Zhu Lei, Huang Zi, Li Zhihui, Xie Liang, Shen Heng Tao
IEEE Trans Neural Netw Learn Syst. 2018 Nov;29(11):5264-5276. doi: 10.1109/TNNLS.2018.2797248. Epub 2018 Feb 14.
Unsupervised hashing can desirably support scalable content-based image retrieval for its appealing advantages of semantic label independence, memory, and search efficiency. However, the learned hash codes are embedded with limited discriminative semantics due to the intrinsic limitation of image representation. To address the problem, in this paper, we propose a novel hashing approach, dubbed as discrete semantic transfer hashing (DSTH). The key idea is to directly augment the semantics of discrete image hash codes by exploring auxiliary contextual modalities. To this end, a unified hashing framework is formulated to simultaneously preserve visual similarities of images and perform semantic transfer from contextual modalities. Furthermore, to guarantee direct semantic transfer and avoid information loss, we explicitly impose the discrete constraint, bit-uncorrelation constraint, and bit-balance constraint on hash codes. A novel and effective discrete optimization method based on augmented Lagrangian multiplier is developed to iteratively solve the optimization problem. The whole learning process has linear computation complexity and desirable scalability. Experiments on three benchmark data sets demonstrate the superiority of DSTH compared with several state-of-the-art approaches.
无监督哈希由于其在语义标签独立性、内存和搜索效率方面具有吸引人的优势，能够理想地支持基于内容的可扩展图像检索。然而，由于图像表示的固有局限性，所学习到的哈希码嵌入的判别语义有限。为了解决这个问题，在本文中，我们提出了一种新颖的哈希方法，称为离散语义转移哈希（DSTH）。关键思想是通过探索辅助上下文模态直接增强离散图像哈希码的语义。为此，制定了一个统一的哈希框架，以同时保留图像的视觉相似性并执行来自上下文模态的语义转移。此外，为了保证直接语义转移并避免信息丢失，我们对哈希码明确施加离散约束、位不相关约束和位平衡约束。开发了一种基于增广拉格朗日乘子的新颖且有效的离散优化方法来迭代求解优化问题。整个学习过程具有线性计算复杂度和理想的可扩展性。在三个基准数据集上的实验证明了DSTH相对于几种现有方法的优越性。
