Unsupervised Deep Cross-Modal Hashing by Knowledge Distillation for Large-scale Cross-modal Retrieval

Cross-modal hashing encodes heterogeneous multimedia data into compact binary code to achieve fast and flexible retrieval across different modalities. Due to its low storage cost and high retrieval efficiency, it has received widespread attention. Supervised deep hashing significantly improves search performance and usually yields more accurate results, but requires a lot of manual annotation of the data. In contrast, unsupervised deep hashing is difficult to achieve satisfactory performance due to the lack of reliable supervisory information. To solve this problem, inspired by knowledge distillation, we propose a novel unsupervised knowledge distillation cross-modal hashing method based on semantic alignment (SAKDH), which can reconstruct the similarity matrix using the hidden correlation information of the pretrained unsupervised teacher model, and the reconstructed similarity matrix can be used to guide the supervised student model. Specifically, firstly, the teacher model adopted an unsupervised semantic alignment hashing method, which can construct a modal fusion similarity matrix. Secondly, under the supervision of teacher model distillation information, the student model can generate more discriminative hash codes. Experimental results on two extensive benchmark datasets (MIRFLICKR-25K and NUS-WIDE) show that compared to several representative unsupervised cross-modal hashing methods, the mean average precision (MAP) of our proposed method has achieved a significant improvement. It fully reflects its effectiveness in large-scale cross-modal data retrieval.

Existing Cross Modal Hashing (CMH) methods are mainly designed for balanced data, while imbalanced data with long-tail distribution is more general in real-world. Several long-tail hashing methods have been proposed but they can not adapt for multi-modal data, due to the complex interplay between labels and individuality and commonality information of multi-modal data. Furthermore, CMH methods mostly mine the commonality of multi-modal data to learn hash codes, which may override tail labels encoded by the individuality of respective modalities. In this paper, we propose LtCMH (Long-tail CMH) to handle imbalanced multi-modal data. LtCMH firstly adopts auto-encoders to mine the individuality and commonality of different modalities by minimizing the dependency between the individuality of respective modalities and by enhancing the commonality of these modalities. Then it dynamically combines the individuality and commonality with direct features extracted from respective modalities to create meta features that enrich the representation of tail labels, and binaries meta features to generate hash codes. LtCMH significantly outperforms state-of-the-art baselines on long-tail datasets and holds a better (or comparable) performance on datasets with balanced labels.

Recently, due to the low storage consumption and high search efficiency of hashing methods and the powerful feature extraction capability of deep neural networks, deep cross-modal hashing has received extensive attention in the field of multi-media retrieval. However, existing methods tend to ignore the latent relationships between heterogeneous data when learning a common semantic subspace, and cannot retain more important semantic information when mining deep correlations. In this paper, an attention mechanism which focuses on the characteristics of the associated features is employed to propose an attention-aware semantic fusion matrix that integrates important information from different modalities. We introduce a novel network that can pass the extracted features through the attention module to efficiently encode rich and relevant features, and can also generate hash codes under the self-supervision of the proposed attention-aware semantic fusion matrix. Our experimental results and detailed analysis prove that our method can achieve better retrieval performance on the three popular datasets, compared with the recent unsupervised cross-modal hashing methods.

Hashing has been extensively utilized in cross-modal retrieval due to its high efficiency in handling large-scale, high-dimensional data. However, most existing cross-modal hashing methods operate as offline learning models, which learn hash codes in a batch-based manner and prove to be inefficient for streaming data. Recently, several online cross-modal hashing methods have been proposed to address the streaming data scenario. Nevertheless, these methods fail to fully leverage the semantic information and accurately optimize hashing in a discrete fashion. As a result, both the accuracy and efficiency of online cross-modal hashing methods are not ideal. To address these issues, this paper introduces the Semantic Embedding-based Online Cross-modal Hashing (SEOCH) method, which integrates semantic information exploitation and online learning into a unified framework. To exploit the semantic information, we map the semantic labels to a latent semantic space and construct a semantic similarity matrix to preserve the similarity between new data and existing data in the Hamming space. Moreover, we employ a discrete optimization strategy to enhance the efficiency of cross-modal retrieval for online hashing. Through extensive experiments on two publicly available multi-label datasets, we demonstrate the superiority of the SEOCH method.

Deep hashing methods have achieved tremendous success in cross-modal retrieval, due to its low storage consumption and fast retrieval speed. Supervised cross-modal hashing methods have achieved substantial advancement by incorporating semantic information. However, to a great extent, supervised methods rely on large-scale labeled cross-modal training data which are laborious to obtain. Moreover, most cross-modal hashing methods only handle two modalities of image and text, without taking the scene of multiple modalities into consideration. In this paper, we propose a novel semi-supervised approach called semi-supervised knowledge distillation for cross-modal hashing (SKDCH) to overcome the above-mentioned challenges, which enables guiding a supervised method using outputs produced by a semi-supervised method for multimodality retrieval. Specifically, we utilize teacher-student optimization to propagate knowledge. Furthermore, we improves triplet ranking loss to better mitigate the heterogeneity gap, which increases the discriminability of our proposed approach. Extensive experiments executed on two benchmark datasets validate that the proposed SKDCH surpasses the state-of-the-art methods.

The booming demands for cross-modal retrieval tasks can often bring in its wake the development of retrieval technologies, as people turn to pursuing a more effective way to improve the performance of search results in both accuracy and efficiency, for example by unsupervised cross-modal hashing. It’s worth noting that most of the cross-modal hashing methods focus on utilizing merely one approach to generate hash codes. However, each approach has its own intrinsic drawback, which would inevitably diminish the quality of hash codes. In this paper, we propose a state-of-the-art model named Soft Constraint Hashing (SCH), using a special soft constraint term defined as an “information tunnel” to achieve the goal that conveys information from one approach to another. In particular, this “tunnel” can eliminate potential data noises to some extent and bridge the gap between two unsupervised discrete hashing allocation approaches to simultaneously reinforce the quality of hash codes. The empirical results on publicly available datasets illustrate that our proposed model outperforms all the existing unsupervised cross-model hashing methods.

Existing unsupervised cross-modal hashing retrieval methods generally are restricted by two limitations: 1. Most existing cross-modal hashing methods explore modal semantic information based on paired data, while the semantic information available in unpaired single-modal data is discarded; unsuper-vised methods that rely only on constructing semantic matrix for retrieval have considerable limitations, and the similarity information between heterogeneous data requires deep mining. In this paper, we propose an unsupervised hash retrieval based on colla-borative semantic distribution (UPJS). First, the method constr-ucts a collaborative semantic similarity matrix between modali-ties, which fuses the original semantic information of heterogen-eous modalities and preserves the semantic connections between different modal instances. Secondly, this paper employs feature fusion to transform unpaired information into paired information, and then achieves semantic similarity by considering both paired and unpaired information. Furthermore, the method constructs inter-modal triplet constraints between paired and unpa-ired data, and utilizes a collaborative matrix to jointly train se-mantic binary codes. Extensive experiments on two benchmark datasets, MIRFlickr and WikiData, show that this method has a favorable performance in both paired and unpaired data.

Label consistent locally linear embedding based cross-modal hashing

Unsupervised cross-modal hashing (UCMH) has attracted increasing research due to its efficient retrieval performance and label irrelevance. However, existing methods have some bottlenecks: Firstly, the existing unsupervised methods suffer from inaccurate similarity measures due to the lack of correlation between features of different modalities and simple features cannot fully describe the fine-grained relationships of multi-modal data. Secondly, existing methods have rarely explored vision-language knowledge distillation schemes to distil multi-modal knowledge of these vision-language models to guide the learning of student networks. To address these bottlenecks, this paper proposes an effective unsupervised cross-modal hashing retrieval method, called Vision-Language Knowledge Distillation for Unsupervised Cross-Modal Hashing Retrieval (VLKD). VLKD uses the vision-language pre-training (VLP) model to encode features on multi-modal data, and then constructs a similarity matrix to provide soft similarity supervision for the student model. It distils the knowledge of the VLP model to the student model to gain an understanding of multi-modal knowledge. In addition, we designed an end-to-end unsupervised hashing learning model that incorporates a graph convolutional auxiliary network. The auxiliary network aggregates information from similar data nodes based on the similarity matrix distilled by the teacher model to generate more consistent hash codes. Finally, the teacher network does not require additional training, it only needs to guide the student network to learn high-quality hash representation, and VLKD is quite efficient in training and retrieval. Sufficient experiments on three multimedia retrieval benchmark datasets show that the proposed method achieves better retrieval performance compared to existing unsupervised cross-modal hashing methods, demonstrating the effectiveness of the proposed method.

Multi-label enhancement based self-supervised deep cross-modal hashing

Unsupervised cross-modal hashing has attracted considerable attention to support large-scale cross-modal retrieval. Although promising progresses have been made so far, existing methods still suffer from limited capability on excavating and preserving the intrinsic multi-modal semantics. In this paper, we propose a Correlation-Identity Reconstruction Hashing (CIRH) method to alleviate this challenging problem. We develop a new unsupervised deep cross-modal hash learning framework to model and preserve the heterogeneous multi-modal correlation semantics into both hash codes and functions, and simultaneously, we involve both the hash codes and functions with the descriptive identity semantics. Specifically, we construct a multi-modal collaborated graph to model the heterogeneous multi-modal correlations, and jointly perform the intra-modal and cross-modal semantic aggregation on homogeneous and heterogeneous graph networks to generate a multi-modal complementary representation with correlation reconstruction. Furthermore, an identity semantic reconstruction process is designed to involve the generated representation with identity semantics by reconstructing the input modality representations. Finally, we propose a correlation-identity consistent hash function learning strategy to transfer the modelled multi-modal semantics into the neural networks of modality-specific deep hash functions. Experiments demonstrate the superior performance of the proposed method on both retrieval accuracy and efficiency. We provide our source codes and experimental datasets at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/XizeWu/CIRH</uri>

Cross-modal hashing methods have attracted considerable attention. Most pioneer approaches only preserve the neighborhood relationship by constructing the correlations among heterogeneous modalities. However, they neglect the fact that the high-dimensional data often exists on a low-dimensional manifold embedded in the ambient space and the relative proximity between the neighbors is also important. Although some methods leverage the manifold learning to generate the hash codes, most of them fail to explicitly explore the discriminative information in the class labels and discard the binary constraints during optimization, generating large quantization errors. To address these issues, in this paper, we present a novel cross-modal hashing method, named Supervised Discrete Manifold-Embedded Cross-Modal Hashing (SDMCH). It can not only exploit the non-linear manifold structure of data and construct the correlation among heterogeneous multiple modalities, but also fully utilize the semantic information. Moreover, the hash codes can be generated discretely by an iterative optimization algorithm, which can avoid the large quantization errors. Extensive experimental results on three benchmark datasets demonstrate that SDMCH outperforms ten state-of-the-art cross-modal hashing methods.

Cross-modal hashing retrieval approaches maps heterogeneous multi-modal data into a common hamming space to achieve efficient and flexible retrieval performance. However, existing cross-modal methods mainly exploit feature-level similarity between multi-modal data, the label-level similarity and relative ranking relationship between adjacent instances have been ignored. To address these problems, we propose a novel Deep Rank Cross-modal Hashing(DRCH) method that fully explores the intra-modal semantic similarity relationship. Firstly, DRCH preserves semantic similarity by combining both label-level and feature-level information. Secondly, the inherent gap between modalities are narrowed by proposing a ranking alignment loss function. Finally, the compact and efficient hash codes are optimized from the common semantic space. Extensive experiments on two real-world image-text retrieval datasets demonstrate the superiority of DRCH compared with several state-of-the-art(SOTA) methods.

Cross-modal hashing maps heterogeneous multimedia data into a common Hamming space to realize fast and flexible cross-modal retrieval. Supervised cross-modal hashing methods have achieved considerable progress by incorporating semantic side information. However, they heavily rely on large-scale labeled cross-modal training data which are hard to obtain, since multiple modalities are involved. They also ignore the rich information contained in the large amount of unlabeled data across different modalities, which can help to model the correlations between different modalities. To address these problems, in this paper, we propose a novel semi-supervised cross-modal hashing approach by generative adversarial network (SCH-GAN). The main contributions can be summarized as follows: 1) we propose a novel generative adversarial network for cross-modal hashing, in which the generative model tries to select margin examples of one modality from unlabeled data when given a query of another modality (e.g., giving a text query to retrieve images and vice versa). The discriminative model tries to distinguish the selected examples and true positive examples of the query. These two models play a minimax game so that the generative model can promote the hashing performance of the discriminative model and 2) we propose a reinforcement learning-based algorithm to drive the training of proposed SCH-GAN. The generative model takes the correlation score predicted by discriminative model as a reward, and tries to select the examples close to the margin to promote a discriminative model. Extensive experiments verify the effectiveness of our proposed approach, compared with nine state-of-the-art methods on three widely used datasets.

Hashing has recently received great attention in cross-modal retrieval. Cross-modal retrieval aims at retrieving information across heterogeneous modalities (e.g., texts vs. images). Cross-modal hashing compresses heterogeneous high-dimensional data into compact binary codes with similarity preserving, which provides efficiency and facility in both retrieval and storage. In this study, we propose a novel fast discrete cross-modal hashing (FDCH) method with regressing from semantic labels to take advantage of supervised labels to improve retrieval performance. In contrast to existing methods that learn the projection from hash codes to semantic labels, the proposed FDCH regresses the semantic labels of training examples to the corresponding hash codes with a drift. It not only accelerates the hash learning process, but also helps generate stable hash codes. Furthermore, the drift can adjust the regression and enhance the discriminative capability of hash codes. Especially in the case of training efficiency, FDCH is much faster than existing methods. Comparisons with several state-of-the-art techniques on three benchmark datasets have demonstrated the superiority of FDCH under various cross-modal retrieval scenarios.