Deep LAC: Deep localization, alignment and classification for fine-grained recognition
We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a nontrivial process, as the input to the classification module should be functions that enable back-propagation in constructing the solver. Our major c...
Saved in:
| Published in | 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1666 - 1674 |
|---|---|
| Main Authors | , , , |
| Format | Conference Proceeding |
| Language | English |
| Published |
IEEE
01.06.2015
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a nontrivial process, as the input to the classification module should be functions that enable back-propagation in constructing the solver. Our major contribution is to propose a valve linkage function (VLF) for back-propagation chaining and form our deep localization, alignment and classification (LAC) system. The VLF can adaptively compromise the errors of classification and alignment when training the LAC model. It in turn helps update localization. The performance on fine-grained object data bears out the effectiveness of our LAC system. |
|---|---|
| AbstractList | We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a nontrivial process, as the input to the classification module should be functions that enable back-propagation in constructing the solver. Our major contribution is to propose a valve linkage function (VLF) for back-propagation chaining and form our deep localization, alignment and classification (LAC) system. The VLF can adaptively compromise the errors of classification and alignment when training the LAC model. It in turn helps update localization. The performance on fine-grained object data bears out the effectiveness of our LAC system. |
| Author | Cewu Lu Xiaoyong Shen Jiaya Jia Di Lin |
| Author_xml | – sequence: 1 surname: Di Lin fullname: Di Lin organization: Chinese Univ. of Hong Kong, Hong Kong, China – sequence: 2 surname: Xiaoyong Shen fullname: Xiaoyong Shen organization: Chinese Univ. of Hong Kong, Hong Kong, China – sequence: 3 surname: Cewu Lu fullname: Cewu Lu organization: Hong Kong Univ. of Sci. & Technol., Hong Kong, China – sequence: 4 surname: Jiaya Jia fullname: Jiaya Jia organization: Chinese Univ. of Hong Kong, Hong Kong, China |
| BookMark | eNotkMtOwzAURI1UJNrSD0Bs_AEkXNvxi10VykOKBELQbeU415Gl1KmSbuDrCaWrGc3RzGIWZJb6hITcMMgZA3tfbt8_cg5M5ppbo7W8IAtWKC2UVQXMyJyBEpmyzF6R1TjGGgSAsZbDnGwfEQ-0WpcP9OS63rsu_rhj7NMdnWyb9piO1KWG-s5N7RD9idLQDzTEhFk7uEkaOqDv2xT_4DW5DK4bcXXWJfl62nyWL1n19vxarqvMF0wcs0IKWTMBPEBR64YZa5hqQs00R-n5lEhh6loaY6XUUlgtDXjnNTZc2QBiSW7_dyMi7g5D3Lvhe3e-QfwCMJBSNw |
| CitedBy_id | crossref_primary_10_1007_s00521_022_07777_2 crossref_primary_10_1145_3231742 crossref_primary_10_1109_ACCESS_2019_2918274 crossref_primary_10_1109_ACCESS_2020_3039345 crossref_primary_10_1016_j_cviu_2019_102865 crossref_primary_10_1109_ACCESS_2020_3040857 crossref_primary_10_3390_s23083970 crossref_primary_10_1109_TPAMI_2017_2724029 crossref_primary_10_3390_app131810493 crossref_primary_10_1109_TIP_2017_2688133 crossref_primary_10_1109_TPAMI_2019_2933510 crossref_primary_10_1007_s11263_017_1048_0 crossref_primary_10_1109_ACCESS_2019_2947717 crossref_primary_10_1007_s11263_023_01760_7 crossref_primary_10_3390_sym10100479 crossref_primary_10_1007_s11063_020_10246_3 crossref_primary_10_1109_TVT_2019_2899972 crossref_primary_10_1109_TIP_2016_2599102 crossref_primary_10_1109_TMM_2017_2710803 crossref_primary_10_1016_j_procs_2018_05_144 crossref_primary_10_1016_j_cosrev_2021_100374 crossref_primary_10_1186_s41074_017_0033_4 crossref_primary_10_1007_s00371_024_03366_7 crossref_primary_10_1016_j_knosys_2021_106840 crossref_primary_10_1109_TCSVT_2021_3065693 crossref_primary_10_1117_1_JEI_33_3_033013 crossref_primary_10_3390_s24134127 crossref_primary_10_1109_LRA_2017_2667039 crossref_primary_10_1016_j_imavis_2023_104753 crossref_primary_10_1145_3446208 crossref_primary_10_1007_s11432_022_3586_y crossref_primary_10_3390_app9020301 crossref_primary_10_1109_ACCESS_2021_3072623 crossref_primary_10_1109_ACCESS_2020_3030249 crossref_primary_10_1109_TCSVT_2023_3248791 crossref_primary_10_1002_int_22775 crossref_primary_10_1109_TCSVT_2020_2978115 crossref_primary_10_1088_1361_665X_aba540 crossref_primary_10_1109_TIP_2019_2921876 crossref_primary_10_1109_ACCESS_2019_2933169 crossref_primary_10_1109_TNNLS_2021_3126046 crossref_primary_10_3390_e20050341 crossref_primary_10_1007_s00371_020_02052_8 crossref_primary_10_1007_s00138_023_01378_2 crossref_primary_10_1109_ACCESS_2022_3179358 crossref_primary_10_1109_TIP_2020_2977457 crossref_primary_10_1109_TIP_2017_2695883 crossref_primary_10_3390_app13074453 crossref_primary_10_1109_ACCESS_2018_2884695 crossref_primary_10_1109_TMM_2018_2796240 crossref_primary_10_1109_TMM_2021_3134156 crossref_primary_10_1109_TMM_2020_3028482 crossref_primary_10_1145_3615659 crossref_primary_10_3390_app10134652 crossref_primary_10_1162_neco_a_01302 crossref_primary_10_1007_s11042_018_7047_5 crossref_primary_10_1109_TNNLS_2020_3027603 crossref_primary_10_3390_s23187920 crossref_primary_10_1007_s11042_022_12921_0 crossref_primary_10_1109_TMM_2023_3291819 crossref_primary_10_1007_s00521_021_06368_x crossref_primary_10_3390_app10093280 crossref_primary_10_1109_TMM_2016_2631122 crossref_primary_10_1007_s11263_018_1109_z crossref_primary_10_1007_s10489_022_03355_0 crossref_primary_10_1049_ipr2_12238 crossref_primary_10_1007_s11042_018_5957_x crossref_primary_10_1016_j_cviu_2023_103658 crossref_primary_10_1007_s00371_023_03226_w crossref_primary_10_1007_s10489_022_03232_w crossref_primary_10_1016_j_patcog_2023_110216 crossref_primary_10_1109_TMM_2016_2602060 crossref_primary_10_1007_s11042_022_13811_1 crossref_primary_10_1109_TMM_2021_3061284 crossref_primary_10_1109_TPAMI_2023_3274593 crossref_primary_10_1109_TIP_2021_3055627 crossref_primary_10_1109_TMM_2019_2954747 crossref_primary_10_1587_transinf_2021EDP7166 crossref_primary_10_3390_electronics12234805 crossref_primary_10_3390_e25040601 crossref_primary_10_1109_TGRS_2023_3311093 crossref_primary_10_1109_TMM_2021_3130414 crossref_primary_10_1587_transinf_2017EDL8076 crossref_primary_10_1007_s00138_021_01180_y crossref_primary_10_1109_TIP_2022_3145159 crossref_primary_10_3390_electronics12183817 crossref_primary_10_1109_TCSVT_2022_3227737 crossref_primary_10_3389_fnbot_2024_1391791 crossref_primary_10_1109_TCYB_2018_2885062 crossref_primary_10_1109_TNNLS_2022_3202534 crossref_primary_10_1109_TNNLS_2017_2728060 crossref_primary_10_1109_ACCESS_2019_2936118 crossref_primary_10_1007_s11431_020_1777_4 crossref_primary_10_1109_TIP_2017_2751960 crossref_primary_10_1109_TIP_2022_3181492 crossref_primary_10_1109_TPAMI_2020_2993147 crossref_primary_10_1587_transinf_2022DLP0006 crossref_primary_10_1007_s11042_018_5875_y crossref_primary_10_1016_j_procs_2019_08_227 crossref_primary_10_1109_ACCESS_2020_2999722 crossref_primary_10_1007_s11042_024_18598_x crossref_primary_10_1111_coin_12638 crossref_primary_10_1109_TCSVT_2018_2834480 crossref_primary_10_1007_s10278_024_01082_1 crossref_primary_10_1007_s12539_021_00479_8 crossref_primary_10_1109_TMM_2020_2993960 crossref_primary_10_1016_j_jvcir_2022_103632 crossref_primary_10_1109_JSTARS_2022_3212680 crossref_primary_10_1007_s11263_019_01176_2 crossref_primary_10_1145_3605892 crossref_primary_10_1007_s41095_020_0184_6 crossref_primary_10_1007_s00138_020_01125_x crossref_primary_10_1007_s11263_021_01498_0 crossref_primary_10_1016_j_neucom_2016_05_089 crossref_primary_10_1109_TNNLS_2021_3100928 crossref_primary_10_1109_TMM_2022_3158001 crossref_primary_10_3390_electronics9122038 crossref_primary_10_1109_TNNLS_2017_2731775 crossref_primary_10_1109_TPAMI_2016_2640295 crossref_primary_10_1109_TIP_2019_2924811 crossref_primary_10_1016_j_cviu_2021_103184 crossref_primary_10_1109_TCYB_2018_2813971 crossref_primary_10_1109_TPAMI_2021_3126648 crossref_primary_10_1007_s11263_016_0970_x crossref_primary_10_1016_j_knosys_2021_106815 crossref_primary_10_1109_TIP_2017_2774041 crossref_primary_10_1109_TITS_2018_2799228 crossref_primary_10_3390_app9091939 crossref_primary_10_1109_ACCESS_2019_2956172 crossref_primary_10_1109_TCSVT_2019_2892802 crossref_primary_10_1117_1_JEI_28_2_023024 |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR.2015.7298775 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library Online IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore (IEEE/IET Electronic Library - IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Computer Science |
| EISBN | 1467369640 9781467369640 |
| EndPage | 1674 |
| ExternalDocumentID | 7298775 |
| Genre | orig-research |
| GroupedDBID | 23M 29F 29O 6IE 6IH 6IK ACGFS ALMA_UNASSIGNED_HOLDINGS CBEJK G8K IPLJI JC5 M43 RIE RIG RIO RNS |
| ID | FETCH-LOGICAL-c413t-4535b1302f04b7d189816dfb172e5c27d1538bb58895575397580cac7ed269f03 |
| IEDL.DBID | RIE |
| ISSN | 1063-6919 |
| IngestDate | Wed Jun 26 19:24:45 EDT 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c413t-4535b1302f04b7d189816dfb172e5c27d1538bb58895575397580cac7ed269f03 |
| OpenAccessLink | http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Lin_Deep_LAC_Deep_2015_CVPR_paper.pdf |
| PageCount | 9 |
| ParticipantIDs | ieee_primary_7298775 |
| PublicationCentury | 2000 |
| PublicationDate | 20150601 |
| PublicationDateYYYYMMDD | 2015-06-01 |
| PublicationDate_xml | – month: 06 year: 2015 text: 20150601 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2015 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssib030089920 ssj0023720 |
| Score | 2.51671 |
| Snippet | We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1666 |
| SubjectTerms | Birds Couplings Feature extraction Head Neural networks Training Valves |
| Title | Deep LAC: Deep localization, alignment and classification for fine-grained recognition |
| URI | https://ieeexplore.ieee.org/document/7298775 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwELbaTkwFWsRbHhjrNC87NhsqVBWiqEK06lbFj3RASitIF349Z8cpAjGwnS5SYjn23Zfcd_4QutFRJPK8yAmLFSVpLAsiOcthx2saxjox3EmyTJ_ZZJ4-LumyhQb7XhhjjCOfmcCarpavN2pnf5UNAQjyLKNt1M4Eq3u1mrWThLZ-ZaGP_9iy6iuu0skSwkQkfEUzCsVwtJi9WFIXDfwNfyiruMQy7qJpM6SaT_IW7CoZqM9fpzX-d8yHqP_dwodn--R0hFqmPEZdjzmx39Ef4GpkHRpfDy3ujdnip7vRLXaWS3e-XXOAwVw7BgHOS42VBd-WbeSuYkDAuADcStZWeQIetOcnbco-mo8fXkcT4uUXiILMVpGUJlTaumYRpjLTERc8YrqQAHkMVTF4IFhKSTkXFEAfABvKQ5WrzOiYiSJMTlCn3JTmFGEIiyIXgI24zFItc8kjI5RMIeonAAjZGerZmVtt6xM2Vn7Szv92X6AD-_ZqwtYl6lTvO3MF0KCS125NfAEBnLVh |
| link.rule.ids | 309,310,780,784,789,790,796,23930,23931,25140,27925,54758 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjZ3PT8IwFMcbxIOeUMH42x48Utyvbq03gxJUIMQA4UbWH-NgMoiOi3-9r12H0Xjw1rwlW9O1fZ_tfV8fQjfK93maZimJA0lJFIiMCBansOIV9QIVamZLsgxHcX8aPc_pvIba21wYrbUVn-mOadpYvlrJjflVdgsgyJKE7qBdGgHnltla1ewJPRPBMvDjPrdM_RUb64xDEnOfu5im7_Hb7mz8amRdtONu-aO2inUtvQYaVp0qFSVvnU0hOvLz13mN_-31AWp9J_Hh8dY9HaKazo9Qw1Endmv6A0xVYYfK1kSzB63XeHDfvcO2ZR2eS9hsY2gurYYAp7nC0uC30RvZqxgYGGdArmRpak_Ag7YKpVXeQtPe46TbJ64AA5Hg2woS0ZAKE9nMvEgkymec-bHKBECPpjIAC2yXQlDGOAXsA7ShzJOpTLQKYp554TGq56tcnyAMGyNPOdARE0mkRCqYr7kUEez7ISBhfIqaZuQW6_KMjYUbtLO_zddorz8ZDhaDp9HLOdo3b7KUb12gevG-0ZcACoW4svPjC79QuLQ |
| 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=proceeding&rft.title=2015+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.atitle=Deep+LAC%3A+Deep+localization%2C+alignment+and+classification+for+fine-grained+recognition&rft.au=Di+Lin&rft.au=Xiaoyong+Shen&rft.au=Cewu+Lu&rft.au=Jiaya+Jia&rft.date=2015-06-01&rft.pub=IEEE&rft.issn=1063-6919&rft.spage=1666&rft.epage=1674&rft_id=info:doi/10.1109%2FCVPR.2015.7298775&rft.externalDocID=7298775 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon |