A dataset distillation method that combines K-means image prototypes with LLM-generated text prototypes to synthesize small, high-accuracy training sets.
Remember the past: Distilling datasets into addressable memories for neural net- works
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
-
Dataset Distillation via Vision-Language Category Prototype
A dataset distillation method that combines K-means image prototypes with LLM-generated text prototypes to synthesize small, high-accuracy training sets.