iNL: Implicit non-local network

The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational burden for deployment Wang et al. (2018). In this work, we explore to release the inference computation for non-local network by decoupling the...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 482; pp. 50 - 59
Main Authors: Han, Yifeng, Chen, Xi, Zhang, Songjie, Qi, Donglian
Format: Journal Article
Language:English
Published: Elsevier B.V 14.04.2022
Subjects:
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational burden for deployment Wang et al. (2018). In this work, we explore to release the inference computation for non-local network by decoupling the training/inference procedure. Specifically, we propose the implicit non-local network (iNL). During training, iNL models the dependency between features across long-range affinities like original non-local blocks; during inference, iNL could be reformulated as only two convolution layers but can rival non-local network. In this way, the computation complexity and the memory costs are reduced. In addition, we take a further step and extend our iNL into a more generalized form, which covers the attentions of different orders in computer vision tasks. iNL brings steady improvements on multiple benchmarks of different vision tasks including classification, detection, and instance segmentation. In the meantime, it provides a brand–new perspective to understand the attention mechanism in deep neural networks.
AbstractList The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational burden for deployment Wang et al. (2018). In this work, we explore to release the inference computation for non-local network by decoupling the training/inference procedure. Specifically, we propose the implicit non-local network (iNL). During training, iNL models the dependency between features across long-range affinities like original non-local blocks; during inference, iNL could be reformulated as only two convolution layers but can rival non-local network. In this way, the computation complexity and the memory costs are reduced. In addition, we take a further step and extend our iNL into a more generalized form, which covers the attentions of different orders in computer vision tasks. iNL brings steady improvements on multiple benchmarks of different vision tasks including classification, detection, and instance segmentation. In the meantime, it provides a brand–new perspective to understand the attention mechanism in deep neural networks.
Author Chen, Xi
Zhang, Songjie
Qi, Donglian
Han, Yifeng
Author_xml – sequence: 1
  givenname: Yifeng
  surname: Han
  fullname: Han, Yifeng
– sequence: 2
  givenname: Xi
  surname: Chen
  fullname: Chen, Xi
– sequence: 3
  givenname: Songjie
  surname: Zhang
  fullname: Zhang, Songjie
– sequence: 4
  givenname: Donglian
  surname: Qi
  fullname: Qi, Donglian
BookMark eNqFz09LwzAYx_EgE9ym70Bwb6A1T5o2yQ6CDP8Mhl70HJKnTyGza0ZaFd-9HfPkQU-_0_cHnxmbdLEjxi6B58Chut7mHb1j3OWCC5FzyLlUJ2wKWolMC11N2JQbUWaiAHHGZn2_5RwUCDNlV-Fps1ysd_s2YBgW43HWRnTtoqPhM6a3c3bauLani5-ds9f7u5fVY7Z5flivbjcZQgkqkyhNo31VG-krj4a0bhAEx8KVKLjxtarLQhbKCelKT-B5QbpS2ngSFWAxZ_L4iyn2faLG7lPYufRlgdsD0m7tEWkPSMvBjsgxW_7KRoUbQuyG5EL7X3xzjGmEfQRKtsdAHVIdEuFg6xj-PvgGwOlwtg
CitedBy_id crossref_primary_10_1016_j_gloei_2024_11_016
crossref_primary_10_1016_j_patcog_2024_110940
Cites_doi 10.1109/TPAMI.2012.89
10.1007/s11042-019-7404-z
10.1016/S0004-3702(02)00399-5
10.1109/TIP.2017.2787612
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2022.01.047
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 59
ExternalDocumentID 10_1016_j_neucom_2022_01_047
S0925231222000662
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c1517-4c49f8b6d94b6bc9e88fc120c3a5c209bd7d53437a24a5be1b03e86789be261c3
ISSN 0925-2312
IngestDate Tue Nov 18 20:52:05 EST 2025
Sat Nov 29 07:18:28 EST 2025
Fri Feb 23 02:40:30 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Computation cost
Implicit method
Generalized form
Attention
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1517-4c49f8b6d94b6bc9e88fc120c3a5c209bd7d53437a24a5be1b03e86789be261c3
PageCount 10
ParticipantIDs crossref_primary_10_1016_j_neucom_2022_01_047
crossref_citationtrail_10_1016_j_neucom_2022_01_047
elsevier_sciencedirect_doi_10_1016_j_neucom_2022_01_047
PublicationCentury 2000
PublicationDate 2022-04-14
PublicationDateYYYYMMDD 2022-04-14
PublicationDate_xml – month: 04
  year: 2022
  text: 2022-04-14
  day: 14
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Chen, Deng, Hu (b0115) 2019
A. Krizhevsky, G. Hinton, et al., Learning multiple layers of features from tiny images.
Sun, Fisher (b0015) 2003; 146
Liao, He, Yang, Zhang (b0105) 2018
Wang, Shen (b0035) 2017; 27
Fukui, Hirakawa, Yamashita, Fujiyoshi (b0010) 2019
Z. Ren, Y. Zhou, Y. Chen, R. Zhou, Y. Gao, Efficient human pose estimation by maximizing fusion and high-level spatial attention, arXiv preprint arXiv:2107.13693.
Hu, Zhang, Xie, Lin (b0145) 2019
Zhu, Xu, Bai, Huang, Bai (b0150) 2019
Li, Xian, Shen, Cao, Lu, Hang (b0045) 2018
He, Zhang, Ren, Sun (b0155) 2016
Wang, Girshick, Gupta, He (b0005) 2018
Yuan, Huang, Guo, Zhang, Chen, Wang (b0110) 2021
Kamigaito, Hayashi, Hirao, Nagata (b0125) 2018
Pan, Yao, Li, Mei (b0135) 2020
Borji, Itti (b0040) 2012; 35
Zhao, Wu (b0090) 2019
Selvaraju, Cogswell, Das, Vedantam, Parikh, Batra (b0170) 2017
Pang, Xie, Khan, Anwer, Khan, Shao (b0080) 2019
Fu, Liu, Tian, Li, Bao, Fang, Lu (b0100) 2019
Zhang, Xu, Arnab, Torr (b0140) 2020
Sun, Wang, Dai, Van Gool (b0075) 2020
Yu, Wang, Peng, Gao, Yu, Sang (b0095) 2018
D. Bahdanau, K. Cho, Y. Bengio, Neural machine translation by jointly learning to align and translate, arXiv preprint arXiv:1409.0473.
Choe, Shim (b0065) 2019
Sarafianos, Xu, Kakadiaris (b0050) 2018
Yue, Sun, Yuan, Zhou, Ding, Xu (b0020) 2018
Lv, Dai, Chen, Lu, Xia, Cao (b0130) 2021
C. Wah, S. Branson, P. Welinder, P. Perona, S. Belongie, The caltech-ucsd birds-200-2011 dataset.
Ge, Yan, Yu, Sun (b0055) 2019; 78
Hu, Shen, Sun (b0085) 2018
Cao, Xu, Lin, Wei, Hu (b0030) 2019
Lu, Wang, Ma, Shen, Shao, Porikli (b0070) 2019
Huang, Wang, Huang, Huang, Wei, Liu (b0025) 2019
Pang (10.1016/j.neucom.2022.01.047_b0080) 2019
Lu (10.1016/j.neucom.2022.01.047_b0070) 2019
Hu (10.1016/j.neucom.2022.01.047_b0145) 2019
10.1016/j.neucom.2022.01.047_b0165
Yu (10.1016/j.neucom.2022.01.047_b0095) 2018
10.1016/j.neucom.2022.01.047_b0120
Selvaraju (10.1016/j.neucom.2022.01.047_b0170) 2017
Yuan (10.1016/j.neucom.2022.01.047_b0110) 2021
Borji (10.1016/j.neucom.2022.01.047_b0040) 2012; 35
Ge (10.1016/j.neucom.2022.01.047_b0055) 2019; 78
Zhang (10.1016/j.neucom.2022.01.047_b0140) 2020
10.1016/j.neucom.2022.01.047_b0160
10.1016/j.neucom.2022.01.047_b0060
Kamigaito (10.1016/j.neucom.2022.01.047_b0125) 2018
Huang (10.1016/j.neucom.2022.01.047_b0025) 2019
Wang (10.1016/j.neucom.2022.01.047_b0035) 2017; 27
Li (10.1016/j.neucom.2022.01.047_b0045) 2018
Yue (10.1016/j.neucom.2022.01.047_b0020) 2018
Chen (10.1016/j.neucom.2022.01.047_b0115) 2019
He (10.1016/j.neucom.2022.01.047_b0155) 2016
Sarafianos (10.1016/j.neucom.2022.01.047_b0050) 2018
Sun (10.1016/j.neucom.2022.01.047_b0015) 2003; 146
Liao (10.1016/j.neucom.2022.01.047_b0105) 2018
Choe (10.1016/j.neucom.2022.01.047_b0065) 2019
Cao (10.1016/j.neucom.2022.01.047_b0030) 2019
Zhu (10.1016/j.neucom.2022.01.047_b0150) 2019
Wang (10.1016/j.neucom.2022.01.047_b0005) 2018
Lv (10.1016/j.neucom.2022.01.047_b0130) 2021
Fu (10.1016/j.neucom.2022.01.047_b0100) 2019
Zhao (10.1016/j.neucom.2022.01.047_b0090) 2019
Hu (10.1016/j.neucom.2022.01.047_b0085) 2018
Pan (10.1016/j.neucom.2022.01.047_b0135) 2020
Sun (10.1016/j.neucom.2022.01.047_b0075) 2020
Fukui (10.1016/j.neucom.2022.01.047_b0010) 2019
References_xml – reference: D. Bahdanau, K. Cho, Y. Bengio, Neural machine translation by jointly learning to align and translate, arXiv preprint arXiv:1409.0473.
– start-page: 7132
  year: 2018
  end-page: 7141
  ident: b0085
  article-title: Squeeze-and-excitation networks
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 593
  year: 2019
  end-page: 602
  ident: b0150
  article-title: Asymmetric non-local neural networks for semantic segmentation
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– start-page: 4967
  year: 2019
  end-page: 4975
  ident: b0080
  article-title: Mask-guided attention network for occluded pedestrian detection
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– reference: C. Wah, S. Branson, P. Welinder, P. Perona, S. Belongie, The caltech-ucsd birds-200-2011 dataset.
– start-page: 10705
  year: 2019
  end-page: 10714
  ident: b0010
  article-title: Attention branch network: Learning of attention mechanism for visual explanation
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 770
  year: 2016
  end-page: 778
  ident: b0155
  article-title: Deep residual learning for image recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 10971
  year: 2020
  end-page: 10980
  ident: b0135
  article-title: X-linear attention networks for image captioning
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 6510
  year: 2018
  end-page: 6519
  ident: b0020
  article-title: Compact generalized non-local network
  publication-title: Advances in Neural Information Processing Systems
– start-page: 1
  year: 2021
  end-page: 24
  ident: b0110
  article-title: Ocnet: Object context for semantic segmentation
  publication-title: International Journal of Computer Vision
– year: 2019
  ident: b0030
  article-title: Gcnet: Non-local networks meet squeeze-excitation networks and beyond
  publication-title: Proceedings of the IEEE International Conference on Computer Vision Workshops
– start-page: 3146
  year: 2019
  end-page: 3154
  ident: b0100
  article-title: Dual attention network for scene segmentation
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 371
  year: 2019
  end-page: 381
  ident: b0115
  article-title: Mixed high-order attention network for person re-identification
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– start-page: 3623
  year: 2019
  end-page: 3632
  ident: b0070
  article-title: See more, know more: Unsupervised video object segmentation with co-attention siamese networks
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– reference: A. Krizhevsky, G. Hinton, et al., Learning multiple layers of features from tiny images.
– start-page: 347
  year: 2020
  end-page: 365
  ident: b0075
  article-title: Mining cross-image semantics for weakly supervised semantic segmentation
  publication-title: European conference on computer vision
– start-page: 1857
  year: 2018
  end-page: 1866
  ident: b0095
  article-title: Learning a discriminative feature network for semantic segmentation
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 2219
  year: 2019
  end-page: 2228
  ident: b0065
  article-title: Attention-based dropout layer for weakly supervised object localization
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 146
  start-page: 77
  year: 2003
  end-page: 123
  ident: b0015
  article-title: Object-based visual attention for computer vision
  publication-title: Artificial intelligence
– start-page: 3085
  year: 2019
  end-page: 3094
  ident: b0090
  article-title: Pyramid feature attention network for saliency detection
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 27
  start-page: 2368
  year: 2017
  end-page: 2378
  ident: b0035
  article-title: Deep visual attention prediction
  publication-title: IEEE Transactions on Image Processing
– start-page: 3726
  year: 2020
  end-page: 3735
  ident: b0140
  article-title: Dynamic graph message passing networks
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 1605
  year: 2021
  end-page: 1609
  ident: b0130
  article-title: Hoca: Higher-order channel attention for single image super-resolution
  publication-title: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
– start-page: 603
  year: 2019
  end-page: 612
  ident: b0025
  article-title: Ccnet: Criss-cross attention for semantic segmentation
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– start-page: 663
  year: 2018
  end-page: 678
  ident: b0045
  article-title: Deep attention-based classification network for robust depth prediction
  publication-title: Asian Conference on Computer Vision
– start-page: 3464
  year: 2019
  end-page: 3473
  ident: b0145
  article-title: Local relation networks for image recognition
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– start-page: 7794
  year: 2018
  end-page: 7803
  ident: b0005
  article-title: Non-local neural networks
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 680
  year: 2018
  end-page: 697
  ident: b0050
  article-title: Deep imbalanced attribute classification using visual attention aggregation
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– volume: 35
  start-page: 185
  year: 2012
  end-page: 207
  ident: b0040
  article-title: State-of-the-art in visual attention modeling
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– start-page: 1716
  year: 2018
  end-page: 1726
  ident: b0125
  article-title: Higher-order syntactic attention network for longer sentence compression
  publication-title: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
– start-page: 618
  year: 2017
  end-page: 626
  ident: b0170
  article-title: Grad-cam: Visual explanations from deep networks via gradient-based localization
  publication-title: Proceedings of the IEEE international conference on computer vision
– volume: 78
  start-page: 20533
  year: 2019
  end-page: 20556
  ident: b0055
  article-title: An attention mechanism based convolutional lstm network for video action recognition
  publication-title: Multimedia Tools and Applications
– reference: Z. Ren, Y. Zhou, Y. Chen, R. Zhou, Y. Gao, Efficient human pose estimation by maximizing fusion and high-level spatial attention, arXiv preprint arXiv:2107.13693.
– start-page: 620
  year: 2018
  end-page: 634
  ident: b0105
  article-title: Video-based person re-identification via 3d convolutional networks and non-local attention
  publication-title: Asian Conference on Computer Vision
– start-page: 6510
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0020
  article-title: Compact generalized non-local network
  publication-title: Advances in Neural Information Processing Systems
– start-page: 593
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0150
  article-title: Asymmetric non-local neural networks for semantic segmentation
– volume: 35
  start-page: 185
  issue: 1
  year: 2012
  ident: 10.1016/j.neucom.2022.01.047_b0040
  article-title: State-of-the-art in visual attention modeling
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2012.89
– start-page: 7132
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0085
  article-title: Squeeze-and-excitation networks
– ident: 10.1016/j.neucom.2022.01.047_b0160
– start-page: 1716
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0125
  article-title: Higher-order syntactic attention network for longer sentence compression
– start-page: 770
  year: 2016
  ident: 10.1016/j.neucom.2022.01.047_b0155
  article-title: Deep residual learning for image recognition
– ident: 10.1016/j.neucom.2022.01.047_b0165
– start-page: 4967
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0080
  article-title: Mask-guided attention network for occluded pedestrian detection
– ident: 10.1016/j.neucom.2022.01.047_b0120
– start-page: 3146
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0100
  article-title: Dual attention network for scene segmentation
– start-page: 10971
  year: 2020
  ident: 10.1016/j.neucom.2022.01.047_b0135
  article-title: X-linear attention networks for image captioning
– start-page: 618
  year: 2017
  ident: 10.1016/j.neucom.2022.01.047_b0170
  article-title: Grad-cam: Visual explanations from deep networks via gradient-based localization
– start-page: 663
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0045
  article-title: Deep attention-based classification network for robust depth prediction
– start-page: 3623
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0070
  article-title: See more, know more: Unsupervised video object segmentation with co-attention siamese networks
– start-page: 371
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0115
  article-title: Mixed high-order attention network for person re-identification
– start-page: 680
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0050
  article-title: Deep imbalanced attribute classification using visual attention aggregation
– start-page: 1857
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0095
  article-title: Learning a discriminative feature network for semantic segmentation
– start-page: 1
  year: 2021
  ident: 10.1016/j.neucom.2022.01.047_b0110
  article-title: Ocnet: Object context for semantic segmentation
  publication-title: International Journal of Computer Vision
– start-page: 3726
  year: 2020
  ident: 10.1016/j.neucom.2022.01.047_b0140
  article-title: Dynamic graph message passing networks
– start-page: 10705
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0010
  article-title: Attention branch network: Learning of attention mechanism for visual explanation
– start-page: 3085
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0090
  article-title: Pyramid feature attention network for saliency detection
– start-page: 620
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0105
  article-title: Video-based person re-identification via 3d convolutional networks and non-local attention
– ident: 10.1016/j.neucom.2022.01.047_b0060
– start-page: 2219
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0065
  article-title: Attention-based dropout layer for weakly supervised object localization
– start-page: 603
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0025
  article-title: Ccnet: Criss-cross attention for semantic segmentation
– year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0030
  article-title: Gcnet: Non-local networks meet squeeze-excitation networks and beyond
– start-page: 347
  year: 2020
  ident: 10.1016/j.neucom.2022.01.047_b0075
  article-title: Mining cross-image semantics for weakly supervised semantic segmentation
– start-page: 7794
  year: 2018
  ident: 10.1016/j.neucom.2022.01.047_b0005
  article-title: Non-local neural networks
– volume: 78
  start-page: 20533
  issue: 14
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0055
  article-title: An attention mechanism based convolutional lstm network for video action recognition
  publication-title: Multimedia Tools and Applications
  doi: 10.1007/s11042-019-7404-z
– start-page: 3464
  year: 2019
  ident: 10.1016/j.neucom.2022.01.047_b0145
  article-title: Local relation networks for image recognition
– volume: 146
  start-page: 77
  issue: 1
  year: 2003
  ident: 10.1016/j.neucom.2022.01.047_b0015
  article-title: Object-based visual attention for computer vision
  publication-title: Artificial intelligence
  doi: 10.1016/S0004-3702(02)00399-5
– start-page: 1605
  year: 2021
  ident: 10.1016/j.neucom.2022.01.047_b0130
  article-title: Hoca: Higher-order channel attention for single image super-resolution
– volume: 27
  start-page: 2368
  issue: 5
  year: 2017
  ident: 10.1016/j.neucom.2022.01.047_b0035
  article-title: Deep visual attention prediction
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2017.2787612
SSID ssj0017129
Score 2.3451695
Snippet The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 50
SubjectTerms Attention
Computation cost
Generalized form
Implicit method
Title iNL: Implicit non-local network
URI https://dx.doi.org/10.1016/j.neucom.2022.01.047
Volume 482
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9tAEF6hpAcutJRWpDzqAzdk5Ox6411uUQWCCkUgqJSerH25ckQdRJIqP5_Zh52IIChIXCzL8trrnfG8duYbhA5Ag1ChBIultKDaIjUx6wm7B68Vp0VhisLhzF5kgwEbDvll6Nk6ce0Esqpi8zm_e1dSwzUgti2dfQW5m4fCBTgHosMRyA7H_yJ8Obiwbv65SxUvp4fg38dOYx1WPuV72R512BzKdXYIMYP-XwudoC2f8IV4crLpd1mYoOhcQoCXWMNyNfg8rv6MyoZlrnwx-9hWDAdmDHEGcFEtoOEizrhaAOOjiJjGYCJ6gWq8DGUZdtXpy0I29S2Ggpj0WLNB4XpE8BVR7qMKo6PKzGxej52SA1j1AJ2PQLKv7UTsPLArPbJKuY0zylkLtfvnJ8Ofzc5S1sUefzFMvC6ndDl_q-962lxZMkFuPqGN4DtEfU_zTbRmqs_oY92XIwpiegt9BxY4jmoGiBoGiAIDfEG_Tk9ufpzFoRFGrMAgg19Ipbxgsqd5KntSccNYobo4UURQhRMudaYpSUkmcCqoNF2ZEMPADOHSgIesyFfUgneZbRQZo5LEaJ0YCbZoobnAItVEpITwHqWsg0j9vbkKKPG2WcltXqcDjnK_SrldpTzp5rBKHRQ3o-48SsoL92f1UubB0vMWXA7Uf3bktzeP3EHrC7beRa3p_czsoQ_q37Sc3O8HNnkA1C11fQ
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=iNL%3A+Implicit+non-local+network&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Han%2C+Yifeng&rft.au=Chen%2C+Xi&rft.au=Zhang%2C+Songjie&rft.au=Qi%2C+Donglian&rft.date=2022-04-14&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=482&rft.spage=50&rft.epage=59&rft_id=info:doi/10.1016%2Fj.neucom.2022.01.047&rft.externalDocID=S0925231222000662
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon