PP-LCNet: A Lightweight CPU Convolutional Neural Network Article Swipe
Cheng Cui
,
Tingquan Gao
,
Shengyu Wei
,
Yuning Du
,
Ruoyu Guo
,
Shuilong Dong
,
Bin Lu
,
Ying Zhou
,
Xueying Lv
,
Qiwen Liu
,
Xiaoguang Hu
,
Dianhai Yu
,
Yanjun Ma
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.15099
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.15099
We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while the latency is almost constant. With these improvements, the accuracy of PP-LCNet can greatly surpass the previous network structure with the same inference time for classification. As shown in Figure 1, it outperforms the most state-of-the-art models. And for downstream tasks of computer vision, it also performs very well, such as object detection, semantic segmentation, etc. All our experiments are implemented based on PaddlePaddle. Code and pretrained models are available at PaddleClas.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2109.15099
- https://arxiv.org/pdf/2109.15099
- OA Status
- green
- Cited By
- 95
- References
- 31
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3201816303
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3201816303Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2109.15099Digital Object Identifier
- Title
-
PP-LCNet: A Lightweight CPU Convolutional Neural NetworkWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-09-17Full publication date if available
- Authors
-
Cheng Cui, Tingquan Gao, Shengyu Wei, Yuning Du, Ruoyu Guo, Shuilong Dong, Bin Lu, Ying Zhou, Xueying Lv, Qiwen Liu, Xiaoguang Hu, Dianhai Yu, Yanjun MaList of authors in order
- Landing page
-
https://arxiv.org/abs/2109.15099Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2109.15099Direct 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/2109.15099Direct OA link when available
- Concepts
-
Convolutional neural network, Computer science, Artificial intelligenceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
95Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 16, 2024: 29, 2023: 33, 2022: 16, 2021: 1Per-year citation counts (last 5 years)
- References (count)
-
31Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3201816303 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2109.15099 |
| ids.doi | https://doi.org/10.48550/arxiv.2109.15099 |
| ids.mag | 3201816303 |
| ids.openalex | https://openalex.org/W3201816303 |
| fwci | |
| type | preprint |
| title | PP-LCNet: A Lightweight CPU Convolutional Neural Network |
| 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 | 0.9998000264167786 |
| 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/T10320 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9977999925613403 |
| 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 | Neural Networks and Applications |
| topics[2].id | https://openalex.org/T12676 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9976000189781189 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Machine Learning and ELM |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C81363708 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8603521585464478 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[0].display_name | Convolutional neural network |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6220628023147583 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.2665140628814697 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| keywords[0].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[0].score | 0.8603521585464478 |
| keywords[0].display_name | Convolutional neural network |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6220628023147583 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.2665140628814697 |
| keywords[2].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2109.15099 |
| 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/2109.15099 |
| 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/2109.15099 |
| locations[1].id | doi:10.48550/arxiv.2109.15099 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2109.15099 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102068162 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Cheng Cui |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I98301712 |
| authorships[0].affiliations[0].raw_affiliation_string | Baidu#TAB# |
| authorships[0].institutions[0].id | https://openalex.org/I98301712 |
| authorships[0].institutions[0].ror | https://ror.org/03vs3wt56 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I98301712 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Baidu (China) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Cheng Cui |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Baidu#TAB# |
| authorships[1].author.id | https://openalex.org/A5015786581 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Tingquan Gao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Tingquan Gao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5079619506 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Shengyu Wei |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Shengyu Wei |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5010944460 |
| authorships[3].author.orcid | https://orcid.org/0009-0007-4995-5472 |
| authorships[3].author.display_name | Yuning Du |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yuning Du |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5083640035 |
| authorships[4].author.orcid | https://orcid.org/0009-0000-0335-4259 |
| authorships[4].author.display_name | Ruoyu Guo |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ruoyu Guo |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5108244490 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Shuilong Dong |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Shuilong Dong |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100715995 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-7962-2333 |
| authorships[6].author.display_name | Bin Lu |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Bin Lu |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5056431851 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-7678-5703 |
| authorships[7].author.display_name | Ying Zhou |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Ying Zhou |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5053775045 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Xueying Lv |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Xueying Lv |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5037089484 |
| authorships[9].author.orcid | https://orcid.org/0000-0003-2776-9162 |
| authorships[9].author.display_name | Qiwen Liu |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Qiwen Liu |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5100602787 |
| authorships[10].author.orcid | https://orcid.org/0000-0002-8092-6246 |
| authorships[10].author.display_name | Xiaoguang Hu |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Xiaoguang Hu |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5084155236 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-0163-2603 |
| authorships[11].author.display_name | Dianhai Yu |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Dianhai Yu |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5047724561 |
| authorships[12].author.orcid | https://orcid.org/0000-0002-1232-6142 |
| authorships[12].author.display_name | Yanjun Ma |
| authorships[12].author_position | last |
| authorships[12].raw_author_name | Yanjun Ma |
| authorships[12].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/2109.15099 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | PP-LCNet: A Lightweight CPU Convolutional Neural Network |
| 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 | 0.9998000264167786 |
| 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/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W2358668433, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4293226380, https://openalex.org/W2382290278, https://openalex.org/W2478288626, https://openalex.org/W4391913857 |
| cited_by_count | 95 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 16 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 29 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 33 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 16 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2109.15099 |
| 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/2109.15099 |
| 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/2109.15099 |
| primary_location.id | pmh:oai:arXiv.org:2109.15099 |
| 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/2109.15099 |
| 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/2109.15099 |
| publication_date | 2021-09-17 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2163605009, https://openalex.org/W2963420686, https://openalex.org/W2963037463, https://openalex.org/W2994749257, https://openalex.org/W2996844762, https://openalex.org/W2982083293, https://openalex.org/W2108598243, https://openalex.org/W2340897893, https://openalex.org/W2962858109, https://openalex.org/W3098389804, https://openalex.org/W2156303437, https://openalex.org/W3034528892, https://openalex.org/W2412782625, https://openalex.org/W3035414587, https://openalex.org/W2963125010, https://openalex.org/W2553303224, https://openalex.org/W1686810756, https://openalex.org/W2967733054, https://openalex.org/W2742165450, https://openalex.org/W1861492603, https://openalex.org/W2630837129, https://openalex.org/W2946948417, https://openalex.org/W2990211757, https://openalex.org/W2194775991, https://openalex.org/W2612445135, https://openalex.org/W2963163009, https://openalex.org/W2097117768, https://openalex.org/W2560622558, https://openalex.org/W3135680385, https://openalex.org/W2883780447, https://openalex.org/W2953106684 |
| referenced_works_count | 31 |
| abstract_inverted_index.a | 2 |
| abstract_inverted_index.1, | 64 |
| abstract_inverted_index.As | 60 |
| abstract_inverted_index.We | 0 |
| abstract_inverted_index.as | 84 |
| abstract_inverted_index.at | 104 |
| abstract_inverted_index.in | 62 |
| abstract_inverted_index.is | 36 |
| abstract_inverted_index.it | 65, 78 |
| abstract_inverted_index.of | 18, 44, 75 |
| abstract_inverted_index.on | 7, 21, 96 |
| abstract_inverted_index.All | 90 |
| abstract_inverted_index.And | 71 |
| abstract_inverted_index.CPU | 4 |
| abstract_inverted_index.and | 99 |
| abstract_inverted_index.are | 93, 102 |
| abstract_inverted_index.can | 29, 46 |
| abstract_inverted_index.for | 58, 72 |
| abstract_inverted_index.our | 91 |
| abstract_inverted_index.the | 8, 16, 34, 42, 49, 54, 67 |
| abstract_inverted_index.Code | 98 |
| abstract_inverted_index.This | 24 |
| abstract_inverted_index.With | 39 |
| abstract_inverted_index.also | 79 |
| abstract_inverted_index.etc. | 89 |
| abstract_inverted_index.most | 68 |
| abstract_inverted_index.same | 55 |
| abstract_inverted_index.such | 83 |
| abstract_inverted_index.time | 57 |
| abstract_inverted_index.very | 81 |
| abstract_inverted_index.with | 53 |
| abstract_inverted_index.based | 6, 95 |
| abstract_inverted_index.lists | 26 |
| abstract_inverted_index.named | 12 |
| abstract_inverted_index.paper | 25 |
| abstract_inverted_index.shown | 61 |
| abstract_inverted_index.tasks | 74 |
| abstract_inverted_index.these | 40 |
| abstract_inverted_index.well, | 82 |
| abstract_inverted_index.which | 14, 28 |
| abstract_inverted_index.while | 33 |
| abstract_inverted_index.Figure | 63 |
| abstract_inverted_index.MKLDNN | 9 |
| abstract_inverted_index.almost | 37 |
| abstract_inverted_index.models | 20, 101 |
| abstract_inverted_index.object | 85 |
| abstract_inverted_index.tasks. | 23 |
| abstract_inverted_index.greatly | 47 |
| abstract_inverted_index.improve | 30 |
| abstract_inverted_index.latency | 35 |
| abstract_inverted_index.models. | 70 |
| abstract_inverted_index.network | 5, 31, 51 |
| abstract_inverted_index.propose | 1 |
| abstract_inverted_index.surpass | 48 |
| abstract_inverted_index.vision, | 77 |
| abstract_inverted_index.PP-LCNet | 45 |
| abstract_inverted_index.accuracy | 32, 43 |
| abstract_inverted_index.computer | 76 |
| abstract_inverted_index.improves | 15 |
| abstract_inverted_index.multiple | 22 |
| abstract_inverted_index.performs | 80 |
| abstract_inverted_index.previous | 50 |
| abstract_inverted_index.semantic | 87 |
| abstract_inverted_index.PP-LCNet, | 13 |
| abstract_inverted_index.available | 103 |
| abstract_inverted_index.constant. | 38 |
| abstract_inverted_index.inference | 56 |
| abstract_inverted_index.strategy, | 11 |
| abstract_inverted_index.structure | 52 |
| abstract_inverted_index.detection, | 86 |
| abstract_inverted_index.downstream | 73 |
| abstract_inverted_index.pretrained | 100 |
| abstract_inverted_index.PaddleClas. | 105 |
| abstract_inverted_index.experiments | 92 |
| abstract_inverted_index.implemented | 94 |
| abstract_inverted_index.lightweight | 3, 19 |
| abstract_inverted_index.outperforms | 66 |
| abstract_inverted_index.performance | 17 |
| abstract_inverted_index.acceleration | 10 |
| abstract_inverted_index.technologies | 27 |
| abstract_inverted_index.PaddlePaddle. | 97 |
| abstract_inverted_index.improvements, | 41 |
| abstract_inverted_index.segmentation, | 88 |
| abstract_inverted_index.classification. | 59 |
| abstract_inverted_index.state-of-the-art | 69 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 13 |
| citation_normalized_percentile |