Extended Feature Pyramid Network for Small Object Detection

Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the perfo...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on multimedia Ročník 24; s. 1968 - 1979
Hlavní autoři:	Deng, Chunfang, Wang, Mengmeng, Liu, Liang, Liu, Yong, Jiang, Yunliang
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Datasets deep learning Detectors Distillation Feature extraction feature pyramid feature super-resolution knowledge distillation Object detection Object recognition Pipelines Semantics Signal resolution Small object detection Superresolution
ISSN:	1520-9210, 1941-0077
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose an extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we introduce a cross resolution distillation mechanism to transfer the ability of perceiving details across the scales of the network, where a foreground-background-balanced loss function is designed to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100 K and small category of general object detection dataset MS COCO.
AbstractList	Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose an extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we introduce a cross resolution distillation mechanism to transfer the ability of perceiving details across the scales of the network, where a foreground-background-balanced loss function is designed to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100 K and small category of general object detection dataset MS COCO.
Author	Jiang, Yunliang Liu, Yong Deng, Chunfang Wang, Mengmeng Liu, Liang
Author_xml	– sequence: 1 givenname: Chunfang orcidid: 0000-0001-9476-3014 surname: Deng fullname: Deng, Chunfang email: dengcf@zju.edu.cn organization: Advanced Perception on Robotics and Intelligent Learning Laboratory, College of Control Science and Enginneering, Zhejiang University, Hangzhou, China – sequence: 2 givenname: Mengmeng orcidid: 0000-0003-4035-0630 surname: Wang fullname: Wang, Mengmeng email: mengmengwang@zju.edu.cn organization: Advanced Perception on Robotics and Intelligent Learning Laboratory, College of Control Science and Enginneering, Zhejiang University, Hangzhou, China – sequence: 3 givenname: Liang orcidid: 0000-0001-7910-810X surname: Liu fullname: Liu, Liang email: leonliuz@zju.edu.cn organization: Advanced Perception on Robotics and Intelligent Learning Laboratory, College of Control Science and Enginneering, Zhejiang University, Hangzhou, China – sequence: 4 givenname: Yong orcidid: 0000-0003-4822-8939 surname: Liu fullname: Liu, Yong email: yongliu@iipc.zju.edu.cn organization: Advanced Perception on Robotics and Intelligent Learning Laboratory, College of Control Science and Enginneering, Zhejiang University, Hangzhou, China – sequence: 5 givenname: Yunliang orcidid: 0000-0003-4500-5836 surname: Jiang fullname: Jiang, Yunliang email: jyl@zjhu.edu.cn organization: Huzhou University, Huzhou, China
BookMark	eNp9kM1PAjEUxBuDiYDeTbxs4nnx9WNpG08GQU1ATMRzU7qvySLsYrdE-e8twXjw4GneYX5vMtMjnbqpkZBLCgNKQd8sZrMBA0YHHKRgkp-QLtWC5gBSdtJdMMg1o3BGem27AqCiANklt-OviHWJZTZBG3cBs5d9sJuqzJ4xfjbhPfNNyF43dr3O5ssVupjdY0xSNfU5OfV23eLFj_bJ22S8GD3m0_nD0-humjumacy9KByFJTikJQjplPZDzcEuNZfOac-8UlI5ypUv0WueIOVVCawsVOHQ8T65Pv7dhuZjh200q2YX6hRp2FCktoWQRXLB0eVC07YBvdmGamPD3lAwh4lMmsgcJjI_EyVk-AdxVbSHajHYav0feHUEK0T8zdECtGSafwO34XQr
CODEN	ITMUF8
CitedBy_id	crossref_primary_10_1109_TGRS_2022_3188677 crossref_primary_10_3390_drones8050181 crossref_primary_10_1088_1361_6501_ad8a80 crossref_primary_10_1016_j_biosystemseng_2024_11_009 crossref_primary_10_1109_TGRS_2021_3128989 crossref_primary_10_1109_ACCESS_2022_3211394 crossref_primary_10_1109_TITS_2023_3304288 crossref_primary_10_1109_TPAMI_2023_3290594 crossref_primary_10_1016_j_infrared_2024_105475 crossref_primary_10_1016_j_engappai_2024_109362 crossref_primary_10_3390_app12115458 crossref_primary_10_32604_cmes_2024_052759 crossref_primary_10_3390_aerospace11050392 crossref_primary_10_1007_s11760_025_04222_4 crossref_primary_10_3390_app15137194 crossref_primary_10_1007_s42979_024_02658_y crossref_primary_10_1109_ACCESS_2024_3349978 crossref_primary_10_1016_j_eswa_2023_120185 crossref_primary_10_3390_s23167242 crossref_primary_10_1109_LGRS_2022_3223470 crossref_primary_10_1007_s11042_022_13735_w crossref_primary_10_1016_j_compag_2024_108719 crossref_primary_10_1007_s11801_024_3063_z crossref_primary_10_3390_electronics14020217 crossref_primary_10_34133_2022_9892464 crossref_primary_10_1016_j_compag_2024_109242 crossref_primary_10_1109_TPAMI_2023_3257546 crossref_primary_10_1109_TMM_2024_3358085 crossref_primary_10_1109_JSEN_2024_3467030 crossref_primary_10_1109_TMM_2024_3358080 crossref_primary_10_1007_s11227_025_07243_5 crossref_primary_10_1109_TGRS_2024_3379436 crossref_primary_10_1016_j_engappai_2025_110092 crossref_primary_10_1177_00405175231205898 crossref_primary_10_1016_j_eswa_2023_121811 crossref_primary_10_1109_ACCESS_2024_3509986 crossref_primary_10_3390_s24175661 crossref_primary_10_1109_JIOT_2025_3559921 crossref_primary_10_1016_j_patcog_2023_109801 crossref_primary_10_3390_s23167027 crossref_primary_10_1007_s11554_024_01562_1 crossref_primary_10_1016_j_imavis_2024_105054 crossref_primary_10_3390_app14041664 crossref_primary_10_3390_s23167145 crossref_primary_10_1007_s10489_023_05216_w crossref_primary_10_1016_j_patcog_2025_112449 crossref_primary_10_1049_ipr2_70027 crossref_primary_10_1109_TCE_2025_3527678 crossref_primary_10_1111_exsy_13444 crossref_primary_10_1016_j_aei_2024_102748 crossref_primary_10_1088_1361_6501_adcf41 crossref_primary_10_1177_14727978251362627 crossref_primary_10_1016_j_imavis_2025_105469 crossref_primary_10_3390_s22124339 crossref_primary_10_1109_ACCESS_2023_3264214 crossref_primary_10_1016_j_compag_2022_107609 crossref_primary_10_1109_TASE_2024_3517537 crossref_primary_10_3389_fmars_2022_1073615 crossref_primary_10_1007_s00371_023_02808_y crossref_primary_10_21015_vtse_v13i2_2136 crossref_primary_10_1016_j_imavis_2023_104697 crossref_primary_10_3390_appliedmath5020058 crossref_primary_10_1109_TCSVT_2023_3284161 crossref_primary_10_1186_s10033_023_00874_w crossref_primary_10_1109_TMM_2025_3542958 crossref_primary_10_1038_s41598_023_43458_3 crossref_primary_10_1109_TMM_2023_3264008 crossref_primary_10_3390_s25010214 crossref_primary_10_1007_s11760_024_03527_0 crossref_primary_10_1109_TPWRD_2024_3450185 crossref_primary_10_1007_s00371_024_03749_w crossref_primary_10_1007_s00521_025_11076_x crossref_primary_10_1016_j_patcog_2024_110976 crossref_primary_10_1109_TMM_2024_3521683 crossref_primary_10_3390_s23218851 crossref_primary_10_1016_j_engappai_2024_109684 crossref_primary_10_1007_s11227_025_06950_3 crossref_primary_10_3390_electronics12173600 crossref_primary_10_1049_ipr2_12766 crossref_primary_10_1016_j_jksuci_2023_101863 crossref_primary_10_1109_ACCESS_2024_3387938 crossref_primary_10_1016_j_patcog_2024_110983 crossref_primary_10_1007_s11042_023_16231_x crossref_primary_10_1016_j_jclepro_2023_140415 crossref_primary_10_1016_j_neucom_2025_130133 crossref_primary_10_1109_TCSVT_2022_3221755 crossref_primary_10_1007_s40747_024_01652_4 crossref_primary_10_1109_TMM_2023_3330103 crossref_primary_10_1016_j_eswa_2022_119148 crossref_primary_10_1117_1_JEI_32_6_063007 crossref_primary_10_1109_JSTARS_2024_3452680 crossref_primary_10_1109_TMM_2024_3453040 crossref_primary_10_3390_app14156398 crossref_primary_10_1109_TCSVT_2025_3532243 crossref_primary_10_1109_TGRS_2025_3581150 crossref_primary_10_1177_00202940241268952 crossref_primary_10_3390_electronics12204293 crossref_primary_10_1016_j_eswa_2024_125732 crossref_primary_10_1109_ACCESS_2023_3286031 crossref_primary_10_3389_fnbot_2023_1315251 crossref_primary_10_1007_s00371_024_03709_4 crossref_primary_10_1109_LGRS_2024_3372500 crossref_primary_10_1016_j_engappai_2023_107513 crossref_primary_10_3390_rs14163919 crossref_primary_10_3390_rs15143525 crossref_primary_10_1016_j_compbiomed_2022_105763 crossref_primary_10_1007_s41060_025_00881_1 crossref_primary_10_1109_ACCESS_2022_3156953 crossref_primary_10_1002_cpe_70118 crossref_primary_10_1186_s13104_025_07263_7 crossref_primary_10_1049_cit2_12411 crossref_primary_10_1109_JSTARS_2022_3176141 crossref_primary_10_1109_TCSVT_2022_3198329 crossref_primary_10_3389_fnbot_2023_1273251 crossref_primary_10_1109_TGRS_2024_3417960 crossref_primary_10_1109_TKDE_2022_3179608 crossref_primary_10_1016_j_eswa_2024_125964 crossref_primary_10_1109_TMM_2022_3178871 crossref_primary_10_1007_s10278_025_01460_3 crossref_primary_10_3390_s23052439 crossref_primary_10_1007_s10044_025_01526_6 crossref_primary_10_1049_ipr2_70188 crossref_primary_10_1080_09540091_2023_2168254 crossref_primary_10_1109_ACCESS_2024_3388590 crossref_primary_10_3390_rs15235575 crossref_primary_10_1109_TMM_2024_3521793 crossref_primary_10_1016_j_patrec_2024_11_027 crossref_primary_10_1109_TMM_2025_3542970 crossref_primary_10_1016_j_patcog_2023_109558 crossref_primary_10_1049_ell2_12732 crossref_primary_10_1016_j_eswa_2024_126375 crossref_primary_10_1109_TGRS_2024_3363614 crossref_primary_10_3390_rs17142415 crossref_primary_10_1007_s11042_023_16309_6 crossref_primary_10_1109_ACCESS_2025_3538873 crossref_primary_10_1007_s00371_025_03878_w crossref_primary_10_1016_j_image_2023_116919 crossref_primary_10_1016_j_neunet_2022_08_029 crossref_primary_10_1109_TGRS_2023_3276995 crossref_primary_10_1121_10_0037080 crossref_primary_10_1016_j_eswa_2022_118665 crossref_primary_10_1038_s41598_024_51868_0 crossref_primary_10_1007_s00521_023_08741_4 crossref_primary_10_1109_TITS_2024_3522195 crossref_primary_10_1109_JSEN_2023_3263539 crossref_primary_10_1109_ACCESS_2023_3260223 crossref_primary_10_1109_TGRS_2024_3454355 crossref_primary_10_1016_j_compag_2022_107587 crossref_primary_10_3390_geosciences12060248 crossref_primary_10_1016_j_bspc_2025_108064 crossref_primary_10_1016_j_eswa_2024_125505 crossref_primary_10_1155_2022_6394823 crossref_primary_10_1016_j_dsp_2025_105268 crossref_primary_10_1007_s10044_024_01323_7 crossref_primary_10_3390_electronics13245014 crossref_primary_10_3390_s25020589 crossref_primary_10_1016_j_neucom_2025_130327 crossref_primary_10_3390_app13116587 crossref_primary_10_1007_s11042_023_17838_w crossref_primary_10_3390_rs17121997 crossref_primary_10_1007_s13197_025_06428_3 crossref_primary_10_3390_rs15092322 crossref_primary_10_1007_s11042_024_18618_w crossref_primary_10_1016_j_eswa_2024_124686 crossref_primary_10_1016_j_sigpro_2024_109619 crossref_primary_10_3390_s25113511 crossref_primary_10_1016_j_autcon_2022_104399 crossref_primary_10_1016_j_cja_2025_103781 crossref_primary_10_1080_01431161_2022_2038396 crossref_primary_10_1109_TGRS_2021_3133956 crossref_primary_10_3390_electronics12051142 crossref_primary_10_3390_electronics12040817 crossref_primary_10_3390_sym16040401 crossref_primary_10_1177_30504554251319452 crossref_primary_10_3390_electronics14081548 crossref_primary_10_1109_ACCESS_2023_3321966 crossref_primary_10_1109_TGRS_2023_3346041 crossref_primary_10_3390_electronics13020409 crossref_primary_10_3390_rs15092433 crossref_primary_10_1007_s00530_023_01243_2 crossref_primary_10_3390_electronics13234820 crossref_primary_10_3390_rs15112728 crossref_primary_10_1088_1361_6501_ad7972 crossref_primary_10_1016_j_isprsjprs_2025_01_005 crossref_primary_10_3390_app14114857 crossref_primary_10_3390_s23187806 crossref_primary_10_1587_elex_22_20240283 crossref_primary_10_1007_s10489_024_05556_1 crossref_primary_10_1109_TPAMI_2025_3544621 crossref_primary_10_1007_s00371_024_03284_8 crossref_primary_10_3390_ijgi14090365 crossref_primary_10_3390_s24175496 crossref_primary_10_1080_22797254_2025_2540109 crossref_primary_10_1016_j_cja_2024_06_036 crossref_primary_10_1007_s11042_021_11413_x crossref_primary_10_3390_insects16090959 crossref_primary_10_1109_TMM_2023_3236212 crossref_primary_10_1007_s10489_024_05418_w crossref_primary_10_1016_j_measurement_2025_117019 crossref_primary_10_1109_TNNLS_2024_3454063 crossref_primary_10_1016_j_engappai_2024_108500 crossref_primary_10_1016_j_undsp_2024_07_003 crossref_primary_10_1007_s00371_024_03277_7 crossref_primary_10_1109_TMM_2024_3521841 crossref_primary_10_3389_fpls_2024_1375118 crossref_primary_10_1109_TIM_2025_3556896 crossref_primary_10_1109_TGRS_2025_3602640 crossref_primary_10_1016_j_ipm_2024_103858 crossref_primary_10_1109_JSTARS_2025_3551551 crossref_primary_10_1109_TGRS_2024_3520161 crossref_primary_10_1109_TITS_2024_3373793 crossref_primary_10_1155_2022_6390260 crossref_primary_10_1109_TMM_2025_3543091 crossref_primary_10_1016_j_imavis_2024_105232 crossref_primary_10_1109_TIM_2022_3219500 crossref_primary_10_3390_rs16040644 crossref_primary_10_1109_ACCESS_2023_3292881 crossref_primary_10_3390_math12050622 crossref_primary_10_3390_drones9090659 crossref_primary_10_1007_s11554_024_01507_8 crossref_primary_10_1007_s10462_023_10455_x crossref_primary_10_1109_TAES_2024_3512525 crossref_primary_10_1007_s11760_025_04085_9 crossref_primary_10_1109_TMM_2025_3535341 crossref_primary_10_1109_JSEN_2024_3374388 crossref_primary_10_3390_machines10080626 crossref_primary_10_1016_j_patcog_2023_110041 crossref_primary_10_1109_TMM_2024_3396281 crossref_primary_10_1016_j_patcog_2024_110312 crossref_primary_10_1109_TPAMI_2022_3166956 crossref_primary_10_1049_ell2_12690 crossref_primary_10_1109_ACCESS_2025_3584952 crossref_primary_10_1109_TGRS_2023_3294241 crossref_primary_10_1371_journal_pone_0304691 crossref_primary_10_1016_j_autcon_2024_105643 crossref_primary_10_1109_TMM_2024_3371787 crossref_primary_10_3390_math10122150 crossref_primary_10_3390_s24123828 crossref_primary_10_1007_s00530_024_01360_6 crossref_primary_10_1109_TMM_2022_3223780 crossref_primary_10_1109_TAES_2023_3238703 crossref_primary_10_1109_TCSVT_2024_3402097 crossref_primary_10_1109_TMM_2023_3347645 crossref_primary_10_1016_j_cviu_2023_103787 crossref_primary_10_1109_TMM_2023_3234368 crossref_primary_10_1109_TGRS_2023_3344584 crossref_primary_10_3390_app122211854 crossref_primary_10_1109_TIV_2024_3450201 crossref_primary_10_1016_j_dsp_2025_105121 crossref_primary_10_1016_j_neucom_2024_127715 crossref_primary_10_1017_pasa_2023_34 crossref_primary_10_1109_TIM_2024_3385846 crossref_primary_10_3390_info16090798 crossref_primary_10_1109_TCSVT_2023_3286896 crossref_primary_10_1016_j_cviu_2025_104428 crossref_primary_10_1109_ACCESS_2023_3286545 crossref_primary_10_1016_j_knosys_2024_112353 crossref_primary_10_1109_TGRS_2023_3343806 crossref_primary_10_3390_app142411604
Cites_doi	10.1109/CVPR.2016.207 10.1109/ICCV.2017.324 10.1109/CVPR.2019.00720 10.1007/978-3-030-01231-1_6 10.1109/CVPR.2016.89 10.1109/CVPR.2017.106 10.1109/ICCV.2019.00615 10.1109/TMM.2018.2863602 10.1109/TMM.2016.2642789 10.1109/ICCV.2015.169 10.1109/CVPR.2018.00062 10.1109/CVPR.2018.00010 10.1109/CVPR.2019.00817 10.1109/TPAMI.2016.2577031 10.1109/CVPR.2016.91 10.3390/s17051062 10.1109/CVPR.2019.00091 10.1609/aaai.v33i01.33019259 10.1109/TMM.2020.2999182 10.1109/CVPR.2017.243 10.1109/ICCV.2019.00975 10.1109/CVPR.2014.81 10.1109/ICCV.2019.00982 10.1109/TMM.2019.2916104 10.1007/978-3-030-01240-3_21 10.1109/ICCV.2019.00972 10.1109/CVPR.2016.232 10.1109/CVPR.2019.00093 10.1007/978-3-319-46493-0_22 10.1109/CVPR.2017.634 10.1109/CVPR.2017.211 10.1007/978-3-030-01252-6_24 10.1109/CVPR.2018.00913 10.1007/978-3-030-00764-5_51
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TMM.2021.3074273
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1941-0077
EndPage	1979
ExternalDocumentID	10_1109_TMM_2021_3074273 9409729
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61836015 funderid: 10.13039/501100001809
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TN5 VH1 ZY4 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-f45c10b0ce1d047c89f6930ab937cc9f2f8878c138fdef932918f8d02d585cec3
IEDL.DBID	RIE
ISICitedReferencesCount	323
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000778959200015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1520-9210
IngestDate	Mon Jun 30 04:47:19 EDT 2025 Sat Nov 29 03:10:07 EST 2025 Tue Nov 18 21:58:05 EST 2025 Wed Aug 27 02:40:51 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-f45c10b0ce1d047c89f6930ab937cc9f2f8878c138fdef932918f8d02d585cec3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-4035-0630 0000-0001-9476-3014 0000-0003-4822-8939 0000-0001-7910-810X 0000-0003-4500-5836
PQID	2647425475
PQPubID	75737
PageCount	12
ParticipantIDs	proquest_journals_2647425475 crossref_primary_10_1109_TMM_2021_3074273 ieee_primary_9409729 crossref_citationtrail_10_1109_TMM_2021_3074273
PublicationCentury	2000
PublicationDate	20220000 2022-00-00 20220101
PublicationDateYYYYMMDD	2022-01-01
PublicationDate_xml	– year: 2022 text: 20220000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE transactions on multimedia
PublicationTitleAbbrev	TMM
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	lin (ref38) 0 ref35 ref13 ref34 ref37 ref36 ref31 ref30 ref33 ref11 ref32 ref2 ref1 ref39 ref17 haris (ref9) 2018 ref16 bai (ref10) 0 ref18 yu (ref19) 0 law (ref14) 0 zhou (ref15) 2019 ref24 ref23 ref26 ref25 ref20 ref42 ref22 ref44 ref21 ref43 ref28 ref27 ref29 ref8 ref7 ref3 liu (ref5) 0 ref6 girshick (ref41) 2018 goodfellow (ref12) 0 ref40 dai (ref4) 0
References_xml	– ident: ref32 doi: 10.1109/CVPR.2016.207 – ident: ref7 doi: 10.1109/ICCV.2017.324 – start-page: 734 year: 0 ident: ref14 article-title: CornerNet: Detecting objects as paired keypoints publication-title: Proc Eur Conf Comput Vis – start-page: 206 year: 0 ident: ref10 article-title: SOD-MTGAN: Small object detection via multi-task generative adversarial network publication-title: Proc Eur Conf Comput Vis – ident: ref27 doi: 10.1109/CVPR.2019.00720 – start-page: 740 year: 0 ident: ref38 article-title: Microsoft COCO: Common objects in context publication-title: Proc Eur Conf Comput Vis – ident: ref36 doi: 10.1007/978-3-030-01231-1_6 – ident: ref40 doi: 10.1109/CVPR.2016.89 – ident: ref8 doi: 10.1109/CVPR.2017.106 – ident: ref22 doi: 10.1109/ICCV.2019.00615 – ident: ref34 doi: 10.1109/TMM.2018.2863602 – ident: ref23 doi: 10.1109/TMM.2016.2642789 – start-page: 2672 year: 0 ident: ref12 article-title: Generative adversarial nets publication-title: Proc Neural Inf Process Syst – start-page: 21 year: 0 ident: ref5 article-title: SSD: Single shot multibox detector publication-title: Proc Eur Conf Comput Vis – year: 2018 ident: ref9 article-title: Task-driven super resolution: Object detection in low-resolution images – ident: ref2 doi: 10.1109/ICCV.2015.169 – ident: ref30 doi: 10.1109/CVPR.2018.00062 – ident: ref29 doi: 10.1109/CVPR.2018.00010 – year: 2019 ident: ref15 article-title: Objects as points – ident: ref35 doi: 10.1109/CVPR.2019.00817 – ident: ref3 doi: 10.1109/TPAMI.2016.2577031 – ident: ref6 doi: 10.1109/CVPR.2016.91 – ident: ref28 doi: 10.3390/s17051062 – ident: ref43 doi: 10.1109/CVPR.2019.00091 – ident: ref26 doi: 10.1609/aaai.v33i01.33019259 – ident: ref33 doi: 10.1109/TMM.2020.2999182 – ident: ref31 doi: 10.1109/CVPR.2017.243 – ident: ref44 doi: 10.1109/ICCV.2019.00975 – ident: ref1 doi: 10.1109/CVPR.2014.81 – ident: ref13 doi: 10.1109/ICCV.2019.00982 – ident: ref18 doi: 10.1109/TMM.2019.2916104 – ident: ref21 doi: 10.1007/978-3-030-01240-3_21 – ident: ref16 doi: 10.1109/ICCV.2019.00972 – ident: ref37 doi: 10.1109/CVPR.2016.232 – ident: ref17 doi: 10.1109/CVPR.2019.00093 – ident: ref24 doi: 10.1007/978-3-319-46493-0_22 – year: 2018 ident: ref41 article-title: Detectron – year: 0 ident: ref19 article-title: Multi-scale context aggregation by dilated convolutions publication-title: Proc Int Conf Learn Representations – start-page: 379 year: 0 ident: ref4 article-title: R-FCN: Object detection via region-based fully convolutional networks publication-title: Proc Neural Inf Process Syst – ident: ref39 doi: 10.1109/CVPR.2017.634 – ident: ref11 doi: 10.1109/CVPR.2017.211 – ident: ref20 doi: 10.1007/978-3-030-01252-6_24 – ident: ref25 doi: 10.1109/CVPR.2018.00913 – ident: ref42 doi: 10.1007/978-3-030-00764-5_51
SSID	ssj0014507
Score	2.7057776
Snippet	Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1968
SubjectTerms	Datasets deep learning Detectors Distillation Feature extraction feature pyramid feature super-resolution knowledge distillation Object detection Object recognition Pipelines Semantics Signal resolution Small object detection Superresolution
Title	Extended Feature Pyramid Network for Small Object Detection
URI	https://ieeexplore.ieee.org/document/9409729 https://www.proquest.com/docview/2647425475
Volume	24
WOSCitedRecordID	wos000778959200015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0077 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014507 issn: 1520-9210 databaseCode: RIE dateStart: 19990101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH9sw4MenG6K0yk5eBHslrZpm-BJ1OHBzYETdivNFwy2TrpN8L83ybqhKIK3HpJS3q_J-71vgEtDKTDHlHicc-oZDa09jjPhhZlgPAoJldI1cX1KBgM6HrNhBa63tTBKKZd8pjr20cXy5VysrKusy2xzpoBVoZok8bpWaxsxIJErjTbqCHvM2DGbkCRm3VG_bwzBwO-E1hBMwm8qyM1U-XERO-3Sq__vuw5gv2SR6HYN-yFUVN6A-mZCAyoPbAP2vrQbbMLNQ-nxRpb4rQqFhh9FNptINFgngyPDYNHLLJtO0TO3Dhp0r5YuVys_gtfew-ju0SuHJ3giYP7S0yQSvoFBKF9ikgjKtJ16mHHDR4RgOtDmeqHCD6mWShsWx3yqqcSBNAaEUCI8hlo-z9UJIBnHmNgIqUw00YRRbd6pFOPcsLk4C1rQ3cgzFWVncTvgYpo6CwOz1CCQWgTSEoEWXG13vK27avyxtmklvl1XCrsF7Q1kaXnsFqlhd2ZPRJLo9PddZ7Ab2PoF50NpQ21ZrNQ57Ij35WRRXLg_6hNo3MeY
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD7MKagPTqfidGoefBHslrbpmuCT6MbEbQ6csLfS3GCwi-wi-O9Nsm4oiuBbH5JSztfkfOcOcGUoBeaYEo9zTj2jobXHcSq8MBWMRyGhUromrq2406H9Puvm4GZdC6OUcslnqmIfXSxfTsTCusqqzDZnCtgGbEaEBHhZrbWOGZDIFUcbhYQ9ZiyZVVASs2qv3TamYOBXQmsKxuE3JeSmqvy4ip1-aRT-92X7sJfxSHS3BP4AcmpchMJqRgPKjmwRdr80HDyE23rm80aW-i2mCnU_puloIFFnmQ6ODIdFL6N0OETP3Lpo0IOau2yt8RG8Nuq9-6aXjU_wRMD8uadJJHwDhFC-xCQWlGk79zDlhpEIwXSgzQVDhR9SLZU2PI75VFOJA2lMCKFEeAz58WSsTgDJWg0TGyOVsSaaMKrNO5VinBs-V0uDElRX8kxE1lvcjrgYJs7GwCwxCCQWgSRDoATX6x1vy74af6w9tBJfr8uEXYLyCrIkO3izxPA7sycicXT6-65L2G722q2k9dh5OoOdwFYzOI9KGfLz6UKdw5Z4nw9m0wv3d30C90LK3w
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=Extended+Feature+Pyramid+Network+for+Small+Object+Detection&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Deng%2C+Chunfang&rft.au=Wang%2C+Mengmeng&rft.au=Liu%2C+Liang&rft.au=Liu%2C+Yong&rft.date=2022&rft.issn=1520-9210&rft.eissn=1941-0077&rft.volume=24&rft.spage=1968&rft.epage=1979&rft_id=info:doi/10.1109%2FTMM.2021.3074273&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMM_2021_3074273
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon