7 papers
Mitigating Biases in Surgical Operating Rooms with Geometry
Tony Danjun Wang, Tobias Czempiel, Nassir Navab +1
Deep neural networks are prone to learning spurious correlations, exploiting dataset-specific artifacts rather than meaningful features for prediction. In surgical operating rooms…
TrackOR: Towards Personalized Intelligent Operating Rooms Through Robust Tracking
Tony Danjun Wang, Christian Heiliger, Nassir Navab +1
Providing intelligent support to surgical teams is a key frontier in automated surgical scene understanding, with the long-term goal of improving patient outcomes. Developing perso…
Forecasting Continuous Non-Conservative Dynamical Systems in SO(3)
Lennart Bastian, Mohammad Rashed, Nassir Navab +1
Modeling the rotation of moving objects is a fundamental task in computer vision, yet extrapolation still presents numerous challenges: (1) unknown quantities such as the m…
Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
Mario Tuci, Lennart Bastian, Benjamin Dupuis +3
Providing generalization guarantees for stochastic optimization algorithms remains a key challenge in learning theory. Recently, numerous works demonstrated the impact of the geome…
Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations
Lennart Bastian, Mohammad Rashed, Nassir Navab +1
Tracking and forecasting the rotation of objects is fundamental in computer vision and robotics, yet SO(3) extrapolation remains challenging as (1) sensor observations can be noisy…
Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
Mustafa Hajij, Lennart Bastian, Sarah Osentoski +9
We introduce copresheaf topological neural networks (CTNNs), a powerful unifying framework that encapsulates a wide spectrum of deep learning architectures, designed to operate on…