paper-with-me

홈 › Papers

Objective Evaluation of Deep Visual Interpretations on Time Series Data

2021-09-29 · Christoffer Löffler, Wei-Cheng Lai, Lukas M Schmidt, Dario Zanca, Bjoern Eskofier, Christopher Mutschler

The correct interpretation and understanding of deep learning models is essential in many applications. (Explanatory) visual interpretation approaches for image and natural language processing allow domain experts to validate and understand almost any deep learning model. However, they fall short when generalizing to arbitrary time series data that is less intuitive and more diverse. Whether a visualization explains the true reasoning or captures the real features is more difficult to judge. Hence, instead of blind trust we need an objective evaluation to obtain reliable quality metrics. This paper proposes a framework of six orthogonal quality metrics for gradient- or perturbation-based post-hoc visual interpretation methods designed for time series classification and segmentation tasks. This comprehensive set is either based on "human perception" or on "functional properties". An extensive experimental study includes commonly used neural network architectures for time series and nine visual interpretation methods. We evaluate the visual interpretation methods with diverse datasets from the UCR repository as well another complex real-world dataset. We show that none of the existing methods consistently outperforms any of the others on all metrics while some of them are ahead in either functional or human-based metrics. Our results allow experts to make an informed choice of suitable visualization techniques for the model and task at hand.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series AnalysisTime Series Classification

Similar Papers 제목 키워드 기반

Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series

2022-03-14 · Christoffer Loeffler, Wei-Cheng Lai, Bjoern Eskofier, Dario Zanca 외

The correct interpretation and understanding of deep learning models are essential in many applications. Explanatory visual interpretation approaches for image, and natural language processing allow domain experts to val…

Time SeriesTime Series AnalysisTime Series Classificationvalid

ST-Tree with Interpretability for Multivariate Time Series Classification

2024-11-18 · Mingsen Du, Yanxuan Wei, Yingxia Tang, Xiangwei Zheng 외

Multivariate time series classification is of great importance in practical applications and is a challenging task. However, deep neural network models such as Transformers exhibit high accuracy in multivariate time seri…

ClassificationDecision MakingRepresentation LearningTime Series+1

m-TSNE: A Framework for Visualizing High-Dimensional Multivariate Time Series

2017-08-26 · Minh Nguyen, Sanjay Purushotham, Hien To, Cyrus Shahabi

Multivariate time series (MTS) have become increasingly common in healthcare domains where human vital signs and laboratory results are collected for predictive diagnosis. Recently, there have been increasing efforts to …

Time SeriesTime Series AnalysisVocal Bursts Intensity Prediction

Position: Empowering Time Series Reasoning with Multimodal LLMs

2025-02-03 · Yaxuan Kong, Yiyuan Yang, Shiyu Wang, Chenghao Liu 외

Understanding time series data is crucial for multiple real-world applications. While large language models (LLMs) show promise in time series tasks, current approaches often rely on numerical data alone, overlooking the…

Decision MakingMultimodal ReasoningPositionTime Series+1

How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labels

2020-08-26 · Hua Shen, Ting-Hao Kenneth Huang

Explaining to users why automated systems make certain mistakes is important and challenging. Researchers have proposed ways to automatically produce interpretations for deep neural network models. However, it is unclear…