4 citations · 11 across the 12 of their papers we have counts for
14 papers
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
Fabian Gröger, Shuo Wen, Maria Brbić
The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics…
Representation-Based Data Quality Audits for Audio
Alvaro Gonzalez-Jimenez, Fabian Gröger, Linda Wermelinger +4
Data quality issues such as off-topic samples, near duplicates, and label errors often limit the performance of audio-based systems. This paper addresses these issues by adapting S…
Clinical Uncertainty Impacts Machine Learning Evaluations
Simone Lionetti, Fabian Gröger, Philippe Gottfrois +4
Clinical dataset labels are rarely certain as annotators disagree and confidence is not uniform across cases. Typical aggregation procedures, such as majority voting, obscure this…
With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You
Fabian Gröger, Shuo Wen, Huyen Le +1
Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment, including zero-shot classification and cross-modal retrieval. However, ex…
Is Hyperbolic Space All You Need for Medical Anomaly Detection?
Alvaro Gonzalez-Jimenez, Simone Lionetti, Ludovic Amruthalingam +4
Medical anomaly detection has emerged as a promising solution to challenges in data availability and labeling constraints. Traditional methods extract features from different layer…
CleanPatrick: A Benchmark for Image Data Cleaning
Fabian Gröger, Simone Lionetti, Philippe Gottfrois +12
Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, limiting comparison and real-world releva…
Evaluation of Deep Audio Representations for Hearables
Fabian Gröger, Pascal Baumann, Ludovic Amruthalingam +3
Effectively steering hearable devices requires understanding the acoustic environment around the user. In the computational analysis of sound scenes, foundation models have emerged…
Towards Scalable Foundation Models for Digital Dermatology
Fabian Gröger, Philippe Gottfrois, Ludovic Amruthalingam +5
The growing demand for accurate and equitable AI models in digital dermatology faces a significant challenge: the lack of diverse, high-quality labeled data. In this work, we inves…
PASSION for Dermatology: Bridging the Diversity Gap with Pigmented Skin Images from Sub-Saharan Africa
Philippe Gottfrois, Fabian Gröger, Faly Herizo Andriambololoniaina +13
Africa faces a huge shortage of dermatologists, with less than one per million people. This is in stark contrast to the high demand for dermatologic care, with 80% of the paediatri…
Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring
Adrian Willi, Pascal Baumann, Sophie Erb +3
Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep-learning models which pose challenges for widespread…
Hyperbolic Metric Learning for Visual Outlier Detection
Alvaro Gonzalez-Jimenez, Simone Lionetti, Dena Bazazian +4
Out-Of-Distribution (OOD) detection is critical to deploy deep learning models in safety-critical applications. However, the inherent hierarchical concept structure of visual data,…
Towards Reliable Dermatology Evaluation Benchmarks
Fabian Gröger, Simone Lionetti, Philippe Gottfrois +6
Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates. We propose a resource-efficient data-cleaning protocol…
Intrinsic Self-Supervision for Data Quality Audits
Fabian Gröger, Simone Lionetti, Philippe Gottfrois +6
Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we rev…
STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains
Fabian Gröger, Anne-Marie Rickmann, Christian Wachinger
We propose an unsupervised domain adaptation (UDA) approach for white matter hyperintensity (WMH) segmentation, which uses Self-Training with Uncertainty DEpendent Label refinement…