基于多特征多核哈希学习的大规模图像检索

Large-scale image retrieval based on multi-feature and multi-kernel hashing learning

哈希学习方法解决了图像大数据的检索效率低,存储代价高的问题.目前已有的核哈希方法中,要么仅使用一种特征对应单个核函数,要么是多特征对应单个核函数,它们忽视了综合考虑不同的核函数具有的不同作用和不同的特征包含不同的信息的事实.本文提出了一种自适应的多特征多核的哈希学习算法(MFMKH),该算法能够自适应学习多特征融合的权重系数和多核融合的权重系数,将多特征和多核的优点进行了双重融合.本算法中的特征融合解决了单特征所包含的信息量单一不足的问题,采用多种不同的核函数能够弥补单核学习能力上的不足,具有多特征自适应融合和多核学习的双重优点.在标准的IRMA,Ultrasound和Cifar10数据集上的实验表明,本文算法检索性能明显优于同类基于核的哈希学习方法,且与监督的深度哈希相比训练时间显著少的情况下检索性能在Cifar10数据集上是可竞争的.

Hashing methods can overcome the problems of low retrieval efficiency and high storage cost. Existing hashing methods use either only one feature or multiple features as the input of one kernel function. The fact that different kernel functions have different roles and different characteristics and contain different information is ignored. In this paper, an adaptive multi-feature and multi-kernel hashing learning（MFMKH） algorithm is proposed, which can adaptively combine the feature weight coefficient and the kernel weight coefficient and doublecombine the multi-feature and multi-kernel advantages. The fusion of these features in the algorithm solves the disadvantage of single feature containing insufficient information. In addition, the use of a variety of different kernel functions can compensate for the lack of a single-kernel learning ability and has the dual advantages of multi-feature fusion and multi-kernel learning. Experiments on the standard datasets IRMA, Ultrasound, and Cifar10 have shown that the retrieval performance of the proposed method clearly outperforms other similar kernel-based hashing learning methods. In addition, compared to the supervised deep hashing, the retrieval performance of the proposed method is competitive on the Cifar10 dataset in the case of the reduced training time.