Binary Generative Adversarial Networks for Image Retrieval

TL;DR

This paper introduces Binary Generative Adversarial Networks (BGAN), an unsupervised method that learns binary codes for images and generates similar images, significantly improving image retrieval performance without requiring labels.

Contribution

The paper proposes a novel unsupervised framework using BGAN with a sign-activation strategy and specialized loss functions for direct binary code generation and accurate image retrieval.

Findings

Outperforms existing hashing methods by up to 107% in mAP

Effective binary code learning without relaxation techniques

Generates plausible images similar to originals

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