Skip to content

EDS-Trans: energy-aware dual-scale transformer for multi-source-free domain adaptation

Aug 2026 · Pattern Analysis and Applications · Vol 29 · 0 citations · 58 references
Computer Science

TL;DR

The Energy-Aware Dual-Scale Transformer (EDS-Trans), which integrates source knowledge by combining Hierarchical Window Attention with the Multi-Source Energy-Aware Dynamic Weighting Strategy and develops an Energy-Driven Pseudo-Labeling strategy that generates initial pseudo labels via dynamically weighted fusion of predictions from multiple source models, leading to more robust and effective adaptation.

View source

Similar papers

Oct 2026

Multiple source-free domain adaptation via efficient-DDPM and adaptive fine-grained weight integration for imbalanced fault diagnosis

Reliable operation of rotating machinery is pivotal to industrial production safety and efficiency. Constrained by data privacy concerns, source-free domain adaptation has emerged as a research focus in fault diagnosis, as it avoids the need to access source domain data. However, target domain data collected from real-...

Song Zou, Shao-Jiang Dong, Zong-You Xia et al. · 0 citations
Oct 2026

Risk-aware source-specific mixture of experts for multi-source few-sample QoT estimation in optical networks

Accurate optical signal-to-noise ratio (OSNR) estimation is important for QoT-aware lightpath provisioning, but machine-learning estimators face scarce target labels and distribution shifts across heterogeneous historical domains. We study multi-source few-sample OSNR regression using the simulation-based Fraunhofer HH...

Hao-Jie Wang, Wu Di, Yong-Li Zhao et al. · 0 citations
Open access Oct 2026

Prior-Guided Dual Stream Time-Frequency Meta Learning Network for Few-Shot Cross-Domain Fault Diagnosis

Drastic fluctuations in fault feature distributions under large-span variable speeds, compounded by target domain label scarcity, severely degrade the generalization performance of diagnostic models. To address these challenges, a Prior-Guided Time-Frequency Dual-Stream Meta-Learning network (PR-TFML) is proposed in...

Zi-Shan Xie, Jun Cheng, Chang-Cai Yang et al. · 0 citations
Book Open access Nov 2026

Resilient Deep Multi-View Clustering via Dual-Time-Scale Kernel Attention

Multi-view clustering aims to cluster data into different groups by leveraging both the consistency and complementarity across multiple views. Nevertheless, existing methods commonly face two primary limitations. First, cross-view information fusion often lacks fine-grained sample-level modeling, leading to semantic dr...

Shao-Jun Shi, Guang-Bin Wang, Yi-Ming Wang et al. · 0 citations
Open access Nov 2026

An Uncertainty-Aware Cross-Modal Fusion Network for Domain Generalization in Mechanical Fault Diagnosis

Condition monitoring of modern industrial machinery increasingly relies on data-driven deep learning methods. However, domain shifts caused by dynamic working conditions often lead to substantial accuracy degradation in unseen target domains. Single-modality sensing also suffers from inherent perception limitations und...

He Ren, Man-Man Bian, Wei-Feng Lian et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.