Similarity-preserving Hashing Research Articles

HARR: Learning Discriminative and High-Quality Hash Codes for Image Retrieval

This article studies deep unsupervised hashing, which has attracted increasing attention in large-scale image retrieval. The majority of recent approaches usually reconstruct semantic similarity information, which then guides the hash code learning. However, they still fail to achieve satisfactory performance in reality for two reasons. On the one hand, without accurate supervised information, these methods usually fail to produce independent and robust hash codes with semantics information well preserved, which may hinder effective image retrieval. On the other hand, due to discrete constraints, how to effectively optimize the hashing network in an end-to-end manner with small quantization errors remains a problem. To address these difficulties, we propose a novel unsupervised hashing method called HARR to learn discriminative and high-quality hash codes. To comprehensively explore semantic similarity structure, HARR adopts the Winner-Take-All hash to model the similarity structure. Then similarity-preserving hash codes are learned under the reliable guidance of the reconstructed similarity structure. Additionally, we improve the quality of hash codes by a bit correlation reduction module, which forces the cross-correlation matrix between a batch of hash codes under different augmentations to approach the identity matrix. In this way, the generated hash bits are expected to be invariant to disturbances with minimal redundancy, which can be further interpreted as an instantiation of the information bottleneck principle. Finally, for effective hashing network training, we minimize the cosine distances between real-value network outputs and their binary codes for small quantization errors. Extensive experiments demonstrate the effectiveness of our proposed HARR.

Multi-label contrastive hashing

Joint learning of image representation and hash encoding represents a dominant solution to approximate nearest neighbor search for large-scale image retrieval. Despite significant advances in deep learning to hash in multi-label setting, optimization of semantic similarity-preserving representations with minimal quantization error remains challenging. Motivated by the recent success of contrastive representation learning in various vision tasks, this article introduces a Multi-label Contrastive Hashing (MCH) method for large-scale multi-label image retrieval. We extend the image similarity modeling in existing supervised contrastive loss from binary to multi-level structure, by which multi-level semantic similarity between multi-label images can be well modeled and captured in learning to hash. Despite the appealing properties of contrastive learning, directly adapting it into multi-label hashing is non-trivial, as the quantization loss may restricts the optimization of the multi-level contrastive loss, degrading the multi-level similarity-preserving hashing. To this end, we design a curriculum strategy to adaptively adjust the weight of quantization loss by leveraging the historical quantization deviations during training, such that the multi-level semantic similarity can be well preserved with progressively reduced quantization deviation. We conduct extensive experiments on three benchmark datasets including MirFlickr25k, NUS-WIDE, and IAPRTC-12. The results indicate the effectiveness of our approach, outperforming several state-of-the-art solutions for hashing-based multi-label image retrieval.

FuzzyDedup: Secure Fuzzy Deduplication for Cloud Storage

Data deduplication is of critical importance to reduce the storage cost for clients and to relieve the unnecessary storage pressure for cloud servers. While various techniques have been proposed for secure deduplication of identical files/blocks, the effective and secure deduplication solutions on fuzzy similar data (image, video, and others) which occupy a large portion in the real world across wide applications, remain open. In this paper, we propose a novel deduplication system, named Fuzzy Deduplication (FuzzyDedup), to implement the secure deduplication of similar data (i.e., similar files, chunks, or blocks). In particular, we leverage the similarity-preserving hash, a fuzzy extractor based on error-correcting codes, and the encryption with customized design to construct a fuzzy-style deduplication encryption scheme (FuzzyMLE), achieving the ciphertext-based deduplication for similar data. Besides, to defend against data ownership cheating attack and duplicate-faking attack, a fuzzy-style proof of ownership scheme (FuzzyPoW) is designed for the cloud server to securely verify a client in possession of the similar data. To further enhance security and efficiency, we also propose both server-aided and random-tag FuzzyMLE to make FuzzyDedup robust against off-line brute-force attack and to support tag randomization, respectively. Then, we design Hamming distance reduction and tag cutting optimization algorithms to improve the tag query efficiency of FuzzyDedup. In the end, we formally prove the security of our solution and conduct experiments on real-world datasets for performance evaluation. Experimental results exhibit the efficiency of FuzzyDedup in terms of computation cost and communication overhead.

Deep collaborative graph hashing for discriminative image retrieval

The most striking success of deep hashing for large-scale image retrieval benefits from its powerful discriminative representation of deep learning and the attractive computational efficiency of compact hash code learning. Most existing deep semantic-preserving hashing regard the available semantic labels as the ground truth for classification or transform them into prevalent pairwise similarities. However, such strategies fail to capture the interactive correlations between the visual semantics embedded in images and the given category-level labels. Moreover, they utilize the fixed piecewise or pairwise semantics as the optimization objectives, which suffers from the limited flexibility on semantic representation and adaptive knowledge communication in hash code learning. In this paper, we propose a novel Deep Collaborative Graph Hashing (DCGH), which collectively considers multi-level semantic embeddings, latent common space construction, and intrinsic structure mining in discriminative hash codes learning, for large-scale image retrieval. To the best of our knowledge, this is the first collaborative graph hashing for image retrieval. Specifically, instead of using the conventional single-flow visual network architecture, we design a dual-stream feature encoding network to jointly explore the multi-level semantic information across visual and semantic features. Moreover, a well-established shared latent space is constructed based on space reconstruction to explore the concurrent information and bridge the semantic gap between visual and semantic space. Furthermore, a graph convolutional network is introduced to preserve the latent structural relations in the optimal pairwise similarity-preserving hash codes. The whole learning framework is optimized in an end-to-end fashion. Extensive experiments on different datasets demonstrate that our DCGH can achieve superb image retrieval performance against state-of-the-art supervised hashing methods. The source codes of the proposed DCGH are available at https://github.com/JalinWang/DCGH .

Adaptive Marginalized Semantic Hashing for Unpaired Cross-Modal Retrieval

In recent years, Cross-Modal Hashing (CMH) has attracted much attention due to its fast query speed and efficient storage. Previous studies have achieved promising results for Cross-Modal Retrieval (CMR) by discovering discriminative hash codes and modality-specific hash functions. Nonetheless, most existing CMR works are subjected to some restrictions: 1) It is assumed that data of different modalities are fully paired, which is impractical in real applications due to sample missing and false data alignment, and 2) binary regression targets including the label matrix and binary codes are too rigid to effectively learn semantic-preserving hash codes and hash functions. To address these problems, this paper proposes an Adaptive Marginalized Semantic Hashing (AMSH) method which not only enhances the discrimination of latent representations and hash codes by adaptive margins, but can also be used for both paired and unpaired CMR. As a two-step method, in the first step, AMSH generates semantic-aware modality-specific latent representations with adaptively marginalized labels, thereby enlarging the distances between different classes, and exploiting the labels to preserve the inter-modal and intra-modal semantic similarities into latent representations and hash codes. In the second step, adaptive margin matrices are embedded into the hash codes, and enlarge the gaps between positive and negative bits, which improves the discrimination and robustness of hash functions. On this basis, AMSH generates similarity-preserving hash codes and robust hash functions without the strict one-to-one data correspondence requirement. Experiments are conducted on several benchmark datasets to demonstrate the superiority and flexibility of AMSH over some state-of-the-art CMR methods. The source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/LKYLKYZ/AMSH</uri> .

Generative face inpainting hashing for occluded face retrieval.

COVID-19 has resulted in a significant impact on individual lives, bringing a unique challenge for face retrieval under occlusion. In this paper, an occluded face retrieval method which consists of generator, discriminator, and deep hashing retrieval network is proposed for face retrieval in a large-scale face image dataset under variety of occlusion situations. In the proposed method, occluded face images are firstly reconstructed using a face inpainting model, in which the adversarial loss, reconstruction loss and hash bits loss are combined for training. With the trained model, hash codes of real face images and corresponding reconstructed face images are aimed to be as similar as possible. Then, a deep hashing retrieval network is used to generate compact similarity-preserving hashing codes using reconstructed face images for a better retrieval performance. Experimental results show that the proposed method can successfully generate the reconstructed face images under occlusion. Meanwhile, the proposed deep hashing retrieval network achieves better retrieval performance for occluded face retrieval than existing state-of-the-art deep hashing retrieval methods.

FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal Retrieval

Cross-modal hashing, favored for its effectiveness and efficiency, has received wide attention to facilitating efficient retrieval across different modalities. Nevertheless, most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes while often involving time-consuming training procedure for handling the large-scale dataset. To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data, so as to minimize the quantization loss of mapping such data to hamming space and propose an efficient fast discriminative discrete hashing (FDDH) approach for large-scale cross-modal retrieval. More specifically, FDDH introduces an orthogonal basis to regress the targeted hash codes of training examples to their corresponding semantic labels and utilizes the ε -dragging technique to provide provable large semantic margins. Accordingly, the discriminative power of semantic information can be explicitly captured and maximized. Moreover, an orthogonal transformation scheme is further proposed to map the nonlinear embedding data into the semantic subspace, which can well guarantee the semantic consistency between the data feature and its semantic representation. Consequently, an efficient closed-form solution is derived for discriminative hash code learning, which is very computationally efficient. In addition, an effective and stable online learning strategy is presented for optimizing modality-specific projection functions, featuring adaptivity to different training sizes and streaming data. The proposed FDDH approach theoretically approximates the bi-Lipschitz continuity, runs sufficiently fast, and also significantly improves the retrieval performance over the state-of-the-art methods. The source code is released at https://github.com/starxliu/FDDH.

FKPIndexNet: An efficient learning framework for finger-knuckle-print database indexing to boost identification

This paper addresses the problem of identification in the Finger-knuckle-print (FKP) databases. Identification determines the identity of a query of the FKP sample. It involves finding the most similar sample in the database by comparing the query FKP with all the templates stored in the database. It is a computationally expensive process that demands huge time for large databases. A technique is required that can reduce the search space and limits the number of comparisons to boost the identification process. Such a technique is called indexing. It devises a fixed size small candidate list for a given FKP sample in constant time for searching. The paper proposes FKPIndexNet that learns similarity-preserving hash codes for generating an index table. It employs a specialized autoencoder network to learn feature embeddings such that they have high intra-class and low inter-class similarity. The proposed technique is examined on two publicly available FKP databases viz., PolyU-FKP and IITD-FKP. Experimental results show that the proposed method achieves 100% hit rate at a penetration rate of only 3.42% for PolyU-FKP database and 0.32% for IITD FKP database, respectively. This implies that for a query FKP sample, to get a true match with 100% confidence, only 3.42% and 0.32% of the PolyU-FKP and IITD FKP database needs to be compared, respectively. Results and analysis demonstrate the superiority of the proposed technique compared to other state-of-the-art approaches.

Probability Ordinal-Preserving Semantic Hashing for Large-Scale Image Retrieval

Semantic hashing enables computation and memory-efficient image retrieval through learning similarity-preserving binary representations. Most existing hashing methods mainly focus on preserving the piecewise class information or pairwise correlations of samples into the learned binary codes while failing to capture the mutual triplet-level ordinal structure in similarity preservation. In this article, we propose a novel Probability Ordinal-preserving Semantic Hashing (POSH) framework, which for the first time defines the ordinal-preserving hashing concept under a non-parametric Bayesian theory. Specifically, we derive the whole learning framework of the ordinal similarity-preserving hashing based on the maximum posteriori estimation, where the probabilistic ordinal similarity preservation, probabilistic quantization function, and probabilistic semantic-preserving function are jointly considered into one unified learning framework. In particular, the proposed triplet-ordering correlation preservation scheme can effectively improve the interpretation of the learned hash codes under an economical anchor-induced asymmetric graph learning model. Moreover, the sparsity-guided selective quantization function is designed to minimize the loss of space transformation, and the regressive semantic function is explored to promote the flexibility of the formulated semantics in hash code learning. The final joint learning objective is formulated to concurrently preserve the ordinal locality of original data and explore potentials of semantics for producing discriminative hash codes. Importantly, an efficient alternating optimization algorithm with the strictly proof convergence guarantee is developed to solve the resulting objective problem. Extensive experiments on several large-scale datasets validate the superiority of the proposed method against state-of-the-art hashing-based retrieval methods.

Similarity-preserving hash for content-based audio retrieval using unsupervised deep neural networks

Due to its efficiency in storage and search speed, binary hashing has become an attractive approach for a large audio database search. However, most existing hashing-based methods focus on data-independent scheme where random linear projections or some arithmetic expression are used to construct hash functions. Hence, the binary codes do not preserve the similarity and may degrade the search performance. In this paper, an unsupervised similarity-preserving hashing method for content-based audio retrieval is proposed. Different from data-independent hashing methods, we develop a deep network to learn compact binary codes from multiple hierarchical layers of nonlinear and linear transformations such that the similarity between samples is preserved. The independence and balance properties are included and optimized in the objective function to improve the codes. Experimental results on the Extended Ballroom dataset with 8 genres of 3,000 musical excerpts show that our proposed method significantly outperforms state-of-the-art data-independent method in both effectiveness and efficiency.

Reinforced Short-Length Hashing

Given that retrieval and storage have compelling efficiency, similarity-preserving hashing has been extensively employed to approximate nearest neighbor search in large-scale image retrieval. Hash codes that are extremely compact not only can further lower the storage cost, but also accelerate the retrieval speed. However, existing methods perform poorly in retrieval based on an extremely short-length hash code, which attributes to the weak ability of classification and poor distribution of hash bit. To tackle this issue, in this study, we propose a novel reinforced short-length hashing (RSLH). In particular, this proposed method applies the mutual reconstruction between the hash representation and semantic label to retain the semantic information. Furthermore, to enhance the accuracy of hash representation, a pairwise similarity matrix is designed to make a balance between accuracy and training expenditure on memory. Besides, we integrate a parameter boosting strategy to strengthen the precision with the consideration of bit balance and uncorrelation constraints. Extensive experiments on three large-scale image benchmarks demonstrate the superior performance of RSLH under various short-length hashing scenarios.

Deep Hashing with Attribute Guidance for Image Retrieval

Similarity-preserving hashing is an important method to solve approximate nearest neighbour search problem for image retrieval. Lots of works have been proposed for supervised hashing and image category labels are utilized as supervised information. However, current works ignore a fact that images can be described by a set of attributes. Intuitively, images of different categories with close visual features can be separated by their attribute features because attributes keep more detailed information. In this paper, we propose a novel supervised deep hashing method with image attribute guidance. Specifically, hash codes are learnt through image visual features and guided by image attributes by maintaining pair wise similarities between images as well as the corresponding attribute descriptions. Extensive experimental results on two benchmark datasets show that our proposed method achieves better performance compared with the state of the art hashing methods.

SensIR: Towards privacy-sensitive image retrieval in the cloud

With the advance in content-based image retrieval and the popularity of Data-as-a-Service, enterprises can outsource their image retrieval systems on cloud platforms to reduce heavy storage, computation, and communication burdens. However, this brings many privacy problems. Although several privacy-preserving image retrieval schemes have been proposed to protect users’ privacy, they have two major drawbacks: i) the outsourced images are fully encrypted and thus cannot be used for other applications, which makes them impractical; ii) they mainly focus on traditional image retrieval systems and do not use new techniques such as convolutional neural network (CNN) to improve the accuracy. To address the above problems, we propose a novel privacy-sensitive image retrieval scheme, named SensIR, to search for similar images from an outsourced image database. In particular, we propose a privacy region detection, PRDet, to prevent private regions of images from exposing. We also propose a partial CNN (PCNN) to reduce the impact of the encrypted pseudorandom pixels. Further, we use similarity-preserving hash encoding and propose a systematic methodology to improve the accuracy of PCNN-based image retrieval when the privacy regions are large. Extensive experiments are conducted to illustrate the efficiency of privacy protection and the superior of the proposed scheme.

Supervised Matrix Factorization Hashing With Quantitative Loss for Image-Text Search

Image-text hashing approaches have been widely applied in large-scale similarity search applications due to their efficiency in both search speed and storage efficiency. Most recent supervised hashing approaches learn a hash function by constructing a pairwise similarity matrix or directly learning the hash function and hash code (i.e.,1 or -1) procedure based on class labels. However, the former suffers from high training complexity and storage cost, and the latter ignores the semantic correlation of the original data, both of which prevent discriminative hash codes. To this end, we propose a novel discrete hashing algorithm called supervised matrix factorization hashing with quantitative loss (SMFH-QL). The proposed SMFH-QL first generates hash codes via the class label, avoiding the construction of a pairwise similarity; then, matrix factorization is used to design hash codes from original image-text data, thereby eliminating the impact of class labels and reducing the quantization error. Moreover, we introduce a quantitative loss function term to learn hash codes by incorporating class labels and the original data information, facilitating learning a similarity-preserving hash function in image-text search. Extensive experiments show that SMFH-QL outperforms several existing hashing methods on three representative datasets.

Improved Search in Hamming Space Using Deep Multi-Index Hashing

Similarity-preserving hashing is a widely used method for nearest neighbor search in large-scale image retrieval tasks. Considerable research has been conducted on deep-network-based hashing approaches to improve the performance. However, the binary codes generated from deep networks may be not uniformly distributed over the Hamming space, which will greatly increase the retrieval time. To this end, we propose a deep-network-based multi-index hashing (MIH) for retrieval efficiency. We first introduce the MIH mechanism into the proposed deep architecture, which divides the binary codes into multiple substrings. Each substring corresponds to one hash table. Then, we add the two balanced constraints to obtain more uniformly distributed binary codes: 1) balanced substrings, where the Hamming distances of each substring are equal for any two binary codes and 2) balanced hash buckets, where the sizes of each bucket are equal. Extensive evaluations on several benchmark image retrieval data sets show that the learned balanced binary codes bring dramatic speedups and achieve comparable performance over the existing baselines.

General Distributed Hash Learning on Image Descriptors for $k$-Nearest Neighbor Search

Hashing methods have attracted much attention due to their superior time and storage properties for image retrieval. To learn similarity-preserving hash function, most existing methods are designed for the centralized setting. However, the current data storage systems are distributed to increase scalability. Obviously, it is infeasible to aggregate all the data into a fusion center because of the prohibitively expensive communication and computation overhead. Motivated by this, some methods are proposed to achieve hashing for distributed data. However, these methods mostly focus on extending one specific hashing to a distributed model without considering the generality. In this letter, we propose a novel general distributed hash learning model, which can be viewed as an effective distributed model of most hashing methods. The proposed model can achieve up to 15.2% accuracy gains over state-of-the-art distributed hashing methods, while the communication cost is independent on the data size.

Minimizing Reconstruction Bias Hashing via Joint Projection Learning and Quantization.

Hashing, a widely-studied solution to the approximate nearest neighbor (ANN) search, aims to map data points in the high-dimensional Euclidean space to the low-dimensional Hamming space while preserving the similarity between original points. As directly learning binary codes can be NP-hard due to discrete constraints, a two-stage scheme, namely "projection and quantization", has already become a standard paradigm for learning similarity-preserving hash codes. However, most existing hashing methods typically separate these two stages and thus fail to investigate complementary effects of both stages. In this paper, we systematically study the relationship between "projection and quantization", and propose a novel minimal reconstruction bias hashing (MRH) method to learn compact binary codes, in which the projection learning and quantization optimizing are jointly performed. By introducing a lower bound analysis, we design an effective ternary search algorithm to solve the corresponding optimization problem. Furthermore, we conduct some insightful discussions on the proposed MRH approach, including the theoretical proof, and computational complexity. Distinct from previous works, MRH can adaptively adjust the projection dimensionality to balance the information loss between projection and quantization. The proposed framework not only provides a unique perspective to view traditional hashing methods but also evokes some other researches, e.g., guiding the design of the loss functions in deep networks. Extensive experiment results have shown that the proposed MRH significantly outperforms a variety of state-of-the-art methods over eight widely used benchmarks.

Index Structures for Fast Similarity Search for Real Vectors. II*

This survey article considers index structures for fast similarity search for objects represented by real-valued vectors. Structures for both exact and faster but approximate similarity search are considered. Index structures based on partitioning into regions (including hierarchical ones) and on proximity graphs are mainly presented. The acceleration of similarity search using the transformation of initial data is also discussed. The ideas of concrete algorithms including recently proposed ones are outlined. The approaches to the acceleration of similarity search in index structures of the considered types and also on the basis of similarity-preserving hashing are discussed and compared.

Structured deep hashing with convolutional neural networks for fast person re-identification

Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views. The critical challenge is how to construct a robust yet discriminative feature representation to capture the compounded variations in pedestrian appearance. To this end, deep learning methods have been proposed to extract hierarchical features against extreme variability of appearance. However, existing methods in this category generally neglect the efficiency in the matching stage whereas the searching speed of a re-identification system is crucial in real-world applications. In this paper, we present a novel deep hashing framework with Convolutional Neural Networks (CNNs) for fast person re-identification. Technically, we simultaneously learn both CNN features and hash functions to get robust yet discriminative features and similarity-preserving hash codes. Thereby, person re-identification can be resolved by efficiently computing and ranking the Hamming distances between images. A structured loss function defined over positive pairs and hard negatives is proposed to formulate a novel optimization problem so that fast convergence and more stable optimized solution can be attained. Extensive experiments on two benchmarks CUHK03 (Li et al., 2014) and Market-1501 (Zheng et al., 2015) show that the proposed deep architecture is efficacy over state-of-the-arts.

Index Structures for Fast Similarity Search for Binary Vectors

This article reviews index structures for fast similarity search for objects represented by binary vectors (with components equal to 0 or 1). Structures for both exact and approximate search by Hamming distance and other similarity measures are considered. Mainly, index structures are presented that are based on hash tables and similarity-preserving hashing and also on tree structures, neighborhood graphs, and distributed neural autoassociative memory. Ideas of well-known algorithms and algorithms proposed in recent years are stated.