Unsupervised deep quantization for object instance search

Unsupervised deep quantization for object instance search
复制标题

用于对象实例搜索的无监督深度量化

DOI:
10.1016/j.neucom.2019.06.088
复制
发表时间:
2019-10
期刊:
影响因子:
6
通讯作者:
Jia Yunde
Jia Yunde
中科院分区:
计算机科学2区
文献类型:
--
作者:
Jiang Wei;Wu Yuwei;Jing Chenchen;Yu Tan;Jia Yunde

文献摘要

参考文献

相似文献

在本文中,我们提出了一种用于对象实例搜索的无监督深度量化(UDQ)方法。UDQ利用乘积量化来发现训练数据的底层自监督信息,并迭代地利用自监督信息以无监督的方式优化训练数据的特征。优化的特征进一步用于更新后续训练过程的自监督信息。我们引入了两个约束条件,可分性约束和可辨别性约束,鼓励功能,以满足集群结构,这是必不可少的有效的监督信息生成与产品量化。采用迭代优化策略对UDQ进行优化,保证了特征和监督信息在统一模型中的交互增强。此外,我们开发了三种细化策略来细化特征,以获得更好的监督信息,用于模型优化。四个数据集上的实验结果表明,我们的UDQ的国家的最先进的方法的优越性。
In this paper, we propose an unsupervised deep quantization (UDQ) method for object instance search. The UDQ utilizes product quantization to discover the underlying self-supervision information of the training data and iteratively exploits the self-supervision information to optimize features of the training data in an unsupervised fashion. The optimized features are further used to update the self-supervision information for the subsequent training procedure. We introduce two constraints, the separability constraint and the discriminability constraint, to encourage the features to satisfy a cluster structure which is essential for the effective supervision information generation with the product quantization. The UDQ is optimized with an iterative optimization strategy which guarantees that the features and the supervision information can be enhanced each other alternately in a unified model. Moreover, we develop three refinement strategies to refine features to obtain better supervision information for the model optimization. Experimental results on four datasets show the superiority of our UDQ over the state-of-the-art methods.
DOI: 10.1109/tip.2018.2845136
发表时间: 2018-06
影响因子: 10.6
作者:
Jufeng Yang;Jie Liang;Hui Shen;K. Wang;Paul L. Rosin;Ming-Hsuan Yang
通讯作者: Jufeng Yang;Jie Liang;Hui Shen;K. Wang;Paul L. Rosin;Ming-Hsuan Yang
DOI: 10.5244/c.31.144
发表时间: 2017-07
期刊: ArXiv
影响因子: --
作者:
Albert Jiménez;J. Álvarez;Xavier Giró-i-Nieto
通讯作者: Albert Jiménez;J. Álvarez;Xavier Giró-i-Nieto
DOI: 10.1023/b:visi.0000029664.99615.94
发表时间: 2004-11-01
影响因子: 19.5
作者:
Lowe, DG
通讯作者: Lowe, DG
DOI: 10.1109/iccv.2013.177
发表时间: 2013-12
期刊: 2013 IEEE International Conference on Computer Vision
影响因子: --
作者:
Giorgos Tolias;Yannis Avrithis;H. Jégou
通讯作者: Giorgos Tolias;Yannis Avrithis;H. Jégou
DOI: 10.1145/2911996.2912061
发表时间: 2016-04
期刊: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval
影响因子: --
作者:
Eva Mohedano;Amaia Salvador;Kevin McGuinness;F. Marqués;N. O’Connor;Xavier Giro-i-Nieto
通讯作者: Eva Mohedano;Amaia Salvador;Kevin McGuinness;F. Marqués;N. O’Connor;Xavier Giro-i-Nieto