Deep Collaborative Multi-View Hashing for Large-Scale Image Search
- 21 February 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149), 4643-4655
- https://doi.org/10.1109/tip.2020.2974065
Abstract
Hashing could significantly accelerate large-scale image search by transforming the high-dimensional features into binary Hamming space, where efficient similarity search can be achieved with very fast Hamming distance computation and extremely low storage cost. As an important branch of hashing methods, multi-view hashing takes advantages of multiple features from different views for binary hash learning. However, existing multi-view hashing methods are either based on shallow models which fail to fully capture the intrinsic correlations of heterogeneous views, or unsupervised deep models which suffer from insufficient semantics and cannot effectively exploit the complementarity of view features. In this paper, we propose a novel Deep Collaborative Multi-view Hashing (DCMVH) method to deeply fuse multi-view features and learn multi-view hash codes collaboratively under a deep architecture. DCMVH is a new deep multi-view hash learning framework. It mainly consists of 1) multiple view-specific networks to extract hidden representations of different views, and 2) a fusion network to learn multi-view fused hash code. DCMVH associates different layers with instance-wise and pair-wise semantic labels respectively. In this way, the discriminative capability of representation layers can be progressively enhanced and meanwhile the complementarity of different view features can be exploited effectively. Finally, we develop a fast discrete hash optimization method based on augmented Lagrangian multiplier to efficiently solve the binary hash codes. Experiments on public multi-view image search datasets demonstrate our approach achieves substantial performance improvement over state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (61802236, 61772322, U1836216)
- Natural Science Foundation of Shandong Province (ZR2019QF002)
- Major Fundamental Research Project of Shandong, China (ZR2019ZD03)
- Youth Innovation Project of Shandong Universities, China (2019KJN040)
- Taishan Scholar Project of Shandong, China (ts20190924)
This publication has 48 references indexed in Scilit:
- Fast Supervised Discrete HashingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Hashing for Scalable Image SearchIEEE Transactions on Image Processing, 2017
- Cross-View Retrieval via Probability-Based Semantics-Preserving HashingIEEE Transactions on Cybernetics, 2016
- Multi-view Latent Hashing for Efficient Multimedia SearchPublished by Association for Computing Machinery (ACM) ,2015
- Multiview Alignment Hashing for Efficient Image SearchIEEE Transactions on Image Processing, 2015
- Preference preserving hashing for efficient recommendationPublished by Association for Computing Machinery (ACM) ,2014
- Multi-view anchor graph hashingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image RetrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- NUS-WIDEPublished by Association for Computing Machinery (ACM) ,2009
- Nonlinear Dimensionality Reduction by Locally Linear InlayingIEEE Transactions on Neural Networks, 2009