Semantics-preserving hashing based on multi-scale fusion for cross-modal retrieval

Research on hash-based cross-modal retrieval has been a hotspot in the field of content-based multimedia retrieval research. Most deep cross-modal hashing methods only consider inter-modal loss that can remain local information of training data, and ignore the loss within data samples of the same modality that can remain the global information of dataset. In addition, they also ignore the factor that different scales of single modal data contain different semantic information, which affects the representation of data features. In this paper, we propose a semantics-preserving hashing method based on multi-scale fusion. More concretely, a multi-scale fusion pooling model is proposed for both image feature training network and text feature training network. Therefore, we can extract the multi-scale features of image dataset and solve the sparsity problem of text BOW vectors. When constructing the loss function, we consider intra-modal loss while considering inter-modal loss. Therefore, the output hash code retains both global and local underlying semantic correlation when image and text feature training network are trained. Experiment results on NUS-WIDE and MIRFlickr-25 K prove that against other existing methods, our algorithm improves cross-modal retrieval accuracy.