arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00587cs.CVcs.LG
收藏

定宾作文中的对称与群

Symmetry and Group in Attribute-Object Compositions

Shanghai Jiao Tong University(上海交通大学)

Yong-Lu Li, Yue Xu, Xiaohan Mao, Cewu Lu

摘要:

属性和对象可以组成不同的组合。要对这些一般概念的组合性质进行建模,通过转换(如耦合和解耦)来学习它们是一个不错的选择。然而,复杂的转换需要满足特定的原则,以保证合理性。在本文中,我们首先提出了一个以前被忽视的属性对象转换的原则:对称性。例如,将peeled-apple与属性peeled耦合应该得到peeled-apple,而将peeled与apple解耦仍然应该输出apple。通过对对称性原理的阐述,建立了一个受群论启发的变换框架,即SymNet。SymNet由耦合网络和解耦网络两个模块组成。以群公理和对称性为目标,我们采用深度神经网络实现SymNet,并以端到端的范式对其进行训练。此外,我们提出了一种基于相对移动距离(RMD)的识别方法,利用属性的变化,而不是属性模式本身来分类属性。我们的对称学习可以用于组合零样本学习任务,并在广泛使用的基准测试中优于最先进的技术。代码可在https://github.com/DirtyHarryLYL/SymNet上获得。

英文摘要:

Attributes and objects can compose diverse compositions. To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee the rationality. In this paper, we first propose a previously ignored principle of attribute-object transformation: Symmetry. For example, coupling peeled-apple with attribute peeled should result in peeled-apple, and decoupling peeled from apple should still output apple. Incorporating the symmetry principle, a transformation framework inspired by group theory is built, i.e. SymNet. SymNet consists of two modules, Coupling Network and Decoupling Network. With the group axioms and symmetry property as objectives, we adopt Deep Neural Networks to implement SymNet and train it in an end-to-end paradigm. Moreover, we propose a Relative Moving Distance (RMD) based recognition method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Our symmetry learning can be utilized for the Compositional Zero-Shot Learning task and outperforms the state-of-the-art on widely-used benchmarks. Code is available at https://github.com/DirtyHarryLYL/SymNet.

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。

↑