Spatial pyramid VLAD

Abstract

In recent years, VLAD has become a popular method which encoding powerful local descriptors to the compact representations. By using this approach, an image can be represented by just a few dozen bytes while preserving excellent retrieval results after the dimensionality reduction and compression. However, throwing away the spatial information is one of the biggest weaknesses of VLAD. This paper adopts the spatial pyramid pooling method to incorporate the spatial information into the VLAD vectors. Furthermore, a new normalization method is proposed to hold this advantage. By the proposed method, the performance of VLAD can be boosted through combining spatial information. The experimental results show that our approach outperforms VLAD in almost all configurations.