Deep Attention-guided Hashing

12/04/2018
by   Zhan Yang, et al.
0

With the rapid growth of multimedia data (e.g., image, audio and video etc.) on the web, learning-based hashing techniques such as Deep Supervised Hashing (DSH) have proven to be very efficient for large-scale multimedia search. The recent successes seen in Learning-based hashing methods are largely due to the success of deep learning-based hashing methods. However, there are some limitations to previous learning-based hashing methods (e.g., the learned hash codes containing repetitive and highly correlated information). In this paper, we propose a novel learning-based hashing method, named Deep Attention-guided Hashing (DAgH). DAgH is implemented using two stream frameworks. The core idea is to use guided hash codes which are generated by the hashing network of the first stream framework (called first hashing network) to guide the training of the hashing network of the second stream framework (called second hashing network). Specifically, in the first network, it leverages an attention network and hashing network to generate the attention-guided hash codes from the original images. The loss function we propose contains two components: the semantic loss and the attention loss. The attention loss is used to punish the attention network to obtain the salient region from pairs of images; in the second network, these attention-guided hash codes are used to guide the training of the second hashing network (i.e., these codes are treated as supervised labels to train the second network). By doing this, DAgH can make full use of the most critical information contained in images to guide the second hashing network in order to learn efficient hash codes in a true end-to-end fashion. Results from our experiments demonstrate that DAgH can generate high quality hash codes and it outperforms current state-of-the-art methods on three benchmark datasets, CIFAR-10, NUS-WIDE, and ImageNet.

READ FULL TEXT
research
03/29/2019

Asymmetric Deep Semantic Quantization for Image Retrieval

Due to its fast retrieval and storage efficiency capabilities, hashing h...
research
05/31/2017

Deep Supervised Discrete Hashing

With the rapid growth of image and video data on the web, hashing has be...
research
03/26/2018

Regularizing Deep Hashing Networks Using GAN Generated Fake Images

Recently, deep-networks-based hashing (deep hashing) has become a leadin...
research
07/26/2022

Adaptive Asymmetric Label-guided Hashing for Multimedia Search

With the rapid growth of multimodal media data on the Web in recent year...
research
04/23/2018

Deep Semantic Hashing with Generative Adversarial Networks

Hashing has been a widely-adopted technique for nearest neighbor search ...
research
09/16/2020

Weakly-Supervised Online Hashing

With the rapid development of social websites, recent years have witness...
research
08/12/2016

Deep Hashing: A Joint Approach for Image Signature Learning

Similarity-based image hashing represents crucial technique for visual d...

Please sign up or login with your details

Forgot password? Click here to reset