Drift detection on feature attributions for monitoring visual reinforcement learning models in maritime port surveillance
FADMON can add an explainability layer to the monitoring system while also supporting detection of changes in the underlying interpretation of the input data by the model, monitoring the concept rather than the data, while matching established drift detection methods metrics-wise.
Authors
- Luis Unzueta
- Francisco Javier Iriarte (ORCID: https://orcid.org/0000-0002-1303-6526)
- Ignacio Arganda-Carreras
- Beatrice Azoubel
- Andrés Chica Linares
- Adrián Carrizo-Pérez
Institutions
- Ikerbasque (ES)
- University of the Basque Country (ES)
- Indra (Spain) (ES)
- Vicomtech (ES)
- Fundación Biofísica Bizkaia (ES)
- Donostia International Physics Center (ES)
Publication Details
- Journal
- Open Research Europe
- Published
- 2026-01-02
- DOI
- https://doi.org/10.12688/openreseurope.22116.1
- Primary Topic
- Data Stream Mining Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission