426 citations
- University of TübingenDE25 papers
- Max Planck Institute for Intelligent SystemsDE11 papers
- Max Planck Institute for Biological CyberneticsDE7 papers
- Max Planck SocietyDE6 papers
- University of LucerneCH3 papers
- University of Maryland, College ParkUS3 papers
- Max Planck Institute for Gravitational PhysicsDE2 papers
- Microsoft Research (United Kingdom)GB2 papers
- Tübingen AI Center2 papers
- University Hospital of BernCH2 papers
- University of BernCH2 papers
- University of BremenDE2 papers
11 papers · 1 filter
Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals
Susu Sun, Stefano Woerner, Andreas Maier +2
Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions…
A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
Stefano Woerner, Arthur Jaques, Christian F. Baumgartner
While the field of medical image analysis has undergone a transformative shift with the integration of machine learning techniques, the main challenge of these techniques is often…
Five Points to Check when Comparing Visual Perception in Humans and Machines
Christina M. Funke, Judy Borowski, Karolina Stosio +3
With the rise of machines to human-level performance in complex recognition tasks, a growing amount of work is directed towards comparing information processing in humans and machi…
Generalisation in humans and deep neural networks
Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber +3
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using thr…
Diverse feature visualizations reveal invariances in early layers of deep neural networks
Santiago A. Cadena, Marissa A. Weis, Leon A. Gatys +2
Visualizing features in deep neural networks (DNNs) can help understanding their computations. Many previous studies aimed to visualize the selectivity of individual units by findi…
End-to-end Recovery of Human Shape and Pose
Angjoo Kanazawa, Michael J. Black, David W. Jacobs +1
We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that c…