无需真实数据即可量化模型，解决隐私敏感场景的部署难题。
Zero-shot Quantization: A Comprehensive Survey
- 不依赖训练数据生成量化所需的统计信息
- 提出零样本量化问题的正式定义与核心挑战
- 系统梳理方法分类，指导未来研究方向
网络量化已被证明是降低深度学习模型内存和计算需求的有效方法，适用于资源受限设备的部署。然而，传统量化方法通常需要访问训练数据，在涉及隐私、安全或监管限制的实际场景中难以应用。零样本量化（ZSQ）作为一种有前景的解决方案，可在无需任何真实数据的情况下实现模型量化。本文对ZSQ方法及其最新进展进行全面综述。首先，我们给出了ZSQ问题的正式定义，并强调其关键挑战；其次，基于数据生成策略将现有方法分为不同类别，分析其动机、核心思想与关键洞见；最后，针对当前局限性提出未来研究方向，以推动该领域发展。据我们所知，本文是首个关于ZSQ的深入综述。
原文摘要 · Abstract (English)
Network quantization has proven to be a powerful approach to reduce the memory and computational demands of deep learning models for deployment on resource-constrained devices. However, traditional quantization methods often rely on access to training data, which is impractical in many real-world scenarios due to privacy, security, or regulatory constraints. Zero-shot Quantization (ZSQ) emerges as a promising solution, achieving quantization without requiring any real data. In this paper, we provide a comprehensive overview of ZSQ methods and their recent advancements. First, we provide a formal definition of the ZSQ problem and highlight the key challenges. Then, we categorize the existing ZSQ methods into classes based on data generation strategies, and analyze their motivations, core ideas, and key takeaways. Lastly, we suggest future research directions to address the remaining limitations and advance the field of ZSQ. To the best of our knowledge, this paper is the first in-depth survey on ZSQ.
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。