Related papers: A note on a better conditioned Domain Wall Operato…
Transformer-based methods have achieved remarkable success in various machine learning tasks. How to design efficient test-time adaptation methods for transformer models becomes an important research task. In this work, motivated by the…
According to the recent experiment by the Fert group, the velocity of domain wall motion in the spin valve ferromagnetic nanowires was almost doubly enhanced compared to the old value. In this work, we propose an additional torque model,…
In this paper, we present a novel convolution theorem which encompasses the well known convolution theorem in (graph) signal processing as well as the one related to time-varying filters. Specifically, we show how a node-wise convolution…
In this note we study the structure of shift-preserving operators acting on a finitely generated shift-invariant space. We define a new notion of diagonalization for these operators, which we call s-diagonalization. We give necessary and…
Domain shifts are critical issues that harm the performance of machine learning. Unsupervised Domain Adaptation (UDA) mitigates this issue but suffers when the domain shifts are steep and drastic. Gradual Domain Adaptation (GDA) alleviates…
The difficulty in frequency domain identification is that frequency components of arbitrary inputs and outputs are not related by the system's transfer function if signals are windowed. When rectangular windows are used, it is well known…
This article describes a series of new results outlining equivalences between certain "rewirings" of filterbank system block diagrams, and the corresponding actions of convolution, modulation, and downsampling operators. This gives rise to…
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques…
The time-modulated array (TMA) is a simple array architecture in which each antenna is connected via a multi-throw switch. The switch acts as a modulator switching state faster than the symbol rate. The phase shifting and beamforming is…
This paper deals with fractional-order controlled systems and fractional-order controllers in the frequency domain. The mathematical description by fractional transfer functions and properties of these systems are presented. The new ways…
Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while…
Domain generalization aims to train models on multiple source domains so that they can generalize well to unseen target domains. Among many domain generalization methods, Fourier-transform-based domain generalization methods have gained…
We investigate the application of windowed Fourier frames (WFFs) to the numerical solution of partial differential equations, focussing on elliptic equations. The action of a partial differential operator (PDO) on a windowed plane wave is…
We consider the space-fractional operator with order $0<\alpha<1$ on the metric star graph. The boundary conditions at the vertices of the metric star graph providing the self-adjointness of the operator are derived. The obtained result is…
Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a…
The aim of this paper is to give an overview of domain adaptation and transfer learning with a specific view on visual applications. After a general motivation, we first position domain adaptation in the larger transfer learning problem.…
Domain walls in equilibrium phase transitions propagate in a preferred direction so as to minimize the free energy of the system. As a result, initial spatio-temporal patterns ultimately decay toward uniform states. The absence of a…
Domain adaption has been widely adapted for cross-domain sentiment analysis to transfer knowledge from the source domain to the target domain. Whereas, most methods are proposed under the assumption that the target (test) domain is known,…
Unsupervised Domain Adaptation (DA) is used to automatize the task of labeling data: an unlabeled dataset (target) is annotated using a labeled dataset (source) from a related domain. We cast domain adaptation as the problem of finding…
Domain Adaptation (DA) is a highly relevant research topic when it comes to image classification with deep neural networks. Combining multiple source domains in a sophisticated way to optimize a classification model can improve the…