Show simple item record

dc.contributor.authorZhou, Bolei
dc.contributor.authorKhosla, Aditya
dc.contributor.authorLapedriza Garcia, Agata
dc.contributor.authorOliva, Aude
dc.contributor.authorTorralba, Antonio
dc.date.accessioned2015-05-08T16:56:01Z
dc.date.available2015-05-08T16:56:01Z
dc.date.issued2015-05
dc.identifier.urihttp://hdl.handle.net/1721.1/96942
dc.description.abstractWith the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discovers meaningful objects detectors, representative of the learned scene categories. With object detectors emerging as a result of learning to recognize scenes, our work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects.en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (Grant 1016862)en_US
dc.description.sponsorshipUnited States. Office of Naval Research. Multidisciplinary University Research Initiative (N000141010933)en_US
dc.description.sponsorshipGoogle (Firm)en_US
dc.description.sponsorshipXerox Corporationen_US
dc.language.isoen_US
dc.relation.isversionofhttp://www.iclr.cc/doku.php?id=iclr2015:main#conference_scheduleen_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleObject detectors emerge in Deep Scene CNNsen_US
dc.typeArticleen_US
dc.identifier.citationBolei, Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. "Object detectors emerge in Deep Scene CNNs." 2015 International Conference on Learning Representations, May 7-9, 2015.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.mitauthorZhou, Boleien_US
dc.contributor.mitauthorKhosla, Adityaen_US
dc.contributor.mitauthorLapedriza Garcia, Agataen_US
dc.contributor.mitauthorOliva, Audeen_US
dc.contributor.mitauthorTorralba, Antonioen_US
dc.relation.journalProceedings of the 2015 International Conference on Learning Representationsen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsBolei, Zhou; Khosla, Aditya; Lapedriza, Agata; Oliva, Aude; Torralba, Antonioen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-0007-3352
dc.identifier.orcidhttps://orcid.org/0000-0002-3570-4396
dc.identifier.orcidhttps://orcid.org/0000-0003-4915-0256
mit.licenseOPEN_ACCESS_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record