Heterogeneous federated domain generalization network with common representation learning for cross-load machinery fault diagnosis
Various federated transfer learning (FTL) methods have been proposed to address domain
shift and safeguard data privacy in the field of fault diagnosis. However, the effectiveness of …
shift and safeguard data privacy in the field of fault diagnosis. However, the effectiveness of …
Pseudo-labeling integrating centers and samples with consistent selection mechanism for unsupervised domain adaptation
L Li, J Yang, Y Ma, X Kong - Information Sciences, 2023 - Elsevier
Pseudo-labeling is widely applied to generate pseudo labels of target samples in most
Unsupervised Domain Adaptation (UDA) methods. Existing UDA methods designed the …
Unsupervised Domain Adaptation (UDA) methods. Existing UDA methods designed the …
Mutual information guided diffusion for zero-shot cross-modality medical image translation
Cross-modality data translation has attracted great interest in medical image computing.
Deep generative models show performance improvement in addressing related challenges …
Deep generative models show performance improvement in addressing related challenges …
Visual domain adaptation through locality information
Traditional machine learning methods have always performed the learning tasks solely. The
models of these conventional methods have to be built from scratch. The idea of domain …
models of these conventional methods have to be built from scratch. The idea of domain …
Zero-shot-learning cross-modality data translation through mutual information guided stochastic diffusion
Cross-modality data translation has attracted great interest in image computing. Deep
generative models (\textit {eg}, GANs) show performance improvement in tackling those …
generative models (\textit {eg}, GANs) show performance improvement in tackling those …
Self-supervised learning minimax entropy domain adaptation for the underwater target recognition
J Yang, S Yan, D Zeng, G Tan - Applied Acoustics, 2024 - Elsevier
With wide research of intelligent methods, studies on underwater target recognition have
been making rapid progress. However, various marine conditions may cause data …
been making rapid progress. However, various marine conditions may cause data …
Asymmetric slack contrastive learning for full use of feature information in image translation
Y Zhang, M Li, Y Gou, Y He - Knowledge-Based Systems, 2024 - Elsevier
Recently, contrastive learning has been proven to be powerful in cross-domain feature
learning and has been widely used in image translation tasks. However, these methods …
learning and has been widely used in image translation tasks. However, these methods …
Underwater signal recognition based on integrating domain adaptation framework with the stochastic classifier
J Yang, S Yan, W Wang, G Tan, D Zeng - Ocean Engineering, 2024 - Elsevier
Although deep learning has made impressive progress in underwater target recognition,
most current methods ignore the dataset mismatch caused by various marine conditions. To …
most current methods ignore the dataset mismatch caused by various marine conditions. To …
ML-based reconfigurable symbol decoder: An alternative for next-generation communication systems
S Srivastava, PP Dash - Engineering Applications of Artificial Intelligence, 2022 - Elsevier
Abstract Modern Machine Learning (ML) techniques offer numerous opportunities to enable
intelligent communication designs while addressing a wide range of problems in …
intelligent communication designs while addressing a wide range of problems in …
RDAOT: Robust Unsupervised Deep Sub-domain Adaptation through Optimal Transport for Image Classification
In traditional machine learning, the training and testing data are assumed to come from the
same independent and identical distributions. This assumption, however, does not hold up …
same independent and identical distributions. This assumption, however, does not hold up …