Deep attentive time warping. (April 2023)

• Record Type: Journal Article
• Authors: Matsuo, Shinnosuke; Wu, Xiaomeng; Atarsaikhan, Gantugs; Kimura, Akisato; Kashino, Kunio; Iwana, Brian Kenji; Uchida, Seiichi
• Is Part Of: Pattern recognition. Volume 136(2023)
• Publication Date: 2023-04
• Subjects: Dynamic time warping -- Attention model -- Metric learning -- Time series classification -- Online signature verification; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109201
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Novel deep method using attention model for learnable, task-adaptive time warping. Pre-training guided by DTW improves discriminative power and stabilizes learning. Extensive experiments conducted on more than 50 public datasets. Superior performance demonstrated in both stand-alone and plug-in scenarios. Abstract: Similarity measures for time series are important problems for time series classification. To handle the nonlinear time distortions, Dynamic Time Warping (DTW) has been widely used. However, DTW is not learnable and suffers from a trade-off between robustness against time distortion and discriminative power. In this paper, we propose a neural network model for task-adaptive time warping. Specifically, we use the attention model, called the bipartite attention model, to develop an explicit time warping mechanism with greater distortion invariance. Unlike other learnable models using DTW for warping, our model predicts all local correspondences between two time series and is trained based on metric learning, which enables it to learn the optimal data-dependent warping for the target task. We also propose to induce pre-training of our model by DTW to improve the discriminative power. Extensive experiments demonstrate the superior effectiveness of our model over DTW and its state-of-the-art performance in online signature verification.