Deep Hashing with Attribute Guidance for Image Retrieval

Abstract

Similarity-preserving hashing is an important method to solve approximate nearest neighbour search problem for image retrieval. Lots of works have been proposed for supervised hashing and image category labels are utilized as supervised information. However, current works ignore a fact that images can be described by a set of attributes. Intuitively, images of different categories with close visual features can be separated by their attribute features because attributes keep more detailed information. In this paper, we propose a novel supervised deep hashing method with image attribute guidance. Specifically, hash codes are learnt through image visual features and guided by image attributes by maintaining pair wise similarities between images as well as the corresponding attribute descriptions. Extensive experimental results on two benchmark datasets show that our proposed method achieves better performance compared with the state of the art hashing methods.