Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
This method addresses the problem of tedious hyper-parameter tuning in quantization for efficient deployment on hardware like ARM, though it is incremental as it builds on prior differentiable quantization techniques.
The paper tackles the challenge of model quantization by introducing a fully differentiable approach to learn quantization parameters, achieving lossless 4-bit quantization for MobileNetV2 on ImageNet.
Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune these values, we present a fully differentiable approach to learn all of them, named Differentiable Dynamic Quantization (DDQ), which has several benefits. (1) DDQ is able to quantize challenging lightweight architectures like MobileNets, where different layers prefer different quantization parameters. (2) DDQ is hardware-friendly and can be easily implemented using low-precision matrix-vector multiplication, making it capable in many hardware such as ARM. (3) Extensive experiments show that DDQ outperforms prior arts on many networks and benchmarks, especially when models are already efficient and compact. e.g., DDQ is the first approach that achieves lossless 4-bit quantization for MobileNetV2 on ImageNet.