Reweighting neural network examples for robust object detection at sea
Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in th...
Saved in:
| Published in | Electronics letters Vol. 57; no. 16; pp. 608 - 610 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Stevenage
John Wiley & Sons, Inc
01.08.2021
Wiley |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in their respective datasets. In this work, methods for achieving robust neural networks, able to tolerate untrusted and possibly erroneous training data, are explored. The proposed method is shown to improve performance and help neural networks learn from untrusted data, provided a thoroughly annotated subset. |
|---|---|
| AbstractList | Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in their respective datasets. In this work, methods for achieving robust neural networks, able to tolerate untrusted and possibly erroneous training data, are explored. The proposed method is shown to improve performance and help neural networks learn from untrusted data, provided a thoroughly annotated subset. Abstract Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in their respective datasets. In this work, methods for achieving robust neural networks, able to tolerate untrusted and possibly erroneous training data, are explored. The proposed method is shown to improve performance and help neural networks learn from untrusted data, provided a thoroughly annotated subset. |
| Author | Nalpantidis, L. Becktor, J. Blanke, M. Boukas, E. |
| Author_xml | – sequence: 1 givenname: J. surname: Becktor fullname: Becktor, J. email: Jbibe@elektro.dtu.dk organization: Technical University of Denmark – sequence: 2 givenname: E. surname: Boukas fullname: Boukas, E. organization: Technical University of Denmark – sequence: 3 givenname: M. surname: Blanke fullname: Blanke, M. organization: Technical University of Denmark – sequence: 4 givenname: L. surname: Nalpantidis fullname: Nalpantidis, L. organization: Technical University of Denmark |
| BookMark | eNp9kFtLAzEQhYMoWC8v_oIF34TVTJJmk0cRL4WCIAq-hVxm69btpiZbqv_erSs--nSY4ZszM-eI7HexQ0LOgF4CFfoK25ZdAgMp98gE-JSWGuB1n0woBV5OQYtDcpTzciiZ1tWE3D3hFpvFW990i6LDTbLtIP02pvcCP-1q3WIu6piKFN0m90V0S_R9EbAfpIldYfsioz0hB7VtM57-6jF5ubt9vnko54_3s5vreekF5bJUwgWmQPmgqQKOXgVVucC5FIqC04pPpYI6sFpXGJxwQisnA0pVBfS84sdkNvqGaJdmnZqVTV8m2sb8NGJaGJv6xrdo-NRVXgbBNChRD98qVmmrUcvgOYIevM5Hr3WKHxvMvVnGTeqG8w2nmikqQLGBuhgpn2LOCeu_rUDNLnOzy9z8ZD7AMMLbpsWvf0hzO5-zceYbfHiD-A |
| CitedBy_id | crossref_primary_10_1016_j_ifacol_2022_10_410 crossref_primary_10_1049_ell2_12690 crossref_primary_10_1016_j_mlwa_2022_100411 crossref_primary_10_1109_TITS_2021_3122275 crossref_primary_10_1155_2023_2768126 |
| Cites_doi | 10.1117/12.898272 10.1016/j.ifacol.2020.12.1455 10.1088/1742-6596/1357/1/012036 10.1109/CVPR.2016.90 10.1088/1757-899X/929/1/012023 10.1613/jair.953 10.1109/ICCV.2011.6126229 10.1109/ICCV.2017.324 10.1006/jcss.1997.1504 |
| ContentType | Journal Article |
| Copyright | 2021 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2021 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology – notice: 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | 24P WIN AAYXX CITATION 8FE 8FG ABJCF AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- L6V M7S P5Z P62 PQEST PQQKQ PQUKI PRINS PTHSS DOA |
| DOI | 10.1049/ell2.12166 |
| DatabaseName | Wiley Open Access Wiley Free Archive CrossRef ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central UK/Ireland Advanced Technologies & Aerospace Database (1962 - current) ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central ProQuest Central Student SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Computer Science Collection Computer Science Database ProQuest Engineering Collection ProQuest Engineering Database ProQuest Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection Directory of Open Access Journals |
| DatabaseTitle | CrossRef Advanced Technologies & Aerospace Collection Engineering Database Computer Science Database ProQuest Central Student Technology Collection ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest One Academic Eastern Edition SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central Advanced Technologies & Aerospace Database ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
| DatabaseTitleList | Advanced Technologies & Aerospace Collection |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 24P name: Wiley Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 3 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1350-911X |
| EndPage | 610 |
| ExternalDocumentID | oai_doaj_org_article_35b7c6d429184f2998279a9e96dc3e19 10_1049_ell2_12166 ELL212166 |
| Genre | article |
| GrantInformation_xml | – fundername: The Danish Maritime Fund, Orients Fund, and the Lauritzen Foundation funderid: 8090‐00063B – fundername: Innovation Fund Denmark |
| GroupedDBID | -4A -~X .DC 0R~ 0ZK 1OC 24P 29G 2QL 3EH 4.4 4IJ 5GY 6IK 8FE 8FG 8VB 96U AAHHS AAHJG AAJGR ABJCF ABQXS ACCFJ ACESK ACGFO ACGFS ACIWK ACXQS ADEYR ADIYS ADZOD AEEZP AEGXH AENEX AEQDE AFAZI AFKRA AI. AIAGR AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ARAPS AVUZU BBWZM BENPR BGLVJ CCPQU CS3 DU5 EBS EJD ELQJU ESX F20 F5P F8P GOZPB GROUPED_DOAJ GRPMH HCIFZ HZ~ IAO IFBGX IFIPE IPLJI JAVBF K1G K7- L6V LAI LXO LXU M43 M7S MCNEO MS~ NADUK NXXTH O9- OCL OK1 P0- P2P P62 PTHSS QWB R4Z RIE RIG RNS RUI TN5 U5U UNMZH VH1 WH7 WIN ZL0 ~ZZ AAYXX CITATION ITC AZQEC DWQXO GNUQQ JQ2 PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c4036-84bd2818cd90813ec8d87bd3364801b9835681fd2f97edb4b498b6de687dec373 |
| IEDL.DBID | 24P |
| ISSN | 0013-5194 |
| IngestDate | Tue Oct 22 15:14:24 EDT 2024 Thu Oct 10 22:17:27 EDT 2024 Thu Sep 26 19:33:31 EDT 2024 Sat Aug 24 01:03:08 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 16 |
| Language | English |
| License | Attribution |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4036-84bd2818cd90813ec8d87bd3364801b9835681fd2f97edb4b498b6de687dec373 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fell2.12166 |
| PQID | 3092804182 |
| PQPubID | 1936364 |
| PageCount | 3 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_35b7c6d429184f2998279a9e96dc3e19 proquest_journals_3092804182 crossref_primary_10_1049_ell2_12166 wiley_primary_10_1049_ell2_12166_ELL212166 |
| PublicationCentury | 2000 |
| PublicationDate | August 2021 2021-08-00 20210801 2021-08-01 |
| PublicationDateYYYYMMDD | 2021-08-01 |
| PublicationDate_xml | – month: 08 year: 2021 text: August 2021 |
| PublicationDecade | 2020 |
| PublicationPlace | Stevenage |
| PublicationPlace_xml | – name: Stevenage |
| PublicationTitle | Electronics letters |
| PublicationYear | 2021 |
| Publisher | John Wiley & Sons, Inc Wiley |
| Publisher_xml | – name: John Wiley & Sons, Inc – name: Wiley |
| References | 2002; 16 2019 2017 2019; 2019 2016 2014 1997; 55 2011 2020; 929 2020 2019; 1357 1953; 1 e_1_2_7_6_1 e_1_2_7_5_1 e_1_2_7_4_1 e_1_2_7_3_1 Kahn H. (e_1_2_7_7_1) 1953; 1 e_1_2_7_9_1 e_1_2_7_8_1 e_1_2_7_2_1 e_1_2_7_15_1 e_1_2_7_14_1 e_1_2_7_13_1 e_1_2_7_12_1 e_1_2_7_11_1 e_1_2_7_10_1 |
| References_xml | – volume: 1 start-page: 5 year: 1953 article-title: Methods of reducing sample size in monte carlo computations publication-title: J. Oper. Res. Soc. – year: 2020 article-title: Vision‐based object tracking in marine environments using features from neural network detections – volume: 55 start-page: 119 issue: 1 year: 1997 end-page: 139 article-title: A Decision‐theoretic generalization of on‐line learning and an application to boosting publication-title: J. Comput. Syst. Sci. – year: 2016 article-title: Deep residual learning for image recognition – year: 2011 article-title: Detection of small surface vessels in near, medium, and far infrared spectral bands – volume: 929 year: 2020 article-title: Lipschitz constrained neural networks for robust object detection at sea – start-page: 2999 year: 2017 end-page: 3007 article-title: Focal loss for dense object detection – year: 2014 article-title: Intriguing properties of neural networks – volume: 1357 year: 2019 article-title: Comparing spectral bands for object detection at sea using convolutional neural networks publication-title: J. Phys. Conf. Ser. – volume: 2019 start-page: 432 year: 2019 end-page: 452 article-title: Sorting out Lipschitz function approximation – year: 2019 – volume: 16 start-page: 321 year: 2002 end-page: 357 article-title: SMOTE: Synthetic Minority Over‐sampling Technique publication-title: Journal of Artificial Intelligence Research – start-page: 89 year: 2011 end-page: 96 article-title: Ensemble of exemplar‐svms for object detection and beyond – ident: e_1_2_7_5_1 doi: 10.1117/12.898272 – ident: e_1_2_7_3_1 doi: 10.1016/j.ifacol.2020.12.1455 – ident: e_1_2_7_6_1 doi: 10.1088/1742-6596/1357/1/012036 – ident: e_1_2_7_14_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_7_13_1 – ident: e_1_2_7_2_1 doi: 10.1088/1757-899X/929/1/012023 – ident: e_1_2_7_11_1 doi: 10.1613/jair.953 – ident: e_1_2_7_9_1 doi: 10.1109/ICCV.2011.6126229 – ident: e_1_2_7_8_1 doi: 10.1109/ICCV.2017.324 – ident: e_1_2_7_4_1 – ident: e_1_2_7_12_1 – ident: e_1_2_7_10_1 doi: 10.1006/jcss.1997.1504 – volume: 1 start-page: 5 year: 1953 ident: e_1_2_7_7_1 article-title: Methods of reducing sample size in monte carlo computations publication-title: J. Oper. Res. Soc. contributor: fullname: Kahn H. – ident: e_1_2_7_15_1 |
| SSID | ssj0012997 |
| Score | 2.4295733 |
| Snippet | Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing... Abstract Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of... |
| SourceID | doaj proquest crossref wiley |
| SourceType | Open Website Aggregation Database Publisher |
| StartPage | 608 |
| SubjectTerms | Annotations Artificial neural networks Computer vision and image processing techniques Datasets Fault detection Fault tolerance Neural nets Neural networks Object recognition Optical, image and video signal processing Robustness Visual tasks |
| SummonAdditionalLinks | – databaseName: Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ09T8MwEIYt1AkGxKcoFGQJJqSoqe36YwTUqkKFAVGpmxXHl6lKUZsKfj5nJ4GywMKWRB6su4vvtX1-TMiN5qkpwoY7S2WWCGFc4gyHRHqUA8qD0CKcRn56lpOZeJwP51tXfYWasBoPXBuuz4dO5dLjsIlzkQIHT82UyQwY6XMOg_roXmrayVSzf4DtVHt3AWoU0YJJhenDYsECUyFyEb9TUST2_5CZ22I1ZpvxAdlvZCK9q7t3SHagPCJ7W_DAYzJ-gfe4rolvNGApsX1ZF3VT-MgC9XdNUZLS1dJt1hVdurDkQj1UsfqqpFlFMc5PyGw8en2YJM2tCEkuIj1YOB8QTrk3mM455Npr5TznMpBgnEFJJfWg8KwwCrwTThjtpAep0fQ5V_yUdMplCWeEDjLjfFoI7o0QPku18YqBLjBrQ5gYdsl1ayD7VsMvbNy0FsYGM9poxi65D7b7ahGA1fEDutE2brR_ubFLeq3lbfMXrS3GEQt8JM265DZ645du2NF0yuLT-X906ILsslC-Emv9eqRTrTZwifqjclcx1D4BXKLS7w priority: 102 providerName: Directory of Open Access Journals – databaseName: ProQuest Technology Collection dbid: 8FG link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8MwDI54XOCAeIrxUiQ4IVVsSZbHCQHaQAg4ICbtFjV1ymVqx9oJfj5x1vK47NZWUVTZif3Fdj4TcqF51-SYcGddmSZCGJc4w30iIcABBV5ogbeRn1_kw0g8jvvjJuBWNWWVrU2MhhrKDGPkV2FOhlw5ml1PPxLsGoXZ1aaFxipZ7zGl8PClh_c_WYRgalXbwSAgFdHSkwpz5ScThswKkR3x1yFF3v5_YPMvZI0-Z7hNthqwSG8W2t0hK77YJZt_KAT3yPDVf8boZnijSE4ZxheL0m7qv1Lk_q1oAKZ0Vrp5VdPSYeCFgq9jDVZB05qG1b5PRsPB291D0vRGSDIROYSFAyRyysAEp859pkErB5xL5INxJgArqXs5sNwoD044YbST4KUOCsi44gdkrSgLf0hoLzUOurngYISAtKsNKOZ1Hny3x-Nhh5y3ArLTBQWGjalrYSyK0UYxdsgtyu5nBNJWxw_l7N02u8DyvlOZhOADw8EyD-rRTJnUeCMh475nOuSklbxt9lJlfzXfIZdRG0t-ww6enlh8Olo-1zHZYFieEmv5TshaPZv704AvancWF9E3hvPLKA priority: 102 providerName: ProQuest |
| Title | Reweighting neural network examples for robust object detection at sea |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fell2.12166 https://www.proquest.com/docview/3092804182 https://doaj.org/article/35b7c6d429184f2998279a9e96dc3e19 |
| Volume | 57 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LS8QwEMcHHxc9iE9cH0tAT0JxN4lpAl5UdhVREXFFvISmSb0sXdmt6Md3Jt2uehG89EUKZSbT-ef1C8ChFh1T0IA776gskdK4xBkREuVRDqQ-SC1pNfLtnboayOvnk-c5OG3WwtR8iFmHG0VG_F9TgGeu3oUERS05cTjkxEZQah4WCRlD5Hwu72djCPijTZv9C1CnyAZOKs3x97u_0lGk9v-Smj8Fa8w4_VVYmUpFdlb7dg3mQrkOyz8AghvQfwgfsW8T7xihKbF8WU_sZuEzI_LvhKEsZeORe59UbOSo24X5UMUZWCXLKoZ1fRMG_d7jxVUy3RkhyWUkCEvnCeOUe4MpXYRce506L4QiGowzKKuU7haeFyYN3kknjXbKB6XR_LlIxRYslKMybAPrZsb5TiGFN1L6rKONT3nQBWbuQI3DFhw0BrJvNQDDxoFraSyZ0UYztuCcbDcrQdDq-GA0frXTGLDixKW58pgBsVlZoHs0T01mglE-F6FrWrDXWN5OI2lisS5xYiRp3oKj6I0_PsP2bm54vNr5T-FdWOI0VSXO69uDhWr8HvZRa1SuHasUHnX_sg2LZ0-DlwGez3t39w_t2H7_AtBN0RM |
| link.rule.ids | 315,783,787,867,2109,11574,12777,21400,27936,27937,33385,33756,43612,43817,46064,46488,50826,50935,74363,74630 |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT9wwEB61cGg5oD7V5dFaak-VInZt49gnBGhXW1hWFQKJmxVnnF5QArtB8POZ8SZAL9ySyLKiGXvm88z4G4BfVg1dxQl3OTRFprULWXAqZgYJDuQYtdV8G_lsbqaX-uRq_6oLuC27ssreJiZDjU3JMfI9mlMyV46VBze3GXeN4uxq10LjLawzVRUdvtaPxvO_5095BDK2ed_DgLCK7glKtduL19eSuRUSP-KzS0rM_f_BzZegNXmdyQfY7OCiOFzp9yO8ifUn2HhBIvgZJufxPsU36U0wPSWNr1fF3SI-FMz-uxQETcWiCXfLVjSBQy8CY5uqsGpRtILW-xe4nIwvjqdZ1x0hK3ViEdYBmcqpREduXcXSos0DKmWYESY4glbGjiqUlcsjBh20s8FgNJZUUKpcfYW1uqnjNxCjwgUcVlqh0xqLoXWYy2gr8t6RD4gD-NkLyN-sSDB8Sl5r51mMPolxAEcsu6cRTFydPjSLf77bB17th7w0SF6QjpYVqcfK3BUuOoOliiM3gJ1e8r7bTUv_rPsB_E7aeOU3_Hg2k-lp6_W5fsC76cXZzM_-zE-34b3kYpVU2bcDa-3iLu4S2mjD925JPQK2u895 |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Nb9QwEB3BVqrggKClYqGAJXqqFG3Wdv1xQhR2VWC7qioq9WbFGYdLlZTdVPDzGXudflx6SyLLimbGnhfPyxuAAyNK28SCOy9VVUhpfeGtCIVCggMagzQy_o18ulQnF_LH5dFl5j-tM61y2BPTRo1dHc_IJzQnj1o5hk-aTIs4-zb_fP2niB2kYqU1t9N4CltaKlGOYOt4tjw7v60p0Marh34GhFvkIFYq7SRcXfGos5C0Eu_SU1LxfwA97wPYlIHmL-FFho7sy8bXr-BJaHfg-T1BwV2Yn4e_6ayT7liUqqTx7YbozcK_KioBrxnBVLbq_M26Z52PxzAMQ58YWS2rekax_xou5rNfX0-K3CmhqGVSFJYeo6xTjZZSvAi1QaM9CqGiOoy3BLOUmTbIG6sDeumlNV5hUIbcUQst9mDUdm14A2xaWY9lIwVaKbEqjUXNg2kok4f4sTiGT4OB3PVGEMOlQra0LprRJTOO4Tja7nZEFLFOD7rVb5fXhBNHXtcKKSPSZ2ZD7jFc28oGq7AWYWrHsD9Y3uWVtXZ3cTCGw-SNR17DzRYLnq7ePj7XR9imaHKL78uf7-AZj7yVRPLbh1G_ugnvCXj0_kOOqP9r79On |
| 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=Reweighting+neural+network+examples+for+robust+object+detection+at+sea&rft.jtitle=Electronics+letters&rft.au=Becktor%2C+J.&rft.au=Boukas%2C+E.&rft.au=Blanke%2C+M.&rft.au=Nalpantidis%2C+L.&rft.date=2021-08-01&rft.issn=0013-5194&rft.eissn=1350-911X&rft.volume=57&rft.issue=16&rft.spage=608&rft.epage=610&rft_id=info:doi/10.1049%2Fell2.12166&rft.externalDBID=10.1049%252Fell2.12166&rft.externalDocID=ELL212166 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0013-5194&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0013-5194&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0013-5194&client=summon |