B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable

28 January 2025

Papers citing "B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable"

3 / 3 papers shown

Title
From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection Moritz Vandenhirtz Julia E. Vogt 12 0 0 09 May 2025
Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning Hubert Baniecki P. Biecek AAML 68 0 0 11 Mar 2025
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Walid Bousselham Angie Boggust Sofian Chaybouti Hendrik Strobelt Hilde Kuehne 83 10 0 04 Apr 2024