A generative dataset distillation method that replaces MSE logits matching with standardized KL-divergence distribution matching, reporting improved accuracy on three benchmarks.
A survey of deep learning and its applica- tions: a new paradigm to machine 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
-
Generative Dataset Distillation Based on Self-knowledge Distillation
A generative dataset distillation method that replaces MSE logits matching with standardized KL-divergence distribution matching, reporting improved accuracy on three benchmarks.