516 citations
- Fraunhofer Institute for Industrial MathematicsDE4 papers
- Carl von Ossietzky Universität OldenburgDE2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- CIC nanoGUNEES2 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- École PolytechniqueFR2 papers
- IkerbasqueES2 papers
- University of MannheimDE2 papers
- Active Technologies (Italy)IT1 paper
- Cochlear (Australia)AU1 paper
- Computing CenterRU1 paper
- Delft University of TechnologyNL1 paper
Showing 2022 · cs.CVShow all
2 papers · 2 filters
cs.CV2022★ 27 cited
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
Paul Gavrikov, Janis Keuper
Currently, many theoretical as well as practically relevant questions towards the transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved. While ongo…
cs.CV2022★ 7 cited
Adversarial Robustness through the Lens of Convolutional Filters
Paul Gavrikov, Janis Keuper
Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models…