Distance metric learning for semantic segmentation based graph hashing

Learning valid similarities is a vital problem in hashing methods, especially in large-scale image search. Similarity pertained hashing method is widely used in image retrieval for its high quality compact binary code mapping. The hashing scheme of most existing hashing methods is that the input data is encoded as a vector of visual features and hashed into binary hash codes via projection functions or quantization methods afterward. However, this separated pipeline may prone to lose accurate similarities of images, since the limited compatible domain between visual feature vectors generation and binary codes mapping process. Encouraged by the extraordinary image representation learning ability of deep neural networks in classification, we propose a structure that merges binary code generation process within deep neural networks for efficient image retrieval. The proposed architecture contains two fundamental blocks. The stacked convolution layers of Network In Network with global average pooling compute effective image representation and the embedded latent layer with binary activation functions learn binary hash codes simultaneously. Experiments show that the proposed method gains improvement over several state-of-the-art hashing methods.

Hashing-based similarity search techniques is becoming increasingly popular in large data sets. To capture meaningful neighbors, the topology of a data set, which represents the neighborhood relationships between its subregions and the relative proximities between the neighbors of each subregion, e.g., the relative neighborhood ranking of each subregion, should be exploited. However, most existing hashing methods are developed to preserve neighborhood relationships while ignoring the relative neighborhood proximities. Moreover, most hashing methods lack in providing a good result ranking, since there are often lots of results sharing the same Hamming distance to a query. In this paper, we propose a novel hashing method to solve these two issues jointly. The proposed method is referred to as topology preserving hashing (TPH). TPH is distinct from prior works by also preserving the neighborhood ranking. Based on this framework, we present three different TPH methods, including linear unsupervised TPH, semisupervised TPH, and kernelized TPH. Particularly, our unsupervised TPH is capable of mining semantic relationship between unlabeled data without supervised information. Extensive experiments on four large data sets demonstrate the superior performances of the proposed methods over several state-of-the-art unsupervised and semisupervised hashing techniques.

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.

Deep supervised hashing hash has been widely utilized in large-scale image retrieval due to its lightweight storage and fast search speed. The distribution of features from the existing hashing methods has been inevitably distorted from the original feature distribution, which resulted in the performance decline on image retrieval. With the constraints of the Euclidian metric, the distortion can be mitigated to certain extent. However, the Euclidian distance is sensitive to the norm of the features. On the point, we propose a novel deep hashing method, called cosine metric supervised deep hashing (CMDH), to perform hash learning by incorporating cosine metric and category loss. CMDH uses the cosine metric to effectively mitigate the impact caused by the diverse sample vector norms on retrieval performance. In addition, joint deep hash learning constructs binary coding over cosine loss and category loss, which further alleviates distortion in binary feature learning for efficient retrieval.KeywordsCosine metricClassification informationSupervised deep hashingImage retrieval

Earth Mover's Distance (EMD), as a similarity measure, has received a lot of attention in the fields of multimedia and probabilistic databases, computer vision, image retrieval, machine learning, etc. EMD on multidimensional histograms provides better distinguishability between the objects approximated by the histograms (e.g., images), compared to classic measures like Euclidean distance. Despite its usefulness, EMD has a high computational cost; therefore, a number of effective filtering methods have been proposed, to reduce the pairs of histograms for which the exact EMD has to be computed, during similarity search. Still, EMD calculations in the refinement step remain the bottleneck of the whole similarity search process. In this paper, we focus on optimizing the refinement phase of EMD-based similarity search by (i) adapting an efficient min-cost flow algorithm (SIA) for EMD computation, (ii) proposing a dynamic distance bound, which can be used to terminate an EMD refinement early, and (iii) proposing a dynamic refinement order for the candidates which, paired with a concurrent EMD refinement strategy, reduces the amount of needless computations. Our proposed techniques are orthogonal to and can be easily integrated with the state-of-the-art filtering techniques, reducing the cost of EMD-based similarity queries by orders of magnitude.

Hashing has been widely applied to the large-scale approximate nearest neighbor search problem owing to its high efficiency and low storage requirement. Most investigations concentrate on learning hashing methods in a centralized setting. However, in existing big data systems, data is often stored across different nodes. In some situations, data is even collected in a distributed manner. A straightforward way to solve this problem is to aggregate all the data into the fusion center to obtain the search result (aggregating method). However, this strategy is not feasible because of the prohibitive communication cost. Although a few distributed hashing methods have been proposed to reduce this cost, they only focus on designing a distributed algorithm for a specific global optimization objective without considering scalability. Moreover, existing distributed hashing methods aim at finding a distributed solution to hashing, meanwhile avoiding accuracy loss, rather than improving accuracy. To address these challenges, we propose a Scalable Distributed Hashing (SDisH) model in which most existing hashing methods can be extended to process distributed data with no changes. Furthermore, to improve accuracy, we utilize the search radius as a global variable across different nodes to achieve a global optimum search result for every iteration. In addition, a voting algorithm is presented based on the results produced by multiple iterations to further reduce search errors. Theoretical analyses of communication, computation, and accuracy demonstrate the superiority of the proposed model. Numerical simulations on three large-scale and two relatively small benchmark datasets also show that the SDisH model achieves up to 44.75% and 10.23% accuracy gains compared to the aggregating method and state-of-the-art distributed hashing methods, respectively.

In this paper, we present a new hashing method to learn compact binary codes for highly efficient image retrieval on large-scale datasets. While the complex image appearance variations still pose a great challenge to reliable retrieval, in light of the recent progress of Convolutional Neural Networks (CNNs) in learning robust image representation on various vision tasks, this paper proposes a novel Deep Supervised Hashing (DSH) method to learn compact similarity-preserving binary code for the huge body of image data. Specifically, we devise a CNN architecture that takes pairs of images (similar/dissimilar) as training inputs and encourages the output of each image to approximate discrete values (e.g. +1/-1). To this end, a loss function is elaborately designed to maximize the discriminability of the output space by encoding the supervised information from the input image pairs, and simultaneously imposing regularization on the real-valued outputs to approximate the desired discrete values. For image retrieval, new-coming query images can be easily encoded by propagating through the network and then quantizing the network outputs to binary codes representation. Extensive experiments on two large scale datasets CIFAR-10 and NUS-WIDE show the promising performance of our method compared with the state-of-the-arts.

Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be optimally compatible with the coding process. Besides, these hashing methods are mainly designed to handle simple pairwise similarity. The complex multilevel ranking semantic structure of instances associated with multiple labels has not been well explored yet. In this paper, we propose a ranking-based deep cross-modal hashing approach (RDCMH). RDCMH firstly uses the feature and label information of data to derive a semi-supervised semantic ranking list. Next, to expand the semantic representation power of hand-crafted features, RDCMH integrates the semantic ranking information into deep cross-modal hashing and jointly optimizes the compatible parameters of deep feature representations and of hashing functions. Experiments on real multi-modal datasets show that RDCMH outperforms other competitive baselines and achieves the state-of-the-art performance in cross-modal retrieval applications.

Hashing methods can overcome the problems of low retrieval efficiency and high storage cost. Existing hashing methods use either only one feature or multiple features as the input of one kernel function. The fact that different kernel functions have different roles and different characteristics and contain different information is ignored. In this paper, an adaptive multi-feature and multi-kernel hashing learning (MFMKH) algorithm is proposed, which can adaptively combine the feature weight coefficient and the kernel weight coefficient and double-combine the multi-feature and multi-kernel advantages. The fusion of these features in the algorithm solves the disadvantage of single feature containing insufficient information. In addition, the use of a variety of different kernel functions can compensate for the lack of a single-kernel learning ability and has the dual advantages of multi-feature fusion and multi-kernel learning. Experiments on the standard datasets IRMA, Ultrasound, and Cifar10 have shown that the retrieval performance of the proposed method clearly outperforms other similar kernel-based hashing learning methods. In addition, compared to the supervised deep hashing, the retrieval performance of the proposed method is competitive on the Cifar10 dataset in the case of the reduced training time.

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.

Hashing methods have been widely used in large-scale image retrieval. However, the constraints on the hash codes of similar images learned by the previous hashing methods are too strong, which may lead to overfitting and difficult convergence. Besides, the binary codes output by the previous hashing methods are not optimally compatible with the multi-index approach, which is the most effective method for Hamming distance query acceleration. In this paper, we propose a novel Robust and Index-Compatible Deep Hashing (RICH) method to learn compact similarity-preserving binary codes, which focuses on improving the retrieval accuracy and time efficiency simultaneously. With the learned binary codes, we can achieve better results compared with the state-of-the-arts in retrieval accuracy. Meanwhile, remarkable promotions of the retrieval time efficiency have been made in the Hamming distance query process.

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.

Discriminative deep metric learning for asymmetric discrete hashing

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.

Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of computer vision tasks such as image retrieval, fine-grained classification, and visual question answering. In this paper, we address the problem of fine-grained classification and image retrieval by leveraging textual information along with visual cues to comprehend the existing intrinsic relation between the two modalities. The novelty of the proposed model consists of the usage of a PHOC descriptor to construct a bag of textual words along with a Fisher Vector Encoding that captures the morphology of text. This approach provides a stronger multimodal representation for this task and as our experiments demonstrate, it achieves state-of-the-art results on two different tasks, fine-grained classification and image retrieval. The code of this model will be publicly available at1.