Picture for Julia Grabinski

Julia Grabinski

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration

Add code
Jun 11, 2024
Viaarxiv icon

Improving Stability during Upsampling -- on the Importance of Spatial Context

Add code
Nov 29, 2023
Viaarxiv icon

On the unreasonable vulnerability of transformers for image restoration -- and an easy fix

Add code
Jul 25, 2023
Viaarxiv icon

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling

Add code
Jul 19, 2023
Figure 1 for Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
Figure 2 for Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
Figure 3 for Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
Figure 4 for Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
Viaarxiv icon

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain

Add code
Jul 19, 2023
Viaarxiv icon

Robust Models are less Over-Confident

Add code
Oct 12, 2022
Figure 1 for Robust Models are less Over-Confident
Figure 2 for Robust Models are less Over-Confident
Figure 3 for Robust Models are less Over-Confident
Figure 4 for Robust Models are less Over-Confident
Viaarxiv icon

FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting

Add code
Apr 01, 2022
Figure 1 for FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Figure 2 for FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Figure 3 for FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Figure 4 for FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Viaarxiv icon