ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing

By Roshan Prakash Rane · Paper · cs.LG

Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning. Concept-based explainability methods screen for shortcuts by testing whether concepts such as a patient's sex or scanner settings can be decoded from a network l

Cs.lg

View original

HomeResourceLoading…