SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment

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.

[1]  Anuj Srivastava,et al.  A Novel Representation for Riemannian Analysis of Elastic Curves in Rn , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  George Trigeorgis,et al.  Deep Canonical Time Warping for Simultaneous Alignment and Representation Learning of Sequences , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Elvis Nunez,et al.  Deep Learning of Warping Functions for Shape Analysis , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  Anuj Srivastava,et al.  Riemannian Analysis of Probability Density Functions with Applications in Vision , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Jenna Wiens,et al.  Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks , 2018, MLHC.

[6]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[7]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[8]  Anuj Srivastava,et al.  Shape Analysis of Elastic Curves in Euclidean Spaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  H. Karcher.  Riemannian center of mass and mollifier smoothing , 1977 .

[10]  John W. Fisher,et al.  Highly-Expressive Spaces of Well-Behaved Transformations: Keeping it Simple , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Rushil Anirudh,et al.  Rate-Invariant Autoencoding of Time-Series , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[13]  Abubakar Abid,et al.  Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders , 2018, NeurIPS.

[14]  Ieva Kazlauskaite,et al.  Gaussian Process Latent Variable Alignment Learning , 2018, AISTATS.

[15]  Pavan Turaga,et al.  Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Anuj Srivastava,et al.  Removing Shape-Preserving Transformations in Square-Root Elastic (SRE) Framework for Shape Analysis of Curves , 2007, EMMCVPR.

[17]  Oren Shriki,et al.  Diffeomorphic Temporal Alignment Nets , 2019, NeurIPS.