BWRF improves quantization-aware training by grafting full-precision blocks onto the low-precision model during training, producing mixed-precision guides that raise ImageNet and CIFAR-10 accuracy at 2 to 4 bits.
Stochastic precision ensemble: self-knowledge distillation for quantized deep neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart
BWRF improves quantization-aware training by grafting full-precision blocks onto the low-precision model during training, producing mixed-precision guides that raise ImageNet and CIFAR-10 accuracy at 2 to 4 bits.