Copertina

Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nieradzik, Lars, Stephani, Henrike, Keuper, Janis
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
di: Nieradzik, Lars, et al.
Pubblicazione: (2024)

Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry
di: Nieradzik, Lars, et al.
Pubblicazione: (2024)

WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images
di: Nieradzik, Lars, et al.
Pubblicazione: (2024)

Can Biases in ImageNet Models Explain Generalization?
di: Gavrikov, Paul, et al.
Pubblicazione: (2024)

How Do Training Methods Influence the Utilization of Vision Models?
di: Gavrikov, Paul, et al.
Pubblicazione: (2024)

Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
di: Grommelt, Patrick, et al.
Pubblicazione: (2024)

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
di: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Pubblicazione: (2024)

Can We Talk Models Into Seeing the World Differently?
di: Gavrikov, Paul, et al.
Pubblicazione: (2024)

Beyond String Matching: Semantic Evaluation of PDF Table Extraction
di: Horn, Pius, et al.
Pubblicazione: (2026)

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

Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods
di: Kiourti, Panagiota, et al.
Pubblicazione: (2025)

Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition
di: Kong, Weizhe, et al.
Pubblicazione: (2025)

Efficient Hyperparameter Importance Assessment for CNNs
di: Wang, Ruinan, et al.
Pubblicazione: (2024)

Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs
di: Horn, Pius, et al.
Pubblicazione: (2025)

Explaning with trees: interpreting CNNs using hierarchies
di: Rodrigues, Caroline Mazini, et al.
Pubblicazione: (2024)

CNNs Avoid Curse of Dimensionality by Learning on Patches
di: Madala, Vamshi C., et al.
Pubblicazione: (2022)

CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability
di: He, Hongjie, et al.
Pubblicazione: (2025)

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
di: Li, Yumeng, et al.
Pubblicazione: (2024)

Explaining Model Overfitting in CNNs via GMM Clustering
di: Dou, Hui, et al.
Pubblicazione: (2024)

Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
di: Lahoti, Aakash, et al.
Pubblicazione: (2024)

TraNCE: Transformative Non-linear Concept Explainer for CNNs
di: Akpudo, Ugochukwu Ejike, et al.
Pubblicazione: (2025)

Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows
di: Eckerle, Achim, et al.
Pubblicazione: (2025)

Stacked Ensemble of Fine-Tuned CNNs for Knee Osteoarthritis Severity Grading
di: Gupta, Adarsh, et al.
Pubblicazione: (2025)

RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model
di: Alomar, Khaled, et al.
Pubblicazione: (2024)

From Ground to Air: Noise Robustness in Vision Transformers and CNNs for Event-Based Vehicle Classification with Potential UAV Applications
di: Almesafri, Nouf, et al.
Pubblicazione: (2025)

Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability
di: Sarkar, Syamantak, et al.
Pubblicazione: (2025)

Do Transformers Understand Ancient Roman Coin Motifs Better than CNNs?
di: Reid, David, et al.
Pubblicazione: (2026)

Domain-Aware Fine-Tuning of Foundation Models
di: Kaplan, Ugur Ali, et al.
Pubblicazione: (2024)

Better Understanding Differences in Attribution Methods via Systematic Evaluations
di: Rao, Sukrut, et al.
Pubblicazione: (2023)

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification
di: De Santis, Antonio, et al.
Pubblicazione: (2024)

Frugal Federated Learning for Violence Detection: A Comparison of LoRA-Tuned VLMs and Personalized CNNs
di: Thuau, Sébastien, et al.
Pubblicazione: (2025)

A Comparative Study of Custom CNNs, Pre-trained Models, and Transfer Learning Across Multiple Visual Datasets
di: Akhand, Annoor Sharara
Pubblicazione: (2026)

Divide & Bind Your Attention for Improved Generative Semantic Nursing
di: Li, Yumeng, et al.
Pubblicazione: (2023)

VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings
di: Scabini, Leonardo, et al.
Pubblicazione: (2025)

Adaptive Knowledge Distillation for Classification of Hand Images using Explainable Vision Transformers
di: Nguyen, Thanh Thi, et al.
Pubblicazione: (2024)

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
di: Burgert, Tom, et al.
Pubblicazione: (2025)

Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
di: Yoo, Seungju, et al.
Pubblicazione: (2025)

Detecção da Psoríase Utilizando Visão Computacional: Uma Abordagem Comparativa Entre CNNs e Vision Transformers
di: Lucena, Natanael, et al.
Pubblicazione: (2025)

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
di: Ahn, Donghoon, et al.
Pubblicazione: (2025)

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
di: Agnihotri, Shashank, et al.
Pubblicazione: (2024)