TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning

TL;DR

TimePoint introduces a self-supervised learning approach that accelerates and improves the accuracy of time series alignment by learning keypoints and descriptors, enabling scalable analysis across various domains.

Contribution

It is the first method to adapt 2D keypoint detection techniques to 1D signals for scalable, accurate time series alignment using synthetic data for training.

Findings

Significantly faster alignment compared to standard DTW.

Typically higher alignment accuracy on real-world data.

Strong generalization from synthetic to real data.

Abstract

Fast and scalable alignment of time series is a fundamental challenge in many domains. The standard solution, Dynamic Time Warping (DTW), struggles with poor scalability and sensitivity to noise. We introduce TimePoint, a self-supervised method that dramatically accelerates DTW-based alignment while typically improving alignment accuracy by learning keypoints and descriptors from synthetic data. Inspired by 2D keypoint detection but carefully adapted to the unique challenges of 1D signals, TimePoint leverages efficient 1D diffeomorphisms, which effectively model nonlinear time warping, to generate realistic training data. This approach, along with fully convolutional and wavelet convolutional architectures, enables the extraction of informative keypoints and descriptors. Applying DTW to these sparse representations yield major speedups and typically higher alignment accuracy than standard DTW applied to the full signals. TimePoint demonstrates strong generalization to real-world time series when trained solely on synthetic data, and further improves with fine-tuning on real data. Extensive experiments demonstrate that TimePoint consistently achieves faster and more accurate alignments than standard DTW, making it a scalable solution for time-series analysis. Our code is available at https://github.com/BGU-CS-VIL/TimePoint