[2511.20779] CHiQPM: Calibrated Hierarchical Interpretable Image Classification

Computer Science > Machine Learning arXiv:2511.20779 (cs) [Submitted on 25 Nov 2025 (v1), last revised 8 Apr 2026 (this version, v2)] Title:CHiQPM: Calibrated Hierarchical Interpretable Image Classification Authors:Thomas Norrenbrock, Timo Kaiser, Sovan Biswas, Neslihan Kose, Ramesh Manuvinakurike, Bodo Rosenhahn View a PDF of the paper titled CHiQPM: Calibrated Hierarchical Interpretable Image Classification, by Thomas Norrenbrock and 5 other authors View PDF Abstract: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 support 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. CHiQPM achieves superior global interpretability by contrastively explaining the majority of classes and offers novel hierarchical explanations that are more similar to how humans reason and can be traversed to offer a built-in interpretable Conformal prediction (CP) method. Our comprehensive evaluation shows that CHiQPM achieves state-of-the-art accuracy as a point predictor, maintaining 99% accuracy of non-interpretable models. This demonstrates a substantial improvement, where interpretability is incorporated without sacrificing overall accuracy. Furthermore, its calibrated set prediction is comp...