61 citations · 170 across the 13 of their papers we have counts for
14 papers
Object-Centric Multiple Object Tracking
Zixu Zhao, Jiaze Wang, Max Horn +13
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing th…
Unsupervised Open-Vocabulary Object Localization in Videos
Ke Fan, Zechen Bai, Tianjun Xiao +11
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video obje…
Assaying Out-Of-Distribution Generalization in Transfer Learning
Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler +9
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance acr…
Pathologies in priors and inference for Bayesian transformers
Tristan Cinquin, Alexander Immer, Max Horn +1
In recent years, the transformer has established itself as a workhorse in many applications ranging from natural language processing to reinforcement learning. Similarly, Bayesian…
Predicting sepsis in multi-site, multi-national intensive care cohorts using deep learning
Michael Moor, Nicolas Bennet, Drago Plecko +5
Despite decades of clinical research, sepsis remains a global public health crisis with high mortality, and morbidity. Currently, when sepsis is detected and the underlying pathoge…
Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
Leslie O'Bray, Max Horn, Bastian Rieck +1
Graph generative models are a highly active branch of machine learning. Given the steady development of new models of ever-increasing complexity, it is necessary to provide a princ…
Translational Equivariance in Kernelizable Attention
Max Horn, Kumar Shridhar, Elrich Groenewald +1
While Transformer architectures have show remarkable success, they are bound to the computation of all pairwise interactions of input element and thus suffer from limited scalabili…
Topological Graph Neural Networks
Max Horn, Edward De Brouwer, Michael Moor +3
Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks, yet have been shown to be oblivious to eminent substructures such as cycles. We present…
Path Imputation Strategies for Signature Models of Irregular Time Series
Michael Moor, Max Horn, Christian Bock +2
The signature transform is a 'universal nonlinearity' on the space of continuous vector-valued paths, and has received attention for use in machine learning on time series. However…
Set Functions for Time Series
Max Horn, Michael Moor, Christian Bock +2
Despite the eminent successes of deep neural networks, many architectures are often hard to transfer to irregularly-sampled and asynchronous time series that commonly occur in real…
Topological Autoencoders
Michael Moor, Max Horn, Bastian Rieck +1
We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topologi…
Machine learning for early prediction of circulatory failure in the intensive care unit
Stephanie L. Hyland, Martin Faltys, Matthias Hüser +12
Intensive care clinicians are presented with large quantities of patient information and measurements from a multitude of monitoring systems. The limited ability of humans to proce…
Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping
Michael Moor, Max Horn, Bastian Rieck +2
Sepsis is a life-threatening host response to infection associated with high mortality, morbidity, and health costs. Its management is highly time-sensitive since each hour of dela…
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
Bastian Rieck, Matteo Togninalli, Christian Bock +4
While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data. Measures for characterizing and…