Abstract Machine learning (ML) has proven to be a powerful tool for utilizing the rapidly
increasing amounts of remote sensing data for environmental monitoring. Yet ML models …

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 …

Abstract Domain adversarial learning aligns the feature distributions across the source and
target domains in a two-player minimax game. Existing domain adversarial networks …

This work addresses the problem of domain adaptation and generalization in a unified
fashion. The main idea is to exploit the siamese architecture with the Contrastive Loss to …

Most existing unsupervised domain adaptation (UDA) methods are based upon the
assumption that source labeled data come from an identical underlying distribution …

This work provides a framework for addressing the problem of supervised domain
adaptation with deep models. The main idea is to exploit adversarial learning to learn an …

The performance of a classifier trained on data coming from a specific domain typically
degrades when applied to a related but different one. While annotating many samples from …

To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer
knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset …

Many few-shot learning models focus on recognising images. In contrast, we tackle a
challenging task of few-shot action recognition from videos. We build on a C3D encoder for …

Domain adaptation aims to exploit the supervision knowledge in a source domain for
learning prediction models in a target domain. In this article, we propose a novel …