LIMO, a transductive loss combining mutual information, zero-shot KL regularization, and LoRA, sets new state-of-the-art few-shot accuracy for CLIP on 11 datasets.
Enhancing remote sensing vision-language models for zero-shot scene classification
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
-
Language-Aware Information Maximization for Transductive Few-Shot CLIP
LIMO, a transductive loss combining mutual information, zero-shot KL regularization, and LoRA, sets new state-of-the-art few-shot accuracy for CLIP on 11 datasets.