Feature Map Alignment - Towards Efficient Design of Mixed-precision Quantization Scheme
VCIP, pp. 1-4, 2019.
Quantization is known as an effective compression method for deploying neural networks on mobile devices. However, most existing works train from scratch a quantized network with universal bitwidth for all layers, making it hard to find the optimal trade-off between compression ratio and inference accuracy. In this paper, we propose a nov...More
Full Text (Upload PDF)
PPT (Upload PPT)