Enrico Ferrari — accepted AI-conference papers

2026

ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees

Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda

AAAI 2026technical

Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley values has been widely used to interpret machine learning (ML) models and their

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Using Stratified Sampling to Improve LIME Image Explanations

Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda

AAAI 2024technical

We investigate the use of a stratified sampling approach for LIME Image, a popular model-agnostic explainable AI method for computer vision tasks, in order to reduce the artifacts generated by typical Monte Carlo sampling. Such artifacts are due to the undersampling of the dependent variable in the…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗