File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Harvesting discriminative meta objects with deep CNN features for scene classification

TitleHarvesting discriminative meta objects with deep CNN features for scene classification
Authors
Issue Date2015
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149
Citation
The 15th IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile, 11-18 December 2015. In Conference Proceedings, 2015, p. 1287-1295 How to Cite?
AbstractRecent work on scene classification still makes use of generic CNN features in a rudimentary manner. In this paper, we present a novel pipeline built upon deep CNN features to harvest discriminative visual objects and parts for scene classification. We first use a region proposal technique to generate a set of high-quality patches potentially containing objects, and apply a pre-trained CNN to extract generic deep features from these patches. Then we perform both unsupervised and weakly supervised learning to screen these patches and discover discriminative ones representing category-specific objects and parts. We further apply discriminative clustering enhanced with local CNN fine-tuning to aggregate similar objects and parts into groups, called meta objects. A scene image representation is constructed by pooling the feature response maps of all the learned meta objects at multiple spatial scales. We have confirmed that the scene image representation obtained using this new pipeline is capable of delivering state-of-the-art performance on two popular scene benchmark datasets, MIT Indoor 67 [22] and Sun397 [31]. © 2015 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/229717
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorWu, R-
dc.contributor.authorWang, B-
dc.contributor.authorWang, W-
dc.contributor.authorYu, Y-
dc.date.accessioned2016-08-23T14:12:51Z-
dc.date.available2016-08-23T14:12:51Z-
dc.date.issued2015-
dc.identifier.citationThe 15th IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile, 11-18 December 2015. In Conference Proceedings, 2015, p. 1287-1295-
dc.identifier.isbn978-146738391-2-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/229717-
dc.description.abstractRecent work on scene classification still makes use of generic CNN features in a rudimentary manner. In this paper, we present a novel pipeline built upon deep CNN features to harvest discriminative visual objects and parts for scene classification. We first use a region proposal technique to generate a set of high-quality patches potentially containing objects, and apply a pre-trained CNN to extract generic deep features from these patches. Then we perform both unsupervised and weakly supervised learning to screen these patches and discover discriminative ones representing category-specific objects and parts. We further apply discriminative clustering enhanced with local CNN fine-tuning to aggregate similar objects and parts into groups, called meta objects. A scene image representation is constructed by pooling the feature response maps of all the learned meta objects at multiple spatial scales. We have confirmed that the scene image representation obtained using this new pipeline is capable of delivering state-of-the-art performance on two popular scene benchmark datasets, MIT Indoor 67 [22] and Sun397 [31]. © 2015 IEEE.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149-
dc.relation.ispartofIEEE International Conference on Computer Vision Proceedings-
dc.rightsIEEE International Conference on Computer Vision Proceedings. Copyright © IEEE.-
dc.rights©2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleHarvesting discriminative meta objects with deep CNN features for scene classification-
dc.typeConference_Paper-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ICCV.2015.152-
dc.identifier.scopuseid_2-s2.0-84973894736-
dc.identifier.hkuros262365-
dc.identifier.spage1287-
dc.identifier.epage1295-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 160914-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats