adapt slider3 60

adapt slider3 60

The paper on convolutional neural network model compression, jointly using distillation and hint-based learning in multiple stages, 

Takumi Morikawa and Keisuke Kameyama

"Multi-Stage Model Compression using Teacher Assistant and Distillation with Hint-Based Training"

was presented in the First Workshop on Pervasive and Resource-Constrained Artificial Intelligence (PerConAI). The workshop was held in part of The 20th IEEE International Conference on Pervasive Computing and Communications (PerCom 2022), on March 25, 2022.


© (c) 2007-2022 Adaptive Media Processing Group, University of Tsukuba.