arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.10890cs.LGcs.AI
收藏

通过物理对称性学习可解释的低维表示

Learning Interpretable Low-dimensional Representation via Physical Symmetry

Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);New York University Shanghai(上海纽约大学)

Xuanjie Liu, Daniel Chin, Yichen Huang, Gus Xia

AI总结:

本研究利用物理对称性作为自洽约束,使模型在无监督条件下从音乐音频和视频中学习可解释的低维表示,并衍生出提高样本效率的反事实增强技术。

摘要:

我们最近见证了在可解释音乐表示学习方面的巨大进展,涵盖从音高和音色等基本因素到和弦和纹理等高层次概念。然而,大多数方法严重依赖音乐领域知识。一个悬而未决的问题是,哪些通用计算原理能够产生可解释的表示,尤其是与人类感知一致的低维因素。在本研究中,我们从现代物理学中汲取灵感,将物理对称性作为时间序列数据潜在空间的自洽约束。具体而言,它要求刻画潜在状态动态的先验模型在特定群变换下具有等变性。我们证明,物理对称性使模型能够以自监督方式从未标记的单音音乐音频中学习线性音高因素。此外,同样的方法可应用于计算机视觉,从无标签的简单运动物体视频中学习三维笛卡尔空间。更进一步,物理对称性自然引出反事实表示增强,这是一种提高样本效率的新技术。

英文摘要:

We have recently seen great progress in learning interpretable music representations, ranging from basic factors, such as pitch and timbre, to high-level concepts, such as chord and texture. However, most methods rely heavily on music domain knowledge. It remains an open question what general computational principles give rise to interpretable representations, especially low-dim factors that agree with human perception. In this study, we take inspiration from modern physics and use physical symmetry as a self consistency constraint for the latent space of time-series data. Specifically, it requires the prior model that characterises the dynamics of the latent states to be equivariant with respect to certain group transformations. We show that physical symmetry leads the model to learn a linear pitch factor from unlabelled monophonic music audio in a self-supervised fashion. In addition, the same methodology can be applied to computer vision, learning a 3D Cartesian space from videos of a simple moving object without labels. Furthermore, physical symmetry naturally leads to counterfactual representation augmentation, a new technique which improves sample efficiency.

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。

↑