2 papers
cs.CV2026
Visual Anomaly Synthesis for Model Selection in Data Scarcity
Daniel Pröll, Thomas Kraxner, Tobias Schaefer +1
Defect detection systems for industrial condition monitoring can only be relied upon if they are validated, yet defective samples are rare and, for a specific asset, often nonexist…
q-fin.RM2025
Probabilistic Rule Models as Diagnostic Layers: Interpreting Structural Concept Drift in Post-Crisis Finance
Dmitry Lesnik, Tobias Schaefer
Machine learning models used for high-stakes predictions in domains like credit risk face critical degradation due to concept drift, requiring robust and transparent adaptation mec…