IEEE Trans Image Process. 2018 Apr;27(4):1626-1638. doi: 10.1109/TIP.2017.2781422.
In order to achieve efficient similarity searching, hash functions are designed to encode images into low-dimensional binary codes with the constraint that similar features will have a short distance in the projected Hamming space. Recently, deep learning-based methods have become more popular, and outperform traditional non-deep methods. However, without label information, most state-of-the-art unsupervised deep hashing (DH) algorithms suffer from severe performance degradation for unsupervised scenarios. One of the main reasons is that the ad-hoc encoding process cannot properly capture the visual feature distribution. In this paper, we propose a novel unsupervised framework that has two main contributions: 1) we convert the unsupervised DH model into supervised by discovering pseudo labels; 2) the framework unifies likelihood maximization, mutual information maximization, and quantization error minimization so that the pseudo labels can maximumly preserve the distribution of visual features. Extensive experiments on three popular data sets demonstrate the advantages of the proposed method, which leads to significant performance improvement over the state-of-the-art unsupervised hashing algorithms.
为了实现高效的相似性搜索，哈希函数被设计成将图像编码成低维二进制代码，其约束条件是相似的特征在投影的汉明空间中具有短距离。最近，基于深度学习的方法变得越来越流行，并且优于传统的非深度学习方法。然而，在没有标签信息的情况下，大多数最先进的无监督深度哈希（DH）算法在无监督场景下的性能严重下降。主要原因之一是，特定于任务的编码过程不能正确地捕获视觉特征分布。在本文中，我们提出了一个新颖的无监督框架，主要有两个贡献：1）通过发现伪标签，将无监督 DH 模型转换为有监督；2）该框架统一了似然最大化、互信息最大化和量化误差最小化，以便伪标签可以最大程度地保留视觉特征的分布。在三个流行的数据集中进行的广泛实验证明了该方法的优势，与最先进的无监督哈希算法相比，该方法显著提高了性能。
