中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Fast Supervised Discrete Hashing

文献类型：期刊论文

作者Gui, Jie1; Liu, Tongliang2,3; Sun, Zhenan4,5; Tao, Dacheng2,3; Tan, Tieniu4,5
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2018-02-01
卷号40期号:2页码:490-496
关键词Fast Supervised Discrete Hashing Supervised Discrete Hashing Learning-based Hashing Least Squares Regression
DOI10.1109/TPAMI.2017.2678475
文献子类Article
英文摘要Learning-based hashing algorithms are "hot topics" because they can greatly increase the scale at which existing methods operate. In this paper, we propose a new learning-based hashing method called "fast supervised discrete hashing" (FSDH) based on "supervised discrete hashing" (SDH). Regressing the training examples (or hash code) to the corresponding class labels is widely used in ordinary least squares regression. Rather than adopting this method, FSDH uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm. To the best of our knowledge, this strategy has not previously been used for hashing. Traditional SDH decomposes the optimization into three sub-problems, with the most critical sub-problem - discrete optimization for binary hash codes - solved using iterative discrete cyclic coordinate descent (DCC), which is time-consuming. However, FSDH has a closed-form solution and only requires a single rather than iterative hash code-solving step, which is highly efficient. Furthermore, FSDH is usually faster than SDH for solving the projection matrix for least squares regression, making FSDH generally faster than SDH. For example, our results show that FSDH is about 12-times faster than SDH when the number of hashing bits is 128 on the CIFAR-10 data base, and FSDH is about 151-times faster than FastHash when the number of hashing bits is 64 on the MNIST data-base. Our experimental results show that FSDH is not only fast, but also outperforms other comparative methods.
WOS关键词LEARNING BINARY-CODES ; IMAGE RETRIEVAL ; ITERATIVE QUANTIZATION ; PROCRUSTEAN APPROACH ; REPRESENTATION ; RECOGNITION ; SCENE
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000422706000017
资助机构National Science Foundation of China(61572463 ; "Thirteenth Five-Year" National Key Research and Development Program of China(2016YFD0702002) ; grant of Strategic Priority Research Program of the Chinese Academy of Sciences(XDB02080007) ; grant of the Open Project Program of the National Laboratory of Pattern Recognition (NLPR)(201700027) ; grant of the Open Project Program of the State Key Lab of CADCG(A1709) ; Zhejiang University ; grant of the Shanghai Key Laboratory of Intelligent Information Processing, China(IIPL-2016-003) ; grant of Australian Research Council Projects(FT-130101457 ; 61573360) ; DP-140102164 ; LP-150100671)
源URL[http://ir.ia.ac.cn/handle/173211/20764]  
专题自动化研究所_智能感知与计算研究中心
作者单位1.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Anhui, Peoples R China
2.Univ Sydney, UBTech Sydney Artificial Intelligence Inst, Fac Engn & Informat Technol, J12 Cleveland St, Darlington, NSW 2008, Australia
3.Univ Sydney, Sch Informat Technol, Fac Engn & Informat Technol, J12 Cleveland St, Darlington, NSW 2008, Australia
4.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
5.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Gui, Jie,Liu, Tongliang,Sun, Zhenan,et al. Fast Supervised Discrete Hashing[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(2):490-496.
APA Gui, Jie,Liu, Tongliang,Sun, Zhenan,Tao, Dacheng,&Tan, Tieniu.(2018).Fast Supervised Discrete Hashing.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(2),490-496.
MLA Gui, Jie,et al."Fast Supervised Discrete Hashing".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.2(2018):490-496.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。