论文标题
扩散桥矢量量化变异自动编码器
Diffusion bridges vector quantized Variational AutoEncoders
论文作者
论文摘要
矢量量化变量自动编码器（VQ-VAE）是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式集合。要生成新的样本，必须分别对离散状态进行自动性先验分布。这一先验通常非常复杂，并导致生成缓慢。在这项工作中，我们提出了一个新模型，以同时训练先验和编码器/解码器网络。我们在连续编码的向量和非信息性先前分布之间建立一个扩散桥。 然后将潜在离散状态作为这些连续向量的随机函数。我们表明，我们的模型在迷你imagenet和Cifar数据集上的自回旋先验具有竞争力，并且在优化和采样方面都是有效的。我们的框架还扩展了标准VQ-VAE，并可以启用端到端培训。
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.
