Nunez Elvis, Lizarraga Andrew, Joshi Shantanu H
Department of Electrical and Computer Engineering, UCLA.
Ahmanson Lovelace Brain Mapping Center, Department of Neurology, UCLA.
Conf Comput Vis Pattern Recognit Workshops. 2021 Jun;2021:4476-4484. doi: 10.1109/cvprw53098.2021.00505. Epub 2021 Sep 1.
We present SrvfNet, a generative deep learning framework for the joint multiple alignment of large collections of functional data comprising square-root velocity functions (SRVF) to their templates. Our proposed framework is fully unsupervised and is capable of aligning to a predefined template as well as jointly predicting an optimal template from data while simultaneously achieving alignment. Our network is constructed as a generative encoder-decoder architecture comprising fully-connected layers capable of producing a distribution space of the warping functions. We demonstrate the strength of our framework by validating it on synthetic data as well as diffusion profiles from magnetic resonance imaging (MRI) data.
我们提出了SrvfNet，这是一个生成式深度学习框架，用于将包含平方根速度函数（SRVF）的大量功能数据集合与它们的模板进行联合多重对齐。我们提出的框架是完全无监督的，能够与预定义模板对齐，也能够从数据中联合预测最优模板，同时实现对齐。我们的网络构建为一个生成式编码器-解码器架构，由能够产生扭曲函数分布空间的全连接层组成。我们通过在合成数据以及磁共振成像（MRI）数据的扩散轮廓上进行验证，展示了我们框架的优势。
