From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pellano, Kimji N., Strümke, Inga, Ihlen, Espen Alexander F.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916131966550016
author Pellano, Kimji N.
Strümke, Inga
Ihlen, Espen Alexander F.
author_facet Pellano, Kimji N.
Strümke, Inga
Ihlen, Espen Alexander F.
contents The advancement of deep learning in human activity recognition (HAR) using 3D skeleton data is critical for applications in healthcare, security, sports, and human-computer interaction. This paper tackles a well-known gap in the field, which is the lack of testing in the applicability and reliability of XAI evaluation metrics in the skeleton-based HAR domain. We have tested established XAI metrics namely faithfulness and stability on Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) to address this problem. The study also introduces a perturbation method that respects human biomechanical constraints to ensure realistic variations in human movement. Our findings indicate that \textit{faithfulness} may not be a reliable metric in certain contexts, such as with the EfficientGCN model. Conversely, stability emerges as a more dependable metric when there is slight input data perturbations. CAM and Grad-CAM are also found to produce almost identical explanations, leading to very similar XAI metric performance. This calls for the need for more diversified metrics and new XAI methods applied in skeleton-based HAR.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12790
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition
Pellano, Kimji N.
Strümke, Inga
Ihlen, Espen Alexander F.
Machine Learning
The advancement of deep learning in human activity recognition (HAR) using 3D skeleton data is critical for applications in healthcare, security, sports, and human-computer interaction. This paper tackles a well-known gap in the field, which is the lack of testing in the applicability and reliability of XAI evaluation metrics in the skeleton-based HAR domain. We have tested established XAI metrics namely faithfulness and stability on Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) to address this problem. The study also introduces a perturbation method that respects human biomechanical constraints to ensure realistic variations in human movement. Our findings indicate that \textit{faithfulness} may not be a reliable metric in certain contexts, such as with the EfficientGCN model. Conversely, stability emerges as a more dependable metric when there is slight input data perturbations. CAM and Grad-CAM are also found to produce almost identical explanations, leading to very similar XAI metric performance. This calls for the need for more diversified metrics and new XAI methods applied in skeleton-based HAR.
title From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition
topic Machine Learning
url https://arxiv.org/abs/2402.12790