Comp-LoRA confines LoRA updates to the SVD residual subspace of CLIP weights, yielding small but consistent improvements over direct LoRA in few-shot classification and in preserving zero-shot ability.
Flamingo: a visual language model for few-shot learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Complementary Subspace Low-Rank Adaptation of Vision-Language Models for Few-Shot Classification
Comp-LoRA confines LoRA updates to the SVD residual subspace of CLIP weights, yielding small but consistent improvements over direct LoRA in few-shot classification and in preserving zero-shot ability.