Open AccessDeep Hashing Based on VAE‐GAN for Efficient Similarity Retrieval
Author(s) -
Jin Guoqing,
Zhang Yongdong,
Lu Ke
Publication year - 2019
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2019.08.001
Subject(s) - hash function , pairwise comparison , computer science , autoencoder , artificial intelligence , pattern recognition (psychology) , benchmark (surveying) , image retrieval , feature (linguistics) , feature hashing , image (mathematics) , similarity (geometry) , feature vector , generative grammar , generative adversarial network , deep learning , hash table , double hashing , linguistics , philosophy , computer security , geodesy , geography
Inspired by the recent advances in generative networks, we propose a VAE‐GAN based hashing framework for fast image retrieval. The method combines a Variational autoencoder (VAE) with a Generative adversarial network (GAN) to generate content preserving images for pairwise hashing learning. By accepting real image and systhesized image in a pairwise form, a semantic perserving feature mapping model is learned under a adversarial generative process. Each image feature vector in the pairwise is converted to a hash codes, which are used in a pairwise ranking loss that aims to preserve relative similarities on images. Extensive experiments on several benchmark datasets demonstrate that the proposed method shows substantial improvement over the state‐of‐the‐art hashing methods.