LG paper review QnA session - Knowledge Distillation

1. Distilling the Knowledge in a Neural Network, 15’NIPS (https://arxiv.org/abs/1503.02531)

2. Knowledge Distillation by On-the-Fly Native Ensemble, 18`NIPS, (https://arxiv.org/abs/1806.04606) (ONE/)

3. Regularizing Class-wise Predictions via Self-knowledge Distillation, 20 `CVPR

4. Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation, 19 `ICCV

• 김성년 ksn4397@kaist.ac.kr
• 최진환 jinhwanchoi@kaist.ac.kr