IEEE Project Abstract

With the rapid development of deep learning, deep hashing methods have achieved promising results in efficient information retrieval. The hashing method maps similar data to binary hashcodes with smaller hamming distance, which has received broad attention due to its low storage cost and fast retrieval speed. Most of the existing deep hashing methods adopt pairwise or triplet losses to deal with similarities underlying the data, but their training is difficult and less efficient because O(n 2 ) data pairs and O(n 3 ) triplets are involved. To address these issues, we propose a novel deep hashing algorithm with the unary loss which can be trained very efficiently. First, we introduce a Unary Upper Bound of the traditional triplet loss, thus reducing the complexity to O(n) and bridging the classification-based unary loss and the triplet loss. Second, we propose a novel Semantic Cluster Deep Hashing (SCDH) algorithm by introducing a modified Unary Upper Bound loss, called Semantic Cluster Unary Loss. The resultant hashcodes form several compact clusters, which means the hashcodes in the same cluster have similar semantic information. We also demonstrate that the proposed SCDH is easy to extend to semi-supervised settings by incorporating the state-of-the-art semi-supervised learning algorithms. The experiments on large-scale datasets show that the proposed method is superior to the state-of-the-art hashing algorithms.