VLCP: A High-Performance FPGA-based CNN Accelerator with Vector-level Cluster Pruning Article Swipe
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3611315.3633271
Convolutional neural networks (CNNs) are widely used in computer vision, natural language processing, and other application scenarios. But deploying CNNs at the edge is challenging due to their large number of parameters. Pruning is a solution that can effectively reduce the number of parameters and off-chip memory accesses. However, high sparsity unstructured pruning is not hardware-friendly, while structured pruning has low compression efficiency. As a result, vector-level pruning, with a coarser granularity, is a promising alternative that balances pruning performance and hardware-friendliness. In this paper, a hardware-oriented vector-level pruning strategy is proposed based on the CNN vector distribution properties. By expanding the dynamic range of vector groups, more important weights can be preserved without sacrificing accuracy. When applied to the VGG-16 and ResNet-18 models on the ImageNet dataset, the proposed strategy achieved 10.93 × and 10.17 × compression ratios in convolutional layers with a 66% reduction in computation and an acceptable drop in top-1 accuracy. Furthermore, the proposed pruning scheme achieves a remarkable performance of 188 FPS on the VCU118 evaluation board, demonstrating its compatibility with hardware. Compared to the state-of-the-art, the proposed strategy reaches 69% performance improvement and up to 2.8 × higher LUT efficiency.
Related Topics
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3611315.3633271
- https://dl.acm.org/doi/pdf/10.1145/3611315.3633271
- OA Status
- gold
- Cited By
- 1
- References
- 11
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4391236123
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4391236123Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3611315.3633271Digital Object Identifier
- Title
-
VLCP: A High-Performance FPGA-based CNN Accelerator with Vector-level Cluster PruningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-12-18Full publication date if available
- Authors
-
Shuo Ran, Bi Wu, Ke Chen, Weiqiang LiuList of authors in order
- Landing page
-
https://doi.org/10.1145/3611315.3633271Publisher landing page
- PDF URL
-
https://dl.acm.org/doi/pdf/10.1145/3611315.3633271Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://dl.acm.org/doi/pdf/10.1145/3611315.3633271Direct OA link when available
- Concepts
-
Computer science, Pruning, Convolutional neural network, Parallel computing, Computation, Field-programmable gate array, Reduction (mathematics), Granularity, Artificial intelligence, Pattern recognition (psychology), Computer engineering, Computer hardware, Algorithm, Mathematics, Agronomy, Geometry, Operating system, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- References (count)
-
11Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4391236123 |
|---|---|
| doi | https://doi.org/10.1145/3611315.3633271 |
| ids.doi | https://doi.org/10.1145/3611315.3633271 |
| ids.openalex | https://openalex.org/W4391236123 |
| fwci | 0.18196834 |
| type | article |
| title | VLCP: A High-Performance FPGA-based CNN Accelerator with Vector-level Cluster Pruning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 6 |
| biblio.first_page | 1 |
| 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 | 1.0 |
| 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 | 0.9975000023841858 |
| 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 | 0.994700014591217 |
| 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 | 0.8010781407356262 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C108010975 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7411351799964905 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[1].display_name | Pruning |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.704461395740509 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C173608175 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5180166363716125 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[3].display_name | Parallel computing |
| concepts[4].id | https://openalex.org/C45374587 |
| concepts[4].level | 2 |
| concepts[4].score | 0.47610554099082947 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[4].display_name | Computation |
| concepts[5].id | https://openalex.org/C42935608 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4427911043167114 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q190411 |
| concepts[5].display_name | Field-programmable gate array |
| concepts[6].id | https://openalex.org/C111335779 |
| concepts[6].level | 2 |
| concepts[6].score | 0.42468178272247314 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3454686 |
| concepts[6].display_name | Reduction (mathematics) |
| concepts[7].id | https://openalex.org/C177774035 |
| concepts[7].level | 2 |
| concepts[7].score | 0.41091856360435486 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1246948 |
| concepts[7].display_name | Granularity |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.40939122438430786 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C153180895 |
| concepts[9].level | 2 |
| concepts[9].score | 0.3642593026161194 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[9].display_name | Pattern recognition (psychology) |
| concepts[10].id | https://openalex.org/C113775141 |
| concepts[10].level | 1 |
| concepts[10].score | 0.34393781423568726 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[10].display_name | Computer engineering |
| concepts[11].id | https://openalex.org/C9390403 |
| concepts[11].level | 1 |
| concepts[11].score | 0.30885618925094604 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q3966 |
| concepts[11].display_name | Computer hardware |
| concepts[12].id | https://openalex.org/C11413529 |
| concepts[12].level | 1 |
| concepts[12].score | 0.30136728286743164 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[12].display_name | Algorithm |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.1025090217590332 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C6557445 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q173113 |
| concepts[14].display_name | Agronomy |
| concepts[15].id | https://openalex.org/C2524010 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[15].display_name | Geometry |
| concepts[16].id | https://openalex.org/C111919701 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[16].display_name | Operating system |
| concepts[17].id | https://openalex.org/C86803240 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[17].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8010781407356262 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/pruning |
| keywords[1].score | 0.7411351799964905 |
| keywords[1].display_name | Pruning |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.704461395740509 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/parallel-computing |
| keywords[3].score | 0.5180166363716125 |
| keywords[3].display_name | Parallel computing |
| keywords[4].id | https://openalex.org/keywords/computation |
| keywords[4].score | 0.47610554099082947 |
| keywords[4].display_name | Computation |
| keywords[5].id | https://openalex.org/keywords/field-programmable-gate-array |
| keywords[5].score | 0.4427911043167114 |
| keywords[5].display_name | Field-programmable gate array |
| keywords[6].id | https://openalex.org/keywords/reduction |
| keywords[6].score | 0.42468178272247314 |
| keywords[6].display_name | Reduction (mathematics) |
| keywords[7].id | https://openalex.org/keywords/granularity |
| keywords[7].score | 0.41091856360435486 |
| keywords[7].display_name | Granularity |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.40939122438430786 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/pattern-recognition |
| keywords[9].score | 0.3642593026161194 |
| keywords[9].display_name | Pattern recognition (psychology) |
| keywords[10].id | https://openalex.org/keywords/computer-engineering |
| keywords[10].score | 0.34393781423568726 |
| keywords[10].display_name | Computer engineering |
| keywords[11].id | https://openalex.org/keywords/computer-hardware |
| keywords[11].score | 0.30885618925094604 |
| keywords[11].display_name | Computer hardware |
| keywords[12].id | https://openalex.org/keywords/algorithm |
| keywords[12].score | 0.30136728286743164 |
| keywords[12].display_name | Algorithm |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.1025090217590332 |
| keywords[13].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.1145/3611315.3633271 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | https://dl.acm.org/doi/pdf/10.1145/3611315.3633271 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the 18th ACM International Symposium on Nanoscale Architectures |
| locations[0].landing_page_url | https://doi.org/10.1145/3611315.3633271 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5093790543 |
| authorships[0].author.orcid | https://orcid.org/0009-0008-8124-6315 |
| authorships[0].author.display_name | Shuo Ran |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I9842412 |
| authorships[0].affiliations[0].raw_affiliation_string | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[0].institutions[0].id | https://openalex.org/I9842412 |
| authorships[0].institutions[0].ror | https://ror.org/01scyh794 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I9842412 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Nanjing University of Aeronautics and Astronautics |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shuo Ran |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[1].author.id | https://openalex.org/A5090343850 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9972-0478 |
| authorships[1].author.display_name | Bi Wu |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I9842412 |
| authorships[1].affiliations[0].raw_affiliation_string | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[1].institutions[0].id | https://openalex.org/I9842412 |
| authorships[1].institutions[0].ror | https://ror.org/01scyh794 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I9842412 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Nanjing University of Aeronautics and Astronautics |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Bi Wu |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[2].author.id | https://openalex.org/A5100452020 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0981-3166 |
| authorships[2].author.display_name | Ke Chen |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I9842412 |
| authorships[2].affiliations[0].raw_affiliation_string | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[2].institutions[0].id | https://openalex.org/I9842412 |
| authorships[2].institutions[0].ror | https://ror.org/01scyh794 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I9842412 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Nanjing University of Aeronautics and Astronautics |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ke Chen |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[3].author.id | https://openalex.org/A5023734605 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8398-8648 |
| authorships[3].author.display_name | Weiqiang Liu |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I9842412 |
| authorships[3].affiliations[0].raw_affiliation_string | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| authorships[3].institutions[0].id | https://openalex.org/I9842412 |
| authorships[3].institutions[0].ror | https://ror.org/01scyh794 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I9842412 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Nanjing University of Aeronautics and Astronautics |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Weiqiang Liu |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | College of Electronic Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics (NUAA), China |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://dl.acm.org/doi/pdf/10.1145/3611315.3633271 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | VLCP: A High-Performance FPGA-based CNN Accelerator with Vector-level Cluster Pruning |
| has_fulltext | True |
| 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 | 1.0 |
| 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/W2931688134, https://openalex.org/W2377919138, https://openalex.org/W2378857091, https://openalex.org/W103652678, https://openalex.org/W4226090359, https://openalex.org/W2059697060, https://openalex.org/W936373746, https://openalex.org/W2975817033, https://openalex.org/W4256502920, https://openalex.org/W4382701072 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1145/3611315.3633271 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3611315.3633271 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the 18th ACM International Symposium on Nanoscale Architectures |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3611315.3633271 |
| primary_location.id | doi:10.1145/3611315.3633271 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3611315.3633271 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the 18th ACM International Symposium on Nanoscale Architectures |
| primary_location.landing_page_url | https://doi.org/10.1145/3611315.3633271 |
| publication_date | 2023-12-18 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W2963122961, https://openalex.org/W3198625877, https://openalex.org/W2949619037, https://openalex.org/W2736953746, https://openalex.org/W2963037989, https://openalex.org/W4283693604, https://openalex.org/W2604319603, https://openalex.org/W3080754330, https://openalex.org/W2886934227, https://openalex.org/W3093799822, https://openalex.org/W3038838661 |
| referenced_works_count | 11 |
| abstract_inverted_index.a | 34, 64, 69, 73, 85, 143, 161 |
| abstract_inverted_index.As | 63 |
| abstract_inverted_index.By | 99 |
| abstract_inverted_index.In | 82 |
| abstract_inverted_index.an | 149 |
| abstract_inverted_index.at | 20 |
| abstract_inverted_index.be | 111 |
| abstract_inverted_index.in | 7, 139, 146, 152 |
| abstract_inverted_index.is | 23, 33, 53, 72, 90 |
| abstract_inverted_index.of | 30, 42, 104, 164 |
| abstract_inverted_index.on | 93, 124, 167 |
| abstract_inverted_index.to | 26, 118, 178, 190 |
| abstract_inverted_index.up | 189 |
| abstract_inverted_index.× | 133, 136, 192 |
| abstract_inverted_index.188 | 165 |
| abstract_inverted_index.2.8 | 191 |
| abstract_inverted_index.66% | 144 |
| abstract_inverted_index.69% | 185 |
| abstract_inverted_index.But | 17 |
| abstract_inverted_index.CNN | 95 |
| abstract_inverted_index.FPS | 166 |
| abstract_inverted_index.LUT | 194 |
| abstract_inverted_index.and | 13, 44, 80, 121, 134, 148, 188 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.can | 37, 110 |
| abstract_inverted_index.due | 25 |
| abstract_inverted_index.has | 59 |
| abstract_inverted_index.its | 173 |
| abstract_inverted_index.low | 60 |
| abstract_inverted_index.not | 54 |
| abstract_inverted_index.the | 21, 40, 94, 101, 119, 125, 128, 156, 168, 179, 181 |
| abstract_inverted_index.CNNs | 19 |
| abstract_inverted_index.When | 116 |
| abstract_inverted_index.drop | 151 |
| abstract_inverted_index.edge | 22 |
| abstract_inverted_index.high | 49 |
| abstract_inverted_index.more | 107 |
| abstract_inverted_index.that | 36, 76 |
| abstract_inverted_index.this | 83 |
| abstract_inverted_index.used | 6 |
| abstract_inverted_index.with | 68, 142, 175 |
| abstract_inverted_index.10.17 | 135 |
| abstract_inverted_index.10.93 | 132 |
| abstract_inverted_index.based | 92 |
| abstract_inverted_index.large | 28 |
| abstract_inverted_index.other | 14 |
| abstract_inverted_index.range | 103 |
| abstract_inverted_index.their | 27 |
| abstract_inverted_index.top-1 | 153 |
| abstract_inverted_index.while | 56 |
| abstract_inverted_index.(CNNs) | 3 |
| abstract_inverted_index.VCU118 | 169 |
| abstract_inverted_index.VGG-16 | 120 |
| abstract_inverted_index.board, | 171 |
| abstract_inverted_index.higher | 193 |
| abstract_inverted_index.layers | 141 |
| abstract_inverted_index.memory | 46 |
| abstract_inverted_index.models | 123 |
| abstract_inverted_index.neural | 1 |
| abstract_inverted_index.number | 29, 41 |
| abstract_inverted_index.paper, | 84 |
| abstract_inverted_index.ratios | 138 |
| abstract_inverted_index.reduce | 39 |
| abstract_inverted_index.scheme | 159 |
| abstract_inverted_index.vector | 96, 105 |
| abstract_inverted_index.widely | 5 |
| abstract_inverted_index.Pruning | 32 |
| abstract_inverted_index.applied | 117 |
| abstract_inverted_index.coarser | 70 |
| abstract_inverted_index.dynamic | 102 |
| abstract_inverted_index.groups, | 106 |
| abstract_inverted_index.natural | 10 |
| abstract_inverted_index.pruning | 52, 58, 78, 88, 158 |
| abstract_inverted_index.reaches | 184 |
| abstract_inverted_index.result, | 65 |
| abstract_inverted_index.vision, | 9 |
| abstract_inverted_index.weights | 109 |
| abstract_inverted_index.without | 113 |
| abstract_inverted_index.Compared | 177 |
| abstract_inverted_index.However, | 48 |
| abstract_inverted_index.ImageNet | 126 |
| abstract_inverted_index.achieved | 131 |
| abstract_inverted_index.achieves | 160 |
| abstract_inverted_index.balances | 77 |
| abstract_inverted_index.computer | 8 |
| abstract_inverted_index.dataset, | 127 |
| abstract_inverted_index.language | 11 |
| abstract_inverted_index.networks | 2 |
| abstract_inverted_index.off-chip | 45 |
| abstract_inverted_index.proposed | 91, 129, 157, 182 |
| abstract_inverted_index.pruning, | 67 |
| abstract_inverted_index.solution | 35 |
| abstract_inverted_index.sparsity | 50 |
| abstract_inverted_index.strategy | 89, 130, 183 |
| abstract_inverted_index.ResNet-18 | 122 |
| abstract_inverted_index.accesses. | 47 |
| abstract_inverted_index.accuracy. | 115, 154 |
| abstract_inverted_index.deploying | 18 |
| abstract_inverted_index.expanding | 100 |
| abstract_inverted_index.hardware. | 176 |
| abstract_inverted_index.important | 108 |
| abstract_inverted_index.preserved | 112 |
| abstract_inverted_index.promising | 74 |
| abstract_inverted_index.reduction | 145 |
| abstract_inverted_index.acceptable | 150 |
| abstract_inverted_index.evaluation | 170 |
| abstract_inverted_index.parameters | 43 |
| abstract_inverted_index.remarkable | 162 |
| abstract_inverted_index.scenarios. | 16 |
| abstract_inverted_index.structured | 57 |
| abstract_inverted_index.alternative | 75 |
| abstract_inverted_index.application | 15 |
| abstract_inverted_index.challenging | 24 |
| abstract_inverted_index.compression | 61, 137 |
| abstract_inverted_index.computation | 147 |
| abstract_inverted_index.effectively | 38 |
| abstract_inverted_index.efficiency. | 62, 195 |
| abstract_inverted_index.improvement | 187 |
| abstract_inverted_index.parameters. | 31 |
| abstract_inverted_index.performance | 79, 163, 186 |
| abstract_inverted_index.processing, | 12 |
| abstract_inverted_index.properties. | 98 |
| abstract_inverted_index.sacrificing | 114 |
| abstract_inverted_index.Furthermore, | 155 |
| abstract_inverted_index.distribution | 97 |
| abstract_inverted_index.granularity, | 71 |
| abstract_inverted_index.unstructured | 51 |
| abstract_inverted_index.vector-level | 66, 87 |
| abstract_inverted_index.Convolutional | 0 |
| abstract_inverted_index.compatibility | 174 |
| abstract_inverted_index.convolutional | 140 |
| abstract_inverted_index.demonstrating | 172 |
| abstract_inverted_index.hardware-oriented | 86 |
| abstract_inverted_index.state-of-the-art, | 180 |
| abstract_inverted_index.hardware-friendly, | 55 |
| abstract_inverted_index.hardware-friendliness. | 81 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.49921643 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |