用产品量化压缩扩散模型，1比特仍保持生成质量
Diffusion Product Quantization
- 采用产品量化提升压缩精度和容量，解决传统量化缺陷
- 压缩至1比特，模型尺寸缩小24倍以上，生成质量仍优
- 适合需极致压缩的扩散模型部署场景，如移动端
本文研究在极端压缩条件下对扩散模型进行量化，以减小模型规模同时保持性能。我们发现经典向量量化对扩散模型敏感，码本大小限制生成质量。为此引入产品量化，提升重建精度与容量，关键在于保留生成能力。进一步提出码本压缩方法，通过评估向量重要性并去除冗余，确保模型尺寸在目标范围内。还设计端到端校准策略，在前向传播中调整分配，并使用DDPM损失优化码本。将模型压缩至1比特（模型尺寸减少超24倍），实现压缩与质量的平衡。在ImageNet上对DiT模型应用该方法，显著优于其他量化方案，生成性能具有竞争力。
原文摘要 · Abstract (English)
In this work, we explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We begin by investigating classical vector quantization but find that diffusion models are particularly susceptible to quantization error, with the codebook size limiting generation quality. To address this, we introduce product quantization, which offers improved reconstruction precision and larger capacity -- crucial for preserving the generative capabilities of diffusion models. Furthermore, we propose a method to compress the codebook by evaluating the importance of each vector and removing redundancy, ensuring the model size remaining within the desired range. We also introduce an end-to-end calibration approach that adjusts assignments during the forward pass and optimizes the codebook using the DDPM loss. By compressing the model to as low as 1 bit (resulting in over 24 times reduction in model size), we achieve a balance between compression and quality. We apply our compression method to the DiT model on ImageNet and consistently outperform other quantization approaches, demonstrating competitive generative performance.
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。