Picture for Shashank Agnihotri

Shashank Agnihotri

How Do Training Methods Influence the Utilization of Vision Models?

Add code
Oct 18, 2024
Viaarxiv icon

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

Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters

Add code
Apr 28, 2023
Figure 1 for Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters
Figure 2 for Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters
Figure 3 for Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters
Figure 4 for Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters
Viaarxiv icon

CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks

Add code
Feb 04, 2023
Viaarxiv icon