Deep semantic preserving hashing for large scale image retrieval

被引：0
作者：
Masoumeh Zareapoor
Jie Yang
Deepak Kumar Jain
Pourya Shamsolmoali
Neha Jain
Surya Kant
机构：
[1] Shanghai Jiao Tong University,Institute Image Processing & Pattern Recognition
[2] Chinese Academy of Sciences,Institute of Automation
[3] Jaypee University of Engineering and Technology,undefined
[4] India Institute of Technology,undefined
来源：
Multimedia Tools and Applications | 2019年 / 78卷
关键词：
Convolutional auto-encoder; Image hashing; Image retrieval; Deep learning; Similarity search; Learning to hash;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Hashing approaches have got a great attention because of its efficient performance for large-scale images. This paper, aims to propose a deep hashing method which can combines stacked convolutional autoencoder with hashing learning, where the input image hierarchically maps to the low dimensional space. The proposed method DCAH contains encoder-decoder, and supervisory sub-network, that generates a low dimensional binary code in a layer-wised manner of the deep conventional neural network. To optimizing the hash algorithm, we added some extra relaxations constraint to the objective function. In our extensive experiments on ultra-high dimensional image datasets, our results demonstrate that the decoder structure can improve the hashing method to preserve the similarities in hashing codes; also, DCAH achieves the best performance comparing to other states of the art approaches.
引用
收藏
页码：23831 / 23846
页数：15
相关论文
共 45 条
  • [1] Alvear-Sandoval RF(2018)On building ensembles of stacked denoising auto-encoding classifiers and their further improvement Information Fusion 39 4152-4152
  • [2] Figueiras-Vidal AR(2016)Deep unsupervised clustering with gaussian mixture variational autoencoders arXiv preprint arXiv 1611.02648-2929
  • [3] Dilokthanakul N(2016)Tutorial on variational autoencoders arXiv preprint arXiv 1606.05908-1104
  • [4] Mediano PAM(2013)Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval IEEE Trans PAMI 35 2916-2324
  • [5] Garnelo M(2012)Kernelized localitysensitive hashing IEEE Trans Pattern Anal Mach Intell 34 1092-2536
  • [6] Lee MCH(1998)Gradient-based learning applied to document recognition Proc IEEE 86 2278-175
  • [7] Salimbeni H(2016)Sequential compact code learning for unsupervised image hashing IEEE Trans Neural Netw learn Syst 27 2526-277
  • [8] Kai A(2001)Modeling the shape of the scene: a holistic representation of the spatial en-velope Int J Comput Vis 42 145-2840
  • [9] Shanahan M(2012)Sparse spectral hashing Pattern Recogn Lett 33 271-3408
  • [10] Doersch C(2015)Neighborhood discriminant hashing for large-scale image retrieval IEEE TIP 24 2827-21
12345