Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalab...
Gespeichert in:
| Veröffentlicht in: | 2014 IEEE Conference on Computer Vision and Pattern Recognition S. 580 - 587 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Tagungsbericht Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
01.06.2014
|
| Schlagworte: | |
| ISSN: | 1063-6919, 1063-6919 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn. |
|---|---|
| AbstractList | Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn. |
| Author | Malik, Jitendra Girshick, Ross Donahue, Jeff Darrell, Trevor |
| Author_xml | – sequence: 1 givenname: Ross surname: Girshick fullname: Girshick, Ross email: rbg@eecs.berkeley.edu – sequence: 2 givenname: Jeff surname: Donahue fullname: Donahue, Jeff email: jdonahue@eecs.berkeley.edu – sequence: 3 givenname: Trevor surname: Darrell fullname: Darrell, Trevor email: trevor@eecs.berkeley.edu – sequence: 4 givenname: Jitendra surname: Malik fullname: Malik, Jitendra email: malik@eecs.berkeley.edu |
| BookMark | eNpNjj1PwzAYhA0qEqV0Y2PxyJLi1_FHPFaFUqRKrcrHGjnOG2rUJMVxBv49QWVgutM9p9NdkVHTNkjIDbAZADP3i_ftbsYZiFkGZ2RqdAZCGyMBMnlOxsBUmigDZvTPX5Jp1_mCcaWVkKkak-3Ouz1doo19QLryGGxwe48drdpA5871wUakm-ITXaQPGAfxbUNtU9IXrG0TvRvMR41NtL_kmlxU9tDh9E8n5G35-LpYJevN0_Nivk481yImQnNUurCaZ7ow1fC9SnlRpKWtSqcALK8El06VQ2pQSMzEwDLQZQalTDGdkLvT7jG0Xz12Ma995_BwsA22fZeD0towJpgeqrenqkfE_Bh8bcN3rgwzQsv0B4ZjYJU |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding Journal Article |
| DBID | 6IE 6IH CBEJK RIE RIO 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/CVPR.2014.81 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present 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 | 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 | Applied Sciences Computer Science |
| EISBN | 9781479951185 1479951188 |
| EISSN | 1063-6919 |
| EndPage | 587 |
| ExternalDocumentID | 6909475 |
| Genre | orig-research |
| GroupedDBID | 23M 29F 29O 6IE 6IH 6IK ABDPE ACGFS ALMA_UNASSIGNED_HOLDINGS CBEJK IPLJI M43 RIE RIO RNS 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-i274t-472e67ba7287b9f814f32bb3dafdc611a2f425c6d32b9e45e843da817d81d53e3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 14636 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000361555600074&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1063-6919 |
| IngestDate | Thu Sep 04 20:16:15 EDT 2025 Wed Aug 27 04:30:17 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i274t-472e67ba7287b9f814f32bb3dafdc611a2f425c6d32b9e45e843da817d81d53e3 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Conference-1 ObjectType-Feature-3 content type line 23 SourceType-Conference Papers & Proceedings-2 |
| PQID | 1677900407 |
| PQPubID | 23500 |
| PageCount | 8 |
| ParticipantIDs | proquest_miscellaneous_1677900407 ieee_primary_6909475 |
| PublicationCentury | 2000 |
| PublicationDate | 20140601 |
| PublicationDateYYYYMMDD | 2014-06-01 |
| PublicationDate_xml | – month: 06 year: 2014 text: 20140601 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | 2014 IEEE Conference on Computer Vision and Pattern Recognition |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2014 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssib026764536 ssj0023720 ssj0003211698 |
| Score | 2.5579128 |
| Snippet | Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex... |
| SourceID | proquest ieee |
| SourceType | Aggregation Database Publisher |
| StartPage | 580 |
| SubjectTerms | Computer vision Conferences Feature extraction Hierarchies Neural networks Object detection Pattern recognition Proposals Support vector machines Tasks Training Vectors Visualization Volatile organic compounds |
| Title | Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation |
| URI | https://ieeexplore.ieee.org/document/6909475 https://www.proquest.com/docview/1677900407 |
| WOSCitedRecordID | wos000361555600074&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 | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR1NT8IwtAHiwRMqGPErNfHogG6lXY8GJZyQGDXclrZ70x0YBjZ_v69l4EEv3pq3bFne9-v7IuQ2YjC0hsuAowIO0EKxQBsIA8FTg_FzDJmJ_bIJOZvFi4WaN8jdvhcGAHzxGfTd0efy05Wt3FXZACM5xeWoSZpSym2v1o53QiEFH213d3stHGFkI9Q-oxC6bSw-8ymiQCim9kXwajB-mz-7Ii_ed9Ot_ZKVX5rZm5tJ-38_ekS6P317dL63SMekAcUJadeOJq3FeIOg3S6HHaxD5q7DnjqHsFoDneauL9l-YBhN0aul99ZWbqYEfTLu3oY-QOlLuAqqC_wwLJE-ucXD-7LuZSq65HXy-DKeBvW2hSDHyLQMuAxBSKMlxlBGZTHjWRQaE6U6S61gTIcZyrcVKUIV8BHEHJ_FTKbo8o4iiE5Jq1gVcEaocIKtwixDYnOwkWZGihQdJUiHWkjokY7DWfK5HaiR1OjqkZsd0hNkcpe50AWsqk3ChBuLiPpGnv_96gU5dATc1nBdkla5ruCKHNivMt-srz2nfAOTkrtg |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR27TsMw8AQFCSYeBVGeRmIkgBPHjkfEQ0WUUiFAbFHsXKBDU9Q2fD9nNy0DLGzWRYmie5_vBXAScbywRqhAkAIOyELxIDMYBlLkhuLnBAuT-GUTqttN3t50bwFO570wiOiLz_DMHX0uPx_ayl2VnVMkp4WKF2EpFiLk026tGfeEUkkRT7d3ez0cUWwj9TynELp9LD73KaNAaq7nZfD6_Oq19-TKvMSZm2_t16z80s3e4Nyu_e9X12Hrp3OP9eY2aQMWsNyEtdrVZLUgjwk02-YwgzWh53rsmXMJqxGydt91JtsPCqQZ-bXs0trKTZVgj8bd3LBrnPgirpJlJX0YB0ShvqXD-6DuZiq34OX25vmqHdT7FoI-xaaTQKgQpTKZoijK6CLhoohCY6I8K3IrOc_CgiTcypygGkWMiaBnCVc5Ob1xhNE2NMphiTvApBNtHRYFkVugjTJulMzJVcL8IpMKW9B0OEs_pyM10hpdLTieIT0lNne5i6zEYTVOuXSDEUnjqN2_Xz2ClfbzQyft3HXv92DVEXNa0bUPjcmowgNYtl-T_nh06LnmG4Dgvqc |
| 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%3Abook&rft.genre=proceeding&rft.title=2014+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=Rich+Feature+Hierarchies+for+Accurate+Object+Detection+and+Semantic+Segmentation&rft.au=Girshick%2C+Ross&rft.au=Donahue%2C+Jeff&rft.au=Darrell%2C+Trevor&rft.au=Malik%2C+Jitendra&rft.date=2014-06-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=580&rft.epage=587&rft_id=info:doi/10.1109%2FCVPR.2014.81&rft.externalDocID=6909475 |
| 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 |