无需数据即可实现高效模型压缩，保持精度的同时大幅降低存储与计算开销。
A Data-Free Analytical Quantization Scheme for Deep Learning Models
- 基于数学推导自动确定最优截断阈值与缩放因子
- 在多个真实数据集上实现模型尺寸与计算量显著降低
- 适合边缘设备部署，特别适用于无训练数据场景
尽管卷积神经网络在图像分类与分割任务中表现优异，但其庞大的计算与存储需求给资源受限设备的实际部署带来挑战。量化通过将模型参数精度降低至低位表示，以缓解存储压力并加速推理。本文提出一种新型后训练量化方法，针对模型权重自动求解最优截断阈值与缩放因子，并提供数学保证：所提方法可最小化量化噪声。在多个真实数据集上的实证结果表明，该量化方案显著减少模型大小与计算需求，同时保持模型精度。
原文摘要 · Abstract (English)
Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices. Quantization is one technique that aims to alleviate these large storage requirements and speed up the inference process by reducing the precision of model parameters to lower-bit representations. In this paper, we introduce a novel post-training quantization method for model weights. Our method finds optimal clipping thresholds and scaling factors along with mathematical guarantees that our method minimizes quantization noise. Empirical results on real-world datasets demonstrate that our quantization scheme significantly reduces model size and computational requirements while preserving model accuracy.
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。