Lightweight design of Convolutional Neural Networks (CNNs) requires co-design
efforts in the model architectures and compression techniques. As a novel
design paradigm that separates training and inference, a structural
re-parameterized (SR) network such as the representative RepVGG revitalizes the
simple VGG-like network with a high accuracy comparable to advanced and often
more complicated networks. However, the merging process in SR networks
introduces outliers into weights, making their distribution distinct from
conventional networks and thus heightening difficulties in quantization. To
address this, we propose an operator-level improvement for training called
Outlier Aware Batch Normalization (OABN). Additionally, to meet the demands of
limited bitwidths while upkeeping the inference accuracy, we develop a
clustering-based non-uniform quantization framework for Quantization-Aware
Training (QAT) named ClusterQAT. Integrating OABN with ClusterQAT, the
quantized performance of RepVGG is largely enhanced, particularly when the
bitwidth falls below 8.

通过在模型架构和压缩技术上进行协同设计，卷积神经网络（CNN）的轻量化设计需要努力。作为一种新颖的设计范式，结构再参数化（SR）网络如代表性的 RepVGG 使简单的 VGG-like 网络以高度准确性得到重塑，与先进且通常更复杂的网络相当。然而，SR 网络中的合并过程会引入权重的异常值，使其分布与传统网络有所不同，从而加大了量化的难度。为了解决这个问题，我们提出了一种称为 Outlier Aware Batch Normalization（OABN）的操作级改进的训练方法。此外，为了满足有限的位宽要求并保持推断准确性，我们开发了一种基于聚类的非均匀量化框架 ClusterQAT 用于量化感知训练（QAT）。集成 OABN 和 ClusterQAT 后，RepVGG 的量化性能得到了大幅提升，尤其在位宽低于 8 时。