Adversarial Deep Mutual Learning
2019 IEEE International Conference on Unmanned Systems and Artificial Intelligence (ICUSAI), pp. 324-329, 2019.
lightweight modeladversarial learningmutual learning
Recently more attention has been paid to neural network compression due to the increasing requirements about limit memory with high performance. The typical methods based on knowledge distillation have to fix a pre-trained teacher model, and most result-orient methods are limited by the teacher model. In this work, we propose a novel ligh...More
Full Text (Upload PDF)
PPT (Upload PPT)