A gradually shrinking teacher signal during knowledge distillation improves 2-bit quantized ResNet20 accuracy on CIFAR-10 and CIFAR-100 compared with fixed-coefficient distillation.
Experimental setup Dataset: We employ CIFAR-10 and CIFAR-100 datasets for exper- iments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Knowledge distillation for optimization of quantized deep neural networks
A gradually shrinking teacher signal during knowledge distillation improves 2-bit quantized ResNet20 accuracy on CIFAR-10 and CIFAR-100 compared with fixed-coefficient distillation.