URM distills CLIP vision-language representations into learnable prototypes for few-shot counting, improving single-domain generalization on unseen datasets.
Reproducible scaling laws for contrastive language-image learning.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2818–2829, 2022
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
-
Single Domain Generalization for Few-Shot Counting via Universal Representation Matching
URM distills CLIP vision-language representations into learnable prototypes for few-shot counting, improving single-domain generalization on unseen datasets.