GAN-DA aligns source and target batch features to pre-designed orthogonal and common class anchor vectors to achieve 'global awareness' for unsupervised domain adaptation.
Mix and reason: Reasoning over semantic topology with data mixing for domain generalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Beyond Batch Learning: Global Awareness Enhanced Domain Adaptation
GAN-DA aligns source and target batch features to pre-designed orthogonal and common class anchor vectors to achieve 'global awareness' for unsupervised domain adaptation.