2 papers
cs.CV2021
Friends and Foes in Learning from Noisy Labels
Yifan Zhou, Yifan Ge, Jianxin Wu
Learning from examples with noisy labels has attracted increasing attention recently. But, this paper will show that the commonly used CIFAR-based datasets and the accuracy evaluat…
cs.CV2020
Distilling Knowledge by Mimicking Features
Guo-Hua Wang, Yifan Ge, Jianxin Wu
Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's s…