English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The most striking successes in image retrieval using deep hashing have mostlyinvolved discriminative models, which require labels. In this paper, we usebinary generative adversarial networks (BGAN) to embed images to binary codesin an unsupervised way. By restricting the input noise variable of generativeadversarial networks (GAN) to be binary and conditioned on the features of eachinput image, BGAN can simultaneously learn a binary representation per image,and generate an image plausibly similar to the original one. In the proposedframework, we address two main problems: 1) how to directly generate binarycodes without relaxation? 2) how to equip the binary representation with theability of accurate image retrieval? We resolve these problems by proposing newsign-activation strategy and a loss function steering the learning process,which consists of new models for adversarial loss, a content loss, and aneighborhood structure loss. Experimental results on standard datasets(CIFAR-10, NUSWIDE, and Flickr) demonstrate that our BGAN significantlyoutperforms existing hashing methods by up to 107\% in terms of~mAP (See Tabletab.res.map.comp) Our anonymous code is available at:https://github.com/htconquer/BGAN.

Binary Generative Adversarial Networks for Image Retrieval