提出混合压缩框架，让扩散模型生成速度翻倍且质量不降。
PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model
- 分两阶段渐进量化，用动量机制自适应调整位宽，减少低精度误差
- 蒸馏时引入全精度校准数据集，学生模型性能逼近全精度教师
- 推理速度减半，生成质量优于固定位宽量化方法，适合部署场景
扩散模型在图像生成上表现优异，但因其依赖迭代马尔可夫链过程，计算与资源消耗大，导致误差累积，使简单压缩技术效果受限。本文提出PQCAD-DM，一种结合渐进量化（PQ）与校准辅助蒸馏（CAD）的新型混合压缩框架。PQ采用两阶段量化，通过基于动量的机制引导自适应位宽切换，降低低精度下的权重扰动。CAD在蒸馏过程中利用全精度校准数据集，使学生模型即使在教师模型量化的情况下仍能匹配全精度性能。实验结果表明，PQCAD-DM在保持竞争性生成质量的同时，将推理时间缩短一半，在多个数据集上均优于固定位宽量化方法。
原文摘要 · Abstract (English)
Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques. In this paper, we propose PQCAD-DM, a novel hybrid compression framework combining Progressive Quantization (PQ) and Calibration-Assisted Distillation (CAD) to address these challenges. PQ employs a two-stage quantization with adaptive bit-width transitions guided by a momentum-based mechanism, reducing excessive weight perturbations in low-precision. CAD leverages full-precision calibration datasets during distillation, enabling the student to match full-precision performance even with a quantized teacher. As a result, PQCAD-DM achieves a balance between computational efficiency and generative quality, halving inference time while maintaining competitive performance. Extensive experiments validate PQCAD-DM's superior generative capabilities and efficiency across diverse datasets, outperforming fixed-bit quantization 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。