Domain adaptation has become a prominent problem setting in machine learning and
related fields. This review asks the question: How can a classifier learn from a source …

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 …

Abstract Domain generalization (DG) aims to generalize a model trained on multiple source
(ie, training) domains to a distributionally different target (ie, test) domain. In contrast to the …

The divergence between labeled training data and unlabeled testing data is a significant
challenge for recent deep learning models. Unsupervised domain adaptation (UDA) …

Transfer learning has recently become the dominant paradigm of machine learning. Pre-
trained models fine-tuned for downstream tasks achieve better performance with fewer …

Surface defect recognition using Deep Learning based computer vision techniques is an
important task in industrial manufacturing. However, surface images have different …

While domain adaptation has been actively researched, most algorithms focus on the single-
source-single-target adaptation setting. In this paper we propose new generalization bounds …

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging
knowledge from a source domain. Existing methods either attempt to align the cross-domain …

Informally, a'spurious correlation'is the dependence of a model on some aspect of the input
data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when …

In industrial manufacturing systems, failures of machines caused by faults in their key
components greatly influence operational safety and system reliability. Many data-driven …