自回归模型
自编码
计算机科学
判别式
先验概率
模式识别(心理学)
忠诚
解码方法
人工智能
编码(内存)
编码器
算法
人工神经网络
数学
贝叶斯概率
统计
操作系统
电信
作者
Ali Razavi,Aäron van den Oord,Oriol Vinyals
出处
期刊:Cornell University - arXiv
日期:2019-06-02
卷期号:32: 14837-14847
被引量:183
摘要
We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in VQ-VAE to generate synthetic samples of much higher coherence and fidelity than possible before. We use simple feed-forward encoder and decoder networks, making our model an attractive candidate for applications where the encoding and/or decoding speed is critical. Additionally, VQ-VAE requires sampling an autoregressive model only in the compressed latent space, which is an order of magnitude faster than sampling in the pixel space, especially for large images. We demonstrate that a multi-scale hierarchical organization of VQ-VAE, augmented with powerful priors over the latent codes, is able to generate samples with quality that rivals that of state of the art Generative Adversarial Networks on multifaceted datasets such as ImageNet, while not suffering from GAN's known shortcomings such as mode collapse and lack of diversity.
科研通智能强力驱动
Strongly Powered by AbleSci AI