arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11820cs.CVcs.LGeess.IVstat.ML
收藏

通过可逆生成流解耦全局和局部表示

Decoupling Global and Local Representations via Invertible Generative Flows

Carnegie Mellon University(卡内基梅隆大学);University of Southern California(南加州大学);University of California, Berkeley(加利福尼亚大学伯克利分校)

Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy

摘要:

在这项工作中,我们提出了一种新的生成模型,能够在完全无监督的设置中自动解耦图像的全局和局部表示,通过在VAE框架中嵌入生成流来对解码器进行建模。具体而言,该模型利用变分自动编码框架来学习潜变量的(低维)向量以捕获图像的全局信息,该图像作为条件输入被馈送到基于流的可逆解码器,该解码器具有从风格转移文献借鉴的架构。在标准图像基准上的实验结果证明了该模型在密度估计、图像生成和无监督表示学习方面的有效性。重要的是,这项工作表明,只有架构归纳偏见,生成模型与基于可能性的目标是能够学习解耦的表示,不需要明确的监督。我们模型的代码可以在https://github.com/XuezheMax/wolf上找到。

英文摘要:

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.

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。

↑