Deep Hashing for Scalable Image Search
- 3 March 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 26 (5), 2352-2367
- https://doi.org/10.1109/tip.2017.2678163
Abstract
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.Keywords
Funding Information
- National Key Research and Development Program of China (2016YFB1001001)
- National Natural Science Foundation of China (61672306, 61225008, 61572271, 61527808, 61373074, 61373090)
- National 1000 Young Talents Plan Program
- National Basic Research Program of China (2014CB349304)
- Ministry of Education of China (20120002110033)
- Tsinghua University Initiative Scientific Research Program
This publication has 54 references indexed in Scilit:
- Deep hash: semantic similarity preserved hash schemeElectronics Letters, 2014
- Scalable Nearest Neighbor Algorithms for High Dimensional DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Multimodal Similarity-Preserving HashingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Hypergraph Spectral Hashing for image retrieval with heterogeneous social contextsNeurocomputing, 2013
- Sparse spectral hashingPattern Recognition Letters, 2011
- Semantic hashingInternational Journal of Approximate Reasoning, 2009
- Learning Deep Architectures for AIFoundations and Trends® in Machine Learning, 2009
- Orthogonal neighborhood preserving discriminant analysis for face recognitionPattern Recognition, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Multidimensional binary search trees used for associative searchingCommunications of the ACM, 1975