This article takes a problem-oriented perspective and presents a comprehensive review of
transfer-learning methods, both shallow and deep, for cross-dataset visual recognition …

Existing domain adaptation focuses on transferring knowledge between domains with
categorical indices (eg, between datasets A and B). However, many tasks involve …

Abstract Domain adaptation aims at knowledge transfer from a labeled source domain to an
unlabeled target domain. Current domain adaptation methods have made substantial …

Currently, food image recognition tasks are evaluated against fixed datasets. However, in
real-world conditions, there are cases in which the number of samples in each class …

Abstract In Unsupervised Domain Adaptation (UDA), a network is trained on a source
domain and adapted on a target domain where no labeled data is available. Existing UDA …

Retinopathy represents a group of retinal diseases that, if not treated timely, can cause
severe visual impairments or even blindness. Many researchers have developed …

Existing concept drift adaptation (CDA) methods aim to continually update outdated
classifiers in a single-labeled stream scenario. However, real-world data streams are …

Technological developments call for increasing perception and action capabilities of robots.
Among other skills, vision systems that can adapt to any possible change in the working …

Domain adaptation (DA) techniques aim to overcome the domain shift between the source
domain used for training and the target domain where testing takes place. However, current …

Change-point detection is a task that looks for specific moments across which a network
changes fundamentally. Change-point detection is one of the most important challenges for …