9 papers
Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication
Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla +2
Edible insects offer an efficient source of alternative protein, requiring less land, water and emitting less greenhouse gas than conventional livestock. However, their successful…
When Multi-Sensor Fusion Fails to Generalize: Cattle Posture Classification Under Animal-Level and Temporal Distribution Shift
Leutrim Uka, Severino Pinto, Gundula Hoffmann +1
Automated cattle posture-classification systems frequently report near-perfect accuracy, yet their robustness under realistic deployment conditions remains largely unknown. In part…
Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence
Georgii Mikriukov, Grégoire Montavon, Marina M. -C. Höhne
Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We…
Manipulating Feature Visualizations with Gradient Slingshots
Dilyara Bareeva, Marina M. -C. Höhne, Alexander Warnecke +5
Feature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a g…
Explaining Bayesian Neural Networks
Kirill Bykov, Marina M. -C. Höhne, Adelaida Creosteanu +4
To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predicti…
Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather
Philine L. Bommer, Marlene Kretschmer, Fiona R. Spuler +2
Predictions on subseasonal-to-seasonal (S2S) timescales--ranging from two weeks to two month--are crucial for early warning systems but remain challenging owing to chaos in the cli…