Triple-Bit Quantization with Asymmetric Distance for Nearest Neighbor Search

Abstract

Binary embedding is an effective way for nearest neighbor (NN) search as binary code is storage efficient and fast to compute. It tries to convert real-value signatures into binary codes while preserving similarity of the original data, and most binary embedding methods quantize each projected dimension to one bit (presented as 0/1). As a consequence, it greatly decreases the discriminability of original signatures. In this paper, we first propose a novel quantization strategy triple-bit quantization (TBQ) to solve the problem by assigning 3-bit to each dimension. Then, asymmetric distance (AD) algorithm is applied to re-rank candidates obtained from hamming space for the final nearest neighbors. For simplicity, we call the framework triple-bit quantization with asymmetric distance (TBAD). The inherence of TBAD is combining the best of binary codes and real-value signatures to get nearest neighbors quickly and concisely. Moreover, TBAD is applicable to a wide variety of embedding techniques. Experimental comparisons on BIGANN set show that the proposed method can achieve remarkable improvement in query accuracy compared to original binary embedding methods.