Cover Image

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schwalbe, Gesina, Keser, Mert, Bayerkuhnlein, Moritz, Heinert, Edgar, Mütze, Annika, Keller, Marvin, Tiwari, Sparsh, Mikriukov, Georgii, Wolter, Diedrich, Lee, Jae Hee, Rottmann, Matthias
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
by: Schwalbe, Gesina, et al.
Published: (2025)

Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
by: Lee, Jae Hee, et al.
Published: (2024)

Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces
by: Mikriukov, Georgii, et al.
Published: (2023)

Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability
by: Mikriukov, Georgii, et al.
Published: (2023)

The Anatomy of Adversarial Attacks: Concept-based XAI Dissection
by: Mikriukov, Georgii, et al.
Published: (2024)

Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation
by: Heinert, Edgar, et al.
Published: (2025)

Weakly Supervised Concept Learning for Object-centric Visual Reasoning
by: Tiwari, Sparsh, et al.
Published: (2026)

Unveiling Ontological Commitment in Multi-Modal Foundation Models
by: Keser, Mert, et al.
Published: (2024)

On the Influence of Shape, Texture and Color for Learning Semantic Segmentation
by: Mütze, Annika, et al.
Published: (2024)

Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks
by: Hamscher, Ben, et al.
Published: (2025)

Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving
by: Keser, Mert, et al.
Published: (2025)

Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties
by: Dankworth, Raik, et al.
Published: (2025)

Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks
by: Heinert, Edgar, et al.
Published: (2024)

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion
by: Heinert, Edgar, et al.
Published: (2024)

Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?
by: Mütze, Annika, et al.
Published: (2025)

Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study
by: Mitra, Pallavi, et al.
Published: (2024)

PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage
by: Gottwald, Thomas, et al.
Published: (2025)

Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?
by: Grabowsky, Natalie, et al.
Published: (2025)

Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learning
by: Ilyas, Sadia, et al.
Published: (2026)

Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence
by: Mikriukov, Georgii, et al.
Published: (2026)

Locally Testing Model Detections for Semantic Global Concepts
by: Motzkus, Franz, et al.
Published: (2024)

LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving
by: Keser, Mert, et al.
Published: (2026)

AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains
by: Lis, Krzysztof, et al.
Published: (2022)

Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis
by: Galappaththige, Chamuditha Jayanga, et al.
Published: (2026)

Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methods
by: Manas, Kumar, et al.
Published: (2025)

How Could Generative AI Support Compliance with the EU AI Act? A Review for Safe Automated Driving Perception
by: Keser, Mert, et al.
Published: (2024)

A Verifier Hierarchy
by: Kaptein, Maurits
Published: (2025)

10Be measured on Akademii Nauk ice core, Russian Arctic, for the period 1590-1950 CE
by: Fritzsche, Diedrich
Published: (2017)

Modelling Population-Level Hes1 Dynamics: Insights from a Multi-Framework Approach
by: Menz, Gesina, et al.
Published: (2024)

From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
by: Lee, Jae Hee, et al.
Published: (2023)

Quantifying Social Presence in Mixed Reality: A Contemporary Review of Techniques and Innovations
by: Srivastava, Sparsh
Published: (2024)

A book proof of the middle levels theorem
by: Mütze, Torsten
Published: (2023)

Combinatorial Gray codes-an updated survey
by: Mütze, Torsten
Published: (2022)

Towards generalizing deep-audio fake detection networks
by: Gasenzer, Konstantin, et al.
Published: (2023)

O homem na linguagem: o entrelaçamento língua e cultura na aquisição da linguagem numa perspectiva enunciativa aquisicional
by: Marlete Sandra Diedrich
Published: (2017)

Fixation probability in Moran-like Processes on graphs
by: Keller, Peter, et al.
Published: (2024)

Bedrohtes Begehren
by: Rottmann, Andrea
Published: (2026)

Learning Brenier Potentials with Convex Generative Adversarial Neural Networks
by: Drygala, Claudia, et al.
Published: (2025)

Adapting AlignScore Mertic for Factual Consistency Evaluation of Text in Russian: A Student Abstract
by: Zimin, Mikhail, et al.
Published: (2025)

Long-term effects of warren ripping for rabbit control in semi-arid South Australia.
by: Mutze, G. J.
Published: (1991)