Tensor Decomposition Via Core Tensor Networks
Tensor Decomposition Via Core Tensor Networks
复制标题
DOI：
10.1109/icassp39728.2021.9413637
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Jianfu Zhang;Zerui Tao;Liqing Zhang;Qibin Zhao
中科院分区：
文献类型：
--
作者：
Jianfu Zhang;Zerui Tao;Liqing Zhang;Qibin Zhao
张量分解（TD）在图像修复和去噪方面表现出了良好的性能。现有的方法总是旨在通过优化基于特定张量模型的特定代价函数来将一个张量分解为潜在因子或核心张量。这些算法迭代地从给定的任意单个张量的随机初始化中学习最优解，导致收敛速度慢且效率低。在本文中，我们提出了一个有效的TD算法，旨在学习从输入张量到潜在的核心张量的全局映射，假设多个张量的映射可能是共享的或高度相关的。为此，我们训练了一个深度神经网络（DNN）来对全局映射进行建模，然后应用它来高效地分解一个新给定的张量。此外，DNN的初始值是基于元学习方法学习的。通过利用预训练的核心张量DNN，我们提出的方法使我们能够有效和准确地执行TD。实验结果表明，我们的方法比其他TD方法在速度和准确性方面的显着改善。
Tensor decomposition (TD) has shown promising performance in image completion and denoising. Existing methods always aim to decompose one tensor into latent factors or core tensors by optimizing a particular cost function based on a specific tensor model. These algorithms iteratively learn the optima from random initialization given any individual tensor, resulting in slow convergence and low efficiency. In this paper, we propose an efficient TD algorithm that aims to learn a global mapping from input tensors to latent core tensors, under the assumption that the mappings of multiple tensors might be shared or highly correlated. To this end, we train a deep neural network (DNN) to model the global mapping and then apply it to decompose a newly given tensor with high efficiency. Furthermore, the initial values of DNN are learned based on meta-learning methods. By leveraging the pretrained core tensor DNN, our proposed method enables us to perform TD efficiently and accurately. Experimental results demonstrate the significant improvements of our method over other TD methods in terms of speed and accuracy.