Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/31322
Title: | A novel feature representation: Aggregating convolution kernels for image retrieval | Authors: | WANG, Qi Lai, Jinxing CLAESEN, Luc Yang, Zhenguo Lei, Liang Liu, Wenyin |
Issue Date: | 2020 | Publisher: | PERGAMON-ELSEVIER SCIENCE LTD | Source: | Neural networks (Print), 130 (October 2020) , p. 1 -10 | Abstract: | Activated hidden unites in convolutional neural networks (CNNs), known as feature maps, dominate image representation, which is compact and discriminative. For ultra-large data sets, high dimensional feature maps in float format not only result in high computational complexity, but also occupy massive memory space. To this end, a new image representation by aggregating convolution kernels (ACK) is proposed, where some convolution kernels capturing certain patterns are activated. The top-n index numbers of the convolution kernels are extracted directly as image representation in discrete integer values, which rebuild relationship between convolution kernels and image. Furthermore, a distance measurement is defined from the perspective of ordered sets to calculate position-sensitive similarities between image representations. Extensive experiments conducted on Oxford Buildings, Paris, and Holidays, etc., manifest that the proposed ACK achieves competitive performance on image retrieval with much lower computational cost, outperforming the ones using feature maps for image representation. | Keywords: | Image Retrieval;Image Representation;Feature Aggregating;Distance Measurement;Convolutional Neural Networks | Document URI: | http://hdl.handle.net/1942/31322 | ISSN: | 0893-6080 | e-ISSN: | 1879-2782 | DOI: | 10.1016/j.neunet.2020.06.010 | ISI #: | WOS:000567813200001 | Rights: | 2020 Elsevier Ltd. | Category: | A1 | Type: | Journal Contribution | Validations: | ecoom 2021 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
WangQ_2020.pdf Restricted Access | Published version | 2.37 MB | Adobe PDF | View/Open Request a copy |
A Novel Feature Representation Aggregating Convolution Kernels for Image Retrieval.pdf | Peer-reviewed author version | 12.55 MB | Adobe PDF | View/Open |
WEB OF SCIENCETM
Citations
17
checked on Sep 27, 2024
Page view(s)
68
checked on Sep 7, 2022
Download(s)
16
checked on Sep 7, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.