Doula, Achref ; Schmidt, Lennart ; Mühlhäuser, Max ; Sanchez Guinea, Alejandro (2022)
Visualization of Machine Learning Uncertainty in AR-Based See-Through Applications.
2022 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR). virtual Conference (12.-14.12.2022)
doi: 10.1109/AIVR56993.2022.00022
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

Augmented reality see-through applications rely mostly on machine learning models to detect and localize occluded objects. In this case, the user is usually presented the result with the highest probability without taking into account the uncertainty of the model. However, the uncertainty plays a vital role when considering applications where a critical decision-making process relies heavily on the predictions of the model, such as in the case where occluded cars are shown to a driver. In this work, we conduct an investigation of the effects of communicating the uncertainty of machine learning models to users in AR-based see-through applications. Through a controlled user study, we compare three visualization modes: no visualization, most probable output, and probability distribution. The results of our evaluation reveal that when considering the visualizations, each of them lead to comparable results in terms of speed and accuracy of the decision-making process. A relevant finding is that participants considered uncertainty as a substantial part of the output of machine learning models and needs to be delivered with the results. An additional important conclusion is that the preference of users over a specific visualization is strongly dependent on the particular use case.

Frage zum Eintrag

Redaktionelle Details anzeigen