Science-advisor
REGISTER info/FAQ
Login
username
password
     
forgot password?
register here
 
Research articles
  search articles
  reviews guidelines
  reviews
  articles index
My Pages
my alerts
  my messages
  my reviews
  my favorites
 
 
Stat
Members: 3667
Articles: 2'599'751
Articles rated: 2609

08 February 2025
 
  » arxiv » 1508.0217

 Article overview



Indexing of CNN Features for Large Scale Image Search
Ruoyu Liu ; Yao Zhao ; Shikui Wei ; Zhenfeng Zhu ; Lixin Liao ; Shuang Qiu ;
Date 2 Aug 2015
AbstractConvolutional neural network (CNN) feature that represents an image with a global and high-dimensional vector has shown highly discriminative capability in image search. Although CNN features are more compact than most of local representation schemes, it still cannot efficiently deal with large-scale image search issues due to its non-negligible computational cost and storage usage. In this paper, we propose a simple but effective image indexing framework to improve the computational and storage efficiency of CNN features. Instead of projecting each CNN feature vector into a global hashing code, the proposed framework adapts Bag-of-Word model and inverted table to global feature indexing. To this end, two strategies, which are based on semantic information associated with CNN features, are proposed to convert a global vector to one or several discrete words. In addition, several strategies for compensating quantization error are fully investigated under the indexing framework. Extensive experimental results on two public benchmarks show the superiority of our framework.
Source arXiv, 1508.0217
Services Forum | Review | PDF | Favorites   
 
Visitor rating: did you like this article? no 1   2   3   4   5   yes

No review found.
 Did you like this article?

This article or document is ...
important:
of broad interest:
readable:
new:
correct:
Global appreciation:

  Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.






ScienXe.org
» my Online CV
» Free

home  |  contact  |  terms of use  |  sitemap
Copyright © 2005-2025 - Scimetrica