Google Research

Learning Binary Codes for High Dimensional Data Using Bilinear Projections

IEEE Computer Vision and Pattern Recognition (2013)

Abstract

Recent advances in visual recognition indicate that to achieve good retrieval and classification accuracy on large scale datasets like ImageNet, extremely high-dimensional visual descriptors, e.g., Fisher Vectors, are needed. We present a novel method for converting such descriptors to compact similarity-preserving binary codes that exploits their natural matrix structure to reduce their dimensionality using compact bilinear projections instead of a single large projection matrix. This method achieves comparable retrieval and classification accuracy to the original descriptors and to the state-of-the-art Product Quantization approach while having orders of magnitude faster code generation time and smaller memory footprint.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work