Saliency strikes back: How filtering out high frequencies improves white-box explanations

Understand

Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process.

• We have identified a significant limitation in one type of attribution methods, known as ``white-box" methods.
• Although highly efficient, as we will show, these methods rely on a gradient signal that is often contaminated by high-frequency artifacts.
• To overcome this limitation, we introduce a new approach called "FORGrad".