Binary Generative Adversarial Networks for Image Retrieval

Authors

  • Jingkuan Song University of Electronic Science and Technology of China
  • Tao He University of Electronic Science and Technology of China
  • Lianli Gao University of Electronic Science and Technology of China
  • Xing Xu University of Electronic Science and Technology of China
  • Alan Hanjalic Delft University of Technology
  • Heng Tao Shen University of Electronic Science and Technology of China

Keywords:

hashing, GAN, image retrieval

Abstract

The most striking successes in image retrieval using deep hashing have mostly involved discriminative models, which require labels. In this paper, we use binary generative adversarial networks (BGAN) to embed images to binary codes in an unsupervised way. By restricting the input noise variable of generative adversarial networks (GAN) to be binary and conditioned on the features of each input image, BGAN can simultaneously learn a binary representation per image, and generate an image plausibly similar to the original one. In the proposed framework, we address two main problems: 1) how to directly generate binary codes without relaxation? 2) how to equip the binary representation with the ability of accurate image retrieval? We resolve these problems by proposing new sign-activation strategy and a loss function steering the learning process, which consists of new models for adversarial loss, a content loss, and a neighborhood structure loss. Experimental results on standard datasets (CIFAR-10, NUSWIDE, and Flickr) demonstrate that our BGAN significantly outperforms existing hashing methods by up to 107% in terms of mAP (See Table 2).

Downloads

Published

2018-04-25

How to Cite

Song, J., He, T., Gao, L., Xu, X., Hanjalic, A., & Shen, H. T. (2018). Binary Generative Adversarial Networks for Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11276