检索结果-内蒙古大学图书馆

binary code learning via optimal class representations

NEUROCOMPUTING 2016年第0期208卷 59-65页

作者： Zhou, Xiang Shen, Fumin Yang, Yang Gao, Guangwei Wang, Yuan Univ Elect Sci & Technol Sch Comp Sci & Engn Chengdu Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Nanjing Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing Jiangsu Peoples R China Natl Univ Singapore Dept Ind & Syst Engn Singapore Singapore

Hashing is an attracting technique for fast retrieval due to its low storage and computation costs. By hashing, each high-dimensional vector is mapped into a low-dimensional binary code vector and retrieval is performed in the Hamming space. Recently several hashing methods have been proposed, among which, supervised hashing methods have shown great performance by incorporating the supervision information. However, most previous supervised methods simply focused on the pairwise label information of data, and ignored the structure information and relationship within data. To tackle this problem, we propose to learn binary codes by explicitly taking into account class semantic relatedness. Specifically, a set of binary codes is computed according to the intrinsic class similarities in data and serves as the optimal class representations. We show that, by mapping images onto the optimal representation of their corresponding classes, our proposed method outperforms several other state-of-the-art supervised hashing methods in image retrieval on three large-scale datasets. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Hashing binary code learning Image retrieval

来源：评论

学校读者我要写书评

暂无评论

A Fast Optimization Method for General binary code learning

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2016年第12期25卷 5610-5621页

作者： Shen, Fumin Zhou, Xiang Yang, Yang Song, Jingkuan Shen, Heng Tao Tao, Dacheng Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Columbia Univ New York NY 10027 USA Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld 4072 Australia Univ Technol Sydney Ctr Artificial Intelligence Ultimo NSW 2007 Australia Univ Technol Sydney Fac Engn & Informat Technol Ultimo NSW 2007 Australia

Hashing or binary code learning has been recognized to accomplish efficient near neighbor search, and has thus attracted broad interests in recent retrieval, vision, and learning studies. One main challenge of learning to hash arises from the involvement of discrete variables in binary code optimization. While the widely used continuous relaxation may achieve high learning efficiency, the pursued codes are typically less effective due to accumulated quantization error. In this paper, we propose a novel binary code optimization method, dubbed discrete proximal linearized minimization (DPLM), which directly handles the discrete constraints during the learning process. Specifically, the discrete (thus nonsmooth nonconvex) problem is reformulated as minimizing the sum of a smooth loss term with a nonsmooth indicator function. The obtained problem is then efficiently solved by an iterative procedure with each iteration admitting an analytical discrete solution, which is thus shown to converge very fast. In addition, the proposed method supports a large family of empirical loss functions, which is particularly instantiated in this paper by both a supervised and an unsupervised hashing losses, together with the bits uncorrelation and balance constraints. In particular, the proposed DPLM with a supervised l(2) loss encodes the whole NUS-WIDE database into 64-b binary codes within 10 s on a standard desktop computer. The proposed approach is extensively evaluated on several large-scale data sets and the generated binary codes are shown to achieve very promising results on both retrieval and classification tasks.

关键词： binary code learning hashing discrete optimization

来源：评论

学校读者我要写书评

暂无评论

binary code learning with semantic ranking based supervision 41

Binary code learning with semantic ranking based supervision

引用

41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016

作者： Nguyen, Viet-Anh Do, Minhn. Singapore Singapore University of Illinois at Urbana-Champaign IL United States

ISBN: (纸本)9781479999880

Recent years have witnessed the increasing popularity of binary hashing for efficient similarity search in large-scale vision problems. This paper presents a novel Supervised Ranking-Based Hashing (SRH) method for efficient binary code learning to better capture the semantic nearest neighbors and improve the search performance. In particular, a family of hash functions is designed to preserve the semantic data structure in the original high-dimensional space by utilizing the semantic ranking order information induced by any specific query. The proposed hashing framework is obtained by jointly minimizing the empirical error over the ranking violation in the binary code space together with the quantization loss between the original data and the binary codes. Furthermore, an effective regularizer for maximizing the even binary code distribution is also taken into account in the optimization to generate more efficient and compact binary codes. Experimental results have demonstrated the proposed method outperforms the state-of-the-art. © 2016 IEEE.

关键词： approximate nearest neighbor search binary code learning image retrieval semantic hashing

来源：评论

学校读者我要写书评

暂无评论

引用

INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL 2024年第3期13卷 28-28页

作者： Elboushaki, Abdessamad Hannane, Rachida Afdel, Karim Cadi Ayyad Univ Fac Sci & Technol Lab Comp Engn & Syst Marrakech 40000 Morocco Cadi Ayyad Univ Fac Sci Semlalia Marrakech Lab Comp Syst Engn Marrakech 40000 Morocco Ibn Zohr Univ Fac Sci Lab Comp Syst & Vis Agadir 80000 Morocco

Human face retrieval has long been established as one of the most interesting research topics in computer vision. With the recent development of deep learning, many researchers have addressed this problem by building deep hashing models to learn binary code from face images, while performing face retrieval as a classification task. Nevertheless, the performance is still unsatisfactory since these models are incapable of handling inter-class variation between multiple persons, as we need to make a class label for each identity. In this backdrop, we propose in this paper an effective deep learning-based framework for face image retrieval. The key to our framework is mainly based on the matching of face pairs, where a two-stream network, named chi Net+chi Match\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\chi Net+\chi Match$$\end{document}, is designed to learn similarities in terms of person identity. Such similarities are investigated by embedding both deep local representation via face components, and deep global face representation via the whole face image. Since the similarities captured over face components are supposed to diversify due to variation in pose, expression and occlusion, we also introduce a Sparse Score Fusion layer that learns automatically the weight of each component according to its contribution to face matching. To allow fast retrieval, we farther propose a method that generates binary codes corresponding to the groups of similar faces through the hierarchical k-means, where the path down binary tree is exploited as a binary code for indexing. The final retrieval is then conducted within a privileged subset of images in the database. Our experiments on different challenging datasets show that our approach obtains outstanding results while outperforming most existi

关键词： Face image retrieval Face matching Deep face representation Sparse score fusion binary code learning

来源：评论

学校读者我要写书评

暂无评论

A binary code learning Method Based on Class-neighborhood for Finger Vein Recognition

A Binary Code Learning Method Based on Class-neighborhood fo...

引用

2018 2nd International Conference on Artificial Intelligence: Technologies and Applications（ICAITA2018）

作者： Liping Zhang Weijun Li Xin Ning Xiaoli Dong Yakun Zhang Institute of Semiconductors Chinese Academy of Sciences School of Microelectronics University of Chinese Academy of Sciences

The finger vein recognition, as a new biometric identification technology, judges the identity of a person by using their finger vein angiography images obtained by near-infrared light, and has recently drawn considerable attention from scientists worldwide. In this work, a novel binary code learning method based on class-neighborhood（BCLCN） is proposed for finger vein recognition. Different from traditional binary code methods based on pixels, BCLCN fully considers the relationships between categories of train set and encodes based those relationships. In this way, the discrimination of the code is enhanced and the binary codes are shortened. Experimental results on self-built finger vein image database demonstrate the effectiveness of BCLCN（EER = 0.512%）.

关键词： finger vein recognition binary code learning class-neighborhood

来源：评论

学校读者我要写书评

暂无评论

Ordinal Constraint binary Coding for Approximate Nearest Neighbor Search

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2019年第4期41卷 941-955页

作者： Liu, Hong Ji, Rongrong Wang, Jingdong Shen, Chunhua Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart City Xiamen Shi 361005 Fujian Sheng Peoples R China Microsoft Res Asia Media Comp Grp Beijing 100190 Peoples R China Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia

binary code learning, a.k.a. hashing, has been successfully applied to the approximate nearest neighbor search in large-scale image collections. The key challenge lies in reducing the quantization error from the original real-valued feature space to a discrete Hamming space. Recent advances in unsupervised hashing advocate the preservation of ranking information, which is achieved by constraining the binary code learning to be correlated with pairwise similarity. However, few unsupervised methods consider the preservation of ordinal relations in the learning process, which serves as a more basic cue to learn optimal binary codes. In this paper, we propose a novel hashing scheme, termed Ordinal Constraint Hashing (OCH), which embeds the ordinal relation among data points to preserve ranking into binary codes. The core idea is to construct an ordinal graph via tensor product, and then train the hash function over this graph to preserve the permutation relations among data points in the Hamming space. Subsequently, an in-depth acceleration scheme, termed Ordinal Constraint Projection (OCP), is introduced, which approximates the n-pair ordinal graph by L-pair anchor-based ordinal graph, and reduce the corresponding complexity from O(n(4)) to O(L-3) (L << n). Finally, to make the optimization tractable, we further relax the discrete constrains and design a customized stochastic gradient decent algorithm on the Stiefel manifold. Experimental results on serval large-scale benchmarks demonstrate that the proposed OCH method can achieve superior performance over the state-of-the-art approaches.

关键词： binary code learning hashing image retrieval ordinal preserving tensor graph discrete optimization

来源：评论

学校读者我要写书评

暂无评论

Binarized network embedding with community structural information

引用

INFORMATION SCIENCES 2022年 616卷 204-216页

作者： Liu, Yanbei Liu, Jinxin Wang, Zhongqiang Wang, Xiao Zhang, Fang Xiao, Zhitao Tiangong Univ Sch Life Sci Tianjin 300387 Peoples R China Tianjin Key Lab Optoelect Detect Technol Tianjin 300387 Peoples R China Tiangong Univ Sch Elect & Informat Engn Tianjin 300387 Peoples R China Echoey Technol Co ltd Tianjin 300387 Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci Beijing 100876 Peoples R China

Network embedding aims to learn low-dimensional vector representations for network nodes by preserving the network structure. The vast majority of existing network embed-ding methods are typically represented in continuous vectors, which impose formidable challenges in storage and computation costs, especially in large-scale applications. To this end, we propose a novel Binarized Network Embedding (BINE) method to learn binary node representations while retaining the community structural information in the network. Specifically, to preserve the community structure among node representations, we absorb the modularity constraint into the matrix factorization-based framework that can approx-imate the first-order and second-order proximity. Meanwhile, the cyclic coordinate des-cent method is adopted to implement the binary node representations for improving storage and computing efficiency. Finally, the conjugate gradient algorithm is employed to jointly optimize the objective function. Extensive experimental results on a variety of real-world network datasets demonstrate that BINE exhibits lower storage and computa-tional complexity than state-of-the-art network embedding methods while achieving com-petitive experimental *** 2022 Published by Elsevier Inc.

关键词： Network embedding Community structure binary code learning

来源：评论

学校读者我要写书评

暂无评论

Modality-Invariant Asymmetric Networks for Cross-Modal Hashing

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第5期35卷 5091-5104页

作者： Zhang, Zheng Luo, Haoyang Zhu, Lei Lu, Guangming Shen, Heng Tao Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Peoples R China Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 610054 Peoples R China

Cross-modal hashing has garnered considerable attention and gained great success in many cross-media similarity search applications due to its prominent computational efficiency and low storage overhead. However, it still remains challenging how to effectively take multilevel advantages of semantics on the entire database to jointly bridge the semantic and heterogeneity gaps across different modalities. In this paper, we propose a novel Modality-Invariant Asymmetric Networks (MIAN) architecture, which explores the asymmetric intra- and inter-modal similarity preservation under a probabilistic modality alignment framework. Specifically, an intra-modal asymmetric network is conceived to capture the query-vs-all internal pairwise similarities for each modality in a probabilistic asymmetric learning manner. Moreover, an inter-modal asymmetric network is deployed to fully harness the cross-modal semantic similarities supported by the maximum inner product search formula between two distinct hash embeddings. Particularly, the pairwise, piecewise and transformed semantics are jointly considered into one unified semantic-preserving hash codes learning scheme. Furthermore, we construct a modality alignment network to distill the redundancy-free visual features and maximize the conditional bottleneck information between different modalities. Such a network could close the heterogeneity and domain shift across different modalities and enable it to yield discriminative modality-invariant hash codes. Extensive experiments evidence that our MIAN approach can outperform the state-of-the-art cross-modal hashing methods.

关键词： Semantics binary codes Electronic mail Training Representation learning Measurement Feature extraction Deep asymmetric learning modality-alignment network binary code learning cross-modal hashing

来源：评论

学校读者我要写书评

暂无评论

Hashing on Nonlinear Manifolds

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2015年第6期24卷 1839-1851页

作者： Shen, Fumin Shen, Chunhua Shi, Qinfeng van den Hengel, Anton Tang, Zhenmin Shen, Heng Tao Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610051 Peoples R China Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia Australian Ctr Robot Vis Brisbane Qld 4000 Australia Nanjing Univ Sci & Technol Sch Comp Sci & Technol Nanjing 210094 Jiangsu Peoples R China Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld 4072 Australia

learning-based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes preserving the Euclidean similarity in the original space. Manifold learning techniques, in contrast, are better able to model the intrinsic structure embedded in the original high-dimensional data. The complexities of these models, and the problems with out-of-sample data, have previously rendered them unsuitable for application to large-scale embedding, however. In this paper, how to learn compact binary embeddings on their intrinsic manifolds is considered. In order to address the above-mentioned difficulties, an efficient, inductive solution to the out-of-sample data problem, and a process by which nonparametric manifold learning may be used as the basis of a hashing method are proposed. The proposed approach thus allows the development of a range of new hashing techniques exploiting the flexibility of the wide variety of manifold learning approaches available. It is particularly shown that hashing on the basis of t-distributed stochastic neighbor embedding outperforms state-of-the-art hashing methods on large-scale benchmark data sets, and is very effective for image classification with very short code lengths. It is shown that the proposed framework can be further improved, for example, by minimizing the quantization error with learned orthogonal rotations without much computation overhead. In addition, a supervised inductive manifold hashing framework is developed by incorporating the label information, which is shown to greatly advance the semantic retrieval performance.

关键词： Hashing binary code learning manifold learning image retrieval

来源：评论

学校读者我要写书评

暂无评论

Structure-aware contrastive hashing for unsupervised cross-modal retrieval

引用

NEURAL NETWORKS 2024年 174卷 106211页

作者： Cui, Jinrong He, Zhipeng Huang, Qiong Fu, Yulu Li, Yuting Wen, Jie South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China Harbin Inst Technol Shenzhen Key Lab Visual Object Detect & Recognit Shenzhen 518055 Peoples R China Guangzhou Key Lab Intelligent Agricuture Guangzhou Peoples R China

Cross -modal hashing has attracted a lot of attention and achieved remarkable success in large-scale crossmedia similarity retrieval applications because of its superior computational efficiency and low storage overhead. However, constructing similarity relationship among samples in cross -modal unsupervised hashing is challenging because of the lack of manual annotation. Most existing unsupervised methods directly use the representations extracted from the backbone of their respective modality to construct instance similarity matrices, leading to inaccurate similarity matrices and resulting in suboptimal hash codes. To address this issue, a novel unsupervised hashing model, named Structure -aware Contrastive Hashing for Unsupervised Crossmodal Retrieval (SACH), is proposed in this paper. Specifically, we concurrently employ both high -dimensional representations and discriminative representations learned by the network to construct a more informative semantic correlative matrix across modalities. Moreover, we design a multimodal structure -aware alignment network to minimize heterogeneous gap in the high -order semantic space of each modality, effectively reducing disparities within heterogeneous data sources and enhancing the consistency of semantic information across modalities. Extensive experimental results on two widely utilized datasets demonstrate the superiority of our proposed SACH method in cross -modal retrieval tasks over existing state-of-the-art methods.

关键词： Multimedia retrieval Unsupervised deep hashing Cross -modal retrieval binary code learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：