UWC: Unit-wise Calibration Towards Rapid Network Compression

01/17/2022
by   Chen Lin, et al.
1

This paper introduces a post-training quantization (PTQ) method achieving highly efficient Convolutional Neural Network  (CNN) quantization with high performance. Previous PTQ methods usually reduce compression error via performing layer-by-layer parameters calibration. However, with lower representational ability of extremely compressed parameters (e.g., the bit-width goes less than 4), it is hard to eliminate all the layer-wise errors. This work addresses this issue via proposing a unit-wise feature reconstruction algorithm based on an observation of second order Taylor series expansion of the unit-wise error. It indicates that leveraging the interaction between adjacent layers' parameters could compensate layer-wise errors better. In this paper, we define several adjacent layers as a Basic-Unit, and present a unit-wise post-training algorithm which can minimize quantization error. This method achieves near-original accuracy on ImageNet and COCO when quantizing FP32 models to INT4 and INT3.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset