arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.10778cs.LGcs.CVcs.RO
收藏

用于对齐路径端到端学习的深度声明式动态时间规整

Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths

Queensland University of Technology(昆士兰科技大学);Australian National University(澳大利亚国立大学)

Ming Xu, Sourav Garg, Michael Milford, Stephen Gould

摘要:

本文讨论了学习端到端模型的时间序列数据,包括通过动态时间规整(DTW)的时间对齐步骤。现有的可微DTW方法要么通过固定的扭曲路径进行区分,要么将可微松弛应用于用于解决DTW问题的递归步骤中的min算子。相反,我们提出了一个基于双层优化和深度声明网络的DTW层,我们将其命名为DecDTW。通过将DTW公式化为一个连续的不等式约束优化问题,我们可以使用隐式微分来计算最优对齐(相对于底层时间序列)的解的梯度。这个公式的一个有趣的副产品是,DecDTW输出两个时间序列之间的最佳扭曲路径,而不是软近似,可从Soft-DTW恢复。我们表明,这个属性是特别有用的下游损失函数的最佳对齐路径本身定义的应用程序。这自然发生,例如,当学习提高预测比对相对于地面实况比对的准确度时。我们评估DecDTW在两个这样的应用程序,即音频到分数对齐任务在音乐信息检索和视觉位置识别任务在机器人技术,展示国家的最先进的结果。

英文摘要:

This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW). Existing approaches to differentiable DTW either differentiate through a fixed warping path or apply a differentiable relaxation to the min operator found in the recursive steps used to solve the DTW problem. We instead propose a DTW layer based around bi-level optimisation and deep declarative networks, which we name DecDTW. By formulating DTW as a continuous, inequality constrained optimisation problem, we can compute gradients for the solution of the optimal alignment (with respect to the underlying time series) using implicit differentiation. An interesting byproduct of this formulation is that DecDTW outputs the optimal warping path between two time series as opposed to a soft approximation, recoverable from Soft-DTW. We show that this property is particularly useful for applications where downstream loss functions are defined on the optimal alignment path itself. This naturally occurs, for instance, when learning to improve the accuracy of predicted alignments against ground truth alignments. We evaluate DecDTW on two such applications, namely the audio-to-score alignment task in music information retrieval and the visual place recognition task in robotics, demonstrating state-of-the-art results in both.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑