Diffeomorphic Temporal Alignment Nets

Ron Shapira Weber, Matan Eyal, Nicki Skafte Detlefsen, Oren Shriki, Oren Freifeld

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

122 Downloads (Pure)


Time-series analysis is confounded by nonlinear time warping of the data. Traditional methods for joint alignment do not generalize: after aligning a given signal ensemble, they lack a mechanism, that does not require solving a new optimization problem, to align previously-unseen signals. In the multi-class case, they must also first classify the test data before aligning it. Here we propose the Diffeomorphic Temporal Alignment Net (DTAN), a learning-based method for time-series joint alignment. Via flexible temporal transformer layers, DTAN learns and applies an input-dependent nonlinear time warping to its input signal. Once learned, DTAN easily aligns previously-unseen signals by its inexpensive forward pass. In a single-class case, the method is unsupervised: the ground-truth alignments are unknown. In the multi-class case, it is semi-supervised in the sense that class labels (but not the ground-truth alignments) are used during learning; in test time, however, the class labels are unknown. As we show, DTAN not only outperforms existing joint-alignment methods in aligning training data but also generalizes well to test data. Our code is available at https://github.com/BGU-CS-VIL/dtan.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 32
Number of pages12
PublisherNeural Information Processing Systems Foundation
Publication date2019
Article number8884
Publication statusPublished - 2019
Event33rd Conference on Neural Information Processing Systems - Vancouver Convention Centre, Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019
Conference number: 33


Conference33rd Conference on Neural Information Processing Systems
LocationVancouver Convention Centre
Internet address
SeriesAdvances in Neural Information Processing Systems


Dive into the research topics of 'Diffeomorphic Temporal Alignment Nets'. Together they form a unique fingerprint.

Cite this