Domain adaptation: challenges, methods, datasets, and applications

P Singhal, R Walambe, S Ramanna, K Kotecha - IEEE access, 2023 - ieeexplore.ieee.org
Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

A balanced and uncertainty-aware approach for partial domain adaptation

J Liang, Y Wang, D Hu, R He, J Feng - European conference on computer …, 2020 - Springer
This work addresses the unsupervised domain adaptation problem, especially in the case of
class labels in the target domain being only a subset of those in the source domain. Such a …

Dual-head contrastive domain adaptation for video action recognition

VGT Da Costa, G Zara, P Rota… - Proceedings of the …, 2022 - openaccess.thecvf.com
Unsupervised domain adaptation (UDA) methods have become very popular in computer
vision. However, while several techniques have been proposed for images, much less …

Self-supervised learning across domains

S Bucci, A D'Innocente, Y Liao… - … on Pattern Analysis …, 2021 - ieeexplore.ieee.org
Human adaptability relies crucially on learning and merging knowledge from both
supervised and unsupervised tasks: the parents point out few important concepts, but then …

Aggregating from multiple target-shifted sources

C Shui, Z Li, J Li, C Gagné, CX Ling… - … on Machine Learning, 2021 - proceedings.mlr.press
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for
predicting a related target domain. Hence, a crucial aspect is to properly combine different …

Generalized domain adaptation

Y Mitsuzumi, G Irie, D Ikami… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Many variants of unsupervised domain adaptation (UDA) problems have been proposed
and solved individually. Its side effect is that a method that works for one variant is often …

One-shot unsupervised cross-domain detection

A D'Innocente, FC Borlino, S Bucci, B Caputo… - Computer Vision–ECCV …, 2020 - Springer
Despite impressive progress in object detection over the last years, it is still an open
challenge to reliably detect objects across visual domains. All current approaches access a …

Adversarial partial domain adaptation by cycle inconsistency

KY Lin, J Zhou, Y Qiu, WS Zheng - European Conference on Computer …, 2022 - Springer
Unsupervised partial domain adaptation (PDA) is a unsupervised domain adaptation
problem which assumes that the source label space subsumes the target label space. A …

Learning from synthetic InSAR with vision transformers: The case of volcanic unrest detection

NI Bountos, D Michail… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The detection of early signs of volcanic unrest preceding an eruption in the form of ground
deformation in interferometric synthetic aperture radar (InSAR) data is critical for assessing …

Distance-based hyperspherical classification for multi-source open-set domain adaptation

S Bucci, FC Borlino, B Caputo… - Proceedings of the …, 2022 - openaccess.thecvf.com
Vision systems trained in closed-world scenarios fail when presented with new
environmental conditions, new data distributions, and novel classes at deployment time …