6 papers
Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring
Dominik Lindner, Johann Schmidt, Tom Siegl +2
Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged. Robustness is usu…
Robust Canonicalization through Bootstrapped Data Re-Alignment
Johann Schmidt, Sebastian Stober
Fine-grained visual classification (FGVC) tasks, such as insect and bird identification, demand sensitivity to subtle visual cues while remaining robust to spatial transformations.…
Saccadic Vision for Fine-Grained Visual Classification
Johann Schmidt, Sebastian Stober, Joachim Denzler +1
Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features - a task that remains challenging due to hi…
Geometrically Constrained and Token-Based Probabilistic Spatial Transformers
Johann Schmidt, Sebastian Stober
Spatial transformations such as rotation and scale obscure the morphological cues needed for accurate image classification. Careful consideration is required for reliable use in hi…
Label Unification for Cross-Dataset Generalization in Cybersecurity NER
Maciej Jalocha, Johan Hausted Schmidt, William Michelseen
The field of cybersecurity NER lacks standardized labels, making it challenging to combine datasets. We investigate label unification across four cybersecurity datasets to increase…
TransferLight: Zero-Shot Traffic Signal Control on any Road-Network
Johann Schmidt, Frank Dreyer, Sayed Abid Hashimi +1
Traffic signal control plays a crucial role in urban mobility. However, existing methods often struggle to generalize beyond their training environments to unseen scenarios with va…