Binary Generative Adversarial Networks For 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 (C

Stats

• citations102
• S2 citations—
• github stars41
• HF likes0
• heat score18.34
• arxiv keysong2017binary

Related papers

• Binary Constrained Deep Hashing Network For Image Retrieval Without Manual Annotation (2018)5.84
• Bingan: Learning Compact Binary Descriptors With A Regularized GAN (2018)0.00
• Compact Hash Code Learning With Binary Deep Neural Network (2017)9.03
• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Irgen: Generative Modeling For Image Retrieval (2023)7.16
• Regularizing Deep Hashing Networks Using GAN Generated Fake Images (2018)0.00
• Supervised Hashing With End-to-end Binary Deep Neural Network (2017)2.26
• Unsupervised Adversarial Attacks On Deep Feature-based Retrieval With GAN (2019)0.00