Semantic Preserving Hash Coding Through VAE-GAN
Lists
Only you see this
Abstract
This paper proposes a novel framework for fast image retrieval. The proposed framework combines variational autoencoder with generative adversarial network to generate content preserving images for learning-based hashing. By accepting real image and systhesized image in a pairwise form, a semantic perserving binary mapping model is learned using pairwise ranking loss under an adversarial generative process. Extensive experiments on several benchmark datasets demonstrate that the proposed method shows substantial improvement over the state-of-the-art hashing methods.
BibTeX
@inproceedings{jin2018semantic,
author = {Guoqing Jin and Dongming Zhang and Feng Dai and Junbo Guo and Yike Ma and Yongdong Zhang},
title = {{Semantic Preserving Hash Coding Through VAE-GAN}},
booktitle = {ICIP},
year = {2018},
doi = {10.1109/icip.2018.8451744},
}Loading related content...