Copertina

Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Penzel, Niklas, Denzler, Joachim
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
di: Schmalwasser, Laines, et al.
Pubblicazione: (2025)

Reducing Bias in Pre-trained Models by Tuning while Penalizing Change
di: Penzel, Niklas, et al.
Pubblicazione: (2024)

Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions
di: Büchner, Tim, et al.
Pubblicazione: (2024)

The Power of Properties: Uncovering the Influential Factors in Emotion Classification
di: Büchner, Tim, et al.
Pubblicazione: (2024)

Gradient Extrapolation for Debiased Representation Learning
di: Asaad, Ihab, et al.
Pubblicazione: (2025)

When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out
di: Piater, Tristan, et al.
Pubblicazione: (2024)

Realistic Face Reconstruction from Facial Embeddings via Diffusion Models
di: Han, Dong, et al.
Pubblicazione: (2026)

Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models
di: Venkataramanan, Aishwarya, et al.
Pubblicazione: (2025)

FGGP: Fixed-Rate Gradient-First Gradual Pruning
di: Zhu, Lingkai, et al.
Pubblicazione: (2024)

Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention
di: Gu, Jiawei, et al.
Pubblicazione: (2025)

Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
di: Sobieski, Bartlomiej, et al.
Pubblicazione: (2026)

Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation
di: Cai, Lincan, et al.
Pubblicazione: (2024)

PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models
di: Sadanandan, Binesh, et al.
Pubblicazione: (2026)

Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
di: Yoshikawa, Yuya, et al.
Pubblicazione: (2024)

Explaining the Impact of Training on Vision Models via Activation Clustering
di: Boubekki, Ahcène, et al.
Pubblicazione: (2024)

Extreme Weather Nowcasting via Local Precipitation Pattern Prediction
di: Song, Changhoon, et al.
Pubblicazione: (2026)

Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations
di: Wang, Bin, et al.
Pubblicazione: (2022)

Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition
di: Zimmermann, Jakob Paul, et al.
Pubblicazione: (2026)

Uncertainty-Aware Diffusion Model for Multimodal Highway Trajectory Prediction via DDIM Sampling
di: Neumeier, Marion, et al.
Pubblicazione: (2026)

Explaining Representation by Mutual Information
di: Gu, Lifeng
Pubblicazione: (2021)

Learning to Predict Gradients for Semi-Supervised Continual Learning
di: Luo, Yan, et al.
Pubblicazione: (2022)

On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process
di: Adhane, Gereziher, et al.
Pubblicazione: (2024)

TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
di: Taghanaki, Saeid Asgari, et al.
Pubblicazione: (2023)

DXAI: Explaining Classification by Image Decomposition
di: Kadar, Elnatan, et al.
Pubblicazione: (2023)

Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
di: Wang, Zixi, et al.
Pubblicazione: (2025)

Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE
di: Roßberg, Niklas, et al.
Pubblicazione: (2026)

Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention
di: Gu, Xunjiang, et al.
Pubblicazione: (2024)

Q-SENN: Quantized Self-Explaining Neural Networks
di: Norrenbrock, Thomas, et al.
Pubblicazione: (2023)

What is Missing? Explaining Neurons Activated by Absent Concepts
di: Hesse, Robin, et al.
Pubblicazione: (2026)

Multimodal Neurodegenerative Disease Subtyping Explained by ChatGPT
di: Reyes, Diego Machado, et al.
Pubblicazione: (2024)

C$^{2}$INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention
di: Li, Xiaohe, et al.
Pubblicazione: (2024)

Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions
di: Vitry, Thomas, et al.
Pubblicazione: (2026)

Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks
di: Alcover-Couso, Roberto, et al.
Pubblicazione: (2024)

TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
di: Stein, Gideon, et al.
Pubblicazione: (2026)

Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling
di: Haber, Eldad, et al.
Pubblicazione: (2025)

Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
di: Jeeveswaran, Kishaan, et al.
Pubblicazione: (2024)

Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
di: Xu, Yuan, et al.
Pubblicazione: (2025)

Balancing Multimodal Domain Generalization via Gradient Modulation and Projection
di: Li, Hongzhao, et al.
Pubblicazione: (2026)

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

Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models
di: Mersha, Melkamu Abay, et al.
Pubblicazione: (2026)