File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2015.152
- Scopus: eid_2-s2.0-84973894736
- WOS: WOS:000380414100144
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Harvesting discriminative meta objects with deep CNN features for scene classification
Title | Harvesting discriminative meta objects with deep CNN features for scene classification |
---|---|
Authors | |
Issue Date | 2015 |
Publisher | IEEE. 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? |
Abstract | Recent 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 Identifier | http://hdl.handle.net/10722/229717 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wu, R | - |
dc.contributor.author | Wang, B | - |
dc.contributor.author | Wang, W | - |
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2016-08-23T14:12:51Z | - |
dc.date.available | 2016-08-23T14:12:51Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | The 15th IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile, 11-18 December 2015. In Conference Proceedings, 2015, p. 1287-1295 | - |
dc.identifier.isbn | 978-146738391-2 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/229717 | - |
dc.description.abstract | Recent 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.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 | - |
dc.relation.ispartof | IEEE International Conference on Computer Vision Proceedings | - |
dc.title | Harvesting discriminative meta objects with deep CNN features for scene classification | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICCV.2015.152 | - |
dc.identifier.scopus | eid_2-s2.0-84973894736 | - |
dc.identifier.hkuros | 262365 | - |
dc.identifier.spage | 1287 | - |
dc.identifier.epage | 1295 | - |
dc.identifier.isi | WOS:000380414100144 | - |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 160914 | - |
dc.identifier.issnl | 1550-5499 | - |