Robustness Learning via Inference-Softmax Cross Entropy in Misaligned Distribution of Image

Robustness Learning via Inference-Softmax Cross Entropy in Misaligned Distribution of Image

Adversarial examples easily mislead vision systems based on deep neural networks (DNNs) trained with softmax cross entropy (SCE) loss. The vulnerability of DNN comes from the fact that SCE drives DNNs to fit on the training examples, whereas the resultant feature distributions between the training a...

Full description

Bibliographic Details
Main Authors: Bingbing Song, Ruxin Wang, Wei He, Wei Zhou
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Mathematics
Subjects:
neural networks
robustness learning
loss function
adversarial examples
Online Access:https://www.mdpi.com/2227-7390/10/19/3716

Internet

https://www.mdpi.com/2227-7390/10/19/3716

Similar Items