ICON decomposition can isolate concepts that models genuinely rely on and quantify unexplained representation in real-world imaging models

On skin-lesion and brain-imaging models, it isolates the concepts on which a model genuinely relies, quantifies the representation unexplained by any of the supplied concepts, and yields sparse explanations that we validate by retraining and out-of-distribution testing.

http://arxiv.org/abs/2608.26083v1