When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX

arXiv:2405.01661v1 Announce Type: new
Abstract: Explanations for Convolutional Neural Networks (CNNs) based on relevance of input pixels might be too unspecific to evaluate which and how input features impact model decisions. Especially in complex real-world domains like biomedicine, the presence of specific concepts (e.g., a certain type of cell) and of relations between concepts (e.g., one cell type is next to another) might be discriminative between classes (e.g., different types of tissue). Pixel relevance is not expressive enough to convey …

abstract arxiv biomedicine classifier cnns concept concepts convolutional convolutional neural networks cs.cv cs.lg decisions domains features impact networks neural networks pixels type world