A Study on Domain Generalization for Failure Detection through Human Reactions in HRI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parreira, Maria Teresa, Lingaraju, Sukruth Gowdru, Ramirez-Aristizabal, Adolfo, Saha, Manaswi, Kuniavsky, Michael, Ju, Wendy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917610056056832
author Parreira, Maria Teresa
Lingaraju, Sukruth Gowdru
Ramirez-Aristizabal, Adolfo
Saha, Manaswi
Kuniavsky, Michael
Ju, Wendy
author_facet Parreira, Maria Teresa
Lingaraju, Sukruth Gowdru
Ramirez-Aristizabal, Adolfo
Saha, Manaswi
Kuniavsky, Michael
Ju, Wendy
contents Machine learning models are commonly tested in-distribution (same dataset); performance almost always drops in out-of-distribution settings. For HRI research, the goal is often to develop generalized models. This makes domain generalization - retaining performance in different settings - a critical issue. In this study, we present a concise analysis of domain generalization in failure detection models trained on human facial expressions. Using two distinct datasets of humans reacting to videos where error occurs, one from a controlled lab setting and another collected online, we trained deep learning models on each dataset. When testing these models on the alternate dataset, we observed a significant performance drop. We reflect on the causes for the observed model behavior and leave recommendations. This work emphasizes the need for HRI research focusing on improving model robustness and real-life applicability.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Study on Domain Generalization for Failure Detection through Human Reactions in HRI
Parreira, Maria Teresa
Lingaraju, Sukruth Gowdru
Ramirez-Aristizabal, Adolfo
Saha, Manaswi
Kuniavsky, Michael
Ju, Wendy
Robotics
Human-Computer Interaction
Machine Learning
Machine learning models are commonly tested in-distribution (same dataset); performance almost always drops in out-of-distribution settings. For HRI research, the goal is often to develop generalized models. This makes domain generalization - retaining performance in different settings - a critical issue. In this study, we present a concise analysis of domain generalization in failure detection models trained on human facial expressions. Using two distinct datasets of humans reacting to videos where error occurs, one from a controlled lab setting and another collected online, we trained deep learning models on each dataset. When testing these models on the alternate dataset, we observed a significant performance drop. We reflect on the causes for the observed model behavior and leave recommendations. This work emphasizes the need for HRI research focusing on improving model robustness and real-life applicability.
title A Study on Domain Generalization for Failure Detection through Human Reactions in HRI
topic Robotics
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2403.06315