469 citations · 703 across the 23 of their papers we have counts for
25 papers
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
Lukas Kuhn, Lucas Maes, Giuseppe Serra +4
Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing self-supervised methods either p…
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Sebastian G. Gruber, Nassim Walha, Francis Bach +1
Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently emerged as a key tool in stat…
LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives
Lukas Kuhn, Giuseppe Serra, Randall Balestriero +1
Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time,…
Grasping Partially Occluded Objects Using Autoencoder-Based Point Cloud Inpainting
Alexander Koebler, Ralf Gross, Florian Buettner +1
Flexible industrial production systems will play a central role in the future of manufacturing due to higher product individualization and customization. A key component in such sy…
How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning
Giuseppe Serra, Ben Werner, Florian Buettner
Many real-world applications require machine-learning models to be able to deal with non-stationary data distributions and thus learn autonomously over an extended period of time,…
Provably Better Explanations with Optimized Aggregation of Feature Attributions
Thomas Decker, Ananta R. Bhattarai, Jindong Gu +2
Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous technique…
Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond
Giuseppe Serra, Florian Buettner
Given the ability to model more realistic and dynamic problems, Federated Continual Learning (FCL) has been increasingly investigated recently. A well-known problem encountered in…
DomainLab: A modular Python package for domain generalization in deep learning
Xudong Sun, Carla Feistner, Alexej Gossmann +10
Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniq…
A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
Sebastian G. Gruber, Florian Buettner
Generative models, like large language models, are becoming increasingly relevant in our daily lives, yet a theoretical framework to assess their generalization behavior and uncert…
Understanding metric-related pitfalls in image analysis validation
Annika Reinke, Minu D. Tizabi, Michael Baumgartner +75
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation int…
Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition
Sebastian G. Gruber, Florian Buettner
Reliably estimating the uncertainty of a prediction throughout the model lifecycle is crucial in many safety-critical applications. The most common way to measure this uncertainty…
Metrics reloaded: Recommendations for image analysis validation
Lena Maier-Hein, Annika Reinke, Patrick Godau +71
Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen…
Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity
Arber Qoku, Florian Buettner
Many real-world systems are described not only by data from a single source but via multiple data views. In genomic medicine, for instance, patients can be characterized by data fr…
Better Uncertainty Calibration via Proper Scores for Classification and Beyond
Sebastian G. Gruber, Florian Buettner
With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neura…
Encoding Domain Information with Sparse Priors for Inferring Explainable Latent Variables
Arber Qoku, Florian Buettner
Latent variable models are powerful statistical tools that can uncover relevant variation between patients or cells, by inferring unobserved hidden states from observable high-dime…
Multi-output Gaussian Processes for Uncertainty-aware Recommender Systems
Yinchong Yang, Florian Buettner
Recommender systems are often designed based on a collaborative filtering approach, where user preferences are predicted by modelling interactions between users and items. Many com…
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
Christian Tomani, Daniel Cremers, Florian Buettner
We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS). Standard deep neural networks typically yield un…
Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalization
Xudong Sun, Florian Buettner
We address the task of domain generalization, where the goal is to train a predictive model such that it is able to generalize to a new, previously unseen domain. We choose a hiera…
Post-hoc Uncertainty Calibration for Domain Drift Scenarios
Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem +2
We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representativ…
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration
Christian Tomani, Florian Buettner
To facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predi…
TIMELY: Improving Labeling Consistency in Medical Imaging for Cell Type Classification
Yushan Liu, Markus M. Geipel, Christoph Tietz +1
Diagnosing diseases such as leukemia or anemia requires reliable counts of blood cells. Hematologists usually label and count microscopy images of blood cells manually. In many cas…
AAAI FSS-19: Human-Centered AI: Trustworthiness of AI Models and Data Proceedings
Florian Buettner, John Piorkowski, Ian McCulloh +1
To facilitate the widespread acceptance of AI systems guiding decision-making in real-world applications, it is key that solutions comprise trustworthy, integrated human-AI systems…
textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior
Pankaj Gupta, Yatin Chaudhary, Florian Buettner +1
We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i.e., P(word|context): (1) No Language Structur…
Document Informed Neural Autoregressive Topic Models with Distributional Prior
Pankaj Gupta, Yatin Chaudhary, Florian Buettner +1
We address two challenges in topic models: (1) Context information around words helps in determining their actual meaning, e.g., "networks" used in the contexts "artificial neural…