Deep supervised hashing using quadratic spherical mutual information for efficient image retrieval

Several deep supervised hashing techniques have been proposed to allow for extracting compact and efficient neural network representations for various tasks. However, many deep supervised hashing techniques ignore several information-theoretic aspects of the process of information retrieval, often leading to sub-optimal results. In this paper, we propose an efficient deep supervised hashing algorithm that optimizes the learned compact codes using an information-theoretic measure, the Quadratic Mutual Information (QMI). The proposed method is adapted to the needs of efficient image hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI). Apart from demonstrating the effectiveness of the proposed method under different scenarios and outperforming existing state-of-the-art image hashing techniques, this paper provides a structured way to model the process of information retrieval and develop novel methods adapted to the needs of different applications.

Automated summary

This paper introduces an efficient deep supervised hashing algorithm that optimizes compact neural network representations using the Quadratic Mutual Information (QMI) and proposes a novel information-theoretic measure, Quadratic Spherical Mutual Information (QSMI), tailored for efficient image hashing and information retrieval. Demonstrating superior performance compared to existing image hashing techniques, the method provides a structured approach to modeling the information retrieval process and developing novel methods for various applications.