PI-Net: A Deep Learning Approach to Extract Topological Persistence Images.
PI-Net: A Deep Learning Approach to Extract Topological Persistence Images.
复制标题
DOI：
10.1109/cvprw50498.2020.00425
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Turaga P
中科院分区：
文献类型：
--
作者：
Som A;Choi H;Ramamurthy KN;Buman MP;Turaga P
诸如持久图之类的拓扑特征以及诸如持久图像(PI)之类的函数近似已经显示出在机器学习和计算机视觉应用方面的巨大前景。这在很大程度上归因于拓扑表示针对真实世界数据中看到的不同类型的物理干扰变量提供的健壮性，例如视点、照明等。然而，大规模采用它们的关键瓶颈是计算开销和将它们整合到可区分的体系结构中的困难。为了缓解这些瓶颈，我们在本文中迈出了重要的一步，提出了一种新的一步法来直接从输入数据生成PI。我们设计了两种独立的卷积神经网络结构，一种设计用于接受多变量时间序列信号作为输入，另一种设计用于接受多通道图像作为输入。我们将这些网络分别称为信号PI网和图像PI网。据我们所知，我们是第一个提出使用深度学习直接从数据计算拓扑特征的方法。我们探索了所提出的PI-Net结构在两个应用上的应用：基于三轴加速度计传感器数据的人体活动识别和图像分类。我们证明了在有监督的深度学习体系结构中PI的融合是容易的，并且从数据中提取PI的速度提高了几个数量级。我们的代码可以在https://github.com/anirudhsom/PI-Net.上找到
Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. This is greatly attributed to the robustness topological representations provide against different types of physical nuisance variables seen in real-world data, such as view-point, illumination, and more. However, key bottlenecks to their large scale adoption are computational expenditure and difficulty incorporating them in a differentiable architecture. We take an important step in this paper to mitigate these bottlenecks by proposing a novel one-step approach to generate PIs directly from the input data. We design two separate convolutional neural network architectures, one designed to take in multi-variate time series signals as input and another that accepts multi-channel images as input. We call these networks Signal PI-Net and Image PI-Net respectively. To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data. We explore the use of the proposed PI-Net architectures on two applications: human activity recognition using tri-axial accelerometer sensor data and image classification. We demonstrate the ease of fusion of PIs in supervised deep learning architectures and speed up of several orders of magnitude for extracting PIs from data. Our code is available at https://github.com/anirudhsom/PI-Net.
登录
查看更多内容
影响因子：
8
作者：
Chintakunta, Harish;Gentimis, Thanos;Krim, Hamid
通讯作者：
Krim, Hamid
影响因子：
0.8
作者：
Edelsbrunner, H;Letscher, D;Zomorodian, A
通讯作者：
Zomorodian, A
影响因子：
4.3
作者：
Cang Z;Wei GW
通讯作者：
Wei GW
DOI：
10.1007/978-3-319-07100-8
发表时间：
2014-01-01
期刊：
COLLECTIVE ATOM-LIGHT INTERACTIONS IN DENSE ATOMIC VAPOURS
影响因子：
--
作者：
Adams, Charles
通讯作者：
Adams, Charles
影响因子：
4.3
作者：
Dabaghian Y;Mémoli F;Frank L;Carlsson G
通讯作者：
Carlsson G