Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI

As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep learning models. Post-hoc methods like GradCAM offer heatmaps but provide limited conceptual insight, while prototype-based approaches offer example-based explanations yet often rely on rigid region selection and lack semantic consistency. To address these limitations, we introduce PCMNet, a part-prototypical concept mining network that learns human-comprehensible prototypes from semantically meaningful image regions without additional supervision. By clustering these prototypes into coherent concept groups and extracting concept activation vectors, PCMNet provides structured, concept-level explanations and enhances robustness to occlusion and challenging conditions, which are both critical for building reliable and aligned AI systems. Experiments on multiple image classification benchmarks show that PCMNet outperforms state-of-the-art methods in interpretability, stability, and robustness. This work contributes to AI alignment by enhancing transparency, controllability, and trustworthiness in AI systems.