2 papers
cs.LG2021
Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19
Dongdong Wang, Shunpu Zhang, Liqiang Wang
An accurate and efficient forecasting system is imperative to the prevention of emerging infectious diseases such as COVID-19 in public health. This system requires accurate transi…
cs.CV2020
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
Dongdong Wang, Yandong Li, Liqiang Wang +1
We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this proble…