94 citations · 126 across the 11 of their papers we have counts for
4 papers · 1 filter
Towards Making Deep Transfer Learning Never Hurt
Ruosi Wan, Haoyi Xiong, Xingjian Li +2
Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for…
Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
Dou Goodman, Xingjian Li, Ji Liu +2
Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversa…
An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity
Yingzhen Yang, Jiahui Yu, Xingjian Li +2
Regularization of Deep Neural Networks (DNNs) for the sake of improving their generalization capability is important and challenging. The development in this line benefits theoreti…
DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks
Xingjian Li, Haoyi Xiong, Hanchao Wang +4
Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is fr…