This paper presents MOAT, a family of neural networks that build on top ...
Despite the impressive representation capacity of vision transformer mod...
Self-Attention has become prevalent in computer vision models. Inspired ...
Compared with common image segmentation tasks targeted at low-resolution...
Patch-based adversarial attacks introduce a perceptible but localized ch...
Patch-based attacks introduce a perceptible but localized change to the ...
Optimizing a deep neural network is a fundamental task in computer visio...
This paper studies teacher-student optimization on neural networks, i.e....