Hash Code Learning Research Articles

Efficient Semi-Supervised Multimodal Hashing With Importance Differentiation Regression.

Multi-modal hashing learns compact binary hash codes by collaborating heterogeneous multi-modal features at both the model training and online retrieval stages to support large-scale multimedia retrieval. Previous multi-modal hashing methods mainly focus on supervised and unsupervised hashing. The performance of supervised hashing largely relies on the number of labeled data, which is practically expensive to obtain. Unsupervised hashing methods cannot effectively capture the semantic correlations of multi-modal data without any labels for supervision. In this paper, we propose an Efficient Semi-supervised Multi-modal Hashing with Importance Differentiation Regression (ESMH-IDR) model, which can alleviate the existing problems by learning from both labeled and unlabeled data. Specifically, in this paper, we develop an efficient semi-supervised multi-modal hash code learning module. It learns the hash codes for labeled data in an efficient asymmetric way, and simultaneously performs nonlinear regression using the same projection matrix as the labeled samples to preserve the intrinsic data structure of unlabeled data. Besides, different from existing methods, we propose an importance differentiation regression strategy to learn hash functions by specially considering the different importance of hash codes learned from the labeled and unlabeled samples. Finally, we develop an efficient discrete optimization method guaranteed with convergence to iteratively solve the hash optimization problem. Experiments on several public multimedia retrieval datasets demonstrate the superiority of our proposed method on both retrieval effectiveness and efficiency. Our source codes and testing datasets can be obtained at https://github.com/ChaoqunZheng/ESMH.

Improve Deep Unsupervised Hashing via Structural and Intrinsic Similarity Learning

Hashing has attracted increasing attention in image retrieval recently due to its storage and computational efficiency. Although several deep unsupervised hashing methods have been proposed lately, their effectiveness is far from satisfactory in practice owing to two drawbacks. On the one hand, they mostly construct binary similarity matrices which could neglect the confidence differences among multiple similarity signals. On the other hand, they ignore the desired properties of hash codes (i.e., independence and robustness). In this paper, we propose an effective unsupervised hashing method called <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</b> ashing via <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> tructural and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</b> ntrinsic si <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> ilarity learning (HashSIM) to tackle these issues in an end-to-end manner. Specifically, HashSIM utilizes both highly and normally confident image pairs to jointly build a continuous similarity matrix, which guides hash code learning via structural similarity learning. Moreover, inspired by contrastive learning, we impose an intrinsic similarity learning objective, which can maximally satisfy the independence and robustness properties of hash bits. Extensive experiments on three popular benchmark datasets demonstrate that our HashSIM outperforms a broad range of state-of-the-art baselines.

Joint Specifics and Consistency Hash Learning for Large-Scale Cross-Modal Retrieval.

With the dramatic increase in the amount of multimedia data, cross-modal similarity retrieval has become one of the most popular yet challenging problems. Hashing offers a promising solution for large-scale cross-modal data searching by embedding the high-dimensional data into the low-dimensional similarity preserving Hamming space. However, most existing cross-modal hashing usually seeks a semantic representation shared by multiple modalities, which cannot fully preserve and fuse the discriminative modal-specific features and heterogeneous similarity for cross-modal similarity searching. In this paper, we propose a joint specifics and consistency hash learning method for cross-modal retrieval. Specifically, we introduce an asymmetric learning framework to fully exploit the label information for discriminative hash code learning, where 1) each individual modality can be better converted into a meaningful subspace with specific information, 2) multiple subspaces are semantically connected to capture consistent information, and 3) the integration complexity of different subspaces is overcome so that the learned collaborative binary codes can merge the specifics with consistency. Then, we introduce an alternatively iterative optimization to tackle the specifics and consistency hashing learning problem, making it scalable for large-scale cross-modal retrieval. Extensive experiments on five widely used benchmark databases clearly demonstrate the effectiveness and efficiency of our proposed method on both one-cross-one and one-cross-two retrieval tasks.

Asymmetric Hash Code Learning for Remote Sensing Image Retrieval

Remote sensing image retrieval (RSIR), aiming at searching for a set of similar items to a given query image, is a very important task in remote sensing applications. Deep hashing learning as the current mainstream method has achieved satisfactory retrieval performance. On one hand, various deep neural networks are used to extract semantic features of remote sensing images. On the other hand, the hashing techniques are subsequently adopted to map the high-dimensional deep features to the low-dimensional binary codes. This kind of method attempts to learn one hash function for both the query and database samples in a symmetric way. However, with the number of database samples increasing, it is typically time-consuming to generate the hash codes of large-scale database images. In this article, we propose a novel deep hashing method, named asymmetric hash code learning (AHCL), for RSIR. The proposed AHCL generates the hash codes of query and database images in an asymmetric way. In more detail, the hash codes of query images are obtained by binarizing the output of the network, while the hash codes of database images are directly learned by solving the designed objective function. In addition, we combine the semantic information of each image and the similarity information of pairs of images as supervised information to train a deep hashing network, which improves the representation ability of deep features and hash codes. The experimental results on three public datasets demonstrate that the proposed method outperforms symmetric methods in terms of retrieval accuracy and efficiency. 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/weiweisong415/Demo_AHCL_for_TGRS2022</uri> .

Deep Discrete Cross-Modal Hashing with Multiple Supervision

Deep hashing has been widely used for large-scale cross-modal retrieval benefited from the low storage cost and fast search speed. However, most existing deep supervised methods only preserve the instance-pairwise relationship supervised by the semantic similarity matrix, which always inufficient heterogeneous correlation. Thus, we propose the Deep Discrete Cross-Modal Hashing with Multiple Supervision (DDCHms) to further enhance the semantic consistency of heterogeneous modalities. It improves the performance of semantic information retrieval with the joint supervision of instance-pairwise, instance-labeled and class-wise similarities. Specifically, we firstly utilize the instance-pairwise similarity matrix to supervise the learning process of heterogeneous networks and it keeps the pairwise correlation from the perspective of instance-instance. Specially, we design a semantic network to fully exploit the semantic information implicated in labels, which is also used to supervise multi-modal networks on instance-label level. Furthermore, we propose the class-wise hash codes to cooperate with the intrinsic label matrix as the prototypes, and it guides the hash learning and further ensures the precision and compactness of the learned hash codes. In addition, we design different discrete optimization strategies to optimize the class-wise hash codes and unified hash codes, respectively. That avoids the optimization errors and ensures the high-quality of learned hash codes. Experiments on three popular datasets indicate that our method outperforms other state-of-the-art methods in terms of cross-modal retrieval.

MOON: Multi-hash codes joint learning for cross-media retrieval

In recent years, cross-media hashing technique has attracted increasing attention for its high computation efficiency and low storage cost. However, the existing approaches still have some limitations, which need to be explored. 1) A fixed hash length (e.g., 16bits or 32bits) is predefined before learning the binary codes. Therefore, these models need to be retrained when the hash length changes, that consumes additional computation power, reducing the scalability in practical applications. 2) Existing cross-modal approaches only explore the information in the original multimedia data to perform the hash learning, without exploiting the semantic information contained in the learned hash codes. To this end, we develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval. Specifically, the developed MOON synchronously learns the hash codes with multiple lengths in a unified framework. Besides, to enhance the underlying discrimination, we combine the clues from the multimodal data, semantic labels and learned hash codes for hash learning. As far as we know, the proposed MOON is the first work to simultaneously learn different length hash codes without retraining in cross-media retrieval. Experiments on several databases show that our MOON can achieve promising performance, outperforming some recent competitive shallow and deep methods.

Discrete Semantics-Guided Asymmetric Hashing for Large-Scale Multimedia Retrieval

Cross-modal hashing technology is a key technology for real-time retrieval of large-scale multimedia data in real-world applications. Although the existing cross-modal hashing methods have achieved impressive accomplishment, there are still some limitations: (1) some cross-modal hashing methods do not make full consider the rich semantic information and noise information in labels, resulting in a large semantic gap, and (2) some cross-modal hashing methods adopt the relaxation-based or discrete cyclic coordinate descent algorithm to solve the discrete constraint problem, resulting in a large quantization error or time consumption. Therefore, in order to solve these limitations, in this paper, we propose a novel method, named Discrete Semantics-Guided Asymmetric Hashing (DSAH). Specifically, our proposed DSAH leverages both label information and similarity matrix to enhance the semantic information of the learned hash codes, and the ℓ2,1 norm is used to increase the sparsity of matrix to solve the problem of the inevitable noise and subjective factors in labels. Meanwhile, an asymmetric hash learning scheme is proposed to efficiently perform hash learning. In addition, a discrete optimization algorithm is proposed to fast solve the hash code directly and discretely. During the optimization process, the hash code learning and the hash function learning interact, i.e., the learned hash codes can guide the learning process of the hash function and the hash function can also guide the hash code generation simultaneously. Extensive experiments performed on two benchmark datasets highlight the superiority of DSAH over several state-of-the-art methods.

Noise-robust Deep Cross-Modal Hashing

Cross-modal hashing has been intensively studied to efficiently retrieve multi-modal data across modalities. Supervised cross-modal hashing methods leverage the labels of training data to improve the retrieval performance. However, most of these methods still assume that the semantic labels of training data are ideally complete and noise-free. This assumption is too optimistic for real multi-modal data, whose label annotations are, in essence, error-prone. To achieve effective cross-modal hashing on multi-modal data with noisy labels, we introduce an end-to-end solution called Noise-robust Deep Cross-modal Hashing (NrDCMH). NrDCMH contains two main components: a noise instance detection module and a hash code learning module. In the noise detection module, NrDCMH firstly detects noisy training instance pairs based on the margin between the label similarity and feature similarity, and specifies weights to pairs using the margin. In the hash learning module, NrDCMH incorporates the weights into a likelihood loss function to reduce the impact of instances with noisy labels and to learn compatible deep features by applying different neural networks on multi-modality data in a unified end-to-end framework. Experimental results on multi-modal benchmark datasets demonstrate that NrDCMH performs significantly better than competitive methods with noisy label annotations. NrDCMH also achieves competitive results in ‘noise-free’ scenarios.

Discrete online cross-modal hashing

With the prevalence of multimedia content on the Web which usually continuously comes in a stream fashion, online cross-modal hashing methods have attracted extensive interest in recent years. However, most online hashing methods adopt a relaxation strategy or real-valued auxiliary variable strategy to avoid complex optimization of hash codes, leading to large quantization errors. In this paper, based on Discrete Latent Factor model-based cross-modal Hashing (DLFH), we propose a novel cross-modal online hashing method, i.e., Discrete Online Cross-modal Hashing (DOCH). To generate uniform high-quality hash codes of different modal, DOCH not only directly exploits the similarity between newly coming data and old existing data in the Hamming space, but also utilizes the fine-grained semantic information by label embedding. Moreover, DOCH can discretely learn hash codes by an efficient optimization algorithm. Extensive experiments conducted on two real-world datasets demonstrate the superiority of DOCH.

Deep Hashing Using Proxy Loss on Remote Sensing Image Retrieval

With the improvement of various space-satellite shooting methods, the sources, scenes, and quantities of remote sensing data are also increasing. An effective and fast remote sensing image retrieval method is necessary, and many researchers have conducted a lot of work in this direction. Nevertheless, a fast retrieval method called hashing retrieval is proposed to improve retrieval speed, while maintaining retrieval accuracy and greatly reducing memory space consumption. At the same time, proxy-based metric learning losses can reduce convergence time. Naturally, we present a proxy-based hash retrieval method, called DHPL (Deep Hashing using Proxy Loss), which combines hash code learning with proxy-based metric learning in a convolutional neural network. Specifically, we designed a novel proxy metric learning network, and we used one hash loss function to reduce the quantified losses. For the University of California Merced (UCMD) dataset, DHPL resulted in a mean average precision (mAP) of up to 98.53% on 16 hash bits, 98.83% on 32 hash bits, 99.01% on 48 hash bits, and 99.21% on 64 hash bits. For the aerial image dataset (AID), DHPL achieved an mAP of up to 93.53% on 16 hash bits, 97.36% on 32 hash bits, 98.28% on 48 hash bits, and 98.54% on 64 bits. Our experimental results on UCMD and AID datasets illustrate that DHPL could generate great results compared with other state-of-the-art hash approaches.

Label Consistent Flexible Matrix Factorization Hashing for Efficient Cross-modal Retrieval

Hashing methods have sparked a great revolution on large-scale cross-media search due to its effectiveness and efficiency. Most existing approaches learn unified hash representation in a common Hamming space to represent all multimodal data. However, the unified hash codes may not characterize the cross-modal data discriminatively, because the data may vary greatly due to its different dimensionalities, physical properties, and statistical information. In addition, most existing supervised cross-modal algorithms preserve the similarity relationship by constructing an n × n pairwise similarity matrix, which requires a large amount of calculation and loses the category information. To mitigate these issues, a novel cross-media hashing approach is proposed in this article, dubbed label flexible matrix factorization hashing (LFMH). Specifically, LFMH jointly learns the modality-specific latent subspace with similar semantic by the flexible matrix factorization. In addition, LFMH guides the hash learning by utilizing the semantic labels directly instead of the large n × n pairwise similarity matrix. LFMH transforms the heterogeneous data into modality-specific latent semantic representation. Therefore, we can obtain the hash codes by quantifying the representations, and the learned hash codes are consistent with the supervised labels of multimodal data. Then, we can obtain the similar binary codes of the corresponding modality, and the binary codes can characterize such samples flexibly. Accordingly, the derived hash codes have more discriminative power for single-modal and cross-modal retrieval tasks. Extensive experiments on eight different databases demonstrate that our model outperforms some competitive approaches.

Combating Ambiguity for Hash-Code Learning in Medical Instance Retrieval.

When encountering a dubious diagnostic case, medical instance retrieval can help radiologists make evidence-based diagnoses by finding images containing instances similar to a query case from a large image database. The similarity between the query case and retrieved similar cases is determined by visual features extracted from pathologically abnormal regions. However, the manifestation of these regions often lacks specificity, i.e., different diseases can have the same manifestation, and different manifestations may occur at different stages of the same disease. To combat the manifestation ambiguity in medical instance retrieval, we propose a novel deep framework called Y-Net, encoding images into compact hash-codes generated from convolutional features by feature aggregation. Y-Net can learn highly discriminative convolutional features by unifying the pixel-wise segmentation loss and classification loss. The segmentation loss allows exploring subtle spatial differences for good spatial-discriminability while the classification loss utilizes class-aware semantic information for good semantic-separability. As a result, Y-Net can enhance the visual features in pathologically abnormal regions and suppress the disturbing of the background during model training, which could effectively embed discriminative features into the hash-codes in the retrieval stage. Extensive experiments on two medical image datasets demonstrate that Y-Net can alleviate the ambiguity of pathologically abnormal regions and its retrieval performance outperforms the state-of-the-art method by an average of 9.27% on the returned list of 10.

Triplet-object loss for large scale deep image retrieval

Deep hashing has been widely applied in large scale image retrieval due to its high computation efficiency and retrieval performance. Recently, training deep hashing networks with a triplet ranking loss become a common framework. However, most of the triplet ranking loss based deep hashing methods cannot obtain satisfactory retrieval performance due to their ignoring the relative similarities among the objects. In this paper, we propose a method to learn the discriminative object features and utilize these features to compute the adaptive margins of the proposed loss for learning powerful hash codes. Experimental results show that our learned hash codes can yield state-of-the-art retrieval performance on three challenging datasets

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.

Non-Intrusive Load Monitoring Based on Deep Pairwise-Supervised Hashing to Detect Unidentified Appliances

Non-intrusive load monitoring (NILM) is a fast developing technique for appliances operation recognition in power system monitoring. At present, most NILM algorithms rely on the assumption that all fluctuations in the data stream are triggered by identified appliances. Therefore, NILM of identifying unidentified appliances is still an open challenge. To pursue a scalable solution to energy monitoring for contemporary unidentified appliances, we propose a voltage-current (V-I) trajectory enabled deep pairwise-supervised hashing (DPSH) method for NILM. DPSH performs simultaneous feature learning and hash-code learning with deep neural networks, which shows higher identification accuracy than a benchmark method. DPSH can generate different hash codes to distinguish identified appliances. For unidentified appliances, it generates completely new codes that are different from codes of multiple identified appliances to distinguish them. Experiments on public datasets show that our method can get better F1-score than the benchmark method to achieve state-of-the-art performance in the identification of unidentified appliances, and this method maintains high sustainability to identify other unidentified appliances through retraining. DPSH can be resilient against appliance changes in the house.

An Efficient Image Search for Content Based Image Retrieval using Semantic-Assisted Visual Hashing

The CBIR system can be used to recover medical images associated with different diseases. The purpose of medicine information system is about providing the right information, at the right time, in the right place, to the right person. This improves the quality and efficiency of the patient care process. In clinical decision manufacturing process, it is important to find other images for a given query. . This is done using the content-based image recovery technique. Data mining is the technique of sorting through massive figured devices in get awareness about the human habits and place up human relationships to resolve problems via figure evaluation. Data gold mining apparatus gives business to anticipate the future qualities. Quality content material-based search offers a large volume of picture selections totally, while both effectiveness and performance are essential problems. An advanced indexing form is essential to scale the large statistics, facilitate the correct assessment.. This is a new technology that supports scalable content-based image retrieval (CBIR) hashing. Recently, CBIR has been focused with the future directions in the field of research. The Unsupervised visual hashing approach called semantic assisted visual hashing (SAVH) has a semi-supervised and supervised visual blending process. This approach is based on a strictly hidden rich semantics integrated into auxiliary image texts to increase the efficiency of visual clutter without any semantic labels. The most native technique for CBIR is to examine query photographs with each sample saved in the database sequentially. Its linear intricacy results in the poor expressions and performance scalability in the actual environment. Also, visual features normally have high dimensions. Picture access is normally transported out while using the complementing features of any predicament picture with the types within the photo data source. It may end up being categorized as textual content, which is primarily contentbased. To extend the scope, an unsupervised framework is deviced to learn hash codes simultaneously preserving the visual similarities of the images, integrating the semantic assistance of the texts on modeling high inter-image relationships, and defining correlations between images and shared content. The present study recommends a book unsupervised visible hashing system, termed as SAVH, to perform visual hashing learning effectively.

Unsupervised Multi-modal Hashing for Cross-Modal Retrieval

The explosive growth of multimedia data on the Internet has magnified the challenge of information retrieval. Multimedia data usually emerges in different modalities, such as image, text, video, and audio. Unsupervised cross-modal hashing techniques that support searching among multi-modal data have gained importance in large-scale retrieval tasks because of the advantage of low storage cost and high efficiency. Current methods learn the hash functions by transforming high-dimensional data into discrete hash codes. However, the original manifold structure and semantic correlation are not preserved well in compact hash codes. We propose a novel unsupervised cross-modal hashing method to cope with this problem from two perspectives. On the one hand, the semantic correlation in textual space and the locally geometric structure in the visual space are reconstructed by unified hashing features seamlessly and simultaneously. On the other hand, the \(\ell _{2,1}\)-norm penalties are imposed on the projection matrices separately to learn the relevant and discriminative hash codes. The experimental results indicate that our proposed method achieves an improvement of 1%, 6%, 9%, and 2% over the best comparison method on the four publicly available datasets (WiKi, PASCAL-VOC, UCI Handwritten Digit, and NUS-WIDE), respectively. In conclusion, the proposed framework which combines hash functions learning and multimodal graph embedding is effective in learning hash codes and achieves superior retrieval performance compared to state-of-the-art methods.

Task-adaptive Asymmetric Deep Cross-modal Hashing

Supervised cross-modal hashing aims to embed the semantic correlations of heterogeneous modality data into the binary hash codes with discriminative semantic labels. It can support efficient large-scale cross-modal retrieval due to the fast retrieval speed and low storage cost. However, existing methods equally handle the cross-modal retrieval tasks, and simply learn the same couple of hash functions in a symmetric way. Under such circumstances, the characteristics of different cross-modal retrieval tasks are ignored and sub-optimal performance may be brought. Motivated by this, we present a Task-adaptive Asymmetric Deep Cross-modal Hashing (TA-ADCMH) method in this paper. It can learn task-adaptive hash functions for two sub-retrieval tasks via simultaneous modality representation and asymmetric hash learning. Different from previous cross-modal hashing methods, our learning framework jointly optimizes the semantic preserving from multi-modal features to the hash codes, and the semantic regression from query modality representation to the explicit labels. With our model, the learned hash codes can effectively preserve the multi-modal semantic correlations, and meanwhile, adaptively capture the query semantics. Besides, we design an efficient discrete optimization strategy to directly learn the binary hash codes, which alleviates the relaxing quantization errors. Extensive experiments demonstrate the state-of-the-art performance of the proposed TA-ADCMH from various aspects.

NSDH: A Nonlinear Supervised Discrete Hashing framework for large-scale cross-modal retrieval

Hashing technology has been widely used in approximate nearest neighbor search algorithms for large-scale cross-modal retrieval due to its significantly reduced storage and high-speed search capabilities. However, most existing supervised cross-modal hashing methods either mainly rely on binary pairwise similarity and fail to exploit the rich semantic information contained in the label matrix, or the use of single linear projections which suffer from limited information completeness. In this paper, we propose a novel method, named Nonlinear Supervised Discrete Hashing (NSDH). Specifically, NSDH consists of two components, (1) a semantic enhancement descriptor consisting of multiple linear projections that is used to extract comprehensive latent representations of heterogeneous multimedia data, which aligns the original heterogeneous features and integrates the rich semantic label matrix; (2) a fast discrete optimization module used to learn discriminative compact hash codes, which preserves the similarity information using an inner product between the real-valued embeddings of the output of the semantic enhancement descriptors. Therefore, NSDH leverages both the label matrix and similarity information in order to enhance the semantic information of the learned hash codes. In this way, the representation learning capability of the output layer of semantic enhancement descriptors can be greatly enhanced and as a result the learned hash codes are more discriminative. In addition, we present a fast discrete optimization algorithm to efficiently learn the binary hash codes. Results from our experiments on two benchmark datasets highlight the superiority of NSDH in comparison to many state-of-the-art cross-modal hashing methods.

SemanticHash: Hash Coding Via Semantics-Guided Label Prototype Learning

In this article, we propose SemanticHash, a simple and effective deep neural network model, to leverage semantic word embeddings (e.g., BERT) in hash codes learning. Both images and class labels are compressed into <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -bit binary vectors by using the visual (or the semantic) hash functions, which are jointly learned and aligned to optimize the semantic consistency. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -dimensional class label prototypes—projected from semantic word embeddings—guide the hash mapping on the image side and vice versa, creating the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -bit image hash codes being aligned with their semantic prototypes and therefore more discriminative. Extensive experimental results on four benchmarks, CIFAR10, NUS-WIDE, ImageNet, and MS-COCO datasets, demonstrate the effectiveness of our approach. We also perform studies to analyze the effects of quantization and word semantic spaces and to explain the relations among the learned class prototypes. Finally, the generalization capability of the proposed approach is further demonstrated. It achieves competitive performance in comparison with state-of-the-art unsupervised and zero-shot hashing methods. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>Impact Statement</i>—Hash code learning is an important technology that enables efficient image retrieval on large-scale data. While existing hashing algorithms can effectively generate compact binary codes in a supervised learning setting trained with a moderate-size dataset, they are demanding to be scalable to large datasets and do not generalize to unseen datasets. The proposed approach overcomes these limitations. Compared with state-of-the-art ones, our solution achieves 2.1% of average performance improvement on four moderate-size benchmarks and 4.7% of improvement on ImageNet, a large-scale dataset with over 1.2 M training images. With superior performance on popular benchmarks for binary hash code learning, the technology introduced performs well on cross-dataset and zero-shot (i.e., the testing concepts are unseen during training) scenarios too. Our approach attains over 17.7% of zero-shot retrieval performance improvement when compared to the state-of-the-art in the area. This article thus provides a powerful solution to utilize massive data for fast and accurate image retrieval in the big data era.