Unified Binary Generative Adversarial Network for Image Retrieval and Compression

Jingkuan Song, Tao He, Lianli Gao*, Xing Xu, Alan Hanjalic, Heng Tao Shen

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

36 Citations (Scopus)
249 Downloads (Pure)


Binary codes have often been deployed to facilitate large-scale retrieval tasks, but not that often for image compression. In this paper, we propose a unified framework, BGAN+, that restricts the input noise variable of generative adversarial networks to be binary and conditioned on the features of each input image, and simultaneously learns two binary representations per image: one for image retrieval and the other serving as image compression. Compared to related methods that attempt to learn a single binary code serving both purposes, we demonstrate that choosing for two codes leads to more effective representations due to less concessions needed when balancing the requirements. The added value of using a unified framework compared to two separate frameworks lies in the synergy in data representation that is beneficial for both learning processes. When devising this framework, we also address another challenge in learning binary codes, namely that of learning supervision. While the most striking successes in image retrieval using binary codes have mostly involved discriminative models requiring labels, the proposed BGAN+ framework learns the binary codes in an unsupervised fashion, yet more effectively than the state-of-the-art supervised approaches. The proposed BGAN+ framework is evaluated on three benchmark datasets for image retrieval and two datasets on image compression. The experimental results show that BGAN+ outperforms the existing retrieval methods with significant margins and achieves promising performance for image compression, especially for low bit rates.

Original languageEnglish
Pages (from-to)2243-2264
Number of pages22
JournalInternational Journal of Computer Vision
Issue number8-9
Publication statusPublished - 2020

Bibliographical note

Accepted author manuscript


  • Binary codes
  • Generative adversarial network
  • Image compression
  • Image retrieval


Dive into the research topics of 'Unified Binary Generative Adversarial Network for Image Retrieval and Compression'. Together they form a unique fingerprint.

Cite this