Discrete Hashing Research Articles

Strongly Constrained Discrete Hashing.

Learning to hash is a fundamental technique widely used in large-scale image retrieval. Most existing methods for learning to hash address the involved discrete optimization problem by the continuous relaxation of the binary constraint, which usually lead to large quantization errors and consequently suboptimal binary codes. A few discrete hashing methods have emerged recently. However, they either completely ignore some useful constraints (specifically the balance and decorrelation of hash bits) or just turn those constraints into regularizers that would make the optimization easier but less accurate. In this paper, we propose a novel supervised hashing method named, Strongly Constrained Discrete Hashing (SCDH), which overcomes such limitations. It can learn the binary codes for all examples in the training set, and meanwhile obtain a hash function for unseen samples with the above mentioned constraints preserved. Although the model of SCDH is fairly sophisticated, we are able to find closed-form solutions to all of its optimization subproblems and thus design an efficient algorithm that converges quickly. In addition, we extend SCDH to a kernelized version SCDHK. Our experiments on three large benchmark datasets have demonstrated that not only can SCDH and SCDHK achieve substantially higher MAP scores than state-of-the-art baselines, but they run much faster than those that are also supervised as well.

Online Adaptive Supervised Hashing for Large-Scale Cross-Modal Retrieval

In recent years, with the continuous growth of multimedia data on the Internet, multimodal hashing has attracted increasing attention for its efficiency in large-scale cross-modal retrieval. Typically, most existing multimodal hashing methods are batch-based methods that cannot deal with the growing streaming data. Online multimodal hashing adopts online learning strategy to learn hash models incrementally, which can process large-scale streaming data. However, existing supervised online multimodal hashing methods still suffer from several limitations: (1) most methods cannot update hash codes of old data when hash model changes, which will hinder the retrieval accuracy. (2) the discrete optimizations of most methods for learning binary hash codes are less efficient or less effective. To address the above limitations, an efficient supervised online multimodal hashing method termed Online Adaptive Supervised Hashing (OASH) is proposed in this paper. OASH regresses class labels and training data to binary hash codes to learn discrete hash codes and hash functions with an efficient online optimization scheme. It learns hash functions incrementally with newly arriving data and updates hash codes with the latest hash model. By adaptively updating hash functions and hash codes with new data rather than accessing to old data, it gains much performance enhancement and computation savings. Extensive experiments on three benchmark data sets validate the superiority of OASH over state-of-the-art methods in both accuracy and efficiency.

Graph Regularized Deep Discrete Hashing for Multi-Label Image Retrieval

Multi-label hashing is a new research topic in image retrieval. As images are usually associated with multiple semantic labels, there is multi-level semantic similarity such as very similar, normally similar and dissimilar among multi-label images. In order to obtain the multi-level semantic similarity, this letter constructs a hypergraph in label space by creating a hyperedge for each semantic label and including all images annotated with a common label into one hyperedge. In this way, the number of common hyperedges shared by the vertices in hypergraph can be used to encode the high-order semantic relations among multiple images. Considering the useful similarity information hidden in the instance space, a kNN graph in instance space is further constructed. By learning from both the hypergraph and kNN graph with spectral learning strategy, a graph regularized deep discrete hashing is developed which updates graph regularized binary codes and deep neural network based robust features iteratively in a discrete optimization framework. The results in comparison with nine state-of-the-art hashing methods on two multi-label image datasets such as MIRFLICKR-25 K and NUS-WISE demonstrate its effectiveness.

Deep Collaborative Multi-view Hashing for Large-scale Image Search.

Hashing could significantly accelerate large-scale image search by transforming the high-dimensional features into binary Hamming space, where efficient similarity search can be achieved with very fast Hamming distance computation and extremely low storage cost. As an important branch of hashing methods, multi-view hashing takes advantages of multiple features from different views for binary hash learning. However, existing multi-view hashing methods are either based on shallow models which fail to fully capture the intrinsic correlations of heterogeneous views, or unsupervised deep models which suffer from insufficient semantics and cannot effectively exploit the complementarity of view features. In this paper, we propose a novel Deep Collaborative Multi-view Hashing (DCMVH) method to deeply fuse multi-view features and learn multi-view hash codes collaboratively under a deep architecture. DCMVH is a new deep multi-view hash learning framework. It mainly consists of 1) multiple view-specific networks to extract hidden representations of different views, and 2) a fusion network to learn multi-view fused hash code. DCMVH associates different layers with instance-wise and pair-wise semantic labels respectively. In this way, the discriminative capability of representation layers can be progressively enhanced and meanwhile the complementarity of different view features can be exploited effectively. Finally, we develop a fast discrete hash optimization method based on augmented Lagrangian multiplier to efficiently solve the binary hash codes. Experiments on public multi-view image search datasets demonstrate our approach achieves substantial performance improvement over state-of-the-art methods.

Joint learning based deep supervised hashing for large-scale image retrieval

Hashing has been widely used for large-scale image retrieval due to its high storage efficiency and fast calculation speed. Recent works have found that deep-supervised hashing methods are superior to non-deep-supervised hashing methods and unsupervised hashing methods in many applications. However, the previous deep-supervised hashing only uses the training set to learn the hash function, which results in that the discrete hash codes corresponding to the retrieval image set and the query image set are derived from the trained hash function. The retrieval image set did not participate in the training and learning of the network. Hence, it is difficult to acquire the real discrete hash code of the retrieval image. In addition, the traditional deep-supervised hashing methods failed to make full use of the supervised information. In this paper, we propose a novel deep supervised hashing method called Joint Learning Based Deep Supervised Hashing (JLDSH). It joints the image classification and hash function learning into the same end-to-end neural network framework. In the training process, we randomly select a subset from the retrieval image set to learn the hash function. The hash code of the entire retrieval image set is directly calculated by the trained hash code of the subset. Meanwhile, JLDSH sets a hyper-parameter on the supervised information to make the output of the network closer to the real discrete hash code. Furthermore, by adding a new loss function, an extended JLDSH-A model is proposed to make the image representation obtained by network training more discrete. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance on benchmark datasets.

Deep discrete hashing with pairwise correlation learning

Hashing technology plays an important role in large-scale visual search due to its low memory and fast retrieval speed. Most existing deep hashing approaches first leverage the continuous relaxation strategy to learn continuous approximate codes, and then transform them into discrete hash codes by separating quantization operations, which results in the suboptimal problem of hash codes and ultimately affects the performance of image retrieval. To solve this problem, we propose a novel deep discrete hashing approach with pairwise labels, namely Pairwise Correlation Discrete Hashing (PCDH), to leverage the pairwise correlation of deep features and semantic supervised information to directly guide discrete hashing codes learning. Firstly, we integrate discrete hash code learning and deep features learning in a unified network framework, which can utilize the semantic supervision to guide discrete hash codes learning. Secondly, we design a novel pairwise correlation constraint to perform pairwise correlation learning of deep features. Thirdly, we develop a novel pairwise construction module to mine good pairwise samples for discrete hash codes learning. Extensive experimental results show that the proposed PCDH approach achieves superior performance over other recent state-of-the-art hashing approaches.

Unsupervised Deep Cross-modal Hashing with Virtual Label Regression

Unsupervised cross-modal hashing learns hash codes without dependence on the semantic labels. It has the desirable advantage of well scalability and thus can effectively support large-scale cross-media retrieval. However, how to directly learn discriminative discrete hash codes under the unsupervised learning paradigm is still an open challenging problem. In this paper, we aim to attack this problem by proposing an Unsupervised Deep Cross-modal Hashing with Virtual Label Regression (UDCH-VLR) method. We propose a novel unified learning framework to jointly perform deep hash function training, virtual label learning and regression. Specifically, we learn unified hash codes via collaborative matrix factorization on the multi-modal deep representations to preserve the multi-modal shared semantics. Further, we incorporate the virtual label learning into the objective functions and simultaneously regress the learned virtual labels to the hash codes. Finally, instead of simply exploiting the existing shallow features and relaxing the binary constraints, we devise an alternative optimization strategy to directly update the deep hash functions and discrete binary codes. Under such circumstance, the discriminative capability of hash codes can be progressively enhanced with iterative learning. Extensive experiments on three publicly available cross-media retrieval datasets demonstrate that our approach outperforms state-of-the-art methods.

Semantic-enhanced discrete matrix factorization hashing for heterogeneous modal matching

The simultaneous hash representation of heterogeneous modalities has shown its excellent performance in the multi-modal learning community. However, the binary discrete constraint of hash brings a great challenge to the common hash representation of heterogeneous modal data. To resolve the issue, this paper proposes a novel discrete hash method, referred to as Semantic enhanced Discrete Matrix Factorization Hashing (SDMFH). SDMFH directly extracts the common discrete hash representation of all modalities from the reconstructed semantic intermodal similarity graph, which makes the hash codes more discriminative. Meanwhile, the semantic labels are regressed to the extracted discrete hash book, so as to further strengthen the discriminating ability of the learned discrete hash book. Moreover, a linear embedding from the kernel space of the original data to the Hamming space is explored to generate the common hash codes of each modality to ensure the consistency of the hash codes of heterogeneous modalities. More importantly, we develop an efficient discrete iterative algorithm based on Stiefel manifold that can directly learn the discrete hash book in a closed form, thus both avoiding quantization loss caused by discrete relaxation and reducing computational complexity. Experimental results on three benchmark data sets show that SDMFH performs better than several state-of-the-art methods for heterogeneous modal matching tasks.

Discriminative deep metric learning for asymmetric discrete hashing

Thanks to its storage and computation efficiency, hashing as a kind of nearest neighbor search method can facilitate massive data processing in recent vision and learning studies. Particularly, deep supervised hashing methods have significantly improved the retrieval performance compared with non-deep supervised hashing methods. However, most existing deep supervised hashing methods approximate the similarity between two images with the hamming distance between the outputs of the same hash function, i.e., the symmetric strategy. Consequently, it is typically time-consuming to train these symmetric hashing methods, and these methods can hardly take full advantage of the supervised information in the large-scale database. In this paper, we propose a novel discriminative deep metric learning approach for asymmetric discrete hashing (ADMH) approach for supervised hashing learning. ADMH integrates an asymmetric strategy with a deep metric learning method to learn the hash function for the query images and the discrete hash codes for database images directly. More specifically, we train a deep neural network to extract the features of the query images. Subsequently, we introduce a metric learning scheme for learning the discrete discriminative hash codes of the database images directly. Finally, the feature learning procedure for generating the hash codes of the query images and the discrete coding procedure for generating the hash codes of the database images are integrated into an end-to-end learning framework. Extensive experiments on various benchmark datasets show that the proposed asymmetric deep hashing method outperforms the existing hashing methods.

Efficient Supervised Discrete Multi-View Hashing for Large-Scale Multimedia Search

Hashing has recently received substantial attention in large-scale multimedia search for its extremely low-cost storage cost and high retrieval efficiency. However, most existing hashing techniques focus on learning hash codes for single-view or cross-view retrieval. It is still an unsolved problem that how to efficiently learn discriminative binary codes for multi-view data that is common in real world multimedia search. In this paper, we propose an efficient Supervised Discrete Multi-view Hashing (SDMH) to solve the problem. SDMH first properly detects the shared binary hash codes, with an integrated multi-view feature mapping and latent hash coding, by exploiting the complementarity of different view-specific features and removing the involved inter-view redundancy. To further enhance the discriminative capability of hash codes, SDMH directly represses the explicit semantic labels of data samples with their corresponding binary codes. Different from most existing multi-view hashing methods that adopt “relaxing+rounding” hash optimization strategy or the discrete optimization method based on discrete cyclic coordinate descent, an efficient augmented Lagrangian multiplier (ALM) based discrete hash optimization method is developed in this paper to optimize the hash codes within a single step. Experimental results on four benchmark datasets demonstrate the superior performance of the proposed approach over state-of-the-art hashing techniques, in terms of both learning efficiency and retrieval accuracy.

Scalable Deep Hashing for Large-scale Social Image Retrieval.

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 stateof- the-art shallow and deep hashing techniques.

WITHDRAWN: SCHEMA: A Discrete Cross-Modal Hashing by Preserving Multiple Similarities

Abstract Recently, cross-modal hashing has attracted much attention. To learn hash codes, many supervised cross-modal hashing methods construct a large-size semantic pairwise similarity matrix and reconstruct it by hash codes, which is time-consuming and neglects the similarity between high-level and low-level features. In addition, the binary constraints of hash codes make the optimization problem NP-hard. Most methods relax the binary constraints, leading to large quantization error. To address these issues, in this paper, we present a novel cross-modal hashing method, i.e., diScrete Cross-modal Hashing by prEserving Multiple similArities, SCHEMA for short. It embeds multiple types of similarity into the learning of binary codes, i.e., the high-level similarity and the low-level similarity. In the light of this, the binary codes may preserve more similarity information of the samples in the original space. In addition, to solve the optimization problem, it equivalently transforms the binary constraints into an intersection of two continuous spaces. Thereafter, the problem is solved with a proposed algorithm without relaxation, avoiding the large quantization error problem. Moreover, the computational complexity of its training is linear to the size of a training set, making it scalable to large-scale datasets. Extensive experimental results on four benchmark datasets demonstrate SCHEMA consistently outperforms some state-of-the-art hashing methods by large gaps.

Discrete Deep Hashing With Ranking Optimization for Image Retrieval.

For large-scale image retrieval task, a hashing technique has attracted extensive attention due to its efficient computing and applying. By using the hashing technique in image retrieval, it is crucial to generate discrete hash codes and preserve the neighborhood ranking information simultaneously. However, both related steps are treated independently in most of the existing deep hashing methods, which lead to the loss of key category-level information in the discretization process and the decrease in discriminative ranking relationship. In order to generate discrete hash codes with notable discriminative information, we integrate the discretization process and the ranking process into one architecture. Motivated by this idea, a novel ranking optimization discrete hashing (RODH) method is proposed, which directly generates discrete hash codes (e.g., +1/-1) from raw images by balancing the effective category-level information of discretization and the discrimination of ranking information. The proposed method integrates convolutional neural network, discrete hash function learning, and ranking function optimizing into a unified framework. Meanwhile, a novel loss function based on label information and mean average precision (MAP) is proposed to preserve the label consistency and optimize the ranking information of hash codes simultaneously. Experimental results on four benchmark data sets demonstrate that RODH can achieve superior performance over the state-of-the-art hashing methods.

Locality-constrained discrete graph hashing

Hashing techniques have been widely used for large-scale image retrieval because of its low storage cost and high query speed. Hashing maps similar data onto binary codes with a smaller Hamming distance, which is essentially a discrete optimization problem with constraints. Recently, several discrete hashing methods have begun focusing on minimizing the discrete loss between hash codes and continuous values but ignoring the hidden structure among data points in the original space. Following these efforts, we propose a locality-constrained discrete graph hashing (LCH) method that attempts to minimize the similarity distance of the data points in the original space by softening the hash codes’ hard constraint into two spaces: the discrete constraint space and the bit-balanced, bit-uncorrected constraint space. Furthermore, both spaces maintain the neighbourhood structure of the data points in the original space, and the best hash codes are found by minimizing the similarity distance between the two spaces. This is consistent with the nature of hashing for similarity preservation. Experiments on four real image datasets show that LCH obtains superior search accuracy over state-of-the-art hashing methods.

SADIH: Semantic-Aware DIscrete Hashing

Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in largescale multimedia retrieval applications. Particularly, supervised hashing has recently received considerable research attention by leveraging the label information to preserve the pairwise similarities of data points in the Hamming space. However, there still remain two crucial bottlenecks: 1) the learning process of the full pairwise similarity preservation is computationally unaffordable and unscalable to deal with big data; 2) the available category information of data are not well-explored to learn discriminative hash functions. To overcome these challenges, we propose a unified Semantic-Aware DIscrete Hashing (SADIH) framework, which aims to directly embed the transformed semantic information into the asymmetric similarity approximation and discriminative hashing function learning. Specifically, a semantic-aware latent embedding is introduced to asymmetrically preserve the full pairwise similarities while skillfully handle the cumbersome n×n pairwise similarity matrix. Meanwhile, a semantic-aware autoencoder is developed to jointly preserve the data structures in the discriminative latent semantic space and perform data reconstruction. Moreover, an efficient alternating optimization algorithm is proposed to solve the resulting discrete optimization problem. Extensive experimental results on multiple large-scale datasets demonstrate that our SADIH can clearly outperform the state-of-the-art baselines with the additional benefit of lower computational costs.

Towards Optimal Discrete Online Hashing with Balanced Similarity

When facing large-scale image datasets, online hashing serves as a promising solution for online retrieval and prediction tasks. It encodes the online streaming data into compact binary codes, and simultaneously updates the hash functions to renew codes of the existing dataset. To this end, the existing methods update hash functions solely based on the new data batch, without investigating the correlation between such new data and the existing dataset. In addition, existing works update the hash functions using a relaxation process in its corresponding approximated continuous space. And it remains as an open problem to directly apply discrete optimizations in online hashing. In this paper, we propose a novel supervised online hashing method, termed Balanced Similarity for Online Discrete Hashing (BSODH), to solve the above problems in a unified framework. BSODH employs a well-designed hashing algorithm to preserve the similarity between the streaming data and the existing dataset via an asymmetric graph regularization. We further identify the “data-imbalance” problem brought by the constructed asymmetric graph, which restricts the application of discrete optimization in our problem. Therefore, a novel balanced similarity is further proposed, which uses two equilibrium factors to balance the similar and dissimilar weights and eventually enables the usage of discrete optimizations. Extensive experiments conducted on three widely-used benchmarks demonstrate the advantages of the proposed method over the stateof-the-art methods.

Supervised learning based discrete hashing for image retrieval

Learning based hashing technologies have been widely adopted in multimedia retrieval as they could afford efficient storage and extract semantic information for high-dimensional data. However, the major difficulty of learning based hashing is the discrete constraint imposed on the required hashing codes, which makes the optimization generally to be NP-hard. In this paper, a novel supervised learning based discrete hashing (SLDH) approach is proposed to learn compact binary codes under the deep learning framework for image retrieval. We adopt multilayer network to convert the original features into binary codes, while it should exploit the semantic relevance of manual labels and keep the semantic similarity. For this purpose, we propose the objective function to obtain the binary codes including: 1) making full use of manual labels to get implicit semantic information; 2) using the weighted similarity matrix to keep the semantic similarity; 3) relaxing the discrete constraint to a normalized optimization problem; 4) adding the orthogonality constraint on binary codes to reduce the information redundancy. The objective function is optimized with the alternating direction method and modified alternating direction of multipliers(ADMM) algorithm with efficient iteration. Experiments are conducted on three databases and the results demonstrate the superiority to several state-of-the-art hashing based image retrieval methods.

Unsupervised cross-modal retrieval via Multi-modal graph regularized Smooth Matrix Factorization Hashing

The existing cross-modal hashing methods often encounter quantization loss which is caused by relaxing discrete hash codes in the process of cross-modal retrieval. To counter this problem, a Multi-modal graph regularized Smooth matrix Factorization Hashing (MSFH) approach is represented for unsupervised cross-modal retrieval. In the proposal framework, a smooth matrix generated by a control parameter is introduced into the matrix decomposition model, which can guarantee the sparsity of the dictionaries learned and the extracted common features at the same time, thus reducing the quantization loss in the hashing process. Furthermore, to preserve the topology of the original data, a multi-modal graph regularization term is drawn into the model, which consists of two parts. One is the intra-modal similarity graph which is used to preserve the geometric structure of each modality. The other is the inter-modal similarity graph reconstructed by the symmetric nonnegative matrix factorization, which is employed to soften the structure difference between modalities. The goal of MSFH is to learn unified hash-codes for multi-modal data in a shared latent semantic space in which the similarity of different modalities can be estimated effectively. And the corresponding experimental results on three benchmark data sets demonstrate the superiority of the proposed approach over several state-of-the-art cross-modality hashing approaches.

Discrete Hashing with Multiple Supervision.

Supervised hashing methods have achieved more promising results than unsupervised ones by leveraging label information to generate compact and accurate hash codes. Most of the prior supervised hashing methods construct an n × n instance-pairwise similarity matrix, where n is the number of training samples. Nevertheless, this kind of similarity matrix results in high memory space cost and makes the optimization time-consuming, which make it unacceptable in many real applications. In addition, most of the methods relax the discrete constraints to solve the optimization problem, which may cause large quantization errors and finally leads to poor performance. To address these limitations, in this paper, we present a novel hashing method, named Discrete Hashing with Multiple Supervision (MSDH). MSDH supervises the hash code learning with both class-wise and instance-class similarity matrices, whose space cost is much less than the instance-pairwise similarity matrix. With multiple supervision information, better hash codes can be learnt. Besides, an iterative optimization algorithm is proposed to directly learn the discrete hash codes instead of relaxing the binary constraints. Experimental results on several widely-used benchmark datasets demonstrate that MSDH outperforms some state-of-the-art methods.

Bilinear Supervised Hashing Based on 2D Image Features

Hashing has been recognized as an efficient representation learning method to effectively handle big data due to its low computational complexity and memory cost. Most of the existing hashing methods focus on learning the low-dimensional vectorized binary features based on the high-dimensional raw vectorized features. However, the studies on how to obtain preferable binary codes from the original 2D image features for retrieval is very limited. This paper proposes a bilinear supervised discrete hashing (BSDH) method based on 2D image features which utilizes bilinear projections to binarize the image matrix features such that the intrinsic characteristics in the 2D image space are preserved in the learned binary codes. Meanwhile, the bilinear projection approximation and vectorization binary codes regression are seamlessly integrated together to formulate the final robust learning framework. Furthermore, a discrete optimization strategy is developed to alternatively update each variable for obtaining the high-quality binary codes. In addition, two 2D image features, traditional SURF-based FVLAD feature, and CNN-based AlexConv5 feature are designed for further improving the performance of the proposed BSDH method. The results of extensive experiments conducted on four benchmark datasets show that the proposed BSDH method almost outperforms all competing hashing methods with different input features by different evaluation protocols.