Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/107960
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | The treasure beneath convolutional layers: cross-convolutional-layer pooling for image classification |
Author: | Liu, L. Shen, C. van den Hengel, A. |
Citation: | Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, vol.07-12-June-2015, pp.4749-4757 |
Publisher: | IEEE |
Issue Date: | 2015 |
Series/Report no.: | IEEE Conference on Computer Vision and Pattern Recognition |
ISBN: | 9781467369640 |
ISSN: | 1063-6919 |
Conference Name: | 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) (7 Jun 2015 - 12 Jun 2015 : Boston, MA) |
Statement of Responsibility: | Lingqiao Liu, Chunhua Shen, Anton van den Hengel |
Abstract: | A number of recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large dataset can be adopted as a universal image descriptor, and that doing so leads to impressive peiformance at a range of image classification tasks. Most of these studies, if not all, adopt activations of the fully-connected layer of a DCNN as the image or region representation and it is believed that convolutional layer activations are less discriminative. This paper, however, advocates that if used appropriately, convolutional layer activations constitute a powerful image representation. This is achieved by adopting a new technique proposed in this paper called crossconvolutional- layer pooling. More specifically, it extracts subarrays of feature maps of one convolutional layer as local features, and pools the extracted features with the guidance of the feature maps of the successive convolutional layer. Compared with existing methods that apply DCNNs in the similar local feature setting, the proposed method avoids the input image style mismatching issue which is usually encountered when applying fully connected layer activations to describe local regions. Also, the proposed method is easier to implement since it is code book free and does not have any tuning parameters. By applying our method to four popular visual classification tasks, it is demonstrated that the proposed method can achieve comparable or in some cases significantly better performance than existing fully-connected layer based image representations. |
Keywords: | Principal component analysis |
Rights: | © 2015 IEEE |
DOI: | 10.1109/CVPR.2015.7299107 |
Grant ID: | http://purl.org/au-research/grants/arc/FT120100969 http://purl.org/au-research/grants/arc/LP130100156 |
Published version: | http://dx.doi.org/10.1109/cvpr.2015.7299107 |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_107960.pdf Restricted Access | Restricted Access | 1.24 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.