Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are quantization, a well-known approach for network compression, and re-parametrization, an emerging technique designed to improve model performance. Although both techniques have been studied individually, there has been limited research on their simultaneous application. To address this gap, we propose a novel approach called RepQ, which applies quantization to re-parametrized networks. Our method is based on the insight that the test stage weights of an arbitrary re-parametrized layer can be presented as a differentiable function of trainable parameters. We enable quantization-aware training by applying quantization on top of this function. RepQ generalizes well to various re-parametrized models and outperforms the baseline method LSQ quantization scheme in all experiments.
@article{arxiv.2311.05317,
title = {RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures},
author = {Anastasiia Prutianova and Alexey Zaytsev and Chung-Kuei Lee and Fengyu Sun and Ivan Koryakovskiy},
journal= {arXiv preprint arXiv:2311.05317},
year = {2023}
}