Stars
Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Workshop (spotlight)
Layer-Wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]
Prototypical Concept-based Explanations, accepted at SAIAD workshop at CVPR 2024.
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.
Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization
Some code for generating voronoy-cell toy data
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.