Fine-tuning pretrained CNNs on ImageNet used far less electricity when weights were quantized to about 8 to 13 bits, while pruning and low-rank factorization did not reliably reduce energy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Energy Considerations for Large Pretrained Neural Networks
Fine-tuning pretrained CNNs on ImageNet used far less electricity when weights were quantized to about 8 to 13 bits, while pruning and low-rank factorization did not reliably reduce energy.