arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.08599cs.LGstat.ML
收藏

关于对称元的学习集

On Learning Sets of Symmetric Elements

NVIDIA Research(英伟达研究院);Stanford University(斯坦福大学);Bar Ilan University(巴伊兰大学)

Haggai Maron, Or Litany, Gal Chechik, Ethan Fetaya

摘要:

从无序集合中学习是一种基本的学习方法,近年来受到越来越多的关注。这方面的研究集中在集合的元素由特征向量表示的情况下,而很少强调集合元素本身坚持自己的对称性的常见情况。这种情况与许多应用相关,从去模糊图像突发到多视图3D形状识别和重建。在本文中,我们提出了一个原则性的方法来学习一般对称元素的集合。我们首先描述的线性层的空间是等变的元素重新排序和元素的固有对称性,如在图像的情况下的翻译。我们进一步表明,由这些层组成的网络,称为Deep Sets for Symmetric Elements(DSS)层,是不变函数和等变函数的通用逼近器,并且这些网络比暹罗网络更有表现力。DSS层也很容易实现。最后,我们证明了它们在一系列图像、图形和点云实验中优于现有的集合学习架构。

英文摘要:

Learning from unordered sets is a fundamental learning setup, recently attracting increasing attention. Research in this area has focused on the case where elements of the set are represented by feature vectors, and far less emphasis has been given to the common case where set elements themselves adhere to their own symmetries. That case is relevant to numerous applications, from deblurring image bursts to multi-view 3D shape recognition and reconstruction. In this paper, we present a principled approach to learning sets of general symmetric elements. We first characterize the space of linear layers that are equivariant both to element reordering and to the inherent symmetries of elements, like translation in the case of images. We further show that networks that are composed of these layers, called Deep Sets for Symmetric Elements (DSS) layers, are universal approximators of both invariant and equivariant functions, and that these networks are strictly more expressive than Siamese networks. DSS layers are also straightforward to implement. Finally, we show that they improve over existing set-learning architectures in a series of experiments with images, graphs, and point-clouds.

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。

↑