Knowledge distillation is reformulated as conditional diffusion over teacher feature tokens, with class-center contraction replacing the classification loss, yielding state-of-the-art ImageNet distillation numbers.
Distilling knowledge via knowledge review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative Distribution Distillation
Knowledge distillation is reformulated as conditional diffusion over teacher feature tokens, with class-center contraction replacing the classification loss, yielding state-of-the-art ImageNet distillation numbers.