Self-supervised asymmetric deep hashing with margin-scalable constraint for image retrieval

Due to its effectivity and efficiency, image retrieval based on deep hashing approaches is widely used especially for large-scale visual search. However, many existing deep hashing methods inadequately utilize label information as guidance for feature learning networks without more advanced exploration of the semantic space. Besides the similarity correlations in the Hamming space are not fully discovered and embedded into hash codes, by which the retrieval quality is diminished with inefficient preservation of pairwise correlations and multi-label semantics. To cope with these problems, we propose a novel self-supervised asymmetric deep hashing method with a margin-scalable constraint(SADH) approach for image retrieval. SADH implements a self-supervised network to preserve semantic information in a semantic feature map and a semantic code map for the semantics of the given dataset, which efficiently and precisely guides a feature learning network to preserve multi-label semantic information using an asymmetric learning strategy. Moreover, for the feature learning part, by further exploiting semantic maps, a new margin-scalable constraint is employed for both highly-accurate construction of pairwise correlations in the hamming space and a more discriminative hash code representation. Extensive empirical research on three benchmark datasets validates the proposed method and shows it outperforms several state-of-the-art approaches.