Deep variational and structural hashing

• Main Authors: Liong, Venice Erin, Lu, Jiwen, Duan, Ling-Yu, Tan, Yap-Peng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering; Scalable Image Search; Fast Similarity Search
• Online Access: https://hdl.handle.net/10356/141944
• Institution: Nanyang Technological University

In this paper, we propose a deep variational and structural hashing (DVStH) method to learn compact binary feature representation inside the network. Then, we design a struct layer rather than a bottleneck hash layer, to obtain binary codes through a simple encoding procedure. By doing these, we are able to obtain binary codes discriminatively and generatively. To make it applicable to cross-modal scalable multimedia retrieval, we extend our method to a cross-modal deep variational and structural hashing (CM-DVStH). We design a deep fusion network with a struct layer to maximize the correlation between image-text input pairs during the training stage so that a unified binary vector can be obtained. We then design modality-specific hashing networks to handle the out-of-sample extension scenario. Specifically, we train a network for each modality which outputs a latent representation that is as close as possible to the binary codes which are inferred from the fusion network. Experimental results on five benchmark datasets are presented to show the efficacy of the proposed approach.