Improved Projection Learning for Lower Dimensional Feature Maps Article Swipe
Ilan Price
,
Jared Tanner
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2210.15170
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2210.15170
The requirement to repeatedly move large feature maps off- and on-chip during inference with convolutional neural networks (CNNs) imposes high costs in terms of both energy and time. In this work we explore an improved method for compressing all feature maps of pre-trained CNNs to below a specified limit. This is done by means of learned projections trained via end-to-end finetuning, which can then be folded and fused into the pre-trained network. We also introduce a new `ceiling compression' framework in which evaluate such techniques in view of the future goal of performing inference fully on-chip.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2210.15170
- https://arxiv.org/pdf/2210.15170
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4307535783
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4307535783Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2210.15170Digital Object Identifier
- Title
-
Improved Projection Learning for Lower Dimensional Feature MapsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-10-27Full publication date if available
- Authors
-
Ilan Price, Jared TannerList of authors in order
- Landing page
-
https://arxiv.org/abs/2210.15170Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2210.15170Direct 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/2210.15170Direct OA link when available
- Concepts
-
Computer science, Inference, Convolutional neural network, Feature (linguistics), Artificial intelligence, Projection (relational algebra), Pattern recognition (psychology), Ceiling (cloud), Machine learning, Algorithm, Engineering, Philosophy, Linguistics, Structural engineeringTop 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)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4307535783 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2210.15170 |
| ids.doi | https://doi.org/10.48550/arxiv.2210.15170 |
| ids.openalex | https://openalex.org/W4307535783 |
| fwci | |
| type | preprint |
| title | Improved Projection Learning for Lower Dimensional Feature Maps |
| 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 | 0.9983999729156494 |
| 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/T11612 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9961000084877014 |
| 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 | Stochastic Gradient Optimization Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7814340591430664 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2776214188 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7665507793426514 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[1].display_name | Inference |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6942943334579468 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C2776401178 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6653540730476379 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[3].display_name | Feature (linguistics) |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.6482667326927185 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C57493831 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5373984575271606 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q3134666 |
| concepts[5].display_name | Projection (relational algebra) |
| concepts[6].id | https://openalex.org/C153180895 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5081875324249268 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[6].display_name | Pattern recognition (psychology) |
| concepts[7].id | https://openalex.org/C2777489069 |
| concepts[7].level | 2 |
| concepts[7].score | 0.44524872303009033 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1589822 |
| concepts[7].display_name | Ceiling (cloud) |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.37497127056121826 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C11413529 |
| concepts[9].level | 1 |
| concepts[9].score | 0.22247585654258728 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[9].display_name | Algorithm |
| concepts[10].id | https://openalex.org/C127413603 |
| concepts[10].level | 0 |
| concepts[10].score | 0.08944767713546753 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[10].display_name | Engineering |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C41895202 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[12].display_name | Linguistics |
| concepts[13].id | https://openalex.org/C66938386 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q633538 |
| concepts[13].display_name | Structural engineering |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7814340591430664 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/inference |
| keywords[1].score | 0.7665507793426514 |
| keywords[1].display_name | Inference |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.6942943334579468 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/feature |
| keywords[3].score | 0.6653540730476379 |
| keywords[3].display_name | Feature (linguistics) |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.6482667326927185 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/projection |
| keywords[5].score | 0.5373984575271606 |
| keywords[5].display_name | Projection (relational algebra) |
| keywords[6].id | https://openalex.org/keywords/pattern-recognition |
| keywords[6].score | 0.5081875324249268 |
| keywords[6].display_name | Pattern recognition (psychology) |
| keywords[7].id | https://openalex.org/keywords/ceiling |
| keywords[7].score | 0.44524872303009033 |
| keywords[7].display_name | Ceiling (cloud) |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.37497127056121826 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/algorithm |
| keywords[9].score | 0.22247585654258728 |
| keywords[9].display_name | Algorithm |
| keywords[10].id | https://openalex.org/keywords/engineering |
| keywords[10].score | 0.08944767713546753 |
| keywords[10].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2210.15170 |
| 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/2210.15170 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2210.15170 |
| locations[1].id | doi:10.48550/arxiv.2210.15170 |
| 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.2210.15170 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5062089651 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-6713-8413 |
| authorships[0].author.display_name | Ilan Price |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Price, Ilan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5059562923 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-5561-9949 |
| authorships[1].author.display_name | Jared Tanner |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Tanner, Jared |
| authorships[1].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2210.15170 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Improved Projection Learning for Lower Dimensional Feature Maps |
| has_fulltext | True |
| 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/W4392749941, https://openalex.org/W2081139303, https://openalex.org/W2767250287, https://openalex.org/W3158338669, https://openalex.org/W2354178882, https://openalex.org/W2581715027, https://openalex.org/W184756157, https://openalex.org/W4238907858, https://openalex.org/W1526175729, https://openalex.org/W2330650530 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2210.15170 |
| 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/2210.15170 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2210.15170 |
| primary_location.id | pmh:oai:arXiv.org:2210.15170 |
| 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/2210.15170 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2210.15170 |
| publication_date | 2022-10-27 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 46, 75 |
| abstract_inverted_index.In | 28 |
| abstract_inverted_index.We | 72 |
| abstract_inverted_index.an | 33 |
| abstract_inverted_index.be | 64 |
| abstract_inverted_index.by | 52 |
| abstract_inverted_index.in | 21, 80, 85 |
| abstract_inverted_index.is | 50 |
| abstract_inverted_index.of | 23, 41, 54, 87, 91 |
| abstract_inverted_index.to | 2, 44 |
| abstract_inverted_index.we | 31 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.all | 38 |
| abstract_inverted_index.and | 9, 26, 66 |
| abstract_inverted_index.can | 62 |
| abstract_inverted_index.for | 36 |
| abstract_inverted_index.new | 76 |
| abstract_inverted_index.the | 69, 88 |
| abstract_inverted_index.via | 58 |
| abstract_inverted_index.CNNs | 43 |
| abstract_inverted_index.This | 49 |
| abstract_inverted_index.also | 73 |
| abstract_inverted_index.both | 24 |
| abstract_inverted_index.done | 51 |
| abstract_inverted_index.goal | 90 |
| abstract_inverted_index.high | 19 |
| abstract_inverted_index.into | 68 |
| abstract_inverted_index.maps | 7, 40 |
| abstract_inverted_index.move | 4 |
| abstract_inverted_index.off- | 8 |
| abstract_inverted_index.such | 83 |
| abstract_inverted_index.then | 63 |
| abstract_inverted_index.this | 29 |
| abstract_inverted_index.view | 86 |
| abstract_inverted_index.with | 13 |
| abstract_inverted_index.work | 30 |
| abstract_inverted_index.below | 45 |
| abstract_inverted_index.costs | 20 |
| abstract_inverted_index.fully | 94 |
| abstract_inverted_index.fused | 67 |
| abstract_inverted_index.large | 5 |
| abstract_inverted_index.means | 53 |
| abstract_inverted_index.terms | 22 |
| abstract_inverted_index.time. | 27 |
| abstract_inverted_index.which | 61, 81 |
| abstract_inverted_index.(CNNs) | 17 |
| abstract_inverted_index.during | 11 |
| abstract_inverted_index.energy | 25 |
| abstract_inverted_index.folded | 65 |
| abstract_inverted_index.future | 89 |
| abstract_inverted_index.limit. | 48 |
| abstract_inverted_index.method | 35 |
| abstract_inverted_index.neural | 15 |
| abstract_inverted_index.explore | 32 |
| abstract_inverted_index.feature | 6, 39 |
| abstract_inverted_index.imposes | 18 |
| abstract_inverted_index.learned | 55 |
| abstract_inverted_index.on-chip | 10 |
| abstract_inverted_index.trained | 57 |
| abstract_inverted_index.`ceiling | 77 |
| abstract_inverted_index.evaluate | 82 |
| abstract_inverted_index.improved | 34 |
| abstract_inverted_index.network. | 71 |
| abstract_inverted_index.networks | 16 |
| abstract_inverted_index.on-chip. | 95 |
| abstract_inverted_index.framework | 79 |
| abstract_inverted_index.inference | 12, 93 |
| abstract_inverted_index.introduce | 74 |
| abstract_inverted_index.specified | 47 |
| abstract_inverted_index.end-to-end | 59 |
| abstract_inverted_index.performing | 92 |
| abstract_inverted_index.repeatedly | 3 |
| abstract_inverted_index.techniques | 84 |
| abstract_inverted_index.compressing | 37 |
| abstract_inverted_index.finetuning, | 60 |
| abstract_inverted_index.pre-trained | 42, 70 |
| abstract_inverted_index.projections | 56 |
| abstract_inverted_index.requirement | 1 |
| abstract_inverted_index.compression' | 78 |
| abstract_inverted_index.convolutional | 14 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/7 |
| sustainable_development_goals[0].score | 0.75 |
| sustainable_development_goals[0].display_name | Affordable and clean energy |
| citation_normalized_percentile |