Hypergraph Hash Learning for Efficient Trajectory Similarity Computation

Learning compact binary codes for image retrieval problem using deep neural networks has recently attracted increasing attention. However, training deep hashing networks is challenging due to the binary constraints on the hash codes. In this paper, we propose deep network models and learning algorithms for learning binary hash codes given image representations under both unsupervised and supervised manners. The novelty of our network design is that we constrain one hidden layer to directly output the binary codes. This design has overcome a challenging problem in some previous works: optimizing non-smooth objective functions because of binarization. In addition, we propose to incorporate independence and balance properties in the direct and strict forms into the learning schemes. We also include a similarity preserving property in our objective functions. The resulting optimizations involving these binary, independence, and balance constraints are difficult to solve. To tackle this difficulty, we propose to learn the networks with alternating optimization and careful relaxation. Furthermore, by leveraging the powerful capacity of convolutional neural networks, we propose an end-to-end architecture that jointly learns to extract visual features and produce binary hash codes. Experimental results for the benchmark datasets show that the proposed methods compare favorably or outperform the state of the art.

Similarity search plays an important role in many applications involving high-dimensional data. Due to the known dimensionality curse, the performance of most existing indexing structures degrades quickly as the feature dimensionality increases. Hashing methods, such as locality sensitive hashing (LSH) and its variants, have been widely used to achieve fast approximate similarity search by trading search quality for efficiency. However, most existing hashing methods make use of randomized algorithms to generate hash codes without considering the specific structural information in the data. In this paper, we propose a novel hashing method, namely, robust hashing with local models (RHLM), which learns a set of robust hash functions to map the high-dimensional data points into binary hash codes by effectively utilizing local structural information. In RHLM, for each individual data point in the training dataset, a local hashing model is learned and used to predict the hash codes of its neighboring data points. The local models from all the data points are globally aligned so that an optimal hash code can be assigned to each data point. After obtaining the hash codes of all the training data points, we design a robust method by employing l2,1 -norm minimization on the loss function to learn effective hash functions, which are then used to map each database point into its hash code. Given a query data point, the search process first maps it into the query hash code by the hash functions and then explores the buckets, which have similar hash codes to the query hash code. Extensive experimental results conducted on real-life datasets show that the proposed RHLM outperforms the state-of-the-art methods in terms of search quality and efficiency.

Meta-path-based random walk strategy has attracted tremendous attention in heterogeneous network representation, which can capture network semantics with heterogeneous neighborhoods of nodes. Despite the success of meta-path-based random walk strategy in plain heterogeneous networks which contain no attributes, it remains unexplored how meta-path-based random walk strategy could be utilized on attributed heterogeneous networks to simultaneously capture structural heterogeneity and attribute proximity. Moreover, the importance of node attributes and structural relations generally varies across data sets, thus requiring careful considerations when they are incorporated into representations. To tackle these problems, we propose a novel method, Attributed Heterogeneous Network embedding based on Aggregate-path (AHNA), which generates aggregate-path-based random walks on attributed heterogeneous networks and adaptively fuses topological structures and node attributes based on the learned importance. Specifically, AHNA first converts node attributes to additional links in the network to deal with the heterogeneity of structures and attributes, which is followed by an adaptive random walk strategy to strike the importance balance between node attributes and topological structures, thereby generating high-quality representations. Extensive experiments are conducted on three real-world data sets, where AHNA outperforms state-of-the-art approaches by up to 22.7%, 2.6%, and 2.3% on link prediction, community detection, and node classification, respectively. Moreover, our qualitative analysis indicates that AHNA can capture different balances of topological structures and node attributes on various data sets and thus boost the quality of node representations.

The content-based remote sensing image retrieval (CBRSIR) has attracted increasing attention with the number of remote sensing (RS) images growing explosively. Benefiting from the strong capacity of the deep convolutional neural network (DCNN), the performance of CBRSIR has been improved in recent years. Although great successes have been obtained, learning the RS images' representative features and enhancing the retrieval efficiency for the large-scale CBRSIR tasks are still two challenging problems. In this article, we propose a new CBRSIR method named feature and hash (FAH) learning, which consists of a deep feature learning model (DFLM) and an adversarial hash learning model (AHLM). The DFLM aims at learning the RS images' dense features to guarantee the retrieval precision. In the DFLM, the DCNN and the proposed feature aggregation are integrated to capture the multiscale features. Then, the discrimination of the obtained features can be highlighted by the attention map in the developed attention branch. The AHLM maps the dense features onto the compact hash codes so that the retrieval efficiency can be improved. The AHLM contains a hash learning submodel and an adversarial regularization submodel. In particular, the hash learning submodel learns the real-valued hash codes that are similarity preserved by semantic supervisions. The adversarial regularization submodel regularizes the real-valued hash codes to learn the discrete uniform distribution with possible values 0 and 1. In this way, the hash codes are coding-balanced and the quantization errors are reduced. Encouraging experimental results counted on three public benchmark data sets demonstrate that our FAH can achieve competitive performance in the CBRSIR task compared with many existing hash learning methods.

Fast similarity search is a key component in large-scale information retrieval, where semantic hashing has become a popular strategy for representing documents as binary hash codes. Recent advances in this area have been obtained through neural network based models: generative models trained by learning to reconstruct the original documents. We present a novel unsupervised generative semantic hashing approach, Ranking based Semantic Hashing (RBSH) that consists of both a variational and a ranking based component. Similarly to variational autoencoders, the variational component is trained to reconstruct the original document conditioned on its generated hash code, and as in prior work, it only considers documents individually. The ranking component solves this limitation by incorporating inter-document similarity into the hash code generation, modelling document ranking through a hinge loss. To circumvent the need for labelled data to compute the hinge loss, we use a weak labeller and thus keep the approach fully unsupervised. Extensive experimental evaluation on four publicly available datasets against traditional baselines and recent state-of-the-art methods for semantic hashing shows that RBSH significantly outperforms all other methods across all evaluated hash code lengths. In fact, RBSH hash codes are able to perform similarly to state-of-the-art hash codes while using 2-4x fewer bits.

Hamming embedding is shown to be efficient for solving large scale image retrieval problems. The k-means hashing is applied to find compact binary codes for hashing. On the other hand, the iterative quantization hashing has been proposed to find better hash codes by minimizing the quantization error between binary hash code and hash function output values of images. The k-means hashing distorts the hypercube of binary codes to minimize quantization error while the iterative quantization hashing rotates the feature vector of images to minimize the quantization error. The proposed rotated k-means hashing combines the distortion of hypercube with the rotation of feature vector of images for further minimization of quantization error. Experimental results show the RKMH preserves good similarities among images.

Supervised discrete discriminant hashing for image retrieval

Sparse Coding is a widely used method to represent an image. However, sparse coding and its improved algorithms have the problem of complex computation and long running time and so on. For these problems, we propose an image classification method based on hash codes and space pyramid, which encodes local feature points with hash codes instead of sparse coding. Firstly, extract the local feature points from the images. Second, learn binary auto-encoder hashing functions, which map the local feature points into hash codes. Third, perform binary k-means cluster on the binary hash codes and generate the binary visual vocabularies. Finally, Combine with spatial pyramid matching model, and represent the image by the histogram vector of space pyramid, which is used in image classification. Experimental results show that compared with other sparse coding methods, our method has the shorter time of learning vocabularies and faster encoder speed and higher classification accuracy.

In the field of fast and large-scale image retrieval, the binary hash code based on convolutional features enjoys powerful advantages. CNN model's leading recognition ability shows that its high-level features distribute intensively and have stable between-class distances. On the basis of the distribution characteristic of convolutional features, this paper presents a new method of improving retrieval performance by means of using the category centers of high-level features to enhance the common semantic content of high-level features of the query image and making the consequent binary hash code gain better retrieval results. Experimental results indicate that (i) the category centers of CNN feature offer comparable discriminability with the initial model when identifying the semantic information of images; (ii) before calculating binary hash code, the integration of the CNN feature of a query image with category centers weighted by predicted probabilities can boost performance in similar image retrieval. State-of-the-art retrieval performance is obtained on the Cifar-10 dataset in this paper among all hash methods.

Deep hashing methods utilize an end-to-end framework to mutually learn feature representations and hash codes, thereby achieving a better retrieval performance. Traditional supervised hashing methods adopt handcrafted features for hashing function learning and then generate hash codes through classification and quantization. The lack of adaptability and independence of the quantization procedure leads to low retrieval accuracy of supervised hashing methods with handcrafted features in image retrieval. In this study, a non-relaxation deep hashing method for fast image retrieval is proposed. In this method, a differentiable host thresholding function is used to encourage hash-like codes to approach -1 or 1 non-linearly at the output of the convolutional neural, instead of the symbol function for quantization used in the traditional method. The output of the host thresholding function is directly used to compute the network training error, and a loss function is elaborately designed with the norm to constrain each bit of the hash-like code to be as binary as possible. Finally, a symbol function is added outside the trained network model to generate binary hash codes for image storage and retrieval in a low-dimensional binary space. Extensive experiments on two large-scale public datasets show that our method can effectively learn image features, generate accurate binary hash codes, and outperform state-of-the-art methods in terms of the mean average precision.

Similarity preserving hashing methods have drawn a lot of attention lately due to their efficiency in performing approximate nearest neighbor searches on high-dimensional large-scale multimedia data. With the development of deep learning techniques, deep supervised hashing has attracted increasing attention lately. Existing deep hashing methods usually take a two-step strategy to generate hash codes. They generate continuous hash codes and then discretize them into binary hash codes. Deep hashing methods have outperformed other methods significantly, but there is still a huge quantization gap between the discrete hash codes and continuous hash codes. The quantization gap prevents existing deep hashing methods from achieving better performance. In this paper, we propose deep supervised hashing with dynamic weighting scheme (DHDW), a novel deep hashing method that narrows down the quantization gap by utilizing Hamming distance information during training. Specifically, we introduce Hamming distance and stability information into the training phase by applying a novel dynamic weighting module to all data of a mini-batch. The dynamic weighting module we present is constructed from real-time Hamming distance and stability information. Additionally, the dynamic weighting module is compatible with all existing pairwise deep supervised hashing methods. Comprehensive experiments show that DHDW outperforms existing state-of-the-art methods on several standard datasets and benchmarks, and the dynamic weighting module effectively improves the performance of deep learning to hash methods.

Multi-modal hashing aims to succinctly encode heterogeneous modalities into binary hash codes, facilitating efficient multimedia retrieval characterized by low storage demands and high retrieval speed. Despite the commendable achievements of existing methods, they still face three crucial challenges: 1) Inadequate bridging of the heterogeneous modality gap through coarse, global feature-level alignment and fusion. 2) The erosion of bit independence and consequent limitations on the semantic representation capacity of hash codes during feature-level hash code learning. 3) The insufficiency of binary label-based pairwise semantic preservation strategies in capturing intricate fine-grained semantic correlations within multi-modal data. To address these challenges, this paper introduces the Dynamic Bit-wise Semantic Transformer Hashing (DBSTH) framework. Remarkably, it treats each hash bit as a unique semantic concept, facilitating concept-level alignment of heterogeneous modalities. This safeguards bit independence and augments representation capabilities. Specifically, we devise a dynamic unit fusion strategy for the adaptive combination of local multi-modal information units, facilitating the acquisition of bit-wise semantic concepts. Subsequently, we incorporate a transformer encoder to refine these concepts by uncovering latent correlations among distinct concepts. Finally, we perform the multi-modal alignment and fusion on the fine-grained concept-level, independently encoding each concept to its corresponding hash bit. To provide enhanced guidance for concept learning, a label prototype learning mechanism is introduced, which learns prototype embeddings for all categories through the consideration of co-occurrence priors. This mechanism effectively captures fine-grained explicit semantic correlations and generates supervising hash codes. Additionally, to improve the robustness of the hashing model in handling noisy multi-modal data, a masked concept learning strategy is introduced, facilitating the acquisition of resilient semantic concepts. Extensive experiments conducted on three widely tested multi-modal retrieval datasets demonstrate the superiority of our method in conventional, noisy, and open-set retrieval scenarios.

This paper proposes a generic formulation that significantly expedites the training and deployment of image classification models, particularly under the scenarios of many image categories and high feature dimensions. As the core idea, our method represents both the images and learned classifiers using binary hash codes, which are simultaneously learned from the training data. Classifying an image thereby reduces to retrieving its nearest class codes in the Hamming space. Specifically, we formulate multiclass image classification as an optimization problem over binary variables. The optimization alternatingly proceeds over the binary classifiers and image hash codes. Profiting from the special property of binary codes, we show that the sub-problems can be efficiently solved through either a binary quadratic program (BQP) or a linear program. In particular, for attacking the BQP problem, we propose a novel bit-flipping procedure which enjoys high efficacy and a local optimality guarantee. Our formulation supports a large family of empirical loss functions and is, in specific, instantiated by exponential and linear losses. Comprehensive evaluations are conducted on several representative image benchmarks. The experiments consistently exhibit reduced computational and memory complexities of model training and deployment, without sacrificing classification accuracy.

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

Efficient sampling of complex network with modified random walk strategies