Efficient discrete cross-modal hashing with semantic correlations and similarity preserving

With its merits in query speed and memory footprint, hashing has elicited considerable monument in cross-media similarity retrieval applications. Many label-dependent supervised hashing methods have been proposed for similarity searching across modality boundaries. However, the current cross-modal hashing (CMH) works are subjected to severe information loss, and their performances may dramatically degrade because of the expensive costs of constructing affinity graphs, inadequate mining of label information, and disregarding label correlations. To facilitate these problems, we propose an Efficient Discrete Cross-Modal Hashing (EDCH) in which an asymmetric model is introduced, which not only conveys external semantic information via embedding high-order labels but also preserves internal modality attributes by introducing binary representations and common subspace. To fully use label semantic information, we integrate the semantic supervised intersection scheme and the category correlations embedding in a shallow framework. Moreover, we elaborately develop an efficient and effective discrete optimization strategy to learn binary representations and a novel mutual linear projection to strengthen the capability and effectiveness of hash functions. Comprehensive experiments are conducted on three representative datasets to evaluate our method. The results validated that our method achieved promising and competitive retrieval performance and surpasses several typical and cutting-edge approaches.