Uncertainty-DTW 用于序列和视觉标记
Uncertainty-DTW for Sequences and Visual Tokens
AI总结：
提出不确定性感知的动态时间规整（uDTW）框架，通过异方差不确定性建模和最大似然估计实现鲁棒对齐，并推广到视觉标记集，在多个领域取得优于现有方法的结果。
摘要：
对齐结构化数据是计算机视觉和机器学习中的一个基本问题，支撑着时间序列分析、人类动作识别和视觉表示学习等任务。现有的对齐方法，包括动态时间规整（DTW）及其可微变体，依赖于确定性相似度度量，因此对异质和噪声特征敏感。在这项工作中，我们引入了不确定性感知对齐，这是一个概率框架，用异方差不确定性建模成对对应关系，并沿对齐路径执行结构化匹配。我们的公式，不确定性-DTW（uDTW），为每个对应分配一个正态分布，并通过最大似然估计目标参数化每条对齐路径，该目标包括（i）一个精度加权匹配项，抑制不可靠特征，以及（ii）一个对数方差正则化，防止退化解。这产生了一个概率对齐机制，对噪声具有鲁棒性且可解释，因为不确定性直接反映了匹配的可靠性。我们进一步将该框架从时间序列推广到标记化的视觉表示，从而能够对视觉标记集进行结构化匹配。学习到的不确定性可以解释为反向注意力：语义相关区域表现出低不确定性并主导对齐，而模糊/噪声区域具有高不确定性。这提供了对齐、注意力和不确定性建模之间的联系。我们在不同领域评估了所提出的框架。结果表明，与最先进的方法相比，该方法持续改进，并且学习到的不确定性与语义重要性相关。这些发现将不确定性感知对齐确立为一个通用、鲁棒且可解释的框架，用于从结构化数据中学习。
英文摘要：
Aligning structured data is a fundamental problem in computer vision and machine learning, underlying tasks such as time series analysis, human action recognition, and visual representation learning. Existing alignment methods, including Dynamic Time Warping (DTW) and its differentiable variants, rely on deterministic similarity measures and are therefore sensitive to heterogeneous and noisy features. In this work, we introduce uncertainty-aware alignment, a probabilistic framework that models pairwise correspondences with heteroscedastic uncertainty and performs structured matching along alignment paths. Our formulation, uncertainty-DTW (uDTW), assigns each correspondence a Normal distribution and parametrizes each alignment path by a Maximum Likelihood Estimate objective consisting of (i) a precision-weighted matching term that suppresses unreliable features, and (ii) a log-variance regularization that prevents degenerate solutions. This yields a probabilistic alignment mechanism that is robust to noise and interpretable, as uncertainty directly reflects the reliability of matches. We further generalize this framework from temporal sequences to tokenized visual representations, enabling structured matching over sets of visual tokens. The learned uncertainty can be interpreted as a reverse-attention: semantically relevant regions exhibit low uncertainty and dominate the alignment, while ambiguous/noisy regions have high uncertainty. This provides a connection between alignment, attention, and uncertainty modeling. We evaluate the proposed framework across diverse domains. The results demonstrate consistent improvements over state-of-the-art methods and show that learned uncertainty correlates with semantic importance. These findings establish uncertainty-aware alignment as a general, robust, and interpretable framework for learning from structured data.
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。
