Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms Article Swipe
Wei Lou
,
Xun Lei
,
Amin Sabet
,
Jia Bi
,
Jonathon Hare
,
Geoff V. Merrett
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2105.03596
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2105.03596
Mobile and embedded platforms are increasingly required to efficiently execute computationally demanding DNNs across heterogeneous processing elements. At runtime, the available hardware resources to DNNs can vary considerably due to other concurrently running applications. The performance requirements of the applications could also change under different scenarios. To achieve the desired performance, dynamic DNNs have been proposed in which the number of channels/layers can be scaled in real time to meet different requirements under varying resource constraints. However, the training process of such dynamic DNNs can be costly, since platform-aware models of different deployment scenarios must be retrained to become dynamic. This paper proposes Dynamic-OFA, a novel dynamic DNN approach for state-of-the-art platform-aware NAS models (i.e. Once-for-all network (OFA)). Dynamic-OFA pre-samples a family of sub-networks from a static OFA backbone model, and contains a runtime manager to choose different sub-networks under different runtime environments. As such, Dynamic-OFA does not need the traditional dynamic DNN training pipeline. Compared to the state-of-the-art, our experimental results using ImageNet on a Jetson Xavier NX show that the approach is up to 3.5x (CPU), 2.4x (GPU) faster for similar ImageNet Top-1 accuracy, or 3.8% (CPU), 5.1% (GPU) higher accuracy at similar latency.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2105.03596
- https://arxiv.org/pdf/2105.03596
- OA Status
- green
- Cited By
- 4
- References
- 24
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3159321466
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3159321466Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2105.03596Digital Object Identifier
- Title
-
Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded PlatformsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-05-08Full publication date if available
- Authors
-
Wei Lou, Xun Lei, Amin Sabet, Jia Bi, Jonathon Hare, Geoff V. MerrettList of authors in order
- Landing page
-
https://arxiv.org/abs/2105.03596Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2105.03596Direct 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/2105.03596Direct OA link when available
- Concepts
-
Computer science, Pipeline (software), Latency (audio), Software deployment, Process (computing), State (computer science), Distributed computing, Embedded system, Real-time computing, Operating system, Algorithm, TelecommunicationsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
4Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2023: 3Per-year citation counts (last 5 years)
- References (count)
-
24Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3159321466 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2105.03596 |
| ids.doi | https://doi.org/10.48550/arxiv.2105.03596 |
| ids.mag | 3159321466 |
| ids.openalex | https://openalex.org/W3159321466 |
| fwci | |
| type | preprint |
| title | Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms |
| awards[0].id | https://openalex.org/G3496335909 |
| awards[0].funder_id | https://openalex.org/F4320334627 |
| awards[0].display_name | |
| awards[0].funder_award_id | EP/S030069/1 |
| awards[0].funder_display_name | Engineering and Physical Sciences Research Council |
| 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 | 0.9984999895095825 |
| 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/T10502 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9907000064849854 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Advanced Memory and Neural Computing |
| funders[0].id | https://openalex.org/F4320334627 |
| funders[0].ror | https://ror.org/0439y7842 |
| funders[0].display_name | Engineering and Physical Sciences Research Council |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8266890048980713 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C43521106 |
| concepts[1].level | 2 |
| concepts[1].score | 0.71197509765625 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2165493 |
| concepts[1].display_name | Pipeline (software) |
| concepts[2].id | https://openalex.org/C82876162 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6549471020698547 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17096504 |
| concepts[2].display_name | Latency (audio) |
| concepts[3].id | https://openalex.org/C105339364 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6122297644615173 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2297740 |
| concepts[3].display_name | Software deployment |
| concepts[4].id | https://openalex.org/C98045186 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5255619287490845 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[4].display_name | Process (computing) |
| concepts[5].id | https://openalex.org/C48103436 |
| concepts[5].level | 2 |
| concepts[5].score | 0.504400372505188 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q599031 |
| concepts[5].display_name | State (computer science) |
| concepts[6].id | https://openalex.org/C120314980 |
| concepts[6].level | 1 |
| concepts[6].score | 0.45858263969421387 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q180634 |
| concepts[6].display_name | Distributed computing |
| concepts[7].id | https://openalex.org/C149635348 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3996185064315796 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q193040 |
| concepts[7].display_name | Embedded system |
| concepts[8].id | https://openalex.org/C79403827 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33955684304237366 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3988 |
| concepts[8].display_name | Real-time computing |
| concepts[9].id | https://openalex.org/C111919701 |
| concepts[9].level | 1 |
| concepts[9].score | 0.15197765827178955 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[9].display_name | Operating system |
| concepts[10].id | https://openalex.org/C11413529 |
| concepts[10].level | 1 |
| concepts[10].score | 0.09180906414985657 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[10].display_name | Algorithm |
| concepts[11].id | https://openalex.org/C76155785 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[11].display_name | Telecommunications |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8266890048980713 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/pipeline |
| keywords[1].score | 0.71197509765625 |
| keywords[1].display_name | Pipeline (software) |
| keywords[2].id | https://openalex.org/keywords/latency |
| keywords[2].score | 0.6549471020698547 |
| keywords[2].display_name | Latency (audio) |
| keywords[3].id | https://openalex.org/keywords/software-deployment |
| keywords[3].score | 0.6122297644615173 |
| keywords[3].display_name | Software deployment |
| keywords[4].id | https://openalex.org/keywords/process |
| keywords[4].score | 0.5255619287490845 |
| keywords[4].display_name | Process (computing) |
| keywords[5].id | https://openalex.org/keywords/state |
| keywords[5].score | 0.504400372505188 |
| keywords[5].display_name | State (computer science) |
| keywords[6].id | https://openalex.org/keywords/distributed-computing |
| keywords[6].score | 0.45858263969421387 |
| keywords[6].display_name | Distributed computing |
| keywords[7].id | https://openalex.org/keywords/embedded-system |
| keywords[7].score | 0.3996185064315796 |
| keywords[7].display_name | Embedded system |
| keywords[8].id | https://openalex.org/keywords/real-time-computing |
| keywords[8].score | 0.33955684304237366 |
| keywords[8].display_name | Real-time computing |
| keywords[9].id | https://openalex.org/keywords/operating-system |
| keywords[9].score | 0.15197765827178955 |
| keywords[9].display_name | Operating system |
| keywords[10].id | https://openalex.org/keywords/algorithm |
| keywords[10].score | 0.09180906414985657 |
| keywords[10].display_name | Algorithm |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2105.03596 |
| 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/2105.03596 |
| 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/2105.03596 |
| locations[1].id | doi:10.48550/arxiv.2105.03596 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2105.03596 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5024492432 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2071-4081 |
| authorships[0].author.display_name | Wei Lou |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wei Lou |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5091490292 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5118-9294 |
| authorships[1].author.display_name | Xun Lei |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lei Xun |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5035478022 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2625-8344 |
| authorships[2].author.display_name | Amin Sabet |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Amin Sabet |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5087963759 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3773-3289 |
| authorships[3].author.display_name | Jia Bi |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jia Bi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5067505586 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-2921-4283 |
| authorships[4].author.display_name | Jonathon Hare |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jonathon Hare |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5001556143 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4980-3894 |
| authorships[5].author.display_name | Geoff V. Merrett |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Geoff V. Merrett |
| 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/2105.03596 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2021-05-10T00:00:00 |
| display_name | Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms |
| 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/W2770234245, https://openalex.org/W96612179, https://openalex.org/W4229499248, https://openalex.org/W2566006169, https://openalex.org/W2987774938, https://openalex.org/W4256492088, https://openalex.org/W632915154, https://openalex.org/W2055733372, https://openalex.org/W2954284861, https://openalex.org/W3036465205 |
| cited_by_count | 4 |
| 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 | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2105.03596 |
| 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/2105.03596 |
| 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/2105.03596 |
| primary_location.id | pmh:oai:arXiv.org:2105.03596 |
| 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/2105.03596 |
| 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/2105.03596 |
| publication_date | 2021-05-08 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2945558825, https://openalex.org/W2963766446, https://openalex.org/W2598097916, https://openalex.org/W2612445135, https://openalex.org/W2883780447, https://openalex.org/W2944779197, https://openalex.org/W2981698279, https://openalex.org/W3035204081, https://openalex.org/W2963918968, https://openalex.org/W2965658867, https://openalex.org/W2949941638, https://openalex.org/W2194775991, https://openalex.org/W3035251378, https://openalex.org/W2964259004, https://openalex.org/W2796438033, https://openalex.org/W3012511001, https://openalex.org/W2994749257, https://openalex.org/W2108598243, https://openalex.org/W2947681860, https://openalex.org/W3105260221, https://openalex.org/W2949117887, https://openalex.org/W2797480241, https://openalex.org/W3108411658, https://openalex.org/W3109154950 |
| referenced_works_count | 24 |
| abstract_inverted_index.a | 104, 120, 125, 132, 165 |
| abstract_inverted_index.As | 143 |
| abstract_inverted_index.At | 17 |
| abstract_inverted_index.NX | 168 |
| abstract_inverted_index.To | 46 |
| abstract_inverted_index.at | 193 |
| abstract_inverted_index.be | 63, 85, 95 |
| abstract_inverted_index.in | 56, 65 |
| abstract_inverted_index.is | 173 |
| abstract_inverted_index.of | 37, 60, 80, 90, 122 |
| abstract_inverted_index.on | 164 |
| abstract_inverted_index.or | 186 |
| abstract_inverted_index.to | 7, 23, 29, 68, 97, 135, 156, 175 |
| abstract_inverted_index.up | 174 |
| abstract_inverted_index.DNN | 107, 152 |
| abstract_inverted_index.NAS | 112 |
| abstract_inverted_index.OFA | 127 |
| abstract_inverted_index.The | 34 |
| abstract_inverted_index.and | 1, 130 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.can | 25, 62, 84 |
| abstract_inverted_index.due | 28 |
| abstract_inverted_index.for | 109, 181 |
| abstract_inverted_index.not | 147 |
| abstract_inverted_index.our | 159 |
| abstract_inverted_index.the | 19, 38, 48, 58, 77, 149, 157, 171 |
| abstract_inverted_index.2.4x | 178 |
| abstract_inverted_index.3.5x | 176 |
| abstract_inverted_index.3.8% | 187 |
| abstract_inverted_index.5.1% | 189 |
| abstract_inverted_index.DNNs | 12, 24, 52, 83 |
| abstract_inverted_index.This | 100 |
| abstract_inverted_index.also | 41 |
| abstract_inverted_index.been | 54 |
| abstract_inverted_index.does | 146 |
| abstract_inverted_index.from | 124 |
| abstract_inverted_index.have | 53 |
| abstract_inverted_index.meet | 69 |
| abstract_inverted_index.must | 94 |
| abstract_inverted_index.need | 148 |
| abstract_inverted_index.real | 66 |
| abstract_inverted_index.show | 169 |
| abstract_inverted_index.such | 81 |
| abstract_inverted_index.that | 170 |
| abstract_inverted_index.time | 67 |
| abstract_inverted_index.vary | 26 |
| abstract_inverted_index.(GPU) | 179, 190 |
| abstract_inverted_index.(i.e. | 114 |
| abstract_inverted_index.Top-1 | 184 |
| abstract_inverted_index.could | 40 |
| abstract_inverted_index.novel | 105 |
| abstract_inverted_index.other | 30 |
| abstract_inverted_index.paper | 101 |
| abstract_inverted_index.since | 87 |
| abstract_inverted_index.such, | 144 |
| abstract_inverted_index.under | 43, 72, 139 |
| abstract_inverted_index.using | 162 |
| abstract_inverted_index.which | 57 |
| abstract_inverted_index.(CPU), | 177, 188 |
| abstract_inverted_index.Jetson | 166 |
| abstract_inverted_index.Mobile | 0 |
| abstract_inverted_index.Xavier | 167 |
| abstract_inverted_index.across | 13 |
| abstract_inverted_index.become | 98 |
| abstract_inverted_index.change | 42 |
| abstract_inverted_index.choose | 136 |
| abstract_inverted_index.family | 121 |
| abstract_inverted_index.faster | 180 |
| abstract_inverted_index.higher | 191 |
| abstract_inverted_index.model, | 129 |
| abstract_inverted_index.models | 89, 113 |
| abstract_inverted_index.number | 59 |
| abstract_inverted_index.scaled | 64 |
| abstract_inverted_index.static | 126 |
| abstract_inverted_index.(OFA)). | 117 |
| abstract_inverted_index.achieve | 47 |
| abstract_inverted_index.costly, | 86 |
| abstract_inverted_index.desired | 49 |
| abstract_inverted_index.dynamic | 51, 82, 106, 151 |
| abstract_inverted_index.execute | 9 |
| abstract_inverted_index.manager | 134 |
| abstract_inverted_index.network | 116 |
| abstract_inverted_index.process | 79 |
| abstract_inverted_index.results | 161 |
| abstract_inverted_index.running | 32 |
| abstract_inverted_index.runtime | 133, 141 |
| abstract_inverted_index.similar | 182, 194 |
| abstract_inverted_index.varying | 73 |
| abstract_inverted_index.Compared | 155 |
| abstract_inverted_index.However, | 76 |
| abstract_inverted_index.ImageNet | 163, 183 |
| abstract_inverted_index.accuracy | 192 |
| abstract_inverted_index.approach | 108, 172 |
| abstract_inverted_index.backbone | 128 |
| abstract_inverted_index.contains | 131 |
| abstract_inverted_index.dynamic. | 99 |
| abstract_inverted_index.embedded | 2 |
| abstract_inverted_index.hardware | 21 |
| abstract_inverted_index.latency. | 195 |
| abstract_inverted_index.proposed | 55 |
| abstract_inverted_index.proposes | 102 |
| abstract_inverted_index.required | 6 |
| abstract_inverted_index.resource | 74 |
| abstract_inverted_index.runtime, | 18 |
| abstract_inverted_index.training | 78, 153 |
| abstract_inverted_index.accuracy, | 185 |
| abstract_inverted_index.available | 20 |
| abstract_inverted_index.demanding | 11 |
| abstract_inverted_index.different | 44, 70, 91, 137, 140 |
| abstract_inverted_index.elements. | 16 |
| abstract_inverted_index.pipeline. | 154 |
| abstract_inverted_index.platforms | 3 |
| abstract_inverted_index.resources | 22 |
| abstract_inverted_index.retrained | 96 |
| abstract_inverted_index.scenarios | 93 |
| abstract_inverted_index.deployment | 92 |
| abstract_inverted_index.processing | 15 |
| abstract_inverted_index.scenarios. | 45 |
| abstract_inverted_index.Dynamic-OFA | 118, 145 |
| abstract_inverted_index.efficiently | 8 |
| abstract_inverted_index.performance | 35 |
| abstract_inverted_index.pre-samples | 119 |
| abstract_inverted_index.traditional | 150 |
| abstract_inverted_index.Dynamic-OFA, | 103 |
| abstract_inverted_index.Once-for-all | 115 |
| abstract_inverted_index.applications | 39 |
| abstract_inverted_index.concurrently | 31 |
| abstract_inverted_index.considerably | 27 |
| abstract_inverted_index.constraints. | 75 |
| abstract_inverted_index.experimental | 160 |
| abstract_inverted_index.increasingly | 5 |
| abstract_inverted_index.performance, | 50 |
| abstract_inverted_index.requirements | 36, 71 |
| abstract_inverted_index.sub-networks | 123, 138 |
| abstract_inverted_index.applications. | 33 |
| abstract_inverted_index.environments. | 142 |
| abstract_inverted_index.heterogeneous | 14 |
| abstract_inverted_index.platform-aware | 88, 111 |
| abstract_inverted_index.channels/layers | 61 |
| abstract_inverted_index.computationally | 10 |
| abstract_inverted_index.state-of-the-art | 110 |
| abstract_inverted_index.state-of-the-art, | 158 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |