Distributed Adaptive Binary Quantization for Fast Nearest Neighbor Search

• Published in: IEEE transactions on image processing Vol. 26; no. 11; pp. 5324 - 5336
• Main Authors: Liu, Xianglong, Li, Zhujin, Deng, Cheng, Tao, Dacheng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2017
• Subjects: Binary codes; binary quantization; distributed learning; Encoding; Hypercubes; Locality-sensitive hashing; nearest neighbor search; Nearest neighbor searches; product quantization; Prototypes; Quantization (signal); Training

Hashing has been proved an attractive technique for fast nearest neighbor search over big data. Compared with the projection based hashing methods, prototype-based ones own stronger power to generate discriminative binary codes for the data with complex intrinsic structure. However, existing prototy...