Multi-scale Pyramid Pooling for Deep Convolutional Representation

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 165
  • Download : 80
Compared 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.
Publisher
IEEE Computer Society and the Computer Vision Foundation (CVF)
Issue Date
2015-06-10
Language
English
Citation

CVPR2015 IEEE Conference on Computer Vision and Pattern Recognition

URI
http://hdl.handle.net/10203/204481
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0