arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10145cs.CV
收藏

SPD神经网络的黎曼局部机制

Riemannian Local Mechanism for SPD Neural Networks

School of Artificial Intelligence and Computer Science, Jiangnan University(江南大学人工智能与计算机学院);School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院);Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey(萨里大学视觉、语音与信号处理中心)

Ziheng Chen, Tianyang Xu, Xiao-Jun Wu, Rui Wang, Zhiwu Huang, Josef Kittler

AI总结:

针对SPD神经网络未显式挖掘局部几何信息的问题,基于范畴论分析定义SPD流形局部信息,设计多尺度子流形模块进行挖掘,并在多个视觉任务中验证了有效性。

摘要:

对称正定(SPD)矩阵在许多科学领域的数据表示中受到了广泛关注。尽管已有许多不同的尝试来开发有效的深度架构以处理SPD矩阵黎曼流形上的数据,但很少有解决方案显式地挖掘深度SPD特征表示中的局部几何信息。鉴于局部机制在欧几里得方法中的巨大成功,我们认为确保SPD网络中局部几何信息的保留至关重要。我们首先从范畴论所提供的更高抽象层次的角度,分析了欧几里得深度网络中常用于捕获局部信息的卷积算子。基于这一分析,我们定义了SPD流形中的局部信息,并设计了一个多尺度子流形模块来挖掘局部几何。涉及多个视觉任务的实验验证了我们方法的有效性。补充材料和源代码可在 https://github.com/GitZH-Chen/MSNet.git 找到。

英文摘要:

The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas. Although there are many different attempts to develop effective deep architectures for data processing on the Riemannian manifold of SPD matrices, very few solutions explicitly mine the local geometrical information in deep SPD feature representations. Given the great success of local mechanisms in Euclidean methods, we argue that it is of utmost importance to ensure the preservation of local geometric information in the SPD networks. We first analyse the convolution operator commonly used for capturing local information in Euclidean deep networks from the perspective of a higher level of abstraction afforded by category theory. Based on this analysis, we define the local information in the SPD manifold and design a multi-scale submanifold block for mining local geometry. Experiments involving multiple visual tasks validate the effectiveness of our approach. The supplement and source code can be found in https://github.com/GitZH-Chen/MSNet.git.

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。

↑