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.
Towards better understanding of gradient-based attribution methods for Deep Neural Networks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Understanding the flow of information in Deep Neural Networks (DNNs) is a challenging problem that has gain increasing attention over the last few years. While several methods have been proposed to explain network predictions, there have been only a few attempts to compare them from a theoretical perspective. What is more, no exhaustive empirical comparison has been performed in the past. In this work, we analyze four gradient-based attribution methods and formally prove conditions of equivalence and approximation between them. By reformulating two of these methods, we construct a unified framework which enables a direct comparison, as well as an easier implementation. Finally, we propose a novel evaluation metric, called Sensitivity-n and test the gradient-based attribution methods alongside with a simple perturbation-based attribution method on several datasets in the domains of image and text classification, using various network architectures.
representative citing papers
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.
Adding a correlation-based clustering step before feature attribution improves selected sensor configurations for structural health monitoring, airfoil lift prediction, and wall-pressure-based velocity estimation.
WSVD delivers over 1.8x faster VLM decoding via weighted low-rank approximation at fine granularity plus quantization, without accuracy loss.
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.
-
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.
-
Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)
Adding a correlation-based clustering step before feature attribution improves selected sensor configurations for structural health monitoring, airfoil lift prediction, and wall-pressure-based velocity estimation.
-
WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
WSVD delivers over 1.8x faster VLM decoding via weighted low-rank approximation at fine granularity plus quantization, without accuracy loss.