Feature hashing

About: Feature hashing is a research topic. Over the lifetime, 993 publications have been published within this topic receiving 51462 citations.

Deep Residual Hashing.

Abstract: Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted features followed by a separate binarization step to generate hash codes. This two-stage process may produce sub-optimal encoding. In this paper, for the first time, we propose a deep architecture for supervised hashing through residual learning, termed Deep Residual Hashing (DRH), for an end-to-end simultaneous representation learning and hash coding. The DRH model constitutes four key elements: (1) a sub-network with multiple stacked residual blocks; (2) hashing layer for binarization; (3) supervised retrieval loss function based on neighbourhood component analysis for similarity preserving embedding; and (4) hashing related losses and regularisation to control the quantization error and improve the quality of hash coding. We present results of extensive experiments on a large public chest x-ray image database with co-morbidities and discuss the outcome showing substantial improvements over the latest state-of-the art methods.

On the Use of Hash Tables for Efficient Analog Circuit Synthesis

Abstract: Achieving accurate and speedy circuit sizing is a challenge in automated analog synthesis. System matrix model based estimators predict circuit performance accurately. In this paper we employ hashing in conjunction with matrix models for faster synthesis convergence. With hash tables some matrix element recomputations are avoided, thus improving synthesis time. Hashing is effectively performed by dividing matrix elements into classes and building class-wise hash tables. Hash tables are updated over several synthesis runs which further expedites convergence. Experimental results show that the proposed method can provide 4x-6x speedup over that offered by synthesis approaches employing macromodels but no hashing.

Perfect Consistent Hashing.

Abstract: Consistent Hashing functions are widely used for load balancing across a variety of applications. However, the original presentation and typical implementations of Consistent Hashing rely on randomised allocation of hash codes to keys which results in a flawed and approximately-uniform allocation of keys to hash codes. We analyse the desired properties and present an algorithm that perfectly achieves them without resorting to any random distributions. The algorithm is simple and adds to our understanding of what is necessary to create a consistent hash function.

Spatial min-Hash for similar image search

Abstract: We propose a spatial min-Hash algorithm that groups the minimal hashing functions into an s-tuples called a sketch depending on the spatial context. We use the bag-of-words technology to represent an image in a spatial pyramid way, and generate a minimal hashing function for each spatial location of the corresponding level. These minimal hashing functions are bundled to form a sketch. Furthermore, we implement the proposed algorithm to similar image searching. We use the binary SIFT combined with Hamming distance to verify the candidate images obtained by the spatial min-Hash in order to improve the retrieval performance. There are two advantages of our method: 1) the spatial min-Hash is more discriminative than the standard min-Hash in term of image representation; 2) the feature matching based on the binary SIFT in the verification stage improves the performance of image retrieval with a low computational cost. We implement our method on Oxford building dataset, and the experimental results demonstrate that the spatial min-Hash is a stronger representation method than the standard min-Hash, and the spatial min-Hash is superior to the standard min-Hash in term of retrieval performance.

Robust image authentication via locality sensitive hashing with core alignment

Abstract: Robust image hashing is a promising technique to represent image’s perceptual content. However, when it comes to image authentication, tradeoff between robustness and discrimination is a non-negligible issue. The allowed content preserving operations and sensitive malicious manipulations on images are quite subjective to human’s perception. So it needs tactics to design good hashing methods. In this paper we incorporate the novel concept of core alignment into hashing, where the proposed core alignment improves the performances of balance. First, we formulize the hashing as a supervised minimal optimization problem based on Locality Sensitive Hashing, in which p-stable distribution is exploited to maintain high dimensional locality features. Then we solve this problem by two sub-optimization problems, i.e., searching for optimal shift and searching for optimal quantization intervals. By using particle swarm optimization and simulated annealing programming approaches we develop two stochastic solutions to those two problems, respectively. Experimental results show that our proposed hashing optimizations can find optimal solutions with limited steps, and the hashing method is superior to other state-of-the-art methods in terms of authentication and robustness.