Slim-neck by GSConv: a lightweight-design for real-time detector architectures
Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement, and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accur...
Saved in:
Published in | Journal of real-time image processing Vol. 21; no. 3; p. 62 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
Berlin/Heidelberg
Springer Berlin Heidelberg
01.05.2024
Springer Nature B.V |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement, and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, slim-neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP
50
for the SODA10M at a speed of ~ 100 FPS on a Tesla T4) compared with the baselines. Code is available at
https://github.com/alanli1997/slim-neck-by-gsconv
. |
---|---|
AbstractList | Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement, and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, slim-neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP
50
for the SODA10M at a speed of ~ 100 FPS on a Tesla T4) compared with the baselines. Code is available at
https://github.com/alanli1997/slim-neck-by-gsconv
. Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement, and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, slim-neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP50 for the SODA10M at a speed of ~ 100 FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv. |
ArticleNumber | 62 |
Author | Li, Jun Wei, Hanbing Zhan, Zhenfei Li, Hulin Liu, Zheng Ren, Qiliang |
Author_xml | – sequence: 1 givenname: Hulin surname: Li fullname: Li, Hulin email: alan@mails.cqjtu.edu.cn organization: College of Traffic and Transportation, Chongqing Jiaotong University – sequence: 2 givenname: Jun surname: Li fullname: Li, Jun organization: School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University – sequence: 3 givenname: Hanbing surname: Wei fullname: Wei, Hanbing organization: School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University – sequence: 4 givenname: Zheng surname: Liu fullname: Liu, Zheng organization: School of Engineering, University of British Columbia Okanagan – sequence: 5 givenname: Zhenfei surname: Zhan fullname: Zhan, Zhenfei organization: School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University – sequence: 6 givenname: Qiliang surname: Ren fullname: Ren, Qiliang organization: College of Traffic and Transportation, Chongqing Jiaotong University |
BookMark | eNqFUctOwzAQtFCRaAs_wCkSZ4PX73JDFRSkCg6FsxWSdZuSJsVOQf17EoLgVg6zO1rNzB5mRAZVXSEh58AugTFzFQGUkpTxFiCFpvqIDMFqoJbDZPDLGTshoxjXjGmjhRqSx0VZbGiF2Vvyuk9mi2ldfVwnaVIWy1Xzid2kOcZiWSW-DknAtKRNscEkxwazpj2lIVsVHd8FjKfk2KdlxLOfPSYvd7fP03s6f5o9TG_mNBNGNVQyraVVygvvJ2iZskaKXGU-RZlraUBzrdH4HA1YmQJ6b5VkLYSeWOPFmFz0udtQv-8wNm5d70LVvnSCaQXcALeHVaCk5Iqb_1QMjBBdFu9VWahjDOjdNhSbNOwdMNd14PoOXNuB--7A6dYkelNsxdUSw1_0AdcXK8GIIQ |
CitedBy_id | crossref_primary_10_3390_electronics13112080 crossref_primary_10_3389_fpls_2024_1387350 crossref_primary_10_3390_agriculture14060961 crossref_primary_10_1007_s11760_024_03337_4 crossref_primary_10_3390_s24134333 crossref_primary_10_1007_s11760_024_03193_2 |
Cites_doi | 10.1109/TPAMI.2015.2389824 10.1145/3065386 10.1109/CVPR.2016.91 10.1109/CVPR.2016.90 10.1109/CVPR.2017.106 10.48550/arXiv.2106.11118 10.1109/CVPR46437.2021.01350 10.1109/CVPR.2018.00418 10.1109/CVPR.2014.81 10.1007/s11263-014-0733-5 10.1109/CVPR42600.2020.00165 10.1007/978-3-030-01234-2_1 10.1109/CVPR.2018.00716 10.1109/TPAMI.2016.2577031 10.1109/CVPR46437.2021.01283 10.1109/ICCV.2019.00972 10.1109/TMM.2019.2929005 10.1109/CVPR.2017.690 10.1109/CVPRW.2019.00103 10.1109/CVPR52729.2023.00721 10.48550/arXiv.1701.06659 10.1109/TPAMI.2019.2913372 10.1609/aaai.v34i07.6999 10.1109/CVPR.2017.195 10.1109/CVPR.2017.243 10.1109/CVPR.2019.00075 10.1109/ICCV.2019.00140 10.1007/s11263-022-01657-x 10.1109/CVPR.2019.00093 10.1109/CVPRW50498.2020.00203 10.1016/j.neucom.2022.07.042 10.1145/3373376.3378534 10.1007/978-3-030-01264-9_8 10.1145/2964284.2967274 10.48550/arXiv.1710.05941 10.1109/CVPR.2018.00474 10.1109/ICCV.2015.169 10.1007/978-3-319-46448-0_2 10.1109/TCYB.2021.3095305 |
ContentType | Journal Article |
Copyright | The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
Copyright_xml | – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
DBID | AAYXX CITATION JQ2 |
DOI | 10.1007/s11554-024-01436-6 |
DatabaseName | CrossRef ProQuest Computer Science Collection |
DatabaseTitle | CrossRef ProQuest Computer Science Collection |
DatabaseTitleList | ProQuest Computer Science Collection ProQuest Computer Science Collection ProQuest Computer Science Collection |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 1861-8219 |
ExternalDocumentID | 10_1007_s11554_024_01436_6 |
GrantInformation_xml | – fundername: Chongqing Postgraduate Joint Training Base grantid: JDLHPYJD2018003 – fundername: Natural Science Foundation of China grantid: 52172381 |
GroupedDBID | -59 -5G -BR -EM -Y2 -~C .VR 06D 0R~ 0VY 1N0 203 29L 2J2 2JN 2JY 2KG 2KM 2LR 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5VS 67Z 6NX 8TC 95- 95. 95~ 96X AAAVM AABHQ AACDK AAFGU AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO ABAKF ABBBX ABBXA ABDZT ABECU ABFGW ABFTV ABHLI ABHQN ABJNI ABJOX ABKAS ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBMV ACBRV ACBXY ACBYP ACDTI ACGFS ACHSB ACHXU ACIGE ACIPQ ACKNC ACMDZ ACMLO ACOKC ACOMO ACTTH ACVWB ACWMK ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADMDM ADOXG ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEFTE AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AESTI AETLH AEVLU AEVTX AEXYK AFBBN AFGCZ AFKRA AFLOW AFNRJ AFQWF AFWTZ AFZKB AGAYW AGDGC AGGBP AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AIMYW AITGF AJBLW AJDOV AJRNO AJZVZ AKQUC ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. BA0 BDATZ BENPR BGLVJ BGNMA CAG CCPQU COF CS3 CSCUP DDRTE DNIVK DPUIP EBLON EBS EIOEI EJD ESBYG FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS HCIFZ HF~ HG5 HG6 HLICF HMJXF HQYDN HRMNR HVGLF HZ~ IHE IJ- IKXTQ ITM IWAJR IXC IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K7- KDC KOV LLZTM M4Y MA- N2Q N9A NPVJJ NQJWS NU0 O9- O93 O9J OAM P9O PF0 PT4 QOS R89 R9I ROL RPX RSV S16 S1Z S27 S3B SAP SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UNUBA UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z7R Z7X Z83 Z88 ZMTXR ~A9 AAYXX CITATION H13 JQ2 |
ID | FETCH-LOGICAL-c375t-40664855f3ff9e8058743d5cfae4d64716266e7fde7184a1eff854085436987f3 |
IEDL.DBID | AGYKE |
ISSN | 1861-8200 |
IngestDate | Thu Oct 10 16:57:51 EDT 2024 Thu Oct 10 22:05:02 EDT 2024 Thu Oct 10 22:10:03 EDT 2024 Thu Sep 12 16:33:14 EDT 2024 Sat Jun 15 09:01:14 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 3 |
Keywords | Deep learning GSConv Real-time detection Lightweight CNNs Edge computing |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c375t-40664855f3ff9e8058743d5cfae4d64716266e7fde7184a1eff854085436987f3 |
PQID | 3015017338 |
PQPubID | 2044148 |
ParticipantIDs | proquest_journals_3065127128 proquest_journals_3015442527 proquest_journals_3015017338 crossref_primary_10_1007_s11554_024_01436_6 springer_journals_10_1007_s11554_024_01436_6 |
PublicationCentury | 2000 |
PublicationDate | 2024-05-01 |
PublicationDateYYYYMMDD | 2024-05-01 |
PublicationDate_xml | – month: 05 year: 2024 text: 2024-05-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Berlin/Heidelberg |
PublicationPlace_xml | – name: Berlin/Heidelberg – name: Heidelberg |
PublicationTitle | Journal of real-time image processing |
PublicationTitleAbbrev | J Real-Time Image Proc |
PublicationYear | 2024 |
Publisher | Springer Berlin Heidelberg Springer Nature B.V |
Publisher_xml | – name: Springer Berlin Heidelberg – name: Springer Nature B.V |
References | Liu, W., Anguelov, D., Erhan, D., Szegedy, C.: Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector. In: Proceedings of European Conference on Computer Vision (ECCV), Sep. 2016, pp. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2 ZablockiÉBen-YounesHPérezPExplainability of deep vision-based autonomous driving systems: review and challengesInt. J. Comput. Vis.202210.1007/s11263-022-01657-x Niu, W., Ma, X., Lin, S., Wang, S., Qian, X. Lin, X., Wang, Y. Ren, B.: PatDNN: achieving real-time DNN execution on mobile devices with pattern-based weight pruning. In: Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems. 2020, pp. 907–922 Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA 21–26 2017, pp. 2261–2269. https://doi.org/10.1109/CVPR.2017.243 Han, J., Liang, X., Xu, H., Chen, K., Hong, L., Ye, C., Zhang, W., Li, Z., Liang, X., Xu, C.: Soda10m: towards large-scale object detection benchmark for autonomous driving. arXiv eprints 2021, arXiv: 2106.11118. https://doi.org/10.48550/arXiv.2106.11118 KrizhevskyASutskeverIHintonGEImageNet classification with deep convolutional neural networksAssoc. Comput. Mach.201225849010.1145/3065386 Zhang, Y., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient IoU loss for accurate bounding box regression. arXiv eprints 2021, arXiv:2101.08158 2021. [Online]. Available: https://arxiv.org/abs-/2101.08158. https://doi.org/10.1016/j.neucom.2022.07.042 HuJShenLAlbanieSSunGWuESqueeze-and-excitation networksIEEE Trans. Pattern Anal. Mach. Intell.202010.1109/TPAMI.2019.2913372 Girshick, R.: Fast R-CNN. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), Santiago, Chile 07–13 December 2015, pp. 1440–1448. https://doi.org/10.1109/ICCV.2015.169 Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DssD: deconvolutional single shot detector. arXiv eprints 2017, arXiv:1701.06659. [Online]. Available: https://arxiv.org/abs/1701.06659. https://doi.org/10.48550/arXiv.1701.06659 Glenn, J.: Yolov5, 2022. https://github.com/ultralytics/yolov5 Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y. M.: Scaled-yolov4: scaling cross stage partial network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25, 2021; pp. 13024–13033. https://doi.org/10.1109/CVPR46437.2021.01283 Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA 15–20 June 2019; pp. 840–849. https://doi.org/10.1109/CVPR.2019.00093 Ma, N., Zhang, X., Zheng, H., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Proceedings of European Conference on Computer Vision (ECCV), 2018, arXiv:1807.11164. [Online]. Available: https://arxiv.org/abs/1807.11164v1. https://doi.org/10.1007/978-3-030-01264-9_8 Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, N., Hartwig, A.:. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv eprints 2017, arXiv:1704.04861. [Online]. Available: https://arxiv.org/abs-/1704.04861 Misra. Mish, D.: A self-regularized non-monotonic activation function. arXiv eprints 2020, arXiv:1908.08681. [Online]. https://arxiv.org/abs/1908.08681 ZhengZWangPLiuWLiJYeRRenDDistance-IoU Loss: faster and better learning for bounding box regressionProc. AAAI Conf. Artif. Intell. (AAAI)2020347129931300010.1609/aaai.v34i07.6999 ZhangSXieYWanJXiaHLiSZGuoGWiderPerson: a diverse dataset for dense pedestrian detection in the wildIEEE Trans. Multimedia202022238039310.1109/TMM.2019.2929005 He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90 Woo, S., Park, J., Lee, J., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of European Conference on Computer Vision (ECCV), Jul. 2018, arXiv:1807.06521. [Online]. Available: https://arxiv.org/abs/1807.06521v1. https://doi.org/10.1007/978-3-030-01234-2_1 Bochkovskiy, A., Wang, C.Y., Liao, H-Y. M.: Yolov4: optimal speed and accuracy of object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, arXiv:2004.10934. [Online]. https://arxiv.org/abs/2004.10934 RenSHeKGirshickRSunJFaster R-CNN: towards real-time object detection with region proposal networksIEEE Trans Pattern Anal. Mach. Intel.20173961137114910.1109/TPAMI.2016.2577031 Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, arXiv:1801.04381. [Online]. Available: https://arxiv.org/abs/1801.-04381v4. https://doi.org/10.1109/CVPR.2018.00474 Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023, pp. 7464–7475 Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019; pp. 658–666. https://doi.org/10.1109/CVPR.2019.00075 Howard, A., Sandler, M., Chu, G., Chen, L., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., Le, Q.V., Adam, H.: Searching for MobileNetV3. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), Apr. 2019, arXiv:1704.04861. [Online]. Available: https://arxiv.org/abs/1704.04861. https://doi.org/10.1109/ICCV.2019.00140 Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA 23–28 June 2014, pp. 580–587. https://doi.org/10.1109/CVPR.2014.81 Wang, C.-Y., Mark Liao, H.-Y., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., Yeh, I.-H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA 14–19 June 2020; pp. 1571–1580. https://doi.org/10.1109/CVPRW50498.2020.00203 Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA 21–26 July 2017; pp. 6517–6525, arXiv:1612.08242. [Online]. Available: https://arxiv.org/abs/1612.-08242v1. https://doi.org/10.1109/CVPR.2017.690 Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA 21–26 July 2017; pp. 936–944. https://doi.org/10.1109/CVPR.2017.106 Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. arXiv eprints 2017, arXiv:1710.05941. [Online]. https://doi.org/10.48550/arXiv.1710.05941 Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv eprints (2018). arXiv:1804.02767. [Online]. https://arxiv.org/abs/1804.02767 ZhengZWangPRenDLiuWYeRHuQZuoWEnhancing geometric factors in model learning and inference for object detection and instance segmentationIEEE Trans. Cybern.202110.1109/TCYB.2021.3095305 Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 15, pp. 315–323 (2011) Everingham, M., Ali Eslami, S.M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98–136. (2015). https://doi.org/10.1007/s11263-014-0733-5 Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA 21–26 July 2017, pp. 1800–1807. [Online]. Available: https://arxiv.org/abs/1610.02357v1. https://doi.org/10.1109/CVPR.2017.195 Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: UnitBox: An advanced object detection network. Association for Computing Machinery, New York, NY, USA Oct. 2016; pp. 516–520. https://doi.org/10.1145/2964284.2967274 HeKZhangXRenSSunJSpatial pyramid pooling in deep convolutional networks for visual recognitionIEEE Trans. Pattern Anal. Mach. Intell.20153791904191610.1109/TPAMI.2015.2389824 Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2021, arXiv:2103.02907. [Online]. Available: https://arxiv.org/abs/2103.02907. https://doi.org/10.1109/CVPR46437.2021.01350 Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: International Conference on Computer Vision. (ICCV), Seoul, Korea (South) 27 October 2019–02 November 2019; pp. 9626–9635. https://doi.org/10.1109/ICCV.2019.00972 Lee, Y., Hwang, J.-w., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA 16–17 June 2019, pp. 752–760. https://doi.org/10.1109/CVPRW.2019.00103 Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las J Hu (1436_CR27) 2020 1436_CR19 Z Zheng (1436_CR35) 2020; 34 1436_CR30 1436_CR31 1436_CR10 1436_CR32 1436_CR15 1436_CR37 S Ren (1436_CR3) 2017; 39 1436_CR38 1436_CR17 1436_CR39 1436_CR11 1436_CR33 1436_CR12 1436_CR34 1436_CR13 1436_CR14 K He (1436_CR26) 2015; 37 1436_CR1 A Krizhevsky (1436_CR18) 2012; 25 É Zablocki (1436_CR16) 2022 1436_CR2 Z Zheng (1436_CR36) 2021 1436_CR5 1436_CR4 1436_CR7 1436_CR6 1436_CR40 1436_CR41 1436_CR20 1436_CR42 1436_CR21 1436_CR9 1436_CR8 1436_CR28 1436_CR29 1436_CR22 S Zhang (1436_CR43) 2020; 22 1436_CR44 1436_CR23 1436_CR45 1436_CR24 1436_CR46 1436_CR25 |
References_xml | – volume: 37 start-page: 1904 issue: 9 year: 2015 ident: 1436_CR26 publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2389824 contributor: fullname: K He – ident: 1436_CR6 – volume: 25 start-page: 84 year: 2012 ident: 1436_CR18 publication-title: Assoc. Comput. Mach. doi: 10.1145/3065386 contributor: fullname: A Krizhevsky – ident: 1436_CR4 doi: 10.1109/CVPR.2016.91 – ident: 1436_CR20 doi: 10.1109/CVPR.2016.90 – ident: 1436_CR22 doi: 10.1109/CVPR.2017.106 – ident: 1436_CR45 doi: 10.48550/arXiv.2106.11118 – ident: 1436_CR29 doi: 10.1109/CVPR46437.2021.01350 – ident: 1436_CR40 – ident: 1436_CR46 doi: 10.1109/CVPR.2018.00418 – ident: 1436_CR19 – ident: 1436_CR1 doi: 10.1109/CVPR.2014.81 – ident: 1436_CR44 doi: 10.1007/s11263-014-0733-5 – ident: 1436_CR17 doi: 10.1109/CVPR42600.2020.00165 – ident: 1436_CR28 doi: 10.1007/978-3-030-01234-2_1 – ident: 1436_CR14 doi: 10.1109/CVPR.2018.00716 – volume: 39 start-page: 1137 issue: 6 year: 2017 ident: 1436_CR3 publication-title: IEEE Trans Pattern Anal. Mach. Intel. doi: 10.1109/TPAMI.2016.2577031 contributor: fullname: S Ren – ident: 1436_CR23 doi: 10.1109/CVPR46437.2021.01283 – ident: 1436_CR11 – ident: 1436_CR7 – ident: 1436_CR24 doi: 10.1109/ICCV.2019.00972 – volume: 22 start-page: 380 issue: 2 year: 2020 ident: 1436_CR43 publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2019.2929005 contributor: fullname: S Zhang – ident: 1436_CR5 doi: 10.1109/CVPR.2017.690 – ident: 1436_CR31 doi: 10.1109/CVPRW.2019.00103 – ident: 1436_CR42 doi: 10.1109/CVPR52729.2023.00721 – ident: 1436_CR9 doi: 10.48550/arXiv.1701.06659 – year: 2020 ident: 1436_CR27 publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2019.2913372 contributor: fullname: J Hu – volume: 34 start-page: 12993 issue: 7 year: 2020 ident: 1436_CR35 publication-title: Proc. AAAI Conf. Artif. Intell. (AAAI) doi: 10.1609/aaai.v34i07.6999 contributor: fullname: Z Zheng – ident: 1436_CR10 doi: 10.1109/CVPR.2017.195 – ident: 1436_CR30 doi: 10.1109/CVPR.2017.243 – ident: 1436_CR34 doi: 10.1109/CVPR.2019.00075 – ident: 1436_CR41 – ident: 1436_CR13 doi: 10.1109/ICCV.2019.00140 – year: 2022 ident: 1436_CR16 publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-022-01657-x contributor: fullname: É Zablocki – ident: 1436_CR25 doi: 10.1109/CVPR.2019.00093 – ident: 1436_CR32 doi: 10.1109/CVPRW50498.2020.00203 – ident: 1436_CR37 doi: 10.1016/j.neucom.2022.07.042 – ident: 1436_CR21 doi: 10.1145/3373376.3378534 – ident: 1436_CR39 – ident: 1436_CR15 doi: 10.1007/978-3-030-01264-9_8 – ident: 1436_CR33 doi: 10.1145/2964284.2967274 – ident: 1436_CR38 doi: 10.48550/arXiv.1710.05941 – ident: 1436_CR12 doi: 10.1109/CVPR.2018.00474 – ident: 1436_CR2 doi: 10.1109/ICCV.2015.169 – ident: 1436_CR8 doi: 10.1007/978-3-319-46448-0_2 – year: 2021 ident: 1436_CR36 publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2021.3095305 contributor: fullname: Z Zheng |
SSID | ssj0067635 |
Score | 2.4522126 |
Snippet | Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting... |
SourceID | proquest crossref springer |
SourceType | Aggregation Database Publisher |
StartPage | 62 |
SubjectTerms | Accuracy Computational efficiency Computer Graphics Computer Science Design Detectors Effectiveness Image Processing and Computer Vision Lightweight Multimedia Information Systems Neural networks Object recognition Pattern Recognition Real time Sensors Signal,Image and Speech Processing Weight reduction |
Title | Slim-neck by GSConv: a lightweight-design for real-time detector architectures |
URI | https://link.springer.com/article/10.1007/s11554-024-01436-6 https://www.proquest.com/docview/3015017338 https://www.proquest.com/docview/3015442527 https://www.proquest.com/docview/3065127128 |
Volume | 21 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLbYuHBhPMVgTDlwg6C1SdOU2zQNJpC4wKRxqtomkRCjIOhA8OtxslbltcPOqaokdvLZsf0Z4Ejx1DZx96mSklGusoxGPMio5GkaqQg1InEJstdiNOaXk2BS13G7ZPcqIuku6rrWzSIfRUihlpJOUNGA1cASfjVhtX9xdzWsLmBhOdasnyWFRxHgemWtzP9_-YlHtZH5Ky7q4Oa8BbdV0c48y-ThdFakp9nnXw7HZVayAeul-Un6c33ZhBWdb0Grau1AypO-Ddc30_tHmuvsgaQf5OJm8JS_nZGETK0v_-6eU6lyyR8ErV6ClueU2jb1ROnCxQHI9wjF6w6Mz4e3gxEtWy_QjIVBgV6lEJY2xjBjIi17gURLQwWZSTRXglvaKSF0aJRGbOOJp42RgSVLw_VEMjRsF5r5U673gBjD_ARVIpTM42EUJRxdFNOLEo8p31OsDceVAOLnOcNGXHMp262Kcatit1WxaEOnklFcnrbXmNlnGy9Eb3vhMMe7yQ8XDAu0ekIE6jacVBKrhxfPZX-5zw9gzXdCt9mSHWgWLzN9iBZNkXZLDe5CY-z3vwA4Dukw |
link.rule.ids | 315,786,790,27955,27956,41114,41556,42183,42625,52144,52267 |
linkProvider | Springer Nature |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWgDLDwjSgU8MAGlprYsR22qqIUKF3aSt2sJLYlREkRDSD-PWc3UQHRgdlRlNzZfu9853cInWuWuibuIdFSUsJ0lpGYRRmRLE1jHcOMSHyBbJ93R-xuHI3LS2Gzqtq9Skn6nXpx2c1BHwFMIU6TjhO-itacnror5BuFrWr_5U5izYVZkgcE8K1ZXpX5-x0_4WjBMX-lRT3adLbRZkkTcWvu1x20YvJdtFW1YMDlitxD_cHk8ZnkJnvC6Se-GbSn-fsVTvDExdwf_tiTaF-kgYGdYmCIE-LayWNtCn9ej79nEmb7aNS5Hra7pGyRQDIqogKiP86dvIul1sZGNiMJjEBHmU0M05w5eSjOjbDaAAaxJDDWysiJmsHPx1JYeoBq-TQ3hwhbS8MEXCckDZiI44RBKGGbcRJQHQaa1tFFZSn1MlfCUAvNY2dXBXZV3q6K11GjMqYqV8VMUXe8EgiIipcOM9hDQrFkmAM7EQCodXRZuWcxvPxbjv73-Bla7w4feqp3278_Rhuhny2uwrGBasXrmzkBFlKkp37SfQG0Ms8p |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46Qbz4W5xOzcGbBtcmTRNvYzrnD4YwB7uVtklAnN1wVfG_9yVr6RR38JxS2peXfN9L3vseQqeKJbaJu0-UEJQwlaZEsiAlgiWJVBI8InYJsj3eHbC7YTCcq-J32e7lleSspsGqNGX5xUSZi6rwzcIgAXwhVp-OE76MViw0Wh8f-K1yL-ZWbs2GXIJ7BLCuWZTN_P2On9BU8c1fV6QOeTqbaL2gjLg1m-MttKSzbbRRtmPAxercQb3-6PmVZDp9wckXvum3x9nHJY7xyMbfn-4IlCiXsIGBqWJgiyNiW8tjpXN3do_nbxWmu2jQuX5qd0nRLoGkNAxyiAQ5t1IvhhojtWgGAtiBClITa6Y4s1JRnOvQKA14xGJPGyMCK3AGPy9FaOgeqmXjTO8jbAz1Y5jGUFCPhVLGDMIK05SxR5XvKVpHZ6WloslMFSOq9I-tXSOwa-TsGvE6apTGjIoVMo2oPWrxQoiQFw4z2E_8cMEwB6YSArjW0Xk5PdXw4m85-N_jJ2j18aoTPdz27g_Rmu-cxSY7NlAtf3vXR0BI8uTY-dw3IMTTbg |
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=Slim-neck+by+GSConv%3A+a+lightweight-design+for+real-time+detector+architectures&rft.jtitle=Journal+of+real-time+image+processing&rft.au=Hulin%2C+Li&rft.au=Li%2C+Jun&rft.au=Wei+Hanbing&rft.au=Liu%2C+Zheng&rft.date=2024-05-01&rft.pub=Springer+Nature+B.V&rft.issn=1861-8200&rft.eissn=1861-8219&rft.volume=21&rft.issue=3&rft_id=info:doi/10.1007%2Fs11554-024-01436-6&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1861-8200&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1861-8200&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1861-8200&client=summon |