# UWC: Unit-wise Calibration Towards Rapid Network Compression

Source: [UWC: Unit-wise Calibration Towards Rapid Network Compression](<https://www.sota2.com/research/paper/68fa6b981e209131cea2f24d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:52:06.013Z

Authors: Chen Lin, Zheyang Li, Bo Peng, Haoji Hu, Wenming Tan, Ye Ren, Shiliang Pu

Published: 2022-01-17T12:27:35.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2201.06376>)

[PDF](<https://arxiv.org/pdf/2201.06376.pdf>)