Time Series Alignment with Global Invariances

In this work we address the problem of comparing time series while taking into account both feature space transformation and temporal variability. The proposed framework combines a latent global transformation of the feature space with the widely used Dynamic Time Warping (DTW). The latent global transformation captures the feature invariance while the DTW (or its smooth counterpart soft-DTW) deals with the temporal shifts. We cast the problem as a joint optimization over the global transformation and the temporal alignments. The versatility of our framework allows for several variants depending on the invariance class at stake. Among our contributions we define a differentiable loss for time series and present two algorithms for the computation of time series barycenters under our new geometry. We illustrate the interest of our approach on both simulated and real world data.

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

[2]  Wotao Yin,et al.  A feasible method for optimization with orthogonality constraints , 2013, Math. Program..

[3]  Nicolas Thome,et al.  Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models , 2019, NeurIPS.

[4]  Tommi S. Jaakkola,et al.  Towards Optimal Transport with Global Invariances , 2018, AISTATS.

[5]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[6]  Gary Bécigneul,et al.  Riemannian Adaptive Optimization Methods , 2018, ICLR.

[7]  Edzer Pebesma,et al.  dtwSat: Time-Weighted Dynamic Time Warping for Satellite Image Time Series Analysis in R , 2019, Journal of Statistical Software.

[8]  Martin Jaggi,et al.  Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization , 2013, ICML.

[9]  Meinard Müller,et al.  Audio Matching via Chroma-Based Statistical Features , 2005, ISMIR.

[10]  Volkmar Frinken,et al.  DTW-NN: A novel neural network for time series recognition using dynamic alignment between inputs and weights , 2020, Knowl. Based Syst..

[11]  Tomoko Matsui,et al.  A Kernel for Time Series Based on Global Alignments , 2006, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[12]  Marco Cuturi,et al.  Soft-DTW: a Differentiable Loss Function for Time-Series , 2017, ICML.

[13]  Hoon Heo,et al.  Cover Song Identification with Metric Learning Using Distance as a Feature , 2017, ISMIR.

[14]  Wouter M. Kouw,et al.  A Review of Domain Adaptation without Target Labels , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Nassir Navab,et al.  Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  David Lopez-Paz,et al.  Invariant Risk Minimization , 2019, ArXiv.

[17]  Daniel P. W. Ellis,et al.  The 2007 LabROSA Cover Song Detection System , 2007 .

[18]  M. Reinders,et al.  Multi-Dimensional Dynamic Time Warping for Gesture Recognition , 2007 .

[19]  Tommi S. Jaakkola,et al.  Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces , 2020, AISTATS.

[20]  C. Goodall.  Procrustes methods in the statistical analysis of shape , 1991 .

[21]  Tyler Lu,et al.  Impossibility Theorems for Domain Adaptation , 2010, AISTATS.

[22]  Pierre Gançarski,et al.  A global averaging method for dynamic time warping, with applications to clustering , 2011, Pattern Recognit..

[23]  Shih-Feng Huang,et al.  Classification of temporal data using dynamic time warping and compressed learning , 2020, Biomed. Signal Process. Control..

[24]  Jim Lawrence,et al.  A Purely Algebraic Justification of the Kabsch-Umeyama Algorithm. , 2019, Journal of research of the National Institute of Standards and Technology.

[25]  Juan Carlos Niebles,et al.  D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Razvan Pascanu,et al.  Relational inductive biases, deep learning, and graph networks , 2018, ArXiv.

[27]  Björn W. Schuller,et al.  A multidimensional dynamic time warping algorithm for efficient multimodal fusion of asynchronous data streams , 2009, Neurocomputing.

[28]  Sanguthevar Rajasekaran,et al.  DTWNet: a Dynamic Time Warping Network , 2019, NeurIPS.

[29]  Quoc V. Le,et al.  Measuring Invariances in Deep Networks , 2009, NIPS.

[30]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[31]  Zheng Zhang,et al.  Dynamic Time Warping under limited warping path length , 2017, Inf. Sci..

[32]  Emilia Gómez,et al.  Transposing Chroma Representations to a Common Key , 2008 .

[33]  Cristian Sminchisescu,et al.  Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.