Diversity Regularized Latent Semantic Match for Hashing

详细信息    查看全文

• 作者：Yong Chen^aAuthor Vitae ; Hui Zhang^a ; ^{hzhang@buaa.edu.cn}Author Vitae ; Yongxin Tong^aAuthor Vitae ; Ming Lu^b ; ^{ming-lu@outlook.com}Author Vitae
• 关键词：Diversity regularizations ; Soft orthogonality ; Learning to match ; Multimodal retrieval ; Representation learning ; Approximate nearest neighbors
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：22 March 2017
• 年：2017
• 卷：230
• 期：Complete
• 页码：77-87
• 全文大小：2396 K
• 卷排序：230

文摘

Hashing based approximate nearest neighbors (ANN) search has drawn considerable attraction owing to its low-memory storage and hardware-level logical computing which is doomed to be greatly applicable to quantities of large-scale and practical scenarios, such as information retrieval, computer vision and natural language processing. However, most existing hashing methods concentrate either on images only or on pairwise image-texts (labels, short documents) and rarely utilize more common sentences. In this paper, we propose D iversity R egularized L atent S emantic M atch for H ashing (DRLSMH), a new multimodal hashing method that projects images and sentences into a shared latent semantic space with label-supervised semantic constraints to proceed on multimodal retrieval. Notably, soft orthogonality is induced as a novel regularizer to preserve diverse hashing functions for compact and accurate representations; what's more, this kind of regularization also benefits the derivations of closed-form solutions with some proper relaxations under iterative optimization framework. Extensive experiments on two public datasets demonstrate the advantages of our method over some state-of-the-art baselines under cross-modal retrieval both on image-query-image, image-query-text and text-query-image tasks.