5 papers · 1 filter
On the Faithfulness of Post-Hoc Concept Bottleneck Models
Laines Schmalwasser, Jan Blunk, Niklas Penzel +2
Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color. To bridge the gap between opaque deep learning representation…
Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions
Tim Büchner, Niklas Penzel, Orlando Guntinas-Lichius +1
Understanding expressions is vital for deciphering human behavior, and nowadays, end-to-end trained black box models achieve high performance. Due to the black-box nature of these…
When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out
Tristan Piater, Niklas Penzel, Gideon Stein +1
A substantial body of research has focused on developing systems that assist medical professionals during labor-intensive early screening processes, many based on convolutional dee…
Reducing Bias in Pre-trained Models by Tuning while Penalizing Change
Niklas Penzel, Gideon Stein, Joachim Denzler
Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it i…
The Power of Properties: Uncovering the Influential Factors in Emotion Classification
Tim Büchner, Niklas Penzel, Orlando Guntinas-Lichius +1
Facial expression-based human emotion recognition is a critical research area in psychology and medicine. State-of-the-art classification performance is only reached by end-to-end…