A UDA framework with multi-scale input mixing and Dirichlet-prior uncertainty estimation improves F1 and calibration on five time-series benchmarks.
Uncertainty awareness for unsupervised domain adaptation on human activity recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data
A UDA framework with multi-scale input mixing and Dirichlet-prior uncertainty estimation improves F1 and calibration on five time-series benchmarks.