Semi-supervised discrete hashing for efficient cross-modal retrieval

Abstract

Cross-modal hashing has recently gained significant popularity to facilitate multimedia retrieval across different modalities. Since the acquisition of large-scale labeled training data are very labor intensive, most supervised cross-modal hashing methods are uncompetitive for real applications. With limited label available, this paper presents a novel S emi-S upervised D iscrete H ashing (SSDH) for efficient cross-modal retrieval. In contrast to most semi-supervised cross-modal hashing works that need to predict the label of unlabeled data, our proposed approach groups the labeled and unlabeled data together, and exploits the informative unlabeled data to promote hashing code learning directly. Specifically, the proposed SSDH approach utilizes the relaxed hash representations to characterize each modality, and learns the semi-supervised semantic-preserving regularization to correlate the semantic consistency between the heterogeneous modalities. Accordingly, an efficient objective function is proposed to learn the hash representation, while designing an efficient optimization algorithm to optimize the hash codes for both labeled and unlabeled data. Without sacrificing the retrieval performance, the proposed SSDH method is adaptive to benefit various kinds of retrieval tasks, i.e., unsupervised, semi-supervised and supervised. Experimental results compared with several competitive algorithms show the effectiveness of the proposed method and its superiority over state-of-the-arts.