Picture for Shunxin Wang

Shunxin Wang

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

Add code
Oct 03, 2024
Figure 1 for Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
Figure 2 for Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
Figure 3 for Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
Figure 4 for Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
Viaarxiv icon

Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification

Add code
Mar 05, 2024
Viaarxiv icon

DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning

Add code
Aug 12, 2023
Viaarxiv icon

Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space

Add code
Jul 28, 2023
Viaarxiv icon

What do neural networks learn in image classification? A frequency shortcut perspective

Add code
Jul 19, 2023
Viaarxiv icon

The Robustness of Computer Vision Models against Common Corruptions: a Survey

Add code
May 10, 2023
Viaarxiv icon