Discrete Hashing Research Articles

Supervised Contrastive Discrete Hashing for cross-modal retrieval

Cross-modal hashing aims at mapping data points from varied modalities to a shared Hamming space for providing swift and adaptive search services. The recent progress in contrastive learning has significantly enhanced the retrieval performance of cross-modal hashing, owing to its strong ability in powerful representations learning. However, most of them face two primary challenges: (1) they select negative samples for anchors randomly in each mini-batch, which may bring false negative samples that destroy the intrinsic semantic similarity in the learned hash codes; (2) the continuous relaxation strategy is commonly used to generate discrete hash codes, which results in quantization errors and consequently impairing the quality of hash codes. To alleviate these issues, we propose a deep supervised cross-modal hashing scheme, termed Supervised Contrastive Discrete Hashing (SCDH). Specifically, we extend the unsupervised contrastive method to the supervised setting to construct the positive and negative data points with class labels, avoiding the performance decreasing caused by false negative data. Besides, multiple positive and negative samples for each anchor can be chosen from the generated global dictionary bank by class labels, which can better capture the global data structure. Moreover, discrete hash codes can be generated directly, enhancing the feature representational capacity of hash codes. Comprehensive experiments conducted on two public datasets affirm the superior performance of the proposed SCDH over several other cutting-edge methods.

Graph Convolutional Network Discrete Hashing for Cross-Modal Retrieval.

With the rapid development of deep neural networks, cross-modal hashing has made great progress. However, the information of different types of data is asymmetrical, that is to say, if the resolution of an image is high enough, it can reproduce almost 100% of the real-world scenes. However, text usually carries personal emotion and it is not objective enough, so we generally think that the information of image will be much richer than text. Although most of the existing methods unify the semantic feature extraction and hash function learning modules for end-to-end learning, they ignore this issue and do not use information-rich modalities to support information-poor modalities, leading to suboptimal results, although they unify the semantic feature extraction and hash function learning modules for end-to-end learning. Furthermore, previous methods learn hash functions in a relaxed way that causes nontrivial quantization losses. To address these issues, we propose a new method called graph convolutional network (GCN) discrete hashing. This method uses a GCN to bridge the information gap between different types of data. The GCN can represent each label as word embedding, with the embedding regarded as a set of interdependent object classifiers. From these classifiers, we can obtain predicted labels to enhance feature representations across modalities. In addition, we use an efficient discrete optimization strategy to learn the discrete binary codes without relaxation. Extensive experiments conducted on three commonly used datasets demonstrate that our proposed method graph convolutional network-based discrete hashing (GCDH) outperforms the current state-of-the-art cross-modal hashing methods.

Two-Step Discrete Hashing for Cross-Modal Retrieval

Two-Step Discrete Hashing for Cross-Modal Retrieval

Jointly sparse fast hashing with orthogonal learning for large-scale image retrieval

Hash learning is a hot topic since it can save storage space and perform fast retrieval. One of the most representative hashing methods is Supervised Discrete Hashing (SDH). However, there exist several problems in SDH. First, the potential of sparse feature extraction has been overlooked in the SDH-based methods. Second, SDH is incapable of preventing large information loss between the binary codes and the features. Third, the discrete cyclic coordinate descent (DCC) method is time-consuming. To address the aforementioned issues, we propose a novel regression model for hash learning named Jointly Sparse Fast Hashing (JSFH). By designing an orthogonal transformation, we introduce the jointly sparse regression into hash learning. The proposed method successfully integrates the feature extraction and hash learning into a unified framework, the original data and the label information can be comprehensively utilized such that the binary code generated by our method can be more discriminative with less information loss. Furthermore, we adopt an iterative algorithm for optimization, the optimization problem has closed-form solutions for each variable such that the designed iterative algorithm is highly efficient compared to the classic supervised hashing methods. The experimental results on four large-scale datasets demonstrate its superior performance.

SCH: Symmetric Consistent Hashing for cross-modal retrieval

When handling large-scale multimodal data, hashing-based retrieval methods have gained significant attention due to their advantages in terms of low storage consumption and quick query speed. Despite the good performance of supervised hashing techniques, there are still certain limitations that need to be addressed. Firstly, they ignore valuable information such as reconstruction residuals when employing matrix factorization to learn the low-dimensional space. Secondly, most methods map heterogeneous data to the same feature space, which is unreasonable because different modalities possess distinct dimensions and distributions. Lastly, some methods relax constraints in order to optimize discrete hash codes, leading to considerable quantization errors. To solve the above problems, a novel two-step hashing-based technology called Symmetric Consistent Hashing (SCH) is proposed. Specifically, in the first step, two separate latent semantic spaces are learned by leveraging Principal Component Analysis to mitigate principal energy loss and Locality Preserving Projections to preserve local similarity. Then, the latent spaces of different modalities are aligned to facilitate the sharing of high-level semantic information by exploiting modality consistency. Next, hash codes are learned from distinct latent spaces, which are embedded in the second step for learning hash functions through Kernel Logistic Regression. To validate the effectiveness of SCH, extensive experiments on three publicly available benchmark datasets are accomplished. The results demonstrate the superiority of SCH over state-of-the-art hashing baselines, thus confirming the potency of the proposed approach.

One for more: Structured Multi-Modal Hashing for multiple multimedia retrieval tasks

Hashing has been widely studied in support of efficient multimedia retrieval due to its high computation and storage efficiency. However, existing multimedia hashing models are designed only for specific multimedia retrieval tasks, e.g., cross-modal retrieval and composite multi-modal retrieval. To simultaneously support multiple multimedia retrieval tasks, multiple different hashing models should be equipped in a multimedia retrieval system. This paper proposes a Structured Multi-Modal Hashing (SMMH) method, which can learn only a hash model for multiple multimedia retrieval tasks. Specifically, we generate structured hash codes by independently projecting the modality data into the Hamming space, where each part of hash codes preserves the specific characteristic of the specific modality data, and they are collaborated to represent the whole multi-modal data. To bridge the heterogeneous gap between multiple modalities, a fusion multi-modal space is constructed based on structured hash codes with label and pair-wise semantic supervision. Besides, we learn hash functions for composite multi-modal retrieval by projecting heterogeneous modalities into the collaborative multi-modal features. Finally, we develop a discrete hash optimization strategy to efficiently solve binary hash codes. Extensive experiments show that our model outperforms the strong baseline methods on multiple multimedia retrieval tasks. Source codes are available at https://github.com/ChaoqunZheng/SMMH.

Label embedding asymmetric discrete hashing for efficient cross-modal retrieval

Given the exponential growth of multimedia data, how to swiftly and accurately retrieve information has grown in popularity. Among retrieval techniques, supervised hashing stands out due to its low memory footprint and relatively precise accuracy. Prior theoretical studies often inserted high-order tags into binary code learning, treating them as independent entities. Nevertheless, such approaches frequently neglect the latent category correlations revealed by the label information. Additionally, in terms of optimization, some algorithms employ a bit-by-bit scheme, leading to time-consuming, while others adopt a relaxation-based strategy, producing quantization inaccuracy. To address these issues, we formulate a novel, two-step hashing strategy, termed Label Embedding Asymmetric Discrete Hashing (LEADH). In this study, we provide an asymmetric technique to protect the discrete binary code constraints. Compared with the symmetric model, this method significantly reduces time consumption. In particular, a label-binary mutual mapping architecture is specifically recommended. This model can fully explore and utilize multi-label semantic information to provide better discriminative learned binary codes. Furthermore, to minimize quantization errors, an efficient and effective discrete optimization module based on augmented Lagrangian multipliers is elaborately designed. Extensive experimentation and theoretical study support our model’s superiority. Compared to the sub-optimal method, our LEADH achieves an improvement of 2.6%, 1.8%, and 1.1% on Wiki, MIRFlickr, and NUS-WIDE, respectively.

Fast Asymmetric and Discrete Cross-Modal Hashing With Semantic Consistency

Hashing has attracted widespread attention in the field of supervised cross-modal retrieval due to its advantages in search and storage. However, there are still some issues to be addressed, e.g.: 1) how to effectively combine sample and label semantics to learn hash codes; 2) how to reduce high computational requirements brought by computing a pairwise similarity matrix; and 3) how to effectively solve discrete optimization problems. To cope with them, a fast asymmetric and discrete cross-modal hashing (FADCH) method is proposed in this article. First, matrix factorization is leveraged to collaboratively construct a common semantic subspace between different modalities. Second, semantic consistency is preserved by aligning the common semantic subspace with the semantic representation constructed from labels, which effectively exploits the semantic complementarity of labels and samples. Third, we embed labels into hash codes and keep the correlation between different modal samples by using a pairwise similarity matrix. Fourth, we use an asymmetric strategy with relaxation to associate hash codes with semantic representation, which not only avoids the difficulty of symmetric frame optimization but also embeds more semantic information into the Hamming space. In addition, a strongly orthogonal constraint is introduced to optimize the hash codes. Finally, an effective optimization algorithm is developed to directly generate discrete hash codes while reducing the complexity from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$O(n^{2})$ </tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$O(n)$ </tex-math></inline-formula> . The experimental results on three benchmark datasets illustrate the superiority of the FADCH method.

Robust Data-Aware Sensing Based on Half Quadratic Hashing for the Visual Internet of Things

In the Visual Internet of Things (VIoT) such as drones over flying ad-hoc networks (FANETs), terminal nodes need to preliminarily identify sensing data. Thus, data can be rapidly dispatched to dedicated edge nodes for further processing. Nonetheless, terminals may collect partially observed visual data, which cause biased labeling. In view of such, this study proposes half quadratic supervised discrete hashing (HQSDH) that can conquer the biased similarity estimation for partially observed images, especially when large continuous occlusion, missing values, or sample-specific outliers exist. The proposed method can automatically and adaptively adjust itself via HQ auxiliary variables to avoid oversensitivity to large errors caused by partially observed data. In this study, to solve HQ discrete optimization problems in HQSDH, HQ discrete cyclic coordinate descent (HQDCCD) is developed. Second, partially observed images may cause inconsistent binary codes and increase the Hamming distances. Thus, this study devises HQ balancing decorrelation constraints along with normalization regularization to accommodate the problems. Third, a systematic and generic solution that allows various HQ functions to jointly work in the same framework is modeled to provide versatility. Experiments on open image data sets were carried out for evaluation. The results showed that the proposed method provided more resilience against continuous occlusion, missing values, and sample-specific outliers than the baselines when dealing with partially observed images.

Hierarchical Semantic Structure Preserving Hashing for Cross-Modal Retrieval

Cross-modal hashing has become a vital technique in cross-modal retrieval due to its fast query speed and low storage cost in recent years. Generally, most of the priors supervised cross-modal hashing methods are flat methods which are designed for non-hierarchical labeled data. They treat different categories independently and ignore the inter-category correlations. In practical applications, many instances are labeled with hierarchical categories. The hierarchical label structure provides rich information among different categories. To rationally take use of category correlations, hierarchical cross-modal hashing is proposed. However, existing methods intend to preserve instance-pairwise or class-pairwise similarities, which cannot fully explore the semantic correlations among different categories and make the learned hash codes less discriminative. In this paper, we propose a deep cross-modal hashing method named hierarchical semantic structure preserving hashing (HSSPH), which directly exploits the label hierarchy information to learn discriminative hash codes. Specifically, HSSPH learns a set of class-wise hash codes for each layer. By augmenting class-wise codes with labels, it generates layer-wise prototype codes which reflect the semantic structure of each layer. In order to enhance the discriminative ability of hash codes, HSSPH supervises the hash codes learning with both labels and semantic structures to preserve the hierarchical semantics. Besides, efficient optimization algorithms are developed to directly learn the discrete hash codes for each instance and each class. Extensive experiments on two benchmark datasets show the superiority of HSSPH over several state-of-the-art methods.

Label Guided Discrete Hashing for Cross-Modal Retrieval

Due to their low storage capacity and fast retrieval speed, hashing techniques have received much attention in cross-modal retrieval. However, there are some issues that need to be further explored. First, some existing hashing methods use the labels to construct the semantic similarity matrix between pairwise data, ignoring the potential manifold structure between heterogeneous data. Second, some existing methods underestimate the importance of multi-label and the gaps between different class labels, making the learned hash codes less discriminative. Third, few of them embed both manifold and balanced structures within the same model, and the relaxation of discrete constraints will lead to an increasing quantization error. To mitigate these problems, this paper proposes a novel supervised hashing method, termed Label Guided Discrete Hashing (LGDH), which simultaneously preserves the comprehensive manifold structure and discriminative balanced codes that are both constructed by label information into Hamming space. We develop a local category distribution of the nearest neighbors, to excavate the underlying manifold structure of heterogeneous data. To maximize the gaps of different categories, a balanced matrix is constructed by labels to generate hash codes with balanced bits. For multi-label data, we also design a novel multi-label manifold and balanced structure matrix to adapt the real-world scenarios. An effective discrete optimization method is used to optimize our proposed objective function instead of the relaxation one. Extensive experiments on three benchmark datasets verify the effectiveness of LGDH. The comparison results demonstrat that LGDH achieves about 2% and 3% improved to different cross-modal tasks on average.

Semantic preserving asymmetric discrete hashing for cross-modal retrieval

Semantic preserving asymmetric discrete hashing for cross-modal retrieval

Two-Stage Supervised Discrete Hashing for Cross-Modal Retrieval

Recently, hashing-based multimodal learning systems have received increasing attention due to their query efficiency and parsimonious storage costs. However, impeded by the quantization loss caused by numerical optimization, the existing cross-media hashing approaches are unable to capture all the discriminative information present in the original multimodal data. Besides, most cross-modal methods belong to the one-step paradigm, which learn the binary codes and hash function simultaneously, increasing the complexity of optimization. To address these issues, we propose a novel two-stage approach, named the two-stage supervised discrete hashing (TSDH) method. In particular, in the first phase, TSDH generates a latent representation for each modality. These representations are then mapped to a common Hamming space to generate the binary codes. In addition, TSDH directly endows the hash codes with the semantic labels, enhancing the discriminatory power of the learned binary codes. A discrete hash optimization approach is developed to learn the binary codes without relaxation, avoiding the large quantization loss. The proposed hash function learning scheme reuses the semantic information contained by the embeddings, endowing the hash functions with enhanced discriminability. Extensive experiments on several databases demonstrate the effectiveness of the developed TSDH, outperforming several recent competitive cross-media algorithms.

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.

Asymmetric similarity-preserving discrete hashing for image retrieval

Asymmetric similarity-preserving discrete hashing for image retrieval

Binary multi-modal matrix factorization for fast item cold-start recommendation

Hashing technology can support large-scale recommendation very effectively due to its advantages of low storage cost and high recommendation efficiency. However, existing hashing-based recommendation methods often suffer from item cold-start problem. This is because they simply consider the user-item interaction and the single content information of the items, but the full interaction history is not always available and the single auxiliary information may be missing. To solve this issue, in this paper we propose a Binary Multi-modal Matrix Factorization (BMMF) method. First, we propose an efficient consensus multi-modal mapping to transform the heterogeneous multi-modal features to the unified factors by exploiting the complementarity of multiple modalities. Then, binary matrix factorization is simultaneously performed on the multi-modal features of the items and past user preferences to learn the compact binary codes of the users/items in a common Hamming space. In addition, inspired by the observation that similar instances often have similar binary codes within a short Hamming distance, we formulate a semantic structure regularization term to preserve the similarities of the items during the binary embedding process. Finally, we develop an effective Discrete Coordinate Descent (DCD) approach to tackle the formulated discrete hash optimization problem directly. Experiments on three publicly available real-world datasets demonstrate the superiority of the proposed method against the state-of-the-art methods. Our source codes and testing datasets are available athttps://github.com/pcm1217/BMMF.

Similarity Learning-Based Supervised Discrete Hash Signature Scheme for Authentication of Smart Home Scenario

Smart home technology is one of the significant emerging applications in the Internet of Things that facilitates the user to control home devices in the remote manner. In this context, investigating and addressing IoT security issues is highly challenging as the operating strategies of IoT application differs due to their heterogeneity characteristics. At this juncture, an authentication mechanism with anonymity and efficiency is necessary for facilitating secure communication in the smart home scenario, since the user or home communication channels are generally determined to be highly insecure. In this paper, Similarity Learning-Based Supervised Discrete Hash Signature Scheme (SLSDHS) is proposed for achieving secure user during the process of smart home authentication. It leverages the mutual association between possible semantic labels in order to learn maximized more stable hash codes, which is a predominant improvement over the traditional hash code approaches. The communication overhead and computation overhead of the proposed SLSDHS is identified to be considerably minimized compared to the benchmarked schemes used for comparison. The security analysis of the proposed SLSDHS scheme evaluated using informal analysis, formal analysis, and AVIPSA tool-based model checks confirmed its predominance with respect to automated testing of internet security protocols.

Similarity Learning-Based Supervised Discrete Hash Signature Scheme for authentication of smart home scenario

Similarity Learning-Based Supervised Discrete Hash Signature Scheme for authentication of smart home scenario

Latent semantic-enhanced discrete hashing for cross-modal retrieval

Latent semantic-enhanced discrete hashing for cross-modal retrieval

Online unsupervised cross-view discrete hashing for large-scale retrieval

Online unsupervised cross-view discrete hashing for large-scale retrieval