Semi-Supervised Metric Learning-Based Anchor Graph Hashing for Large-Scale Image Retrieval
Semi-Supervised Metric Learning-Based Anchor Graph Hashing for Large-Scale Image Retrieval
复制标题
用于大规模图像检索的基于半监督度量学习的锚图哈希
DOI：
10.1109/tip.2018.2860898
复制
发表时间：
2019
影响因子：
10.6
通讯作者：
Yang Zhen
中科院分区：
文献类型：
--
作者：
Hu Haifeng;Wang Kun;Lv Chenggang;Wu Jiansheng;Yang Zhen
基于哈希的图像检索方法以其高效、低成本的特点成为信息检索领域的前沿课题。为了通过同时保留特征空间中的语义相似性和数据结构来进行有效的哈希学习，本文提出了基于半监督度量学习的锚图哈希方法。我们提出的方法可以分为三个部分。首先，我们利用变换矩阵来构建训练集的基于锚的相似度图。其次，我们提出了基于三元组关系的目标函数，其中可以利用标签的平滑度和三元组约束引起的边缘铰链损失来学习最优变换矩阵。此外，随机梯度下降（SGD）方法利用每个三元组上的梯度来更新变换矩阵。最后设计了惩罚因子来加快SGD的执行速度。通过与几种最先进的方法在多个图像基准上的检索结果进行比较，实验验证了我们提出的方法的可行性和优势。
Hashing-based image retrieval methods have become a cutting-edge topic in the information retrieval domain due to their high efficiency and low cost. In order to perform efficient hash learning by simultaneously preserving the semantic similarity and data structures in the feature space, this paper presents the semi-supervised metric learning-based anchor graph hashing method. Our proposed approach can be divided into three parts. First, we exploit a transformation matrix to construct the anchor-based similarity graph of the training set. Second, we propose the objective function based on the triplet relationship, in which the optimal transformation matrix can be learned by using the smoothness of labels and the margin hinge loss incurred by the triplet constraint. Moreover, the stochastic gradient descent (SGD) method leverages the gradient on each triplet to update the transformation matrix. Finally, a penalty factor is designed to accelerate the execution speed of SGD. Through comparison with the retrieval results of several state-of-the-art methods on several image benchmarks, the experiments validate the feasibility and advantages of our proposed methods.