arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.06030cs.CVcs.LGstat.ML
收藏

基于能量模型的组合视觉生成与推理

Compositional Visual Generation and Inference with Energy Based Models

MIT(麻省理工学院);Google Brain(谷歌大脑)

Yilun Du, Shuang Li, Igor Mordatch

摘要:

人类智能的一个重要方面是能够从简单的想法中组成越来越复杂的概念,从而实现快速学习和适应知识。在本文中,我们表明,基于能量的模型可以表现出这种能力,直接结合概率分布。来自组合分布的样本对应于概念的组合。例如,给定一个笑脸分布和另一个男性面孔分布,我们可以将它们组合起来生成微笑的男性面孔。这使我们能够生成同时满足概念的合取、析取和否定的自然图像。我们评估了我们的模型在自然面孔和合成3D场景图像的CelebA数据集上的合成生成能力。我们还展示了我们的模型的其他独特优势,如不断学习和融入新概念的能力,或推断图像背后的概念属性的组合。

英文摘要:

A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge. In this paper we show that energy-based models can exhibit this ability by directly combining probability distributions. Samples from the combined distribution correspond to compositions of concepts. For example, given a distribution for smiling faces, and another for male faces, we can combine them to generate smiling male faces. This allows us to generate natural images that simultaneously satisfy conjunctions, disjunctions, and negations of concepts. We evaluate compositional generation abilities of our model on the CelebA dataset of natural faces and synthetic 3D scene images. We also demonstrate other unique advantages of our model, such as the ability to continually learn and incorporate new concepts, or infer compositions of concept properties underlying an image.

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。

↑