activity
20242026
collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2026

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…

cs.CV2024

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…

cs.CV2024

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…

cs.CV2024

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…

cs.CV2024

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…