期刊
CHINESE JOURNAL OF ELECTRONICS
卷 28, 期 6, 页码 1191-1197出版社
WILEY
DOI: 10.1049/cje.2019.08.001
关键词
file organisation; image retrieval; learning (artificial intelligence); neural nets; pairwise hashing learning; semantic perserving feature mapping model; adversarial generative process; image feature vector; hash codes; pairwise ranking loss; generative networks; VAE-GAN based hashing framework; image retrieval; content preserving images; similarity retrieval; variational autoencoder; generative adversarial network; Image retrieval; Learning to hash; Variational autoencoder(VAE); Generative adversarial network(GAN)
资金
- National Key Research and Development Program of China [2017YFB1002203]
- National Nature Science Foundation of China [61525206, 61672495, 61771458, 61702479, 61571424]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据