当前位置: X-MOL 学术IEEE Trans. Circ. Syst. Video Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Bilinear Supervised Hashing Based on 2D Image Features
IEEE Transactions on Circuits and Systems for Video Technology ( IF 8.4 ) Pub Date : 2019-01-01 , DOI: 10.1109/tcsvt.2019.2891246
Yujuan Ding , Wai Kueng Wong , Zhihui Lai , Zheng Zhang

Hashing has been recognized as an efficient representation learning method to effectively handle big data due to its low computational complexity and memory cost. Most of the existing hashing methods focus on learning the low-dimensional vectorized binary features based on the high-dimensional raw vectorized features. However, the studies on how to obtain preferable binary codes from the original 2D image features for retrieval is very limited. This paper proposes a bilinear supervised discrete hashing (BSDH) method based on 2D image features which utilizes bilinear projections to binarize the image matrix features such that the intrinsic characteristics in the 2D image space are preserved in the learned binary codes. Meanwhile, the bilinear projection approximation and vectorization binary codes regression are seamlessly integrated together to formulate the final robust learning framework. Furthermore, a discrete optimization strategy is developed to alternatively update each variable for obtaining the high-quality binary codes. In addition, two 2D image features, traditional SURF-based FVLAD feature, and CNN-based AlexConv5 feature are designed for further improving the performance of the proposed BSDH method. The results of extensive experiments conducted on four benchmark datasets show that the proposed BSDH method almost outperforms all competing hashing methods with different input features by different evaluation protocols.

中文翻译:

基于二维图像特征的双线性监督哈希

由于其计算复杂度和内存成本低,散列已被公认为有效处理大数据的有效表示学习方法。现有的散列方法大多侧重于在高维原始矢量化特征的基础上学习低维矢量化二值特征。然而,关于如何从原始二维图像特征中获取优选的二进制代码进行检索的研究非常有限。本文提出了一种基于二维图像特征的双线性监督离散散列 (BSDH) 方法,该方法利用双线性投影对图像矩阵特征进行二值化,从而在学习的二进制代码中保留二维图像空间中的内在特征。同时,双线性投影近似和矢量化二进制代码回归无缝集成在一起,以制定最终的稳健学习框架。此外,开发了一种离散优化策略来交替更新每个变量以获得高质量的二进制代码。此外,设计了两个二维图像特征,传统的基于 SURF 的 FVLAD 特征和基于 CNN 的 AlexConv5 特征,以进一步提高所提出的 BSDH 方法的性能。在四个基准数据集上进行的大量实验的结果表明,所提出的 BSDH 方法几乎优于具有不同评估协议的具有不同输入特征的所有竞争散列方法。开发了一种离散优化策略来交替更新每个变量以获得高质量的二进制代码。此外,设计了两个二维图像特征,传统的基于 SURF 的 FVLAD 特征和基于 CNN 的 AlexConv5 特征,以进一步提高所提出的 BSDH 方法的性能。在四个基准数据集上进行的大量实验的结果表明,所提出的 BSDH 方法几乎优于所有具有不同评估协议的具有不同输入特征的竞争散列方法。开发了一种离散优化策略来交替更新每个变量以获得高质量的二进制代码。此外,设计了两个二维图像特征,传统的基于 SURF 的 FVLAD 特征和基于 CNN 的 AlexConv5 特征,以进一步提高所提出的 BSDH 方法的性能。在四个基准数据集上进行的大量实验的结果表明,所提出的 BSDH 方法几乎优于具有不同评估协议的具有不同输入特征的所有竞争散列方法。
更新日期:2019-01-01
down
wechat
bug