Xindi Wu

collaborators

2 papers

cs.LG2020

Squared $ℓ_{2}$ Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations

Haohan Wang, Zeyi Huang, Xindi Wu +1

Data augmentation is one of the most popular techniques for improving the robustness of neural networks. In addition to directly training the model with original samples and augmen…

cs.CV2019

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

Haohan Wang, Xindi Wu, Zeyi Huang +1

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNN's ability i…

Squared ℓ2​ Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

Squared $ℓ_{2}$ Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations