70 citations · 130 across the 41 of their papers we have counts for
8 papers · 1 filter
Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?
Teodor Chiaburu, Franz Motzkus, Frank Haußer +1
Vision Sparse Autoencoders (SAEs) have become a popular tool in Mechanistic Interpretability due to their presumed ability to disentangle complex features learned by a model into m…
Monocular 3D Object Position Estimation with VLMs for Human-Robot Interaction
Ari Wahl, Dorian Gawlinski, David Przewozny +3
Pre-trained general-purpose Vision-Language Models (VLM) hold the potential to enhance intuitive human-machine interactions due to their rich world knowledge and 2D object detectio…
The Influence of Faulty Labels in Data Sets on Human Pose Estimation
Arnold Schwarz, Levente Hernadi, Felix Bießmann +1
In this study we provide empirical evidence demonstrating that the quality of training data impacts model performance in Human Pose Estimation (HPE). Inaccurate labels in widely us…
Generating Synthetic Satellite Imagery for Rare Objects: An Empirical Comparison of Models and Metrics
Tuong Vy Nguyen, Johannes Hoster, Alexander Glaser +2
Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How…
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models
Teodor Chiaburu, Frank Haußer, Felix Bießmann
Mounting evidence in explainability for artificial intelligence (XAI) research suggests that good explanations should be tailored to individual tasks and should relate to concepts…
Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification
Tuong Vy Nguyen, Alexander Glaser, Felix Biessmann
Novel deep-learning (DL) architectures have reached a level where they can generate digital media, including photorealistic images, that are difficult to distinguish from real data…
Using Game Engines and Machine Learning to Create Synthetic Satellite Imagery for a Tabletop Verification Exercise
Johannes Hoster, Sara Al-Sayed, Felix Biessmann +4
Satellite imagery is regarded as a great opportunity for citizen-based monitoring of activities of interest. Relevant imagery may however not be available at sufficiently high reso…
A psychophysics approach for quantitative comparison of interpretable computer vision models
Felix Biessmann, Dionysius Irza Refiano
The field of transparent Machine Learning (ML) has contributed many novel methods aiming at better interpretability for computer vision and ML models in general. But how useful the…