Universität Bielefeld Play

[BA/MA/Project]

3D Concept Extraction

Contact: Jay (Isaac) Roberts - Alexander Schulz

Concepts have gained significant attention as an explainable AI (XAI) technique due to their human interpretability. While concept-based explanations are widely studied in image and text domains, much less work has been done in the context of 3D data. This project will explore whether human-interpretable concepts can be identified in 3D datasets, and if so, evaluate their suitability as an explanation technique.

Literature

  1. Fel, Thomas, et al. “Craft: Concept recursive activation factorization for explainability.”
  2. “Intrinsic Mesh CNNs”