2 papers
cs.CV2025
Toward Simple and Robust Contrastive Explanations for Image Classification by Leveraging Instance Similarity and Concept Relevance
Yuliia Kaidashova, Bettina Finzel, Ute Schmid
Understanding why a classification model prefers one class over another for an input instance is the challenge of contrastive explanation. This work implements concept-based contra…
cs.LG2024
When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX
Bettina Finzel, Patrick Hilme, Johannes Rabold +1
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. Es…