Binary Generative Adversarial Networks for Image Retrieval

08/08/2017
by   Jingkuan Song, et al.
0

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 tab.res.map.comp) Our anonymous code is available at: https://github.com/htconquer/BGAN.

READ FULL TEXT

page 3

page 8

research
07/07/2017

Deep Discrete Hashing with Self-supervised Pairwise Labels

Hashing methods have been widely used for applications of large-scale im...
research
02/21/2018

Binary Constrained Deep Hashing Network for Image Retrieval without Human Intervention

Learning compact binary codes for image retrieval problem using deep neu...
research
01/15/2022

Asymmetric Hash Code Learning for Remote Sensing Image Retrieval

Remote sensing image retrieval (RSIR), aiming at searching for a set of ...
research
06/02/2021

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Learning binary representations of instances and classes is a classical ...
research
04/03/2018

DeSIGN: Design Inspiration from Generative Networks

Can an algorithm create original and compelling fashion designs to serve...
research
08/26/2017

3D Object Reconstruction from a Single Depth View with Adversarial Learning

In this paper, we propose a novel 3D-RecGAN approach, which reconstructs...
research
10/10/2018

Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation

We propose the BinaryGAN, a novel generative adversarial network (GAN) t...

Please sign up or login with your details

Forgot password? Click here to reset