Joint learning based deep supervised hashing for large-scale image retrieval

Hashing has been widely used for large-scale image retrieval due to its high storage efficiency and fast calculation speed. Recent works have found that deep-supervised hashing methods are superior to nondeep-supervised hashing methods and unsupervised hashing methods in many applications. However, the previous deep-supervised hashing only uses the training set to learn the hash function, which results in that the discrete hash codes corresponding to the retrieval image set and the query image set are derived from the trained hash function. The retrieval image set did not participate in the training and learning of the network. Hence, it is difficult to acquire the real discrete hash code of the retrieval image. In addition, the traditional deep-supervised hashing methods failed to make full use of the supervised information. In this paper, we propose a novel deep supervised hashing method called Joint Learning Based Deep Supervised Hashing (JLDSH). It joints the image classification and hash function learning into the same end-to-end neural network framework. In the training process, we randomly select a subset from the retrieval image set to learn the hash function. The hash code of the entire retrieval image set is directly calculated by the trained hash code of the subset. Meanwhile, JLDSH sets a hyper-parameter on the supervised information to make the output of the network closer to the real discrete hash code. Furthermore, by adding a new loss function, an extended JLDSH-A model is proposed to make the image representation obtained by network training more discrete. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance on benchmark datasets. (C) 2019 Published by Elsevier B.V.