Leveraging Implicit Gaze-Based User Feedback for Interactive Machine Learning

Omair Shahzad Bhatti; Michael Barz; Daniel Sonntag

In: Ralph Bergmann; Lukas Malburg; Stephanie C. Rodermund; Ingo J. Timm (Hrsg.). KI 2022: Advances in Artificial Intelligence. German Conference on Artificial Intelligence (KI), Cham, Pages 9-16, ISBN 978-3-031-15791-2, Springer International Publishing, 2022.


Interactive Machine Learning (IML) systems incorporate humans into the learning process to enable iterative and continuous model improvements. The interactive process can be designed to leverage the expertise of domain experts with no background in machine learning, for instance, through repeated user feedback requests. However, excessive requests can be perceived as annoying and cumbersome and could reduce user trust. Hence, it is mandatory to establish an efficient dialog between a user and a machine learning system. We aim to detect when a domain expert disagrees with the output of a machine learning system by observing its eye movements and facial expressions. In this paper, we describe our approach for modelling user disagreement and discuss how such a model could be used for triggering user feedback requests in the context of interactive machine learning.


Weitere Links

Leveraging_implicit_gaze_based_user_feedback_for_interactive_machine_learning__KI_22__Accepted__(6).pdf (pdf, 212 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence