FOCoOp uses global, local, and OOD prompts with bi-level distributionally robust optimization and semi-unbalanced optimal transport to improve OOD robustness in federated prompt learning.
Describing textures in the wild
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
-
FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
FOCoOp uses global, local, and OOD prompts with bi-level distributionally robust optimization and semi-unbalanced optimal transport to improve OOD robustness in federated prompt learning.