Deep Hashing for Scalable Image Search

In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for scalable image search. Unlike most existing binary codes learning methods, which usually seek a single linear projection to map each sample into a binary feature vector, we develop a deep neural network to s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2017-05, Vol.26 (5), p.2352-2367
Main Authors: Jiwen Lu, Liong, Venice Erin, Jie Zhou
Format: Article
Language:English
Subjects:
Artificial neural networks
Binary codes
Binary system
Codes
Constraint modelling
Data search
deep learning
DH-HEMTs
fast similarity search
hashing
Linear transformations
Machine learning
multi-label learning
Neural networks
Scalable image search
Synchronous digital hierarchy
Training
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for scalable image search. Unlike most existing binary codes learning methods, which usually seek a single linear projection to map each sample into a binary feature vector, we develop a deep neural network to seek multiple hierarchical non-linear transformations to learn these binary codes, so that the non-linear relationship of samples can be well exploited. Our model is learned under three constraints at the top layer of the developed deep network: 1) the loss between the compact real-valued code and the learned binary vector is minimized, 2) the binary codes distribute evenly on each bit, and 3) different bits are as independent as possible. To further improve the discriminative power of the learned binary codes, we extend DH into supervised DH (SDH) and multi-label SDH by including a discriminative term into the objective function of DH, which simultaneously maximizes the inter-class variations and minimizes the intra-class variations of the learned binary codes with the single-label and multi-label settings, respectively. Extensive experimental results on eight widely used image search data sets show that our proposed methods achieve very competitive results with the state-of-the-arts.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2017.2678163