Regularizing Deep Hashing Networks Using GAN Generated Fake Images

Abstract

Recently, deep-networks-based hashing (deep hashing) has become a leading approach for large-scale image retrieval. It aims to learn a compact bitwise representation for images via deep networks, so that similar images are mapped to nearby hash codes. Since a deep network model usually has a large number of parameters, it may probably be too complicated for the training data we have, leading to model over-fitting. To address this issue, in this paper, we propose a simple two-stage pipeline to learn deep hashing models, by regularizing the deep hashing networks using fake images. The first stage is to generate fake images from the original training set without extra data, via a generative adversarial network (GAN). In the second stage, we propose a deep architec- ture to learn hash functions, in which we use a maximum-entropy based loss to incorporate the newly created fake images by the GAN. We show that this loss acts as a strong regularizer of the deep architecture, by penalizing low

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygeng2018regularizing

Related papers

• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Prototype-supervised Adversarial Network For Targeted Attack Of Deep Hashing (2021)15.97
• One Network For Multi-domains: Domain Adaptive Hashing With Intersectant Generative Adversarial Network (2019)7.81
• Binary Generative Adversarial Networks For Image Retrieval (2017)18.34
• Deep Hashing: A Joint Approach For Image Signature Learning (2016)5.24
• Hashgan:attention-aware Deep Adversarial Hashing For Cross Modal Retrieval (2017)15.34
• HHF: Hashing-guided Hinge Function For Deep Hashing Retrieval (2021)14.24
• Coophash: Cooperative Learning Of Multipurpose Descriptor And Contrastive Pair Generator Via Variational MCMC Teaching For Supervised Image Hashing (2022)0.00