scholarly journals Deep Binary Representation for Efficient Image Retrieval

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Xuchao Lu ◽  
Li Song ◽  
Rong Xie ◽  
Xiaokang Yang ◽  
Wenjun Zhang
Keyword(s):  
Image Retrieval ◽  
Hamming Distance ◽  
Binary Representation ◽  
Deep Network ◽  
Deep Hashing ◽  
Hash Code ◽  
Representation Method ◽  
The Relationship ◽  
Determining Factor ◽  
Hash Codes

With the fast growing number of images uploaded every day, efficient content-based image retrieval becomes important. Hashing method, which means representing images in binary codes and using Hamming distance to judge similarity, is widely accepted for its advantage in storage and searching speed. A good binary representation method for images is the determining factor of image retrieval. In this paper, we propose a new deep hashing method for efficient image retrieval. We propose an algorithm to calculate the target hash code which indicates the relationship between images of different contents. Then the target hash code is fed to the deep network for training. Two variants of deep network, DBR and DBR-v3, are proposed for different size and scale of image database. After training, our deep network can produce hash codes with large Hamming distance for images of different contents. Experiments on standard image retrieval benchmarks show that our method outperforms other state-of-the-art methods including unsupervised, supervised, and deep hashing methods.

scholarly journals Discriminative Deep Hashing for Scalable Face Image Retrieval

2017 ◽  
Author(s):  
Jie Lin ◽  
Zechao Li ◽  
Jinhui Tang
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Prediction Errors ◽  
Unified Framework ◽  
Multi Scale ◽  
Deep Hashing ◽  
Hash Codes

With the explosive growth of images containing faces, scalable face image retrieval has attracted increasing attention. Due to the amazing effectiveness, deep hashing has become a popular hashing method recently. In this work, we propose a new Discriminative Deep Hashing (DDH) network to learn discriminative and compact hash codes for large-scale face image retrieval. The proposed network incorporates the end-to-end learning, the divide-and-encode module and the desired discrete code learning into a unified framework. Specifically, a network with a stack of convolution-pooling layers is proposed to extract multi-scale and robust features by merging the outputs of the third max pooling layer and the fourth convolutional layer. To reduce the redundancy among hash codes and the network parameters simultaneously, a divide-and-encode module to generate compact hash codes. Moreover, a loss function is introduced to minimize the prediction errors of the learned hash codes, which can lead to discriminative hash codes. Extensive experiments on two datasets demonstrate that the proposed method achieves superior performance compared with some state-of-the-art hashing methods.

scholarly journals Locality Constrained Deep Supervised Hashing for Image Retrieval

2017 ◽  
Author(s):  
Hao Zhu ◽  
Shenghua Gao
Keyword(s):  
Neural Network ◽  
Image Retrieval ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Quantization Error ◽  
Deep Convolutional Neural Network ◽  
Training Phase ◽  
Deep Hashing ◽  
Image Pairs ◽  
Hash Codes

Deep Convolutional Neural Network (DCNN) based deep hashing has shown its success for fast and accurate image retrieval, however directly minimizing the quantization error in deep hashing will change the distribution of DCNN features, and consequently change the similarity between the query and the retrieved images in hashing. In this paper, we propose a novel Locality-Constrained Deep Supervised Hashing. By simultaneously learning discriminative DCNN features and preserving the similarity between image pairs, the hash codes of our scheme preserves the distribution of DCNN features thus favors the accurate image retrieval.The contributions of this paper are two-fold: i) Our analysis shows that minimizing quantization error in deep hashing makes the features less discriminative which is not desirable for image retrieval; ii) We propose a Locality-Constrained Deep Supervised Hashing which preserves the similarity between image pairs in hashing.Extensive experiments on the CIFARA-10 and NUS-WIDE datasets show that our method significantly boosts the accuracy of image retrieval, especially on the CIFAR-10 dataset, the improvement is usually more than 6% in terms of the MAP measurement. Further, our method demonstrates 10 times faster than state-of-the-art methods in the training phase.

scholarly journals Deep Hashing Based Fusing Index Method for Large-Scale Image Retrieval

2017 ◽  
Vol 2017 ◽  
pp. 1-8
Author(s):  
Lijuan Duan ◽  
Chongyang Zhao ◽  
Jun Miao ◽  
Yuanhua Qiao ◽  
Xing Su
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Feature Learning ◽  
Index Method ◽  
Storage And Retrieval ◽  
Deep Hashing ◽  
Indexing Method ◽  
Hash Code ◽  
Large Scale Image Retrieval

Hashing has been widely deployed to perform the Approximate Nearest Neighbor (ANN) search for the large-scale image retrieval to solve the problem of storage and retrieval efficiency. Recently, deep hashing methods have been proposed to perform the simultaneous feature learning and the hash code learning with deep neural networks. Even though deep hashing has shown the better performance than traditional hashing methods with handcrafted features, the learned compact hash code from one deep hashing network may not provide the full representation of an image. In this paper, we propose a novel hashing indexing method, called the Deep Hashing based Fusing Index (DHFI), to generate a more compact hash code which has stronger expression ability and distinction capability. In our method, we train two different architecture’s deep hashing subnetworks and fuse the hash codes generated by the two subnetworks together to unify images. Experiments on two real datasets show that our method can outperform state-of-the-art image retrieval applications.

scholarly journals Deep Supervised Hashing for Fast Multi-Label Image

2018 ◽  
Vol 173 ◽  
pp. 03032
Author(s):  
Qian Ying ◽  
Ye Qingqing
Keyword(s):  
Objective Function ◽  
Loss Function ◽  
Binary Code ◽  
Hamming Distance ◽  
Binary Vector ◽  
Experimental Results ◽  
Training Data ◽  
Retrieval Accuracy ◽  
Deep Hashing ◽  
Hash Code

In this paper, most of the existing Hashing methods is mapping the hand extracted features to binary code, and designing the loss function with the label of images. However, hand-crafted features and inadequacy considering all the loss of the network will reduce the retrieval accuracy. Supervised hashing method improves the similarity between sample and hash code by training data and labels of image. In this paper, we propose a novel deep hashing method which combines the objective function with pairwise label which is produced by the Hamming distance between the label binary vector of images, quantization error and the loss of hashing code between the balanced value as loss function to train network. The experimental results show that the proposed method is more accurate than most of current restoration methods.

scholarly journals Semi-Supervised Deep Hashing with a Bipartite Graph

2017 ◽  
Author(s):  
Xinyu Yan ◽  
Lijun Zhang ◽  
Wu-Jun Li
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Bipartite Graph ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Underlying Structure ◽  
Deep Hashing ◽  
Hash Code ◽  
Out Of Sample ◽  
Hash Codes

Recently, deep learning has been successfully applied to the problem of hashing, yielding remarkable performance compared to traditional methods with hand-crafted features. However, most of existing deep hashing methods are designed for the supervised scenario and require a large number of labeled data. In this paper, we propose a novel semi-supervised hashing method for image retrieval, named Deep Hashing with a Bipartite Graph (DHBG), to simultaneously learn embeddings, features and hash codes. More specifically, we construct a bipartite graph to discover the underlying structure of data, based on which an embedding is generated for each instance. Then, we feed raw pixels as well as embeddings to a deep neural network, and concatenate the resulting features to determine the hash code. Compared to existing methods, DHBG is a universal framework that is able to utilize various types of graphs and losses. Furthermore, we propose an inductive variant of DHBG to support out-of-sample extensions. Experimental results on real datasets show that our DHBG outperforms state-of-the-art hashing methods.

scholarly journals Improved Deep Hashing with Scalable Interblock for Tourist Image Retrieval

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Jiangfan Feng ◽  
Wenzheng Sun
Keyword(s):  
Image Retrieval ◽  
Deep Neural Networks ◽  
Feature Vector ◽  
Semantic Distance ◽  
Retrieval Performance ◽  
Deep Hashing ◽  
Binary Feature ◽  
Two Samples ◽  
Image Representations ◽  
Hash Codes

Tourist image retrieval has attracted increasing attention from researchers. Mainly, supervised deep hash methods have significantly boosted the retrieval performance, which takes hand-crafted features as inputs and maps the high-dimensional binary feature vector to reduce feature-searching complexity. However, their performance depends on the supervised labels, but few labeled temporal and discriminative information is available in tourist images. This paper proposes an improved deep hash to learn enhanced hash codes for tourist image retrieval. It jointly determines image representations and hash functions with deep neural networks and simultaneously enhances the discriminative capability of tourist image hash codes with refined semantics of the accompanying relationship. Furthermore, we have tuned the CNN to implement end-to-end training hash mapping, calculating the semantic distance between two samples of the obtained binary codes. Experiments on various datasets demonstrate the superiority of the proposed approach compared to state-of-the-art shallow and deep hashing techniques.

INTER AKSI AGAMA DAN BUDAYA

EMPIRISMA ◽  
2018 ◽  
Vol 27 (1) ◽  
Author(s):  
Mohammad Arif Dan Yuli Darwati
Keyword(s):  
Human Life ◽  
Belief System ◽  
Cultural Interaction ◽  
Cultural Economic ◽  
Modern Period ◽  
Or Groups ◽  
Close Relationship ◽  
History Of ◽  
The Relationship ◽  
Determining Factor

This paper will try to explain the relationship between religion and culture. These two topics are the most important items that are inseparable in the history of human civilization from the classical to the modern period. Religion is ahuman belief system that is related to God. If the rule comes from God, then it cannot be said to be a culture, because it is not human creation, but God’s creation that is absolute. Religion is interpreted as part of the life (culture) ofindividuals or groups, each of which has the authority to understand religion and apply it. With the characteristics as indicated by Fazlur Rahman, wherever religion is located, it is hoped that it can provide guidance on values or moralsfor all activities of human life, whether social, cultural, economic or political. Not infrequently also religion becomes a determining factor in the adhesive process of social cultural interaction of the community as well as unifying thenation. Culture and religion are something different but can influence each other so that new cultures or mixing of cultures emerge. The opinion of Endang Saifudin Anshari who said in his writing that religion and culture do notinclude each other, in principle one is not part of the other and each consists of itself. Between them, of course, they are closely related like us, we see in everyday life and human life. As also seen in the close relationship between husband and wife who can give birth to a son but the husband is not part of the wife, and vice versa. Religion and culture are two different things but cannot be separated. The existence of a religion will be greatly influenced and affect thepractice of a religion in question. And conversely, a culture will be greatly influenced by the beliefs of the society in which culture develops. Therefore religion is not only an individual problem but religion is also a social affair whichultimately religious people are not only able to give birth to individual piety but also must be able to give birth to social piety.Key words: Interaction, Religion, Culture,

scholarly journals Deep Hash with Improved Dual Attention for Image Retrieval

Information ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 285
Author(s):  
Wenjing Yang ◽  
Liejun Wang ◽  
Shuli Cheng ◽  
Yongming Li ◽  
Anyu Du
Keyword(s):  
Image Retrieval ◽  
Contextual Information ◽  
Quantization Error ◽  
Feature Representation ◽  
Semantic Features ◽  
Average Value ◽  
Hash Code ◽  
Feature Information ◽  
Learning To Hash ◽  
Study Designs

Recently, deep learning to hash has extensively been applied to image retrieval, due to its low storage cost and fast query speed. However, there is a defect of insufficiency and imbalance when existing hashing methods utilize the convolutional neural network (CNN) to extract image semantic features and the extracted features do not include contextual information and lack relevance among features. Furthermore, the process of the relaxation hash code can lead to an inevitable quantization error. In order to solve these problems, this paper proposes deep hash with improved dual attention for image retrieval (DHIDA), which chiefly has the following contents: (1) this paper introduces the improved dual attention mechanism (IDA) based on the ResNet18 pre-trained module to extract the feature information of the image, which consists of the position attention module and the channel attention module; (2) when calculating the spatial attention matrix and channel attention matrix, the average value and maximum value of the column of the feature map matrix are integrated in order to promote the feature representation ability and fully leverage the features of each position; and (3) to reduce quantization error, this study designs a new piecewise function to directly guide the discrete binary code. Experiments on CIFAR-10, NUS-WIDE and ImageNet-100 show that the DHIDA algorithm achieves better performance.

Sign in / Sign up

Export Citation Format

Share Document