collaborators

12 papers

cs.CV2026

MUFASA: A Multi-Layer Framework for Slot Attention

Sebastian Bock, Leonie Schüßler, Krishnakant Singh +2

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vector…

cs.LG2026

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance

Doğukan Bağcı, Bernt Schiele, Simone Schaub-Meyer +2

Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons often encode multiple unrelate…

cs.CV2026

What is Missing? Explaining Neurons Activated by Absent Concepts

Robin Hesse, Simone Schaub-Meyer, Janina Hesse +2

Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically by estimating a simplified causal…

cs.CV2026

Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?

Robin Hesse, Doğukan Bağcı, Bernt Schiele +2

Deep learning has become an essential part of computer vision, with deep neural networks (DNNs) excelling in predictive performance. However, they often fall short in other critica…

cs.CV2026

Multimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing Modalities

Maria Santos-Villafranca, Dustin Carrión-Ojeda, Alejandro Perez-Yus +3

Egocentric action recognition enables robots to facilitate human-robot interactions and monitor task progress. Existing methods often rely solely on RGB videos, although additional…

cs.CV2026

Evaluating Object-Centric Models beyond Object Discovery

Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth

Object-centric learning (OCL) aims to learn structured scene representations that support compositional generalization and robustness to out-of-distribution (OOD) data. However, OC…