J. M. Miñoza

eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts

eX2L demonstrates that functional domain invariance can be enforced by explicitly decoupling label and nuisance attributes at the group level by penalizing the similarity between Grad-CAM activation maps generated by a primary label classifier and those from a concurrently trained confounder classifier.