Don’t get me wrong: How to apply deep visual interpretations to time series

Löffler C, Lai WC, Zanca D, Schmidt L, Eskofier B, Mutschler C (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Applied Intelligence Springer Verlag (Germany)

Book Volume: 55

Article Number: 920

Journal Issue: 13

DOI: 10.1007/s10489-025-06798-3

Abstract

The correct interpretation of convolutional models is a hard problem for time series data. While saliency methods promise visual validation of predictions for image and language processing, they fall short when applied to time series. These tend to be less intuitive and represent highly diverse data, such as the tool-use time series dataset. Furthermore, saliency methods often generate varied, conflicting explanations, complicating the reliability of these methods. Consequently, a rigorous objective assessment is necessary to establish trust in them. This paper investigates saliency methods on time series data to formulate recommendations for interpreting convolutional models and implements them on the tool-use time series problem. To achieve this, we first employ nine gradient-, propagation-, or perturbation-based post-hoc saliency methods across six varied and complex real-world datasets. Next, we evaluate these methods using five independent metrics to generate recommendations. Subsequently, we implement a case study focusing on tool-use time series using convolutional classification models. Our results validate our recommendations that indicate that none of the saliency methods consistently outperforms others on all metrics, while some are sometimes ahead. Our insights and step-by-step guidelines allow experts to choose suitable saliency methods for a given model and dataset.

Authors with CRIS profile

Dario Zanca Machine Learning and Data Analytics Lab Björn Eskofier Machine Learning and Data Analytics Lab

Involved external institutions

Hasso-Plattner-Institut für Digital Engineering gGmbH (HPI) DE Germany (DE) Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE) Pontifical Catholic University of Valparaiso / Pontificia Universidad Católica de Valparaíso (PUCV) CL Chile (CL)

How to cite

APA:

Löffler, C., Lai, W.C., Zanca, D., Schmidt, L., Eskofier, B., & Mutschler, C. (2025). Don’t get me wrong: How to apply deep visual interpretations to time series. Applied Intelligence, 55(13). https://doi.org/10.1007/s10489-025-06798-3

MLA:

Löffler, Christoffer, et al. "Don’t get me wrong: How to apply deep visual interpretations to time series." Applied Intelligence 55.13 (2025).

BibTeX: Download