Deep Hashing Based on VAE-GAN for Efficient Similarity Retrieval  

作　　者：JIN Guoqing ZHANG Yongdong LU Ke 

机构地区：[1]Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China [2]University of Chinese Academy of Sciences,Beijing 100049,China

出　　处：《Chinese Journal of Electronics》2019年第6期1191-1197,共7页电子学报（英文版）

基　　金：supported by the National Key Research and Development Program of China(No.2017YFB1002203);the National Nature Science Foundation of China(No.61525206,No.61672495,No.61771458,No.61702479,No.61571424)

摘　　要：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.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.

关 键 词：Image retrieval Learning to HASH VARIATIONAL autoencoder(VAE) GENERATIVE adversarial network(GAN) 

分 类 号：TN[电子电信]