DPL searches the per-layer prompt length for CLIP with differentiable architecture search, and reports higher few-shot accuracy than fixed-length prompt baselines.
Understanding and improving visual prompting: A label-mapping perspec- tive
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Differentiable Prompt Learning for Vision Language Models
DPL searches the per-layer prompt length for CLIP with differentiable architecture search, and reports higher few-shot accuracy than fixed-length prompt baselines.