Diffeomorphic Temporal Alignment Nets

Abstract

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 singleclass 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 jointalignment methods in aligning training data but also generalizes well to test data.