Approximate Asymmetric Search for Binary Embedding Codes

Abstract

In this article, we propose a method of approximate asymmetric nearest-neighbor search for binary embedding codes. The asymmetric distance takes advantage of less information loss at the query side. However, calculating asymmetric distances through exhaustive search is prohibitive in a large-scale dataset. We present a novel method, called multi-index voting, that integrates the multi-index hashing technique with a voting mechanism to select appropriate candidates and calculate their asymmetric distances. We show that the candidate selection scheme can be formulated as the tail of the binomial distribution function. In addition, a binary feature selection method based on minimal quantization error is proposed to address the memory insufficiency issue and improve the search accuracy. Substantial experimental evaluations were made to demonstrate that the proposed method can yield an approximate accuracy to the exhaustive search method while significantly accelerating the runtime. For example, one result shows that in a dataset of one billion 256-bit binary codes, examining only 0.5% of the dataset, can reach 95--99% close accuracy to the exhaustive search method and accelerate the search by 73--128 times. It also demonstrates an excellent tradeoff between the search accuracy and time efficiency compared to the state-of-the-art nearest-neighbor search methods. Moreover, the proposed feature selection method shows its effectiveness and improves the accuracy up to 8.35% compared with other feature selection methods.

Learning to Index for Nearest Neighbor Search

“…PQTable [45] was proposed to accelerate exhaustive PQ search by using the concatenation of PQ codes from multiple hash tables to index a data point. Multiindex voting [46] employs a voting mechanism to generate high-quality NN candidates by traversing across multiple hash tables derived from the intermediate spaces.…”