FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration
Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper,...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Chen, Yanming [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea - Wang, Jiliang ELSEVIER, 2018, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:238 ; year:2022 ; day:28 ; month:02 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.knosys.2021.107876 |
|---|
| Katalog-ID: |
ELV056533942 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV056533942 | ||
| 003 | DE-627 | ||
| 005 | 20230626043517.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220205s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.knosys.2021.107876 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica |
| 035 | |a (DE-627)ELV056533942 | ||
| 035 | |a (ELSEVIER)S0950-7051(21)01049-2 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 550 |q VZ |
| 084 | |a 38.00 |2 bkl | ||
| 100 | 1 | |a Chen, Yanming |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| 264 | 1 | |c 2022transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. | ||
| 520 | |a Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. | ||
| 650 | 7 | |a Neural network |2 Elsevier | |
| 650 | 7 | |a Filter pruning |2 Elsevier | |
| 650 | 7 | |a Model compression |2 Elsevier | |
| 650 | 7 | |a Singular Value Decomposition (SVD) |2 Elsevier | |
| 700 | 1 | |a Wen, Xiang |4 oth | |
| 700 | 1 | |a Zhang, Yiwen |4 oth | |
| 700 | 1 | |a He, Qiang |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Wang, Jiliang ELSEVIER |t Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea |d 2018 |g Amsterdam [u.a.] |w (DE-627)ELV001104926 |
| 773 | 1 | 8 | |g volume:238 |g year:2022 |g day:28 |g month:02 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.knosys.2021.107876 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OPC-GGO | ||
| 936 | b | k | |a 38.00 |j Geowissenschaften: Allgemeines |q VZ |
| 951 | |a AR | ||
| 952 | |d 238 |j 2022 |b 28 |c 0228 |h 0 | ||
| author_variant |
y c yc |
|---|---|
| matchkey_str |
chenyanmingwenxiangzhangyiwenheqiang:2022----:pflepuigiteotiuinfuptetrmpodecnouinl |
| hierarchy_sort_str |
2022transfer abstract |
| bklnumber |
38.00 |
| publishDate |
2022 |
| allfields |
10.1016/j.knosys.2021.107876 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica (DE-627)ELV056533942 (ELSEVIER)S0950-7051(21)01049-2 DE-627 ger DE-627 rakwb eng 550 VZ 38.00 bkl Chen, Yanming verfasserin aut FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) Elsevier Wen, Xiang oth Zhang, Yiwen oth He, Qiang oth Enthalten in Elsevier Science Wang, Jiliang ELSEVIER Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea 2018 Amsterdam [u.a.] (DE-627)ELV001104926 volume:238 year:2022 day:28 month:02 pages:0 https://doi.org/10.1016/j.knosys.2021.107876 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-GGO 38.00 Geowissenschaften: Allgemeines VZ AR 238 2022 28 0228 0 |
| spelling |
10.1016/j.knosys.2021.107876 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica (DE-627)ELV056533942 (ELSEVIER)S0950-7051(21)01049-2 DE-627 ger DE-627 rakwb eng 550 VZ 38.00 bkl Chen, Yanming verfasserin aut FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) Elsevier Wen, Xiang oth Zhang, Yiwen oth He, Qiang oth Enthalten in Elsevier Science Wang, Jiliang ELSEVIER Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea 2018 Amsterdam [u.a.] (DE-627)ELV001104926 volume:238 year:2022 day:28 month:02 pages:0 https://doi.org/10.1016/j.knosys.2021.107876 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-GGO 38.00 Geowissenschaften: Allgemeines VZ AR 238 2022 28 0228 0 |
| allfields_unstemmed |
10.1016/j.knosys.2021.107876 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica (DE-627)ELV056533942 (ELSEVIER)S0950-7051(21)01049-2 DE-627 ger DE-627 rakwb eng 550 VZ 38.00 bkl Chen, Yanming verfasserin aut FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) Elsevier Wen, Xiang oth Zhang, Yiwen oth He, Qiang oth Enthalten in Elsevier Science Wang, Jiliang ELSEVIER Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea 2018 Amsterdam [u.a.] (DE-627)ELV001104926 volume:238 year:2022 day:28 month:02 pages:0 https://doi.org/10.1016/j.knosys.2021.107876 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-GGO 38.00 Geowissenschaften: Allgemeines VZ AR 238 2022 28 0228 0 |
| allfieldsGer |
10.1016/j.knosys.2021.107876 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica (DE-627)ELV056533942 (ELSEVIER)S0950-7051(21)01049-2 DE-627 ger DE-627 rakwb eng 550 VZ 38.00 bkl Chen, Yanming verfasserin aut FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) Elsevier Wen, Xiang oth Zhang, Yiwen oth He, Qiang oth Enthalten in Elsevier Science Wang, Jiliang ELSEVIER Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea 2018 Amsterdam [u.a.] (DE-627)ELV001104926 volume:238 year:2022 day:28 month:02 pages:0 https://doi.org/10.1016/j.knosys.2021.107876 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-GGO 38.00 Geowissenschaften: Allgemeines VZ AR 238 2022 28 0228 0 |
| allfieldsSound |
10.1016/j.knosys.2021.107876 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica (DE-627)ELV056533942 (ELSEVIER)S0950-7051(21)01049-2 DE-627 ger DE-627 rakwb eng 550 VZ 38.00 bkl Chen, Yanming verfasserin aut FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) Elsevier Wen, Xiang oth Zhang, Yiwen oth He, Qiang oth Enthalten in Elsevier Science Wang, Jiliang ELSEVIER Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea 2018 Amsterdam [u.a.] (DE-627)ELV001104926 volume:238 year:2022 day:28 month:02 pages:0 https://doi.org/10.1016/j.knosys.2021.107876 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-GGO 38.00 Geowissenschaften: Allgemeines VZ AR 238 2022 28 0228 0 |
| language |
English |
| source |
Enthalten in Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea Amsterdam [u.a.] volume:238 year:2022 day:28 month:02 pages:0 |
| sourceStr |
Enthalten in Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea Amsterdam [u.a.] volume:238 year:2022 day:28 month:02 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Geowissenschaften: Allgemeines |
| institution |
findex.gbv.de |
| topic_facet |
Neural network Filter pruning Model compression Singular Value Decomposition (SVD) |
| dewey-raw |
550 |
| isfreeaccess_bool |
false |
| container_title |
Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea |
| authorswithroles_txt_mv |
Chen, Yanming @@aut@@ Wen, Xiang @@oth@@ Zhang, Yiwen @@oth@@ He, Qiang @@oth@@ |
| publishDateDaySort_date |
2022-01-28T00:00:00Z |
| hierarchy_top_id |
ELV001104926 |
| dewey-sort |
3550 |
| id |
ELV056533942 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV056533942</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626043517.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220205s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.knosys.2021.107876</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV056533942</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0950-7051(21)01049-2</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">550</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">38.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chen, Yanming</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Neural network</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Filter pruning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Model compression</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Singular Value Decomposition (SVD)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wen, Xiang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yiwen</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">He, Qiang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Wang, Jiliang ELSEVIER</subfield><subfield code="t">Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea</subfield><subfield code="d">2018</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV001104926</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:238</subfield><subfield code="g">year:2022</subfield><subfield code="g">day:28</subfield><subfield code="g">month:02</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.knosys.2021.107876</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">38.00</subfield><subfield code="j">Geowissenschaften: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">238</subfield><subfield code="j">2022</subfield><subfield code="b">28</subfield><subfield code="c">0228</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Chen, Yanming |
| spellingShingle |
Chen, Yanming ddc 550 bkl 38.00 Elsevier Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| authorStr |
Chen, Yanming |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV001104926 |
| format |
electronic Article |
| dewey-ones |
550 - Earth sciences |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
550 VZ 38.00 bkl FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) Elsevier |
| topic |
ddc 550 bkl 38.00 Elsevier Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) |
| topic_unstemmed |
ddc 550 bkl 38.00 Elsevier Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) |
| topic_browse |
ddc 550 bkl 38.00 Elsevier Neural network Elsevier Filter pruning Elsevier Model compression Elsevier Singular Value Decomposition (SVD) |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
x w xw y z yz q h qh |
| hierarchy_parent_title |
Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea |
| hierarchy_parent_id |
ELV001104926 |
| dewey-tens |
550 - Earth sciences & geology |
| hierarchy_top_title |
Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV001104926 |
| title |
FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| ctrlnum |
(DE-627)ELV056533942 (ELSEVIER)S0950-7051(21)01049-2 |
| title_full |
FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| author_sort |
Chen, Yanming |
| journal |
Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea |
| journalStr |
Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
500 - Science |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Chen, Yanming |
| container_volume |
238 |
| class |
550 VZ 38.00 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Chen, Yanming |
| doi_str_mv |
10.1016/j.knosys.2021.107876 |
| dewey-full |
550 |
| title_sort |
fpc: filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| title_auth |
FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| abstract |
Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. |
| abstractGer |
Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. |
| abstract_unstemmed |
Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-GGO |
| title_short |
FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration |
| url |
https://doi.org/10.1016/j.knosys.2021.107876 |
| remote_bool |
true |
| author2 |
Wen, Xiang Zhang, Yiwen He, Qiang |
| author2Str |
Wen, Xiang Zhang, Yiwen He, Qiang |
| ppnlink |
ELV001104926 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth |
| doi_str |
10.1016/j.knosys.2021.107876 |
| up_date |
2024-07-06T20:40:27.233Z |
| _version_ |
1803863643635318784 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV056533942</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626043517.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220205s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.knosys.2021.107876</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001647.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV056533942</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0950-7051(21)01049-2</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">550</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">38.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chen, Yanming</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Neural network</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Filter pruning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Model compression</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Singular Value Decomposition (SVD)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wen, Xiang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yiwen</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">He, Qiang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Wang, Jiliang ELSEVIER</subfield><subfield code="t">Subsurface fluid flow at an active cold seep area in the Qiongdongnan Basin, northern South China Sea</subfield><subfield code="d">2018</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV001104926</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:238</subfield><subfield code="g">year:2022</subfield><subfield code="g">day:28</subfield><subfield code="g">month:02</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.knosys.2021.107876</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">38.00</subfield><subfield code="j">Geowissenschaften: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">238</subfield><subfield code="j">2022</subfield><subfield code="b">28</subfield><subfield code="c">0228</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.3999033 |