Search Results for author:
Found 18 papers, 13 papers with code
Unsupervised Open-Vocabulary Object Localization in Videos
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 object localization.
Object-Centric Multiple Object Tracking
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines.
Image retrieval outperforms diffusion models on data augmentation
Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification.
Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning
Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions.
Bridging the Gap to Real-World Object-Centric Learning
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world.
Assaying Out-Of-Distribution Generalization in Transfer Learning
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e. g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations.
Adversarial Robustness
Out-of-Distribution Generalization
+1
Pathologies in priors and inference for Bayesian transformers
In recent years, the transformer has established itself as a workhorse in many applications ranging from natural language processing to reinforcement learning.
Predicting sepsis in multi-site, multi-national intensive care cohorts using deep learning
Here, we developed and validated a machine learning (ML) system for the prediction of sepsis in the ICU.
Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
Graph generative models are a highly active branch of machine learning.
Translational Equivariance in Kernelizable Attention
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 scalability.
Topological Graph Neural Networks
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.
Challenging Euclidean Topological Autoencoders
Topological autoencoders (TopoAE) have demonstrated their capabilities for performing dimensionality reduction while at the same time preserving topological information of the input space.
Path Imputation Strategies for Signature Models of Irregular Time Series
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.
Set Functions for Time Series
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-world datasets, especially in healthcare applications.
Topological Autoencoders
We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders.
Machine learning for early prediction of circulatory failure in the intensive care unit
Intensive care clinicians are presented with large quantities of patient information and measurements from a multitude of monitoring systems.
Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping
This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner based on time series distances.
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data.
