Imagen de Portada

Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Elisha, Yehonatan, Cohen, Seffi, Barkan, Oren, Koenigstein, Noam
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

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
por: Elisha, Yehonatan, et al.
Publicado: (2026)

BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation
por: Barkan, Oren, et al.
Publicado: (2024)

Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems
por: Arviv, Dor, et al.
Publicado: (2025)

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
por: Barkan, Oren, et al.
Publicado: (2025)

Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon
por: Cohen-Inger, Nurit, et al.
Publicado: (2025)

Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
por: Suwal, Sanish, et al.
Publicado: (2025)

A Fresh Look at Sanity Checks for Saliency Maps
por: Hedström, Anna, et al.
Publicado: (2024)

Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification
por: Hinns, James, et al.
Publicado: (2025)

CNN Explainability with Multivector Tucker Saliency Maps for Self-Supervised Models
por: Bouayed, Aymene Mohammed, et al.
Publicado: (2024)

DejAIvu: Identifying and Explaining AI Art on the Web in Real-Time with Saliency Maps
por: Dzuong, Jocelyn
Publicado: (2025)

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

Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
por: Dereka, Stanislav, et al.
Publicado: (2023)

Modeling Saliency Dataset Bias
por: Kümmerer, Matthias, et al.
Publicado: (2025)

Guided AbsoluteGrad: Magnitude of Gradients Matters to Explanation's Localization and Saliency
por: Huang, Jun, et al.
Publicado: (2024)

Rethinking the Evaluation Protocol of Domain Generalization
por: Yu, Han, et al.
Publicado: (2023)

Aligning Machine and Human Visual Representations across Abstraction Levels
por: Muttenthaler, Lukas, et al.
Publicado: (2024)

Correlation of Object Detection Performance with Visual Saliency and Depth Estimation
por: Bartolo, Matthias, et al.
Publicado: (2024)

Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection
por: Bartolo, Matthias, et al.
Publicado: (2024)

Rethinking Evaluation Paradigms in IBP-based Certified Training
por: Kaulen, Konstantin, et al.
Publicado: (2026)

Saliency-guided Emotion Modeling: Predicting Viewer Reactions from Video Stimuli
por: Yaragoppa, Akhila, et al.
Publicado: (2025)

X-Mark: Saliency-Guided Robust Dataset Ownership Verification for Medical Imaging
por: Kulkarni, Pranav, et al.
Publicado: (2026)

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

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation
por: Termritthikun, Chakkrit, et al.
Publicado: (2024)

Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization
por: Wall, Casey, et al.
Publicado: (2025)

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
por: Mallinar, Neil, et al.
Publicado: (2022)

Explanation Bottleneck Models
por: Yamaguchi, Shin'ya, et al.
Publicado: (2024)

Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
por: Luo, Weijian
Publicado: (2024)

Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where
por: Chin, Zhi-Yi, et al.
Publicado: (2023)

Saliency strikes back: How filtering out high frequencies improves white-box explanations
por: Muzellec, Sabine, et al.
Publicado: (2023)

Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy
por: Pattnayak, Priyaranjan, et al.
Publicado: (2024)

LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies
por: Shi, Jia, et al.
Publicado: (2024)

Cognitive Science-Inspired Evaluation of Core Capabilities for Object Understanding in AI
por: Rutar, Danaja, et al.
Publicado: (2025)

MEGL: Multimodal Explanation-Guided Learning
por: Zhang, Yifei, et al.
Publicado: (2024)

Guaranteed Optimal Compositional Explanations for Neurons
por: La Rosa, Biagio, et al.
Publicado: (2025)

Human-Centered Evaluation of XAI Methods
por: Dawoud, Karam, et al.
Publicado: (2023)

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
por: Kim, Beomsu, et al.
Publicado: (2025)

On Spectral Properties of Gradient-based Explanation Methods
por: Mehrpanah, Amir, et al.
Publicado: (2025)

Measuring the (Un)Faithfulness of Concept-Based Explanations
por: Kumar, Shubham, et al.
Publicado: (2025)

Open Vocabulary Compositional Explanations for Neuron Alignment
por: La Rosa, Biagio, et al.
Publicado: (2025)

Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach
por: Nieradzik, Lars, et al.
Publicado: (2024)