EfficientQuant applies uniform weight quantization to CNN blocks and logarithmic activation quantization to transformer blocks in hybrid models, reporting latency reductions of 2.5x to 8.7x with modest accuracy loss.
Low-bit quantization of neural networks for efficient infer- ence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices
EfficientQuant applies uniform weight quantization to CNN blocks and logarithmic activation quantization to transformer blocks in hybrid models, reporting latency reductions of 2.5x to 8.7x with modest accuracy loss.