论文标题
通过可逆生成流将全球和本地表示
Decoupling Global and Local Representations via Invertible Generative Flows
论文作者
论文摘要
在这项工作中，我们提出了一个新的生成模型，该模型能够在完全无监督的设置中自动将图像的全局和局部表示形式解耦，通过将生成流嵌入VAE框架中以建模解码器。具体而言，提出的模型利用变异自动编码框架来学习潜在变量的（低维）向量来捕获图像的全局信息，该信息作为基于流的可逆解码器的有条件输入，并从样式转移文献中借用的架构。标准图像基准的实验结果证明了我们模型在密度估计，图像产生和无监督的表示学习方面的有效性。重要的是，这项工作表明，只有建筑归纳偏见，具有基于可能性的目标的生成模型能够学习解耦表示，不需要明确的监督。我们的模型代码可从https://github.com/xuezhemax/wolf获得。
In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framework to model the decoder. Specifically, the proposed model utilizes the variational auto-encoding framework to learn a (low-dimensional) vector of latent variables to capture the global information of an image, which is fed as a conditional input to a flow-based invertible decoder with architecture borrowed from style transfer literature. Experimental results on standard image benchmarks demonstrate the effectiveness of our model in terms of density estimation, image generation and unsupervised representation learning. Importantly, this work demonstrates that with only architectural inductive biases, a generative model with a likelihood-based objective is capable of learning decoupled representations, requiring no explicit supervision. The code for our model is available at https://github.com/XuezheMax/wolf.
