Multi-scale Pyramid Pooling for Deep Convolutional Representation

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 169
  • Download : 82
DC FieldValueLanguage
dc.contributor.authorYoo, Dong Geunko
dc.contributor.authorPark, Sung Gyunko
dc.contributor.authorLee, Joon Youngko
dc.contributor.authorKweon, In Soko
dc.identifier.citationCVPR2015 IEEE Conference on Computer Vision and Pattern Recognition-
dc.description.abstractCompared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we extract a fair amount of multi-scale dense local activations from a pre-trained CNN. We then aggregate the activations by Fisher kernel framework, which has been modified with a simple scale-wise normalization essential to make it suitable for CNN activations. Our representation demonstrates new state-of-the-art performances on three public datasets: 80.78% (Acc.) on MIT Indoor 67, 83.20% (mAP) on PASCAL VOC 2007 and 91.28% (Acc.) on Oxford 102 Flowers. The results suggest that our proposal can be used as a primary image representation for better performances in wide visual recognition tasks.-
dc.publisherIEEE Computer Society and the Computer Vision Foundation (CVF)-
dc.titleMulti-scale Pyramid Pooling for Deep Convolutional Representation-
dc.citation.publicationnameCVPR2015 IEEE Conference on Computer Vision and Pattern Recognition-
dc.identifier.conferencelocationHynes Convention Center, Boston-
dc.contributor.localauthorKweon, In So-
dc.contributor.nonIdAuthorPark, Sung Gyun-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item


  • mendeley


rss_1.0 rss_2.0 atom_1.0