Imagen de Portada

On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Schwalbe, Gesina, Mikriukov, Georgii, Heinert, Edgar, Gerolymatos, Stavros, Keser, Mert, Knoll, Alois, Rottmann, Matthias, Mütze, Annika
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
por: Schwalbe, Gesina, et al.
Publicado: (2026)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Cluster Exploration using Informative Manifold Projections
por: Gerolymatos, Stavros, et al.
Publicado: (2023)

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
por: Guimard, Quentin, et al.
Publicado: (2026)

GPT-4V as Traffic Assistant: An In-depth Look at Vision Language Model on Complex Traffic Events
por: Zhou, Xingcheng, et al.
Publicado: (2024)

Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
por: Erogullari, Eren, et al.
Publicado: (2025)

BiSeg-SAM: Weakly-Supervised Post-Processing Framework for Boosting Binary Segmentation in Segment Anything Models
por: Su, Encheng, et al.
Publicado: (2025)

ReVision : A Post-Hoc, Vision-Based Technique for Replacing Unacceptable Concepts in Image Generation Pipeline
por: Singh, Gurjot, et al.
Publicado: (2026)

Crystal structure prediction using graph neural combinatorial optimization
por: Gerolymatos, Stavros, et al.
Publicado: (2026)

DepthVision: Enabling Robust Vision-Language Models with GAN-Based LiDAR-to-RGB Synthesis for Autonomous Driving
por: Kirchner, Sven, et al.
Publicado: (2025)

Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs
por: Ji, SeungWon, et al.
Publicado: (2025)

Periodicity - Based Computation of Optical Flow
por: Georgii Khachaturov
Publicado: (2014)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
por: Lian, Jiawei, et al.
Publicado: (2024)

Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification
por: Rottmann, Matthias, et al.
Publicado: (2022)

False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation
por: Maag, Kira, et al.
Publicado: (2022)

Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems
por: Kirchner, Sven, et al.
Publicado: (2025)