QwT-v2让模型量化更高效，无需额外硬件支持
QwT-v2: Practical, Effective and Efficient Post-Training Quantization
- 用轻量级通道补偿模块替代原方法的复杂结构
- 参数和计算开销大幅降低，精度不降反升
- 可无缝接入现有推理引擎，适合实际部署
网络量化是降低现代深度神经网络资源消耗最实用的压缩方法之一。传统方法通常需针对特定架构和任务设计复杂的方案。QwT虽简单通用，但引入额外参数和延迟，且不兼容多数硬件平台。本文提出QwT-v2，采用轻量级通道级仿射补偿（CWAC）模块，显著减少额外参数与计算量，同时保持或超越QwT的精度表现。该补偿模块可轻松集成至量化推理引擎，有效消除额外开销，兼容绝大多数现有硬件平台。
原文摘要 · Abstract (English)
Network quantization is arguably one of the most practical network compression approaches for reducing the enormous resource consumption of modern deep neural networks. They usually require diverse and subtle design choices for specific architecture and tasks. Instead, the QwT method is a simple and general approach which introduces lightweight additional structures to improve quantization. But QwT incurs extra parameters and latency. More importantly, QwT is not compatible with many hardware platforms. In this paper, we propose QwT-v2, which not only enjoys all advantages of but also resolves major defects of QwT. By adopting a very lightweight channel-wise affine compensation (CWAC) module, QwT-v2 introduces significantly less extra parameters and computations compared to QwT, and at the same time matches or even outperforms QwT in accuracy. The compensation module of QwT-v2 can be integrated into quantization inference engines with little effort, which not only effectively removes the extra costs but also makes it compatible with most existing hardware platforms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。