Zero-shot Quantization: A Comprehensive Survey

TL;DR

This survey provides a comprehensive overview of Zero-shot Quantization (ZSQ), a method to quantize neural networks without access to training data, highlighting recent advancements, challenges, and future directions.

Contribution

It is the first in-depth survey that categorizes and analyzes existing ZSQ methods, outlining their motivations, core ideas, and key challenges.

Findings

Categorized ZSQ methods based on data generation strategies.

Identified key challenges and limitations of current ZSQ approaches.

Suggested future research directions for advancing ZSQ.

Abstract

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.