From the counterculture of the 1960s to today’s ‘Gen Z revolutions’, mass uprisings have repeatedly failed to dismantle ...
Abstract: As a front-burner problem in incremental learning, class incremental semantic segmentation (CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods have ...
Abstract: We introduce Adversarial Sparse Teacher (AST), a robust defense method against distillation-based model stealing attacks. Our approach trains a teacher model using adversarial examples to ...