融合注意力机制的非对称深度监督哈希

Asymmetric Deep Supervised Hashing with Attention Mechanism

随着大数据时代的到来,互联网上的信息数据呈指数级增长。在这些数据中,图像资源占比巨大,因此如何在海量图像中进行准确而高效的图像检索成为当今的重要研究课题之一。目前大多数方法提取到的特征信息含有大量冗余信息,使得在图像检索中不能有效关注到图像的重点区域而导致检索性能差、准确度低等问题。基于以上不足,本文提出一种融合注意力机制的非对称深度哈希算法。以卷积神经网络为基础,对现有的由语义特征引导的混合注意力机制进行改进,将其嵌入进网络中,使得哈希网络将全局语义信息和局部语义信息共同分析。同时设计新的量化函数来减少量化误差,从而增强哈希编码的特征表达能力。并采用mAP作为评价指标,在数据集CIFAR-10和NUS-WIDE数据集上将本文方法与其他哈希方法进行比较,结果表明本文设计的网络模型能很好地结合全局和局部的特征信息,提高图像检索性能。

With the advent of the era of big data,the information data on the Internet is growing exponentially.Among these data,image resource accounts for a very large proportion,so how to carry out accurate and efficient image retrieval from massive images has become one of the important research topics today.At present,there are some problems in large-scale image re⁃trieval,such as poor retrieval performance and low accuracy due to the inability to effectively focus on the key areas of the image.Based on the above shortcomings,an asymmetric deep hash algorithm that integrates the attention mechanism is proposed,which is modified based on convolutional neural network.The existing mixed attention mechanism guided by semantic features is im⁃proved and embedded into the network,so that the hash network can analyze the global semantic information and local semantic information together.At the same time,a new quantization function is designed to reduce quantization error,so as to enhance the feature expression ability of hash coding.This method is compared with other hashing methods on the CIFAR-10 and NUSWIDE datasets with evaluation standard mAP.The results show that the proposed network model can combine global and local spatial features well,and improve the image retrieval performance.