Kernelised supervised context hashing. Issue 12 (1st December 2016)

• Record Type: Journal Article
• Authors: Li, Yun‐Qiang; Zha, Yu‐Fei; Qin, Bing; Tian, Jun; Liu, Chang
• Is Part Of: IET image processing. Volume 10:Issue 12(2016)
• Page Start: 986
• Page End: 995
• Publication Date: 2016-12-01
• Subjects: data structures -- learning (artificial intelligence) -- image retrieval -- binary codes -- gradient methods -- approximation theory -- quantisation (signal); kernelised supervised context hashing -- affinity‐preserving binary codes -- high‐dimensional data representation -- hashing code -- hashing bits -- context association -- quantisation reduction -- gradient descent method -- metric measurement -- Hamming affinity -- data similarity preservation -- CIFAR‐10 image benchmark -- MNIST image benchmark -- NUS‐WIDE image benchmark; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2015.0848
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Most existing supervised hashing methods learn the affinity‐preserving binary codes to represent the high‐dimensional data. However, each hashing code is assumed as independent and irrelevant with other codes. In practice, the authors find that there exists context association among hashing bits. This study proposes a novel hashing method dubbed kernelised supervised context hashing, which considers the hashing codes interrelation to reduce the quantisation. In this work, the kernel formulation is employed to tackle the high‐dimensional data which is mostly linear inseparable first; and then different distributions are utilised to describe the binary codes context; finally, the hashing codes can be approximated by gradient descent method iteratively. Therefore, the correlation between the hash codes is integrated to redefine the metric measurement (i.e. Hamming affinity) to preserve the data similarity in the raw space. The authors evaluate the proposed method on three image benchmarks CIFAR‐10, MNIST and NUS‐WIDE for image retrieval, and experimental results show that it achieves better performance than several other state‐of‐the‐art methods.