SIDA generates three synthetic images per target domain, mixes their style statistics across patches of source features, and fine-tunes only the classifier, outperforming text-driven zero-shot domain adaptation baselines.
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
-
SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
SIDA generates three synthetic images per target domain, mixes their style statistics across patches of source features, and fine-tunes only the classifier, outperforming text-driven zero-shot domain adaptation baselines.