无需数据即可高精度量化模型，解决零样本量化三大难题。
SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
- 用低通滤波减少生成数据噪声，提升合成数据质量。
- 通过对齐激活图使量化模型准确率显著优于现有方法。
- 仅对难样本使用软标签，避免错误标签误导训练。
如何在无任何训练数据的情况下实现高精度模型量化？量化算法广泛用于在资源受限的边缘设备上部署神经网络。零样本量化（ZSQ）解决了训练数据因隐私或安全原因不可访问这一关键且实际的问题。然而，现有ZSQ方法面临三大挑战：1）生成数据中的噪声；2）基于非目标模式的预测；3）错误硬标签带来的误导。本文提出SynQ（面向零样本量化的合成感知微调框架），通过低通滤波减少生成样本噪声，利用类激活图对齐使量化模型与预训练模型保持一致，并仅对困难样本采用软标签以缓解预训练模型错误的干扰。大量实验表明，SynQ在多项指标上达到当前最优性能。
原文摘要 · Abstract (English)
How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy or security reasons. However, three significant challenges hinder the performance of existing ZSQ methods: 1) noise in the synthetic dataset, 2) predictions based on off-target patterns, and the 3) misguidance by erroneous hard labels. In this paper, we propose SynQ (Synthesis-aware Fine-tuning for Zero-shot Quantization), a carefully designed ZSQ framework to overcome the limitations of existing methods. SynQ minimizes the noise from the generated samples by exploiting a low-pass filter. Then, SynQ trains the quantized model to improve accuracy by aligning its class activation map with the pre-trained model. Furthermore, SynQ mitigates misguidance from the pre-trained model's error by leveraging only soft labels for difficult samples. Extensive experiments show that SynQ provides the state-of-the-art accuracy, over existing ZSQ methods.
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。