Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are designed to detect objects with relatively low-quality prediction of locations, i.e., often trained with the threshold of...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
22.03.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are designed to detect objects with relatively low-quality prediction of locations, i.e., often trained with the threshold of Intersection over Union (IoU) set to 0.5 by default, which can yield low-quality or even noisy detections. It remains an open challenge for how to devise and train a high-quality detector that can achieve more precise localization (i.e., IoU\(>\)0.5) without sacrificing the detection performance. In this paper, we propose a novel single-shot detection framework of Bidirectional Pyramid Networks (BPN) towards high-quality object detection, which consists of two novel components: (i) a Bidirectional Feature Pyramid structure for more effective and robust feature representations; and (ii) a Cascade Anchor Refinement to gradually refine the quality of predesigned anchors for more effective training. Our experiments showed that the proposed BPN achieves the best performances among all the single-stage object detectors on both PASCAL VOC and MS COCO datasets, especially for high-quality detections. |
---|---|
AbstractList | Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are designed to detect objects with relatively low-quality prediction of locations, i.e., often trained with the threshold of Intersection over Union (IoU) set to 0.5 by default, which can yield low-quality or even noisy detections. It remains an open challenge for how to devise and train a high-quality detector that can achieve more precise localization (i.e., IoU\(>\)0.5) without sacrificing the detection performance. In this paper, we propose a novel single-shot detection framework of Bidirectional Pyramid Networks (BPN) towards high-quality object detection, which consists of two novel components: (i) a Bidirectional Feature Pyramid structure for more effective and robust feature representations; and (ii) a Cascade Anchor Refinement to gradually refine the quality of predesigned anchors for more effective training. Our experiments showed that the proposed BPN achieves the best performances among all the single-stage object detectors on both PASCAL VOC and MS COCO datasets, especially for high-quality detections. |
Author | Zhang, Daoxin Wu, Xiongwei Hoi, Steven C H Zhu, Jianke |
Author_xml | – sequence: 1 givenname: Xiongwei surname: Wu fullname: Wu, Xiongwei – sequence: 2 givenname: Daoxin surname: Zhang fullname: Zhang, Daoxin – sequence: 3 givenname: Jianke surname: Zhu fullname: Zhu, Jianke – sequence: 4 givenname: Steven surname: Hoi middlename: C H fullname: Hoi, Steven C H |
BookMark | eNqNjE0LgjAAQEcUZOV_GHQezC01r33hIfrA7rJy6mxttU3Cf59QP6DTu7z3JmCotOID4BFKA7RcEDIGvrUNxphEMQlD6oF9JlQlOcpq7eBKFMLwmxNaMQlPnWEPUcADd29t7haW2sBUVDU6t0wK18HjteltuOHuG83AqGTScv_HKZjvtpd1ip5Gv1puXd7o1vRvmxMcBwkOSBLR_6wPpoc_JQ |
ContentType | Paper |
Copyright | 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_20719012963 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 17:32:52 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_20719012963 |
OpenAccessLink | https://www.proquest.com/docview/2071901296?pq-origsite=%requestingapplication% |
PQID | 2071901296 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2071901296 |
PublicationCentury | 2000 |
PublicationDate | 20180322 |
PublicationDateYYYYMMDD | 2018-03-22 |
PublicationDate_xml | – month: 03 year: 2018 text: 20180322 day: 22 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2018 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.1423273 |
SecondaryResourceType | preprint |
Snippet | Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Anchors Cameras Detectors Machine learning Object recognition Quality |
Title | Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection |
URI | https://www.proquest.com/docview/2071901296 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQSTZMSwUdUqJrmQzsm5iYm6XoWlokGYMmHIE9ItMks1Tw_Sm-fmYeoSZeEaYR0AG3YuiySliZCC6oU_KTQWPkoJEQUN1lZGlmX1CoC7o1CjS7Cr1Cg5mB1cjQBDRNy-rk6hcQBB9lMTIzB7aZjTEKWnDt4SbIwBqQWJBaJMTAlJonzMAOXnSZXCzC4AO66z4nVTc4I79EwSkTUruAh-YUAiqLEnMzUxT8IKu0ixWAbUsF0JoMXcihF5UK_kmgERQFl9QSiCZRBmU31xBnD12YE-KhyaQ4HuEpYzEGFmB_P1WCQSElxSzVINk8ySDFwgI065hoaGCQnGxgbJkMZJmkmEoyyOAzSQq_tDQDF7DOB2-rMzKSYWApKSpNlQXWqyVJcgzMFm7uctAgBPJ861wBuTmCYg |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQSTZMSwUdUqJrmQzsm5iYm6XoWlokGYMmHIE9ItMks1Tw_Sm-fmYeoSZeEaYR0AG3YuiySliZCC6oU_KTQWPkoJEQUN1lZGlmX1CoC7o1CjS7Cr1Cg5mB1cTYzBiUzi3c3OFjLEZm5sAWszFGMQuuO9wEGVgDEgtSi4QYmFLzhBnYwUsuk4tFGHxAN93npOoGZ-SXKDhlQuoW8MCcQkBlUWJuZoqCH2SNdrECsGWpAFqRoQs58qJSwT8JNH6i4JJaAtEkyqDs5hri7KELc0I8NJEUxyO8ZCzGwALs7adKMCikpJilGiSbJxmkWFiA5hwTDQ0MkpMNjC2TgSyTFFNJBhl8Jknhl5Zn4PQI8fWJ9_H085Zm4ALW_uANdkZGMgwsJUWlqbLAGrYkSQ4cjAChUIHS |
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=Single-Shot+Bidirectional+Pyramid+Networks+for+High-Quality+Object+Detection&rft.jtitle=arXiv.org&rft.au=Wu%2C+Xiongwei&rft.au=Zhang%2C+Daoxin&rft.au=Zhu%2C+Jianke&rft.au=Hoi%2C+Steven+C+H&rft.date=2018-03-22&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |