基于伪成对标签的深度无监督哈希学习  

Deep Unsupervised Hashing with Pseudo Pairwise Labels

作　　者：林计文 刘华文 LIN Jiwen;LIU Huawen(College of Mathematics and Computer Science,Zhejiang Normal University,Jinhua 321004)

机构地区：[1]浙江师范大学数学与计算机科学学院,金华321004

出　　处：《模式识别与人工智能》2020年第3期258-267,共10页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.61572443);浙江省自然科学基金项目(No.LY14F020019)资助。

摘　　要：无监督的深度哈希学习方法由于缺少相似性监督信息,难以获取高质量的哈希编码.因此,文中提出端到端的基于伪成对标签的深度无监督哈希学习模型.首先对由预训练的深度卷积神经网络得到的图像特征进行统计分析,用于构造数据的语义相似性标签.再进行基于成对标签的有监督哈希学习.在两个常用的图像数据集CIFAR-10、NUS-WIDE上的实验表明,经文中方法得到的哈希编码在图像检索上的性能较优.It is difficult to obtain high-quality hash codes for unsupervised deep hashing methods due to the lack of similarity supervised information.Therefore,an end-to-end deep unsupervised hashing model based on pseudo-pairwise labels is proposed.Statistical analysis is performed on the image features extracted by the pre-trained deep convolutional neural network to construct the semantic similarity labels for data.Supervised deep hashing based on pairwise labels is then conducted.Experiments on commonly used image datasets CIFAR-10 and NUS-WIDE indicate that hash codes obtained by the proposed method perform better on image retrieval.

关 键 词：哈希学习 深度无监督哈希学习 伪标签 近似最近邻搜索 图像检索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]