Style-Pro learns style bases to synthesize distribution shifts and regularizes prompted CLIP against the frozen model, achieving slightly higher average accuracy on standard prompt-learning benchmarks.
Stylip: Multi-scale style- conditioned prompt learning for clip-based domain gener- alization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models
Style-Pro learns style bases to synthesize distribution shifts and regularizes prompted CLIP against the frozen model, achieving slightly higher average accuracy on standard prompt-learning benchmarks.