当前位置: X-MOL 学术Inf. Process. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Enhanced Deep Discrete Hashing with semantic-visual similarity for image retrieval
Information Processing & Management ( IF 8.6 ) Pub Date : 2021-06-01 , DOI: 10.1016/j.ipm.2021.102648
Zhan Yang , Liu Yang , Wenti Huang , Longzhi Sun , Jun Long

Hashing has been shown to be successful in a number of Approximate Nearest Neighbor (ANN) domains, ranging from medicine, computer vision to information retrieval. However, current deep hashing methods either ignore both rich information of labels and visual linkages of image pairs, or leverage relaxation-based algorithms to address discrete problems, resulting in a large information loss. To address the aforementioned problems, in this paper, we propose an Enhanced Deep Discrete Hashing (EDDH) method to leverage both label embedding and semantic-visual similarity to learn the compact hash codes. In EDDH, the discriminative capability of hash codes is enhanced by a distribution-based continuous semantic-visual similarity matrix, where not only the margin between the positive pairs and negative pairs is expanded, but also the visual linkages between image pairs is considered. Specifically, the semantic-visual continuous similarity matrix is constructed by analyzing the asymmetric generalized Gaussian distribution of the visual linkages between pairs with label consideration. Besides, in order to achieve an efficient hash learning framework, EDDH employs an asymmetric real-valued learning structure to learn the compact hash codes. In addition, we develop a fast discrete optimization algorithm, which can directly generate discrete binary codes in single step, and introduce an intermediate term before iterations to avoid the problems caused by directly the use of large semantic-visual similarity matrix, which results in a significant reduction in the computational overhead. Finally, we conducted extensive experiments on three datasets to show that EDDH has a significantly enhanced performance compared to the compared state-of-the-art baselines.



中文翻译:

用于图像检索的具有语义-视觉相似性的增强型深度离散哈希

散列已被证明在许多近似最近邻 (ANN) 领域取得成功,从医学、计算机视觉到信息检索。然而,当前的深度哈希方法要么忽略标签的丰富信息和图像对的视觉链接,要么利用基于松弛的算法来解决离散问题,导致大量信息丢失。为了解决上述问题,在本文中,我们提出了一个Ë nhanced d EEP d iscrete ^ h灰化(EDDH)方法利用标签嵌入和语义视觉相似性来学习紧凑的哈希码。在 EDDH 中,基于分布的连续语义-视觉相似度矩阵增强了哈希码的判别能力,其中不仅扩大了正负对之间的余量,还考虑了图像对之间的视觉联系。具体而言,语义-视觉连续相似度矩阵是通过分析对之间视觉联系的非对称广义高斯分布,并考虑标签来构建的。此外,为了实现高效的哈希学习框架,EDDH 采用非对称实值学习结构来学习紧凑的哈希码。此外,我们开发了一种快速离散优化算法,可以直接一步生成离散的二进制代码,并在迭代前引入中间项,避免了直接使用大的语义视觉相似矩阵带来的问题,从而显着降低了计算开销。最后,我们对三个数据集进行了大量实验,以表明与比较的最先进基线相比,EDDH 具有显着增强的性能。

更新日期:2021-06-01
down
wechat
bug