4 citations · 5 across the 6 of their papers we have counts for
7 papers
DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
Robert Zimmermann, Thomas Norrenbrock, Bodo Rosenhahn
Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles…
Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction
Patrick Glandorf, Thomas Norrenbrock, Bodo Rosenhahn
Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning…
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
Thomas Norrenbrock, Timo Kaiser, Sovan Biswas +3
Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial compl…
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
Timo Kaiser, Thomas Norrenbrock, Bodo Rosenhahn
The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of…
QPM: Discrete Optimization for Globally Interpretable Image Classification
Thomas Norrenbrock, Timo Kaiser, Sovan Biswas +2
Understanding the classifications of deep neural networks, e.g. used in safety-critical situations, is becoming increasingly important. While recent models can locally explain a si…
Q-SENN: Quantized Self-Explaining Neural Networks
Thomas Norrenbrock, Marco Rudolph, Bodo Rosenhahn
Explanations in Computer Vision are often desired, but most Deep Neural Networks can only provide saliency maps with questionable faithfulness. Self-Explaining Neural Networks (SEN…
Take 5: Interpretable Image Classification with a Handful of Features
Thomas Norrenbrock, Marco Rudolph, Bodo Rosenhahn
Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimens…