Recently, transform-based tensor nuclear norm (TNN) minimization methods have received
increasing attention for recovering third-order tensors in multi-dimensional imaging …

This paper proposes a regularizer called Implicit Neural Representation Regularizer (INRR)
to improve the generalization ability of the Implicit Neural Representation (INR). The INR is a …

Recently, the tensor completion problem has witnessed significant advancements with the
introduction of the tensor nuclear norm based on self-supervised nonlinear transformations …

Matrix completion problems arise in many applications including recommendation systems,
computer vision, and genomics. Increasingly larger neural networks have been successful in …

Multi-fidelity matrices refer to a pair of data matrices, whose entries are the measurements of
a specific physical quantity at different fidelity levels wrt two environment variables arranged …

As an emerging and popular technique for boosting CNNs, structural reparameterization
(SR) decouples the training and inference structures to alter the training dynamics and …

The explicit low-rank regularization, eg, nuclear norm regularization, has been widely used
in imaging sciences. However, it has been found that implicit regularization outperforms …

Electromagnetic field exposure (EMF) has grown to be a critical concern as a consequence
of the ongoing installation of fifth-generation cellular networks (5G). The lack of …

Image stitching is an important method for digital image processing, which is often prone to
the problem of the irregularity of stitched images after stitching. And the traditional image …

In this thesis, we establish and analyze two core principles driving the success of neural
networks: over-parameterization and feature learning. We leverage these principles to …