Deep Self-Taught Hashing for Image Retrieval

Hash Bit Selection via Collaborative Neurodynamic Optimization With Discrete Hopfield Networks

Hash bit selection (HBS) aims to find the most discriminative and informative hash bits from a hash pool generated by using different hashing algorithms. It is usually formulated as a binary quadratic programming problem with an information-theoretic objective function and a string-length constraint. In this article, it is equivalently reformulated in the form of a quadratic unconstrained binary optimization problem by augmenting the objective function with a penalty function. The reformulated problem is solved via collaborative neurodynamic optimization (CNO) with a population of classic discrete Hopfield networks. The two most important hyperparameters of the CNO approach are determined based on Monte Carlo test results. Experimental results on three benchmark data sets are elaborated to substantiate the superiority of the collaborative neurodynamic approach to several existing methods for HBS.

Fast Cross-Modal Hashing With Global and Local Similarity Embedding

Recently, supervised cross-modal hashing has attracted much attention and achieved promising performance. To learn hash functions and binary codes, most methods globally exploit the supervised information, for example, preserving an at-least-one pairwise similarity into hash codes or reconstructing the label matrix with binary codes. However, due to the hardness of the discrete optimization problem, they are usually time consuming on large-scale datasets. In addition, they neglect the class correlation in supervised information. From another point of view, they only explore the global similarity of data but overlook the local similarity hidden in the data distribution. To address these issues, we present an efficient supervised cross-modal hashing method, that is, fast cross-modal hashing (FCMH). It leverages not only global similarity information but also the local similarity in a group. Specifically, training samples are partitioned into groups; thereafter, the local similarity in each group is extracted. Moreover, the class correlation in labels is also exploited and embedded into the learning of binary codes. In addition, to solve the discrete optimization problem, we further propose an efficient discrete optimization algorithm with a well-designed group updating scheme, making its computational complexity linear to the size of the training set. In light of this, it is more efficient and scalable to large-scale datasets. Extensive experiments on three benchmark datasets demonstrate that FCMH outperforms some state-of-the-art cross-modal hashing approaches in terms of both retrieval accuracy and learning efficiency.

Hash Bit Selection Based on Collaborative Neurodynamic Optimization

Hash bit selection determines an optimal subset of hash bits from a candidate bit pool. It is formulated as a zero-one quadratic programming problem subject to binary and cardinality constraints. In this article, the problem is equivalently reformulated as a global optimization problem. A collaborative neurodynamic optimization (CNO) approach is applied to solve the problem by using a group of neurodynamic models initialized with particle swarm optimization iteratively in the CNO. Lévy mutation is used in the CNO to avoid premature convergence by ensuring initial state diversity. A theoretical proof is given to show that the CNO with the Lévy mutation operator is almost surely convergent to global optima. Experimental results are discussed to substantiate the efficacy and superiority of the CNO-based hash bit selection method to the existing methods on three benchmarks.

Equivalent Continuous Formulation of General Hashing Problem

Hashing-based approximate nearest neighbors search has attracted broad research interest, due to its low computational cost and fast retrieval speed. The hashing technique maps the data points into binary codes and, meanwhile, preserves the similarity in the original space. Generally, we need to solve a discrete optimization problem to learn the binary codes and hash functions, which is NP-hard. In the literature, most hashing methods choose to solve a relaxed problem by discarding the discrete constraints. However, such a relaxation scheme will cause large quantization error, which makes the learned binary codes less effective. In this paper, we present an equivalent continuous formulation of the discrete hashing problem. Specifically, we show that the discrete hashing problem can be transformed into a continuous optimization problem without any relaxations, while the transformed continuous optimization problem has the same optimal solutions and the same optimal value as the original discrete hashing problem. After transformation, the continuous optimization methods can be applied. We devise the algorithms based on the idea of DC (difference of convex functions) programming to solve this problem. The proposed continuous hashing scheme can be easily applied to the existing hashing models, including both supervised and unsupervised hashing. We evaluate the proposed method on several benchmarks and the results show the superiority of the proposed method compared with the state-of-the-art hashing methods.

Adversarial Examples for Hamming Space Search

Due to its strong representation learning ability and its facilitation of joint learning for representation and hash codes, deep learning-to-hash has achieved promising results and is becoming increasingly popular for the large-scale approximate nearest neighbor search. However, recent studies highlight the vulnerability of deep image classifiers to adversarial examples; this also introduces profound security concerns for deep retrieval systems. Accordingly, in order to study the robustness of modern deep hashing models to adversarial perturbations, we propose hash adversary generation (HAG), a novel method of crafting adversarial examples for Hamming space search. The main goal of HAG is to generate imperceptibly perturbed examples as queries, whose nearest neighbors from a targeted hashing model are semantically irrelevant to the original queries. Extensive experiments prove that HAG can successfully craft adversarial examples with small perturbations to mislead targeted hashing models. The transferability of these perturbations under a variety of settings is also verified. Moreover, by combining heterogeneous perturbations, we further provide a simple yet effective method of constructing adversarial examples for black-box attacks.

SCH-GAN: Semi-Supervised Cross-Modal Hashing by Generative Adversarial Network

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.

Zero-Shot Learning via Latent Space Encoding

Zero-shot learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and the class semantic modality (e.g., attributes or word vector) is a key to the success of ZSL. In this paper, we propose a novel encoder-decoder approach, namely latent space encoding (LSE), to connect the semantic relations of different modalities. Instead of requiring a projection function to transfer information across different modalities like most previous work, LSE performs the interactions of different modalities via a feature aware latent space, which is learned in an implicit way. Specifically, different modalities are modeled separately but optimized jointly. For each modality, an encoder-decoder framework is performed to learn a feature aware latent space via jointly maximizing the recoverability of the original space from the latent space and the predictability of the latent space from the original space. To relate different modalities together, their features referring to the same concept are enforced to share the same latent codings. In this way, the common semantic characteristics of different modalities are generalized with the latent representations. Another property of the proposed approach is that it is easily extended to more modalities. Extensive experimental results on four benchmark datasets [animal with attribute, Caltech UCSD birds, aPY, and ImageNet] clearly demonstrate the superiority of the proposed approach on several ZSL tasks, including traditional ZSL, generalized ZSL, and zero-shot retrieval.