MSGCoOp improves CLIP few-shot generalization by averaging multiple learnable prompts guided by GPT-4 class descriptions and an orthogonality loss, gaining 1.10% harmonic mean over KgCoOp.
Describing textures in the wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot Learning
MSGCoOp improves CLIP few-shot generalization by averaging multiple learnable prompts guided by GPT-4 class descriptions and an orthogonality loss, gaining 1.10% harmonic mean over KgCoOp.