MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes

arXiv:2404.08968v1 Announce Type: cross
Abstract: Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model training. Although being effective in bridging the semantic gap between a model's latent space and human interpretation, these explanation methods only partially reveal the model's decision-making process. The outcome is typically limited to high-level semantics derived from the last feature map. We argue that …

abstract analysis arxiv black box box classifier concept cs.cv cs.lg gap human semantic space through training type via