Cover Image

Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Róisín, McDermott, James, O'Riordan, Colm
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sampling Matters in Explanations: Towards Trustworthy Attribution Analysis Building Block in Visual Models through Maximizing Explanation Certainty
by: Luo, Róisín, et al.
Published: (2025)

Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization
by: Luo, Róisín, et al.
Published: (2024)

Higher-Order Singular-Value Derivatives of Rectangular Real Matrices
by: Luo, Róisín, et al.
Published: (2025)

Optimization-Induced Dynamics of Lipschitz Continuity in Neural Networks
by: Luo, Róisín, et al.
Published: (2025)

Embedding Compression for Efficient Re-Identification
by: McDermott, Luke
Published: (2024)

A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields
by: McDermott, Matthew, et al.
Published: (2024)

ICET Online Accuracy Characterization for Geometry-Based Laser Scan Matching
by: McDermott, Matthew, et al.
Published: (2023)

Interpreting CLIP's Image Representation via Text-Based Decomposition
by: Gandelsman, Yossi, et al.
Published: (2023)

Towards Robust Sequential Decomposition for Complex Image Editing
by: Zeng, Zilai, et al.
Published: (2026)

Can Synthetic Data Improve Symbolic Regression Extrapolation Performance?
by: Ramlan, Fitria Wulandari, et al.
Published: (2025)

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
by: Lee, Tae-Young, et al.
Published: (2025)

Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
by: Meleshin, Igor, et al.
Published: (2025)

Empowering Morphing Attack Detection using Interpretable Image-Text Foundation Model
by: Patwardhan, Sushrut, et al.
Published: (2025)

ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation
by: Zhang, Yi, et al.
Published: (2024)

Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection
by: Mandelli, Sara, et al.
Published: (2025)

Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
by: Bu, Edmund, et al.
Published: (2025)

On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
by: Guo, Jianing, et al.
Published: (2025)

Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework
by: Jia, Furong, et al.
Published: (2025)

Interpretable Medical Image Classification using Prototype Learning and Privileged Information
by: Gallee, Luisa, et al.
Published: (2023)

DEPICT: Diffusion-Enabled Permutation Importance for Image Classification Tasks
by: Jabbour, Sarah, et al.
Published: (2024)

Explaining Human Comparisons using Alignment-Importance Heatmaps
by: Truong, Nhut, et al.
Published: (2024)

Understanding Semantic Perturbations on In-Processing Generative Image Watermarks
by: Nakra, Anirudh, et al.
Published: (2026)

Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosis
by: Wang, Hongmei, et al.
Published: (2024)

An Interpretable Local Editing Model for Counterfactual Medical Image Generation
by: Min, Hyungi, et al.
Published: (2026)

Unsupervised Learning of Robust Spectral Shape Matching
by: Cao, Dongliang, et al.
Published: (2023)

Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts
by: Crabbé, Jonathan, et al.
Published: (2023)

Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images
by: Monfared, Vahid, et al.
Published: (2026)

Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis
by: Lee, Haeil, et al.
Published: (2024)

FAIR-ESI: Feature Adaptive Importance Refinement for Electrophysiological Source Imaging
by: Zou, Linyong, et al.
Published: (2026)

StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
by: Li, Yanjie, et al.
Published: (2025)

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
by: Wu, Kai, et al.
Published: (2024)

P-TAME: Explain Any Image Classifier with Trained Perturbations
by: Ntrougkas, Mariano V., et al.
Published: (2025)

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought
by: Lee, Eunsoo, et al.
Published: (2026)

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
by: Han, Sangyu, et al.
Published: (2024)

IConMark: Robust Interpretable Concept-Based Watermark For AI Images
by: Sadasivan, Vinu Sankar, et al.
Published: (2025)

Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis
by: Wang, Pu, et al.
Published: (2026)

Customizable Perturbation Synthesis for Robust SLAM Benchmarking
by: Xu, Xiaohao, et al.
Published: (2024)

I2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps
by: Park, Junseo, et al.
Published: (2024)

Spectral Compressive Imaging via Chromaticity-Intensity Decomposition
by: Wang, Xiaodong, et al.
Published: (2025)

Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography
by: Zhou, Kailai, et al.
Published: (2024)