File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: DeepID-Net: Deformable deep convolutional neural networks for object detection

TitleDeepID-Net: Deformable deep convolutional neural networks for object detection
Authors
Issue Date2015
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, v. 07-12-June-2015, p. 2403-2412 How to Cite?
Abstract© 2015 IEEE. In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [14], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provide a global view for people to understand the deep learning object detection pipeline.
Persistent Identifierhttp://hdl.handle.net/10722/273547
ISSN

 

DC FieldValueLanguage
dc.contributor.authorOuyang, Wanli-
dc.contributor.authorWang, Xiaogang-
dc.contributor.authorZeng, Xingyu-
dc.contributor.authorQiu, Shi-
dc.contributor.authorLuo, Ping-
dc.contributor.authorTian, Yonglong-
dc.contributor.authorLi, Hongsheng-
dc.contributor.authorYang, Shuo-
dc.contributor.authorWang, Zhe-
dc.contributor.authorLoy, Chen Change-
dc.contributor.authorTang, Xiaoou-
dc.date.accessioned2019-08-12T09:55:54Z-
dc.date.available2019-08-12T09:55:54Z-
dc.date.issued2015-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, v. 07-12-June-2015, p. 2403-2412-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/273547-
dc.description.abstract© 2015 IEEE. In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [14], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provide a global view for people to understand the deep learning object detection pipeline.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleDeepID-Net: Deformable deep convolutional neural networks for object detection-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2015.7298854-
dc.identifier.scopuseid_2-s2.0-84948382785-
dc.identifier.volume07-12-June-2015-
dc.identifier.spage2403-
dc.identifier.epage2412-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats