Supervised hashing with latent factor models

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Due to its low storage cost and fast query speed, hashing has been widely adopted for approximate nearest neighbor search in large-scale datasets. Traditional hashing methods try to learn the hash codes in an unsupervised way where the metric (Euclidean) structure of the training data is preserved. Very recently, supervised hashing methods, which try to preserve the semantic structure constructed from the semantic labels of the training points, have exhibited higher accuracy than unsupervised methods. In this paper, we propose a novel supervised hashing method, called latent factor hashing(LFH), to learn similarity-preserving binary codes based on latent factor models. An algorithm with convergence guarantee is proposed to learn the parameters of LFH. Furthermore, a linear-time variant with stochastic learning is proposed for training LFH on large-scale datasets. Experimental results on two large datasets with semantic labels show that LFH can achieve superior accuracy than state-of-the-art methods with comparable training time.
Funding Information
  • National Natural Science Foundation of China (61272099, 61100125, 61261160502)
  • Program for Changjiang Scholars and Innovative Research Team in University of China (IRT1158 PCSIRT)
  • Shanghai Excellent Academic Leaders Plan (11XD1402900)
  • Ministry of Science and Technology of the People's Republic of China (2012AA011003)
  • Science and Technology Commission of Shanghai Municipality (13511504200)