JUGAL800813
x22
WORLD1-1
TIME000
Home Projects Publications Experiences About Contact Resume/CV
FASS.app - Project Details

Overview

FASS (Feature Attribution Stability Suite) is a benchmarking framework for evaluating the robustness of explanation methods under prediction-invariant perturbations. It addresses a critical gap in explainable AI, where attribution methods often produce unstable explanations despite identical model predictions. FASS provides a systematic way to assess and compare the stability of different attribution techniques, guiding the development of more reliable and trustworthy explainability tools.

Framework

1. Apply controlled perturbations (geometric, photometric, compression)
2. Generate attribution maps using selected XAI methods
3. Align perturbed and original inputs for comparison
4. Compute stability metrics across attribution maps
5. Aggregate results into benchmark scores

Stability Decomposition

FASS introduces a three-axis decomposition for attribution stability:

Structural Similarity: pixel-level consistency (SSIM)
Rank Correlation: ordering consistency of feature importance
Top-k Overlap: agreement on most important features

Evaluation Scope

• Supports Grad-CAM, Integrated Gradients, SHAP, and LIME
• Evaluates across image classification and vision models
• Enables robustness comparison under realistic perturbations

Key Contributions

• First systematic framework for attribution stability benchmarking
• Decouples prediction correctness from explanation robustness
• Provides standardized metrics for XAI evaluation

Tech. Stack

Python, PyTorch, OpenCV, PIL, NumPy, SciPy, XAI Libraries

Links

Publication Page GitHub Repository

← Back to Projects
FASS.app | Super Mario Edition | Built by Jugal Gajjar Ready
?
MARIO X
Hey! I'm Mario, Jugal's portfolio assistant. Ask me anything about his projects, publications, experience, skills, or education!