当前位置: X-MOL 学术Calcolo › 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.)
Tensor-Train decomposition for image recognition
Calcolo ( IF 1.4 ) Pub Date : 2020-02-01 , DOI: 10.1007/s10092-020-0358-8
D. Brandoni , V. Simoncini

We explore the potential of Tensor-Train (TT) decompositions in the context of multi-feature face or object recognition strategies. We devise a new recognition algorithm that can handle three or more way tensors in the TT format, and propose a truncation strategy to limit memory usage. Numerical comparisons with other related methods—including the well established recognition algorithm based on high-order SVD—illustrate the features of the various strategies on benchmark datasets.

中文翻译:

Tensor-Train分解用于图像识别

我们探索在多特征人脸或物体识别策略的背景下Tensor-Train(TT)分解的潜力。我们设计了一种新的识别算法,该算法可以处理TT格式的三个或更多方向张量,并提出了一种截断策略来限制内存使用。与其他相关方法(包括基于高阶SVD的公认的识别算法)的数值比较说明了基准数据集上各种策略的特征。
更新日期:2020-02-01
down
wechat
bug