | 83 |
| abstract_inverted_index.the | 54, 72, 105 |
| abstract_inverted_index.via | 131 |
| abstract_inverted_index.GDWS | 70, 86, 108, 130 |
| abstract_inverted_index.code | 140 |
| abstract_inverted_index.high | 8 |
| abstract_inverted_index.this | 50 |
| abstract_inverted_index.with | 29 |
| abstract_inverted_index.SVHN, | 136 |
| abstract_inverted_index.costs | 10 |
| abstract_inverted_index.error | 124 |
| abstract_inverted_index.exact | 115 |
| abstract_inverted_index.found | 143 |
| abstract_inverted_index.large | 90 |
| abstract_inverted_index.model | 20, 26 |
| abstract_inverted_index.since | 92 |
| abstract_inverted_index.their | 1 |
| abstract_inverted_index.these | 32 |
| abstract_inverted_index.under | 121 |
| abstract_inverted_index.while | 42 |
| abstract_inverted_index.works | 17 |
| abstract_inverted_index.(GDWS) | 58 |
| abstract_inverted_index.Recent | 16 |
| abstract_inverted_index.method | 55 |
| abstract_inverted_index.models | 97 |
| abstract_inverted_index.neural | 5 |
| abstract_inverted_index.robust | 19 |
| abstract_inverted_index.unable | 35 |
| abstract_inverted_index.Despite | 0 |
| abstract_inverted_index.Lastly, | 85 |
| abstract_inverted_index.address | 22 |
| abstract_inverted_index.doesn't | 99 |
| abstract_inverted_index.improve | 37 |
| abstract_inverted_index.methods | 33 |
| abstract_inverted_index.network | 78 |
| abstract_inverted_index.optimal | 119 |
| abstract_inverted_index.present | 114 |
| abstract_inverted_index.propose | 53 |
| abstract_inverted_index.require | 100 |
| abstract_inverted_index.hardware | 41 |
| abstract_inverted_index.networks | 6 |
| abstract_inverted_index.operates | 94 |
| abstract_inverted_index.overcome | 49 |
| abstract_inverted_index.problem, | 51 |
| abstract_inverted_index.scalable | 88 |
| abstract_inverted_index.standard | 67, 76 |
| abstract_inverted_index.CIFAR-10, | 135 |
| abstract_inverted_index.combining | 25 |
| abstract_inverted_index.establish | 104 |
| abstract_inverted_index.extensive | 132 |
| abstract_inverted_index.real-life | 80 |
| abstract_inverted_index.training. | 102 |
| abstract_inverted_index.algorithms | 116 |
| abstract_inverted_index.complexity | 122 |
| abstract_inverted_index.efficient, | 62 |
| abstract_inverted_index.optimality | 106 |
| abstract_inverted_index.preserving | 44, 82 |
| abstract_inverted_index.robustness | 45 |
| abstract_inverted_index.successes, | 3 |
| abstract_inverted_index.techniques | 28 |
| abstract_inverted_index.throughput | 38, 73 |
| abstract_inverted_index.tremendous | 2 |
| abstract_inverted_index.vulnerable | 13 |
| abstract_inverted_index.adversarial | 30 |
| abstract_inverted_index.compression | 21, 27 |
| abstract_inverted_index.convolution | 59 |
| abstract_inverted_index.demonstrate | 127 |
| abstract_inverted_index.experiments | 133 |
| abstract_inverted_index.pre-trained | 77, 96 |
| abstract_inverted_index.robustness. | 84 |
| abstract_inverted_index.constraints. | 125 |
| abstract_inverted_index.constructing | 118 |
| abstract_inverted_index.convolution. | 69 |
| abstract_inverted_index.(CNNs)\nincur | 7 |
| abstract_inverted_index.approximation | 64 |
| abstract_inverted_index.convolutional | 4 |
| abstract_inverted_index.on\nreal-life | 40 |
| abstract_inverted_index.problem\nsizes | 91 |
| abstract_inverted_index.simultaneously | 43 |
| abstract_inverted_index.training.\nBut | 31 |
| abstract_inverted_index.any\nadditional | 101 |
| abstract_inverted_index.hardware\nwhile | 81 |
| abstract_inverted_index.these\nchallenges | 23 |
| abstract_inverted_index.GDWS\nconvolutions | 120 |
| abstract_inverted_index.the\neffectiveness | 128 |
| abstract_inverted_index.(frames-per-second) | 39 |
| abstract_inverted_index.ImageNet\ndatasets. | 138 |
| abstract_inverted_index.computational/storage | 9 |
| abstract_inverted_index.dramatically\nimproves | 71 |
| abstract_inverted_index.convolution\napproximator | 112 |
| abstract_inverted_index.universal,\npost-training | 63 |
| abstract_inverted_index.adversarial\nperturbations. | 15, 47 |
| abstract_inverted_index.Generalized\nDepthwise-Separable | 57 |
| abstract_inverted_index.https://github.com/hsndbk4/GDWS.\n | 145 |
| cited_by_percentile_year.max | 96 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile.value | 0.66690644 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |