UAP, an alternating two-stage training protocol, improves unseen-domain accuracy in semi-supervised federated learning by aligning client and server features to a Gaussian distribution defined by the classifier weights.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains
UAP, an alternating two-stage training protocol, improves unseen-domain accuracy in semi-supervised federated learning by aligning client and server features to a Gaussian distribution defined by the classifier weights.