Accumulative Quantization for Approximate Nearest Neighbor Search

Abstract

To further improve the approximate nearest neighbor (ANN) search performance, an accumulative quantization (AQ) is proposed and applied to effective ANN search. It approximates a vector with the accumulation of several centroids, each of which is selected from a different codebook. To provide accurate approximation for an input vector, an iterative optimization is designed when training codebooks for improving their approximation power. Besides, another optimization is introduced into offline vector quantization procedure for the purpose of minimizing overall quantization errors. A hypersphere-based filtration mechanism is designed when performing AQ-based exhaustive ANN search to reduce the number of candidates put into sorting, thus yielding better search time efficiency. For a query vector, a self-centered hypersphere is constructed, so that those vectors not lying in the hypersphere are filtered out. Experimental results on public datasets demonstrate that hypersphere-based filtration can improve ANN search time efficiency with no weakening of search accuracy; besides, the proposed AQ is superior to the state of the art on ANN search accuracy.

Approximate Nearest Neighbor Search Using Enhanced Accumulative Quantization

“…In our former work [34], after decomposing vectors into partial-vectors of the same dimension, each codebook was trained on partial-vectors. Then, we used accumulative quantization (AQ) to approximate a vector according to the sum of its partial vectors, which we quantized with the corresponding codebook.…”

“…Figure 5 shows the comparison of training error produced by training codebooks between E-AQ and AQ [34] under different parameters on SIFT-1M and GIST-1M. The training error was measured by the MSE, computed according to Formula ( 5).…”

“…We compared our method with six state-of-the-art methods regarding the accuracy of exhaustive ANN search. These methods included PQ [18], OPQ [19], RVQ [30], QPQ [24], NOCQ [28] and AQ [34].…”

“…Residual vector quantization (RVQ) [30] has multiple different low-complexity quantizers to reduce the quantization error sequentially. Moreover, to optimize the effect of quantization, some significant methods [31][32][33] have been proposed to provide modified strategies. On the other hand, an analogous method called accumulative quantization (AQ) [34] also constructs approximations by addition.…”

“…Moreover, to optimize the effect of quantization, some significant methods [31][32][33] have been proposed to provide modified strategies. On the other hand, an analogous method called accumulative quantization (AQ) [34] also constructs approximations by addition.…”