Universal Domain Adaptation Benchmark for Time Series Data Representation
This work provides a benchmark for practitioners to assess robustness in time series domain adaptation, but it is incremental as it applies existing UniDA methods to a new data type.
The authors tackled the problem of evaluating deep learning models for time series data under domain shifts by implementing a Universal Domain Adaptation (UniDA) benchmark, showing that backbone selection critically influences performance across various datasets.
Deep learning models have significantly improved the ability to detect novelties in time series (TS) data. This success is attributed to their strong representation capabilities. However, due to the inherent variability in TS data, these models often struggle with generalization and robustness. To address this, a common approach is to perform Unsupervised Domain Adaptation, particularly Universal Domain Adaptation (UniDA), to handle domain shifts and emerging novel classes. While extensively studied in computer vision, UniDA remains underexplored for TS data. This work provides a comprehensive implementation and comparison of state-of-the-art TS backbones in a UniDA framework. We propose a reliable protocol to evaluate their robustness and generalization across different domains. The goal is to provide practitioners with a framework that can be easily extended to incorporate future advancements in UniDA and TS architectures. Our results highlight the critical influence of backbone selection in UniDA performance and enable a robustness analysis across various datasets and architectures.