AI RESEARCH
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
arXiv CS.LG
•
ArXi:2511.20779v2 Announce Type: replace Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial complement to effectively human experts during inference. This work proposes the Calibrated Hierarchical QPM (CHiQPM) which offers uniquely comprehensive global and local interpretability, paving the way for human-AI complementarity.