UniJDOT is a new optimal-transport method for universal domain adaptation on time series that accounts for unknown target samples in the transport cost, adds a joint decision space and auto-thresholding, and uses a Fourier layer to reach state-of-the-art performance.
Villani, et al., Optimal transport: old and new, vol- ume 338, Springer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Joint Distribution Optimal Transport for Universal Domain Adaptation on Time Series
UniJDOT is a new optimal-transport method for universal domain adaptation on time series that accounts for unknown target samples in the transport cost, adds a joint decision space and auto-thresholding, and uses a Fourier layer to reach state-of-the-art performance.