arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.04895stat.ML
收藏

扩散桥矢量量化变分AutoEncoders

Diffusion bridges vector quantized Variational AutoEncoders

Max Cohen, Guillaume Quispe, Sylvain Le Corff, Charles Ollion, Eric Moulines

摘要:

矢量量化-变分自编码器(VQ-VAE)是一种基于数据的离散潜在表示的生成模型,其中输入被映射到有限的学习嵌入集合,为了生成新的样本,必须单独训练离散状态上的自回归先验分布。这种先验通常非常复杂,并且导致生成缓慢。在这项工作中,我们提出了一个新的模型,训练的先验和编码器/解码器网络同时进行。我们建立了一个连续的编码向量和一个无信息的先验分布之间的扩散桥梁。潜离散状态,然后给出这些连续向量的随机函数。我们表明,我们的模型是有竞争力的自回归先验的迷你Imagenet和CIFAR数据集,是有效的优化和采样。我们的框架还扩展了标准VQ-VAE,并实现了端到端培训。

英文摘要:

Vector Quantized-Variational AutoEncoders (VQ-VAE) are generative models based on discrete latent representations of the data, where inputs are mapped to a finite set of learned embeddings.To generate new samples, an autoregressive prior distribution over the discrete states must be trained separately. This prior is generally very complex and leads to slow generation. In this work, we propose a new model to train the prior and the encoder/decoder networks simultaneously. We build a diffusion bridge between a continuous coded vector and a non-informative prior distribution. The latent discrete states are then given as random functions of these continuous vectors. We show that our model is competitive with the autoregressive prior on the mini-Imagenet and CIFAR dataset and is efficient in both optimization and sampling. Our framework also extends the standard VQ-VAE and enables end-to-end training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑