Hierarchical Spherical Hashing for Compressing High Dimensional Vectors

Abstract

We present a hierarchical approach to compress large dimensional vectors using hyperspherical hashing functions. We provide a practical solution for learning hyperspherical hashing functions by partitioning the vectors and learning hyperspheres in subspaces. Our method is an efficient way to preserve the hashing properties of sub-space hashing functions to generate the full-hashing functions in a divide and conquer fashion. We demonstrate the performance of our approach on the ILSVRC2010 Validation dataset and two large scale datasets: ILSVRC2010 Train and Holidays+Flickr 1M with high dimensional representations of size 128000, 25600 and 12800 respectively. Our results highlight the compact nature of hyperspherical hashing functions which significantly outperform the state-of-the art methods at compression ratios of 512, 256 and 128. Furthermore, we boost the retrieval performance by introducing an assymetric distance for spherical hashing functions.