← Search

Jia-Yu Pan

2 accepted papers

2019

Complement Objective Training

ICLR 2019poster

Learning with a primary objective, such as softmax cross entropy for classification and sequence generation, has been the norm for training deep neural networks for years. Although being a widely-adopted approach, using cross entropy as the primary objective exploits mostly the information from the…

2019

Improving Adversarial Robustness via Guided Complement Entropy

ICCV 2019poster

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by utilizing adversarial training or model distillation, which adds…

Cited by 73PDFScholar