DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural\n Networks Article Swipe
Hassan Dbouk
,
Hetul Sanghvi
,
Mahesh Mehendale
,
Naresh R. Shanbhag
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2007.09818
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2007.09818
Deep neural networks have achieved state-of-the art performance on various\ncomputer vision tasks. However, their deployment on resource-constrained\ndevices has been hindered due to their high computational and storage\ncomplexity. While various complexity reduction techniques, such as lightweight\nnetwork architecture design and parameter quantization, have been successful in\nreducing the cost of implementing these networks, these methods have often been\nconsidered orthogonal. In reality, existing quantization techniques fail to\nreplicate their success on lightweight architectures such as MobileNet. To this\nend, we present a novel fully differentiable non-uniform quantizer that can be\nseamlessly mapped onto efficient ternary-based dot product engines. We conduct\ncomprehensive experiments on CIFAR-10, ImageNet, and Visual Wake Words\ndatasets. The proposed quantizer (DBQ) successfully tackles the daunting task\nof aggressively quantizing lightweight networks such as MobileNetV1,\nMobileNetV2, and ShuffleNetV2. DBQ achieves state-of-the art results with\nminimal training overhead and provides the best (pareto-optimal)\naccuracy-complexity trade-off.\n
Related Topics
Concepts
Computer science
Differentiable function
Artificial neural network
Deep neural networks
Deep learning
Quantization (signal processing)
Overhead (engineering)
Benchmark (surveying)
Replicate
Computer engineering
Artificial intelligence
Modular design
Distributed computing
Algorithm
Operating system
Geography
Mathematics
Statistics
Geodesy
Mathematical analysis
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2007.09818
- https://arxiv.org/pdf/2007.09818
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287712612
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287712612Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2007.09818Digital Object Identifier
- Title
-
DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural\n NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-07-19Full publication date if available
- Authors
-
Hassan Dbouk, Hetul Sanghvi, Mahesh Mehendale, Naresh R. ShanbhagList of authors in order
- Landing page
-
https://arxiv.org/abs/2007.09818Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2007.09818Direct 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/2007.09818Direct OA link when available
- Concepts
-
Computer science, Differentiable function, Artificial neural network, Deep neural networks, Deep learning, Quantization (signal processing), Overhead (engineering), Benchmark (surveying), Replicate, Computer engineering, Artificial intelligence, Modular design, Distributed computing, Algorithm, Operating system, Geography, Mathematics, Statistics, Geodesy, Mathematical analysisTop 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/W4287712612 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2007.09818 |
| ids.openalex | https://openalex.org/W4287712612 |
| fwci | 0.0 |
| type | preprint |
| title | DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural\n Networks |
| 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/T10627 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9970999956130981 |
| 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 | Advanced Image and Video Retrieval Techniques |
| topics[2].id | https://openalex.org/T12702 |
| topics[2].field.id | https://openalex.org/fields/28 |
| topics[2].field.display_name | Neuroscience |
| topics[2].score | 0.9965999722480774 |
| topics[2].domain.id | https://openalex.org/domains/1 |
| topics[2].domain.display_name | Life Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2808 |
| topics[2].subfield.display_name | Neurology |
| topics[2].display_name | Brain Tumor Detection and Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7451014518737793 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C202615002 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6334065198898315 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q783507 |
| concepts[1].display_name | Differentiable function |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.566892147064209 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C2984842247 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5567980408668518 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[3].display_name | Deep neural networks |
| concepts[4].id | https://openalex.org/C108583219 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5333554744720459 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[4].display_name | Deep learning |
| concepts[5].id | https://openalex.org/C28855332 |
| concepts[5].level | 2 |
| concepts[5].score | 0.52077716588974 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q198099 |
| concepts[5].display_name | Quantization (signal processing) |
| concepts[6].id | https://openalex.org/C2779960059 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4886811077594757 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7113681 |
| concepts[6].display_name | Overhead (engineering) |
| concepts[7].id | https://openalex.org/C185798385 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4871194362640381 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[7].display_name | Benchmark (surveying) |
| concepts[8].id | https://openalex.org/C2781162219 |
| concepts[8].level | 2 |
| concepts[8].score | 0.45196470618247986 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q26250693 |
| concepts[8].display_name | Replicate |
| concepts[9].id | https://openalex.org/C113775141 |
| concepts[9].level | 1 |
| concepts[9].score | 0.45166802406311035 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[9].display_name | Computer engineering |
| concepts[10].id | https://openalex.org/C154945302 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4220477044582367 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[10].display_name | Artificial intelligence |
| concepts[11].id | https://openalex.org/C101468663 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4149400591850281 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1620158 |
| concepts[11].display_name | Modular design |
| concepts[12].id | https://openalex.org/C120314980 |
| concepts[12].level | 1 |
| concepts[12].score | 0.4110887050628662 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q180634 |
| concepts[12].display_name | Distributed computing |
| concepts[13].id | https://openalex.org/C11413529 |
| concepts[13].level | 1 |
| concepts[13].score | 0.2034519612789154 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[13].display_name | Algorithm |
| concepts[14].id | https://openalex.org/C111919701 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[14].display_name | Operating system |
| concepts[15].id | https://openalex.org/C205649164 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[15].display_name | Geography |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| concepts[17].id | https://openalex.org/C105795698 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[17].display_name | Statistics |
| concepts[18].id | https://openalex.org/C13280743 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q131089 |
| concepts[18].display_name | Geodesy |
| concepts[19].id | https://openalex.org/C134306372 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[19].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7451014518737793 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/differentiable-function |
| keywords[1].score | 0.6334065198898315 |
| keywords[1].display_name | Differentiable function |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.566892147064209 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[3].score | 0.5567980408668518 |
| keywords[3].display_name | Deep neural networks |
| keywords[4].id | https://openalex.org/keywords/deep-learning |
| keywords[4].score | 0.5333554744720459 |
| keywords[4].display_name | Deep learning |
| keywords[5].id | https://openalex.org/keywords/quantization |
| keywords[5].score | 0.52077716588974 |
| keywords[5].display_name | Quantization (signal processing) |
| keywords[6].id | https://openalex.org/keywords/overhead |
| keywords[6].score | 0.4886811077594757 |
| keywords[6].display_name | Overhead (engineering) |
| keywords[7].id | https://openalex.org/keywords/benchmark |
| keywords[7].score | 0.4871194362640381 |
| keywords[7].display_name | Benchmark (surveying) |
| keywords[8].id | https://openalex.org/keywords/replicate |
| keywords[8].score | 0.45196470618247986 |
| keywords[8].display_name | Replicate |
| keywords[9].id | https://openalex.org/keywords/computer-engineering |
| keywords[9].score | 0.45166802406311035 |
| keywords[9].display_name | Computer engineering |
| keywords[10].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[10].score | 0.4220477044582367 |
| keywords[10].display_name | Artificial intelligence |
| keywords[11].id | https://openalex.org/keywords/modular-design |
| keywords[11].score | 0.4149400591850281 |
| keywords[11].display_name | Modular design |
| keywords[12].id | https://openalex.org/keywords/distributed-computing |
| keywords[12].score | 0.4110887050628662 |
| keywords[12].display_name | Distributed computing |
| keywords[13].id | https://openalex.org/keywords/algorithm |
| keywords[13].score | 0.2034519612789154 |
| keywords[13].display_name | Algorithm |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2007.09818 |
| 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/2007.09818 |
| 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/2007.09818 |
| 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/A5064188494 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Hetul Sanghvi |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sanghvi, Hetul |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5109238173 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Mahesh Mehendale |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Mehendale, Mahesh |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5057014407 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-4323-9164 |
| authorships[3].author.display_name | Naresh R. Shanbhag |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Shanbhag, Naresh |
| authorships[3].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/2007.09818 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-26T00:00:00 |
| display_name | DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural\n Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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/W4254851101, https://openalex.org/W3171007296, https://openalex.org/W22115721, https://openalex.org/W4205547277, https://openalex.org/W3204400881, https://openalex.org/W3214410901, https://openalex.org/W3204296682, https://openalex.org/W3183118997, https://openalex.org/W2917767146, https://openalex.org/W4285818394 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2007.09818 |
| 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/2007.09818 |
| 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/2007.09818 |
| primary_location.id | pmh:oai:arXiv.org:2007.09818 |
| 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/2007.09818 |
| 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/2007.09818 |
| publication_date | 2020-07-19 |
| publication_year | 2020 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 75 |
| abstract_inverted_index.In | 56 |
| abstract_inverted_index.To | 71 |
| abstract_inverted_index.We | 91 |
| abstract_inverted_index.as | 33, 69, 115 |
| abstract_inverted_index.of | 46 |
| abstract_inverted_index.on | 8, 15, 65, 94 |
| abstract_inverted_index.to | 21 |
| abstract_inverted_index.we | 73 |
| abstract_inverted_index.DBQ | 119 |
| abstract_inverted_index.The | 101 |
| abstract_inverted_index.and | 25, 37, 97, 117, 127 |
| abstract_inverted_index.art | 6, 122 |
| abstract_inverted_index.can | 82 |
| abstract_inverted_index.dot | 88 |
| abstract_inverted_index.due | 20 |
| abstract_inverted_index.has | 17 |
| abstract_inverted_index.the | 44, 107, 129 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.Wake | 99 |
| abstract_inverted_index.been | 18, 41 |
| abstract_inverted_index.best | 130 |
| abstract_inverted_index.cost | 45 |
| abstract_inverted_index.fail | 61 |
| abstract_inverted_index.have | 3, 40, 52 |
| abstract_inverted_index.high | 23 |
| abstract_inverted_index.onto | 85 |
| abstract_inverted_index.such | 32, 68, 114 |
| abstract_inverted_index.that | 81 |
| abstract_inverted_index.(DBQ) | 104 |
| abstract_inverted_index.While | 27 |
| abstract_inverted_index.fully | 77 |
| abstract_inverted_index.novel | 76 |
| abstract_inverted_index.often | 53 |
| abstract_inverted_index.their | 13, 22, 63 |
| abstract_inverted_index.these | 48, 50 |
| abstract_inverted_index.Visual | 98 |
| abstract_inverted_index.design | 36 |
| abstract_inverted_index.mapped | 84 |
| abstract_inverted_index.neural | 1 |
| abstract_inverted_index.tasks. | 11 |
| abstract_inverted_index.vision | 10 |
| abstract_inverted_index.methods | 51 |
| abstract_inverted_index.present | 74 |
| abstract_inverted_index.product | 89 |
| abstract_inverted_index.results | 123 |
| abstract_inverted_index.success | 64 |
| abstract_inverted_index.tackles | 106 |
| abstract_inverted_index.various | 28 |
| abstract_inverted_index.However, | 12 |
| abstract_inverted_index.achieved | 4 |
| abstract_inverted_index.achieves | 120 |
| abstract_inverted_index.daunting | 108 |
| abstract_inverted_index.engines. | 90 |
| abstract_inverted_index.existing | 58 |
| abstract_inverted_index.hindered | 19 |
| abstract_inverted_index.networks | 2, 113 |
| abstract_inverted_index.overhead | 126 |
| abstract_inverted_index.proposed | 102 |
| abstract_inverted_index.provides | 128 |
| abstract_inverted_index.reality, | 57 |
| abstract_inverted_index.task\nof | 109 |
| abstract_inverted_index.training | 125 |
| abstract_inverted_index.CIFAR-10, | 95 |
| abstract_inverted_index.ImageNet, | 96 |
| abstract_inverted_index.efficient | 86 |
| abstract_inverted_index.networks, | 49 |
| abstract_inverted_index.parameter | 38 |
| abstract_inverted_index.quantizer | 80, 103 |
| abstract_inverted_index.reduction | 30 |
| abstract_inverted_index.MobileNet. | 70 |
| abstract_inverted_index.complexity | 29 |
| abstract_inverted_index.deployment | 14 |
| abstract_inverted_index.quantizing | 111 |
| abstract_inverted_index.successful | 42 |
| abstract_inverted_index.techniques | 60 |
| abstract_inverted_index.this\nend, | 72 |
| abstract_inverted_index.experiments | 93 |
| abstract_inverted_index.lightweight | 66, 112 |
| abstract_inverted_index.non-uniform | 79 |
| abstract_inverted_index.orthogonal. | 55 |
| abstract_inverted_index.performance | 7 |
| abstract_inverted_index.techniques, | 31 |
| abstract_inverted_index.aggressively | 110 |
| abstract_inverted_index.architecture | 35 |
| abstract_inverted_index.implementing | 47 |
| abstract_inverted_index.in\nreducing | 43 |
| abstract_inverted_index.quantization | 59 |
| abstract_inverted_index.state-of-the | 5, 121 |
| abstract_inverted_index.successfully | 105 |
| abstract_inverted_index.trade-off.\n | 132 |
| abstract_inverted_index.ShuffleNetV2. | 118 |
| abstract_inverted_index.architectures | 67 |
| abstract_inverted_index.computational | 24 |
| abstract_inverted_index.quantization, | 39 |
| abstract_inverted_index.ternary-based | 87 |
| abstract_inverted_index.to\nreplicate | 62 |
| abstract_inverted_index.with\nminimal | 124 |
| abstract_inverted_index.be\nseamlessly | 83 |
| abstract_inverted_index.differentiable | 78 |
| abstract_inverted_index.Words\ndatasets. | 100 |
| abstract_inverted_index.been\nconsidered | 54 |
| abstract_inverted_index.various\ncomputer | 9 |
| abstract_inverted_index.lightweight\nnetwork | 34 |
| abstract_inverted_index.storage\ncomplexity. | 26 |
| abstract_inverted_index.conduct\ncomprehensive | 92 |
| abstract_inverted_index.MobileNetV1,\nMobileNetV2, | 116 |
| abstract_inverted_index.resource-constrained\ndevices | 16 |
| abstract_inverted_index.(pareto-optimal)\naccuracy-complexity | 131 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.24556043 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |