AIM is a new saliency-guided adversarial feature replacement method to evaluate faithfulness of saliency maps and reliability of masking operators on image, audio, and EEG tasks.
Evaluating feature importance estimates
5 Pith papers cite this work, alongside 382 external citations. Polarity classification is still indexing.
5
Pith papers citing it
382
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
The C-Score quantifies intra-class explanation consistency for CAM methods via confidence-weighted pairwise soft IoU and detects AUC-consistency dissociation as an early warning for model instability on chest X-ray classification.
Introduces a perturbation-based fidelity metric tailored to few-class CNN classifiers for real-conditions XAI evaluation, tested on medical and natural imaging against human-centric metrics.
A generative AI pipeline scrapes public residential data, uses LLaVA and GPT to build GeoJSON and inspection notes, runs EnergyPlus simulations, and labels homes, but external validation is missing.
Gradient- and perturbation-based XAI methods show substantial agreement on frontal, temporal, and posterior EEG regions for an InceptionTime MDD classifier, while DeepSHAP differs, with overall partial convergence and method-dependent variability.
citing papers explorer
-
AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps
AIM is a new saliency-guided adversarial feature replacement method to evaluate faithfulness of saliency maps and reliability of masking operators on image, audio, and EEG tasks.
-
Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification
The C-Score quantifies intra-class explanation consistency for CAM methods via confidence-weighted pairwise soft IoU and detects AUC-consistency dissociation as an early warning for model instability on chest X-ray classification.
-
Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations
Introduces a perturbation-based fidelity metric tailored to few-class CNN classifiers for real-conditions XAI evaluation, tested on medical and natural imaging against human-centric metrics.
-
Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity
A generative AI pipeline scrapes public residential data, uses LLaVA and GPT to build GeoJSON and inspection notes, runs EnergyPlus simulations, and labels homes, but external validation is missing.
-
Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection
Gradient- and perturbation-based XAI methods show substantial agreement on frontal, temporal, and posterior EEG regions for an InceptionTime MDD classifier, while DeepSHAP differs, with overall partial convergence and method-dependent variability.