用扩散模型做编码器，解决传统VAE训练不稳问题。
The Diffusion Encoder
- 用交替训练模拟期望最大化，让编码器与解码器协同工作。
- 保持扩散模型高效训练优势，同时提升编码质量。
- 适合想改进自编码器结构的研究者或从业者。
我们构建了一种新型编码器，利用扩散模型的表达能力。在传统变分自编码器中，编码器和解码器通过重参数化技巧共同协商输入的潜在表示，但该方法限制编码器只能采用简单分布族。当用扩散模型替代编码器时，需重新思考如何将解码器的反馈传递回编码器，因为两者通常会朝相反方向更新潜变量估计。本文提出一种受期望最大化算法启发的交替训练方案，实现了编码器与解码器更可靠的同步，同时保留了标准扩散模型的简单高效训练目标。
原文摘要 · Abstract (English)
We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is made possible by the reparameterization trick, which simplifies training at the cost of restricting the encoder to a simple family of distributions. Replacing this encoder with a diffusion model requires rethinking how the decoder pressure can be transmitted back to the encoder, given that they tend to update their internal estimates of the latent in opposing directions. We solve this problem with an alternating training scheme, inspired by the expectation-maximization algorithm. Our method enables more reliable synchronization between encoder and decoder, while preserving the simple and efficient training objective of standard diffusion models.
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。