标题:Scalable Deep Hashing for Large-Scale Social Image Retrieval
作者:Cui, Hui; Zhu, Lei; Li, Jingjing; Yang, Yang; Nie, Liqiang
作者机构:[Cui, Hui; Zhu, Lei] Shandong Normal Univ, Sch Informat Sci & Engn, Jinan 250358, Shandong, Peoples R China.; [Li, Jingjing; Yang, Yang] Univ Elect 更多
通讯作者:Zhu, Lei;Zhu, L
通讯作者地址:[Zhu, L]Shandong Normal Univ, Sch Informat Sci & Engn, Jinan 250358, Shandong, Peoples R China.
来源:IEEE TRANSACTIONS ON IMAGE PROCESSING
出版年:2020
卷:29
页码:1271-1284
DOI:10.1109/TIP.2019.2940693
关键词:Semantics; Image retrieval; Optimization; Hash functions; Scalability;; Quantization (signal); Visualization; Unsupervised deep hashing; social; tags; augmented Lagrangian multiplier; discrete optimization
摘要:Recent years have witnessed the wide application of hashing for large-scale image retrieval, because of its high computation efficiency and low storage cost. Particularly, benefiting from current advances in deep learning, supervised deep hashing methods have greatly boosted the retrieval performance, under the strong supervision of large amounts of manually annotated semantic labels. However, their performance is highly dependent upon the supervised labels, which significantly limits the scalability. In contrast, unsupervised deep hashing without label dependence enjoys the advantages of well scalability. Nevertheless, due to the relaxed hash optimization, and more importantly, the lack of semantic guidance, existing methods suffer from limited retrieval performance. In this paper, we propose a SCAlable Deep Hashing (SCADH) to learn enhanced hash codes for social image retrieval. We formulate a unified scalable deep hash learning framework which explores the weak but free supervision of discriminative user tags that are commonly accompanied with social images. It jointly learns image representations and hash functions with deep neural networks, and simultaneously enhances the discriminative capability of image hash codes with the refined semantics from the accompanied social tags. Further, instead of simple relaxed hash optimization, we propose a discrete hash optimization method based on Augmented Lagrangian Multiplier to directly solve the hash codes and avoid the binary quantization information loss. Experiments on two standard social image datasets demonstrate the superiority of the proposed approach compared with state-of-the-art shallow and deep hashing techniques.
收录类别:EI;SCOPUS;SCIE
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85077491757&doi=10.1109%2fTIP.2019.2940693&partnerID=40&md5=54fc1fe8d4361236dfa9c50a0e0bf877
TOP