Universal Domain Adaptation Benchmark for Time Series Data Representation

TL;DR

This paper introduces a comprehensive benchmark for Universal Domain Adaptation in time series data, evaluating different models' robustness and generalization across domains.

Contribution

It provides a standardized protocol and comparison framework for UniDA in time series, highlighting the impact of backbone choice on performance.

Findings

Backbone selection significantly affects UniDA performance.

The proposed protocol enables robustness evaluation across datasets.

The benchmark facilitates future extensions in UniDA for time series.

Abstract

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.