Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Logit Distillation via Student Diversity

    Knowledge distillation (KD) is a technique of transferring the knowledge from a large teacher network to a small student network. Current KD methods either make a student mimic diverse teachers with knowledge ...

    Dingyao Chen, Long Lan, Mengzhu Wang, **ang Zhang in Neural Information Processing (2023)