A perturbation-based metric using FGSM flips of ±1/255 instead of zero-masking gives more consistent and monotonic evaluation of attribution maps across 15 CNN-dataset pairs, with SmoothGrad ranked first.
The Weighting Game: Evaluating Quality of Explainability Methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The objective of this paper is to assess the quality of explanation heatmaps for image classification tasks. To assess the quality of explainability methods, we approach the task through the lens of accuracy and stability. In this work, we make the following contributions. Firstly, we introduce the Weighting Game, which measures how much of a class-guided explanation is contained within the correct class' segmentation mask. Secondly, we introduce a metric for explanation stability, using zooming/panning transformations to measure differences between saliency maps with similar contents. Quantitative experiments are produced, using these new metrics, to evaluate the quality of explanations provided by commonly used CAM methods. The quality of explanations is also contrasted between different model architectures, with findings highlighting the need to consider model architecture when choosing an explainability method.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach
A perturbation-based metric using FGSM flips of ±1/255 instead of zero-masking gives more consistent and monotonic evaluation of attribution maps across 15 CNN-dataset pairs, with SmoothGrad ranked first.