David Stutz

Publications by Year

Research Areas

Adversarial Robustness in Machine Learning, Anomaly Detection Techniques and Applications, Advanced Neural Network Applications, Domain Adaptation and Few-Shot Learning, Integrated Circuits and Semiconductor Failure Analysis

Most-Cited Works

• → Superpixels: An evaluation of the state-of-the-art(2017)522 cited
• → Learning 3D Shape Completion from Laser Scan Data with Weak Supervision(2018)246 cited
• → Capabilities of Gemini Models in Medicine(2024)89 cited
• Understanding Convolutional Neural Networks(2014)
• Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks(2020)
• → Superpixel Segmentation: An Evaluation(2015)33 cited
• → Relating Adversarially Robust Generalization to Flat Minima(2021)28 cited
• → Robustifying Token Attention for Vision Transformers(2023)26 cited