Linfeng Ye*

Markov Knowledge Distillation: Make Nasty Teachers trained by Self-undermining Knowledge Distillation Fully Distillable

"To protect intellectual property of a deep neural network (DNN), two knowledge distillation (KD) related concepts are proposed: distillable DNN and KD-resistant DNN. A DNN is said to be distillable if used as a black-box input-output teacher, it can be distilled by a KD method to train a student mo…