arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15646cs.CVcs.GRcs.LG
收藏

重写深度生成模型

Rewriting a Deep Generative Model

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Adobe Research(Adobe 研究院)

David Bau, Steven Liu, Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba

摘要:

像GAN这样的深度生成模型学习对关于目标分布的一组丰富的语义和物理规则进行建模,但到目前为止,这些规则如何在网络中编码,或者如何改变规则,还不清楚。在本文中,我们介绍了一个新的问题设置:操纵由深度生成模型编码的特定规则。为了解决这个问题,我们提出了一个公式,其中所需的规则是通过操纵一层深度网络作为线性联想记忆来改变的。我们推导出一个算法,用于修改一个条目的联想记忆,我们证明了几个有趣的结构规则可以定位和修改层内的国家的最先进的生成模型。我们提出了一个用户界面,使用户能够交互式地改变生成模型的规则,以达到预期的效果,我们展示了几个概念验证的应用程序。最后,多个数据集上的结果表明,我们的方法对标准的微调方法和编辑传输算法的优势。

英文摘要:

A deep generative model such as a GAN learns to model a rich set of semantic and physical rules about the target distribution, but up to now, it has been obscure how such rules are encoded in the network, or how a rule could be changed. In this paper, we introduce a new problem setting: manipulation of specific rules encoded by a deep generative model. To address the problem, we propose a formulation in which the desired rule is changed by manipulating a layer of a deep network as a linear associative memory. We derive an algorithm for modifying one entry of the associative memory, and we demonstrate that several interesting structural rules can be located and modified within the layers of state-of-the-art generative models. We present a user interface to enable users to interactively change the rules of a generative model to achieve desired effects, and we show several proof-of-concept applications. Finally, results on multiple datasets demonstrate the advantage of our method against standard fine-tuning methods and edit transfer algorithms.

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。

↑