Towards domain adaptation with open-set target data: Review of theory and computer vision applications R1# C1

R Ghaffari, MS Helfroush, A Khosravi, K Kazemi… - Information …, 2023 - Elsevier
Open-set domain adaptation is a develo** and practical solution to training deep networks
using unlabeled data which have been collected among unknown data and are under …

Cross-domain open-set machinery fault diagnosis based on adversarial network with multiple auxiliary classifiers

J Zhu, CG Huang, C Shen… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Cross-domain fault diagnosis methods based on transfer learning attempt to leverage
knowledge from a domain with sufficient labeled samples to a different but related domain …

Interactive dual adversarial neural network framework: An open-set domain adaptation intelligent fault diagnosis method of rotating machinery

G Mao, Y Li, S Jia, K Noman - Measurement, 2022 - Elsevier
The domain-adaptation technique has been proven to be able to resolve the fault diagnosis
under various working conditions. Most research presumes that the health states in the …

Multi-scale adversarial network for vehicle detection in UAV imagery

R Zhang, S Newsam, Z Shao, X Huang, J Wang… - ISPRS Journal of …, 2021 - Elsevier
Abstract Vehicle detection in Unmanned Aerial Vehicle (UAV) imagery plays a crucial role in
a variety of applications. However, UAVs are usually small, very maneuverable, and can …

A self-supervised-driven open-set unsupervised domain adaptation method for optical remote sensing image scene classification and retrieval

S Wang, D Hou, H **ng - IEEE Transactions on Geoscience …, 2023 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) is an important solution to reduce the bias between
the labeled source domain and the unlabeled target domain. It has attracted more attention …

PSDC: A prototype-based shared-dummy classifier model for open-set domain adaptation

Z Liu, G Chen, Z Li, Y Kang, S Qu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Open-set domain adaptation (OSDA) aims to achieve knowledge transfer in the presence of
both domain shift and label shift, which assumes that there exist additional unknown target …

Decompose to adapt: Cross-domain object detection via feature disentanglement

D Liu, C Zhang, Y Song, H Huang… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed
great success in cross-domain computer vision tasks, enhancing the generalization ability of …

Transferable SAR image classification crossing different satellites under open set condition

S Zhao, Z Zhang, T Zhang, W Guo… - IEEE Geoscience and …, 2022 - ieeexplore.ieee.org
For synthetic aperture radar (SAR) image classification problem, we need to take into
account unlabeled datasets containing unknown classes crossing different satellites. In this …

Seeing through darkness: Visual localization at night via weakly supervised learning of domain invariant features

B Fan, Y Yang, W Feng, F Wu, J Lu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Long term visual localization has to conquer the problem of matching images with dramatic
photometric changes caused by different seasons, natural and man-made illumination …

Open-set domain adaptation for scene classification using multi-adversarial learning

J Zheng, Y Wen, M Chen, S Yuan, W Li, Y Zhao… - ISPRS Journal of …, 2024 - Elsevier
Abstract Domain adaptation methods are able to transfer knowledge across different
domains, tackling multi-sensor, multi-temporal or cross-regional remote sensing scenarios …