Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/43592
Title: Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification
Authors: Zhang, R
Lin, L
Zhang, R
Zuo, W
Zhang, L 
Keywords: Deep model
Hashing learning
Image retrieval
Person re-identification
Similarity comparison
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on image processing, 2015, v. 24, no. 12, 7185403, p. 4766-4779 How to cite?
Journal: IEEE transactions on image processing 
Abstract: Extracting informative image features and learning effective approximate hashing functions are two crucial steps in image retrieval. Conventional methods often study these two steps separately, e.g., learning hash functions from a predefined hand-crafted feature space. Meanwhile, the bit lengths of output hashing codes are preset in the most previous methods, neglecting the significance level of different bits and restricting their practical flexibility. To address these issues, we propose a supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images. We pose hashing learning as a problem of regularized similarity learning. In particular, we organize the training images into a batch of triplet samples, each sample containing two images with the same label and one with a different label. With these triplet samples, we maximize the margin between the matched pairs and the mismatched pairs in the Hamming space. In addition, a regularization term is introduced to enforce the adjacency consistency, i.e., images of similar appearances should have similar codes. The deep convolutional neural network is utilized to train the model in an end-to-end fashion, where discriminative image features and hash functions are simultaneously optimized. Furthermore, each bit of our hashing codes is unequally weighted, so that we can manipulate the code lengths by truncating the insignificant bits. Our framework outperforms state-of-the-arts on public benchmarks of similar image search and also achieves promising results in the application of person re-identification in surveillance. It is also shown that the generated bit-scalable hashing codes well preserve the discriminative powers with shorter code lengths.
URI: http://hdl.handle.net/10397/43592
ISSN: 1057-7149 (print)
1941-0042 (online)
DOI: 10.1109/TIP.2015.2467315
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

35
Last Week
0
Last month
Citations as of Mar 24, 2017

WEB OF SCIENCETM
Citations

21
Last Week
1
Last month
Citations as of Mar 25, 2017

Page view(s)

21
Last Week
0
Last month
Checked on Mar 26, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.