Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search
share
In this paper, we present a new cluster-wise unsupervised hashing (CUH) approach to learn compact binary codes for cross-modal similarity retrieval. We develop a discrete optimization method to jointly learn binary codes and the corresponding hash functions for each modality which can improve the performance, unlike existing cross-modal hashing methods that often drop the binary constraints to obtain the binary codes. Moreover, considering the semantic consistency between observed modalities, our CUH generates one unified hash code for all observed modalities of any instance. Specifically, we construct a co-training framework for learning to hash, in which we simultaneously realize the multi-view clustering and the learning of hash. Firstly, our CUH utilize the re-weighted discriminatively embedded K-means for multi-view clustering to learn the corresponding dimension reduced data and the cluster centroid points in the low-dimensional common subspaces, which are used as the approximation to the corresponding hash codes of original data and the cluster-wise code-prototypes respectively. Secondly, in the process for learning of hash, these cluster-wise code-prototypes can guide the learning of the codes to further improve the performance of the binary codes. The reasonableness and effectiveness of CUH is well demonstrated by comprehensive experiments on diverse benchmark datasets.
READ FULL TEXT