Tensor Methods in Computer Vision and Deep Learning

by   Yannis Panagakis, et al.

Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic spaces and high-order interactions, tensors have a long history of applications in a wide span of computer vision problems. With the advent of the deep learning paradigm shift in computer vision, tensors have become even more fundamental. Indeed, essential ingredients in modern deep learning architectures, such as convolutions and attention mechanisms, can readily be considered as tensor mappings. In effect, tensor methods are increasingly finding significant applications in deep learning, including the design of memory and compute efficient network architectures, improving robustness to random noise and adversarial attacks, and aiding the theoretical understanding of deep networks. This article provides an in-depth and practical review of tensors and tensor methods in the context of representation learning and deep learning, with a particular focus on visual data analysis and computer vision applications. Concretely, besides fundamental work in tensor-based visual data analysis methods, we focus on recent developments that have brought on a gradual increase of tensor methods, especially in deep learning architectures, and their implications in computer vision applications. To further enable the newcomer to grasp such concepts quickly, we provide companion Python notebooks, covering key aspects of the paper and implementing them, step-by-step with TensorLy.


page 1

page 4

page 7

page 14


Bayesian Methods in Tensor Analysis

Tensors, also known as multidimensional arrays, are useful data structur...

Tensor Regression

Regression analysis is a key area of interest in the field of data analy...

High-Order Multilinear Discriminant Analysis via Order-n Tensor Eigendecomposition

Higher-order data with high dimensionality is of immense importance in m...

Introduction to Tensor Decompositions and their Applications in Machine Learning

Tensors are multidimensional arrays of numerical values and therefore ge...

Dictionary Learning and Sparse Coding for Third-order Super-symmetric Tensors

Super-symmetric tensors - a higher-order extension of scatter matrices -...

High Performance Rearrangement and Multiplication Routines for Sparse Tensor Arithmetic

Researchers are increasingly incorporating numeric high-order data, i.e....

The Immersion of Directed Multi-graphs in Embedding Fields. Generalisations

The purpose of this paper is to outline a generalised model for represen...

Please sign up or login with your details

Forgot password? Click here to reset