Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval
This work addresses the need for better semantic discriminative ability in hashing for image retrieval, though it appears incremental by building on existing deep supervised hashing approaches.
The paper tackles the problem of preserving semantic similarity in large-scale image retrieval by introducing a hierarchy neighborhood discriminative hashing method that unifies single-label and multi-label retrieval, demonstrating improved performance over state-of-the-art methods on two large-scale datasets.
Recently, deep supervised hashing methods have become popular for large-scale image retrieval task. To preserve the semantic similarity notion between examples, they typically utilize the pairwise supervision or the triplet supervised information for hash learning. However, these methods usually ignore the semantic class information which can help the improvement of the semantic discriminative ability of hash codes. In this paper, we propose a novel hierarchy neighborhood discriminative hashing method. Specifically, we construct a bipartite graph to build coarse semantic neighbourhood relationship between the sub-class feature centers and the embeddings features. Moreover, we utilize the pairwise supervised information to construct the fined semantic neighbourhood relationship between embeddings features. Finally, we propose a hierarchy neighborhood discriminative hashing loss to unify the single-label and multilabel image retrieval problem with a one-stream deep neural network architecture. Experimental results on two largescale datasets demonstrate that the proposed method can outperform the state-of-the-art hashing methods.