Gesina Schwalbe

34 papers A 1B 1Misc 2Journal 21Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings.
CoRR
Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika Mütze, Marvin Keller, Sparsh Tiwari, Georgii Mikriukov, Diedrich Wolter, Jae Hee Lee, Matthias Rottmann
2025 — conf
Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties.
OVERLAY
Raik Dankworth, Gesina Schwalbe
2025 J jnl
Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties.
CoRR
Raik Dankworth, Gesina Schwalbe
2025 J jnl
Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving.
CoRR
Mert Keser, Halil Ibrahim Orhan, Niki Amini-Naieni, Gesina Schwalbe, Alois Knoll, Matthias Rottmann
2025 J jnl
Correction: Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces.
Int. J. Comput. Vis.
Georgii Mikriukov, Gesina Schwalbe, Korinna Bade
2025 B conf
Hidden-Layer Monitoring for Out-of-Distribution Localization in Image Segmentation.
RV
Jan Kretínský, Sabine Rieder, Gesina Schwalbe, Youssef Shoeb
2025 J jnl
Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces.
Int. J. Comput. Vis.
Georgii Mikriukov, Gesina Schwalbe, Korinna Bade
2025 — conf
On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs.
xAI (4)
Gesina Schwalbe, Georgii Mikriukov, Edgar Heinert, Stavros Gerolymatos, Mert Keser, Alois Knoll, Matthias Rottmann, Annika Mütze
2025 J jnl
On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs.
CoRR
Gesina Schwalbe, Georgii Mikriukov, Edgar Heinert, Stavros Gerolymatos, Mert Keser, Alois Knoll, Matthias Rottmann, Annika Mütze
2024 J jnl
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts.
Data Min. Knowl. Discov.
Gesina Schwalbe, Bettina Finzel
2024 — conf
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
ECCV Workshops (21)
Jae Hee Lee, Georgii Mikriukov, Gesina Schwalbe, Stefan Wermter, Diedrich Wolter
2024 J jnl
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
CoRR
Jae Hee Lee, Georgii Mikriukov, Gesina Schwalbe, Stefan Wermter, Diedrich Wolter
2024 A conf
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes.
WACV
Youssef Shoeb, Robin Chan, Gesina Schwalbe, Azarm Nowzad, Fatma Güney, Hanno Gottschalk
2024 — conf
Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study.
CVPR Workshops
Pallavi Mitra, Gesina Schwalbe, Nadja Klein
2024 J jnl
Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study.
CoRR
Pallavi Mitra, Gesina Schwalbe, Nadja Klein
2024 J jnl
The Anatomy of Adversarial Attacks: Concept-based XAI Dissection.
CoRR
Georgii Mikriukov, Gesina Schwalbe, Franz Motzkus, Korinna Bade
2024 J jnl
Unveiling Ontological Commitment in Multi-Modal Foundation Models.
CoRR
Mert Keser, Gesina Schwalbe, Niki Amini-Naieni, Matthias Rottmann, Alois Knoll
2024 — conf
Unveiling the Anatomy of Adversarial Attacks: Concept-Based XAI Dissection of CNNs.
xAI (1)
Georgii Mikriukov, Gesina Schwalbe, Franz Motzkus, Korinna Bade
2023 — conf
Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability.
xAI (2)
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
2023 J jnl
Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability.
CoRR
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
2023 J jnl
GCPV: Guided Concept Projection Vectors for the Explainable Inspection of CNN Feature Spaces.
CoRR
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
2023 J jnl
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes.
CoRR
Youssef Shoeb, Robin Chan, Gesina Schwalbe, Azarm Nowzad, Fatma Güney, Hanno Gottschalk
2023 — conf
Interpretable Model-Agnostic Plausibility Verification for 2D Object Detectors Using Domain-Invariant Concept Bottleneck Models.
CVPR Workshops
Mert Keser, Gesina Schwalbe, Azarm Nowzad, Alois Knoll
2023 J jnl
Quantified Semantic Comparison of Convolutional Neural Networks.
CoRR
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
2023 — conf
Revealing Similar Semantics Inside CNNs: An Interpretable Concept-Based Comparison of Feature Spaces.
PKDD/ECML Workshops (1)
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
2022 J jnl
Concept Embedding Analysis: A Review.
CoRR
Gesina Schwalbe
2022 J jnl
Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks.
CoRR
Gesina Schwalbe, Christian Wirth, Ute Schmid
2021 J jnl
Expressive Explanations of DNNs by Combining Concept Analysis with ILP.
CoRR
Johannes Rabold, Gesina Schwalbe, Ute Schmid
2021 J jnl
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety.
CoRR
Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas Bär, Felix Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser, Christian Heinzemann, Marco Hoffmann, Nikhil Kapoor, Falk Kappel, Marvin Klingner, Jan Kronenberger, Fabian Küppers, Jonas Löhdefink, Michael Mlynarski, Michael Mock, Firas Mualla, Svetlana Pavlitskaya, Maximilian Poretschkin, Alexander Pohl, Varun Ravi Kumar, Julia Rosenzweig, Matthias Rottmann, Stefan Rüping, Timo Sämann, Jan David Schneider, Elena Schulz, Gesina Schwalbe, Joachim Sicking, Toshika Srivastava, Serin Varghese, Michael Weber, Sebastian Wirkert, Tim Wirtz, Matthias Woehrle
2021 Misc conf
Verification of Size Invariance in DNN Activations Using Concept Embeddings.
AIAI
Gesina Schwalbe
2021 J jnl
Verification of Size Invariance in DNN Activations using Concept Embeddings.
CoRR
Gesina Schwalbe
2021 J jnl
XAI Method Properties: A (Meta-)study.
CoRR
Gesina Schwalbe, Bettina Finzel
2020 Misc conf
Expressive Explanations of DNNs by Combining Concept Analysis with ILP.
KI
Johannes Rabold, Gesina Schwalbe, Ute Schmid
2020 — conf
Structuring the Safety Argumentation for Deep Neural Network Based Perception in Automotive Applications.
SAFECOMP Workshops
Gesina Schwalbe, Bernhard Knie, Timo Sämann, Timo Dobberphul, Lydia Gauerhof, Shervin Raafatnia, Vittorio Rocco