23 citations · 49 across the 9 of their papers we have counts for
9 papers
VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
Yumeng Li, William Beluch, Margret Keuper +2
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolvin…
Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation
Dan Zhang, Kaspar Sakmann, William Beluch +2
Within the context of autonomous driving, encountering unknown objects becomes inevitable during deployment in the open world. Therefore, it is crucial to equip standard semantic s…
A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing
Sophie Henning, William Beluch, Alexander Fraser +1
Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, curren…
Improving Uncertainty of Deep Learning-based Object Classification on Radar Spectra using Label Smoothing
Kanil Patel, William Beluch, Kilian Rambach +2
Object type classification for automotive radar has greatly improved with recent deep learning (DL) solutions, however these developments have mostly focused on the classification…
DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
Elias Eulig, Piyapat Saranrittichai, Chaithanya Kumar Mummadi +4
Common deep neural networks (DNNs) for image classification have been shown to rely on shortcut opportunities (SO) in the form of predictive and easy-to-represent visual factors. T…
Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra
Kanil Patel, William Beluch, Kilian Rambach +3
Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar.In addition to high accuracy, it is crucial for decision ma…
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
Kanil Patel, William Beluch, Bin Yang +2
Post-hoc multi-class calibration is a common approach for providing high-quality confidence estimates of deep neural network predictions. Recent work has shown that widely used sca…
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Kanil Patel, William Beluch, Dan Zhang +2
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.…
Uncertainty Based Detection and Relabeling of Noisy Image Labels
Jan M. Köhler, Maximilian Autenrieth, William H. Beluch
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to th…