SrvfRegNet: Elastic Function Registration Using Deep Neural Networks
SrvfRegNet: Elastic Function Registration Using Deep Neural Networks
复制标题
DOI：
10.1109/cvprw53098.2021.00503
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Chao Chen;Anuj Srivastava
中科院分区：
文献类型：
--
作者：
Chao Chen;Anuj Srivastava
使用时间转换（重新参数）的注册功能（曲线）是许多计算机视觉和形状分析解决方案的核心。 - 根速度函数（SRVF）导致理论和实际性能的显着改善。 $ {\ Mathbb {l}^2} $ norm在给定函数的srvf之间。曲线和k <t是一个参数 - 限制了涉及大数据的应用程序通过在训练数据上优化基于弹性的目标功能，然后将该训练的网络应用于测试数据，以执行快速注册，以防训练数据，如果培训和测试数据来自不同的类别，它通常会使用不同类别来进行测试数据，它通常使用测试数据，它通常使用测试数据，它通常使用测试数据来使用测试数据，从而将其应用于测试数据，从而使用架构进行训练。转移学习，即仅对网络的最后几层进行重新培训。该框架使用多个标准曲线数据集的功效。
Registering functions (curves) using time warpings (re-parameterizations) is central to many computer vision and shape analysis solutions. While traditional registration methods minimize penalized-${\mathbb{L}^2}$ norm, the elastic Riemannian metric and square-root velocity functions (SRVFs) have resulted in significant improvements in terms of theory and practical performance. This solution uses the dynamic programming algorithm to minimize the ${\mathbb{L}^2}$ norm between SRVFs of given functions. However, the computational cost of this elastic dynamic programming framework – O(nT2k) – where T is the number of time samples along curves, n is the number of curves, and k < T is a parameter – limits its use in applications involving big data. This paper introduces a deep-learning approach, named SRVF Registration Net or SrvfRegNet to overcome these limitations. SrvfRegNet architecture trains by optimizing the elastic metric-based objective function on the training data and then applies this trained network to the test data to perform fast registration. In case the training and the test data are from different classes, it generalizes to the test data using transfer learning, i.e., retraining of only the last few layers of the network. It achieves the state-of-the-art alignment performance albeit at much reduced computational cost. We demonstrate the efficiency and efficacy of this framework using several standard curve datasets.