发帖
雷达卡
On Mixup Training: Improved Calibration and
Predictive Uncertainty for Deep Neural Networks
Sunil Thulasidasan,1,2 , Gopinath Chennupati1 , Jeff Bilmes2 ,
Tanmoy Bhattacharya1 , Sarah Michalak1
1
Los Alamos National Laboratory
2
Department of Electrical and Computer Engineering, University of Washington
Abstract
Mixup [37] is a recently proposed method for training deep neura ...
京公网安备 11010802022788号
