Common feature learning transforms features from heterogeneous teacher networks into a shared space so a student model can imitate them all and outperform individual teachers without annotations.
Progressive blockwise knowledge distillation for neural network acceleration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
Common feature learning transforms features from heterogeneous teacher networks into a shared space so a student model can imitate them all and outperform individual teachers without annotations.