← Search

John Pauly

2 accepted papers

2022

Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers

ICML 2022spotlight

Vision transformers using self-attention or its proposed alternatives have demonstrated promising results in many image related tasks. However, the underpinning inductive bias of attention is not well understood. To address this issue, this paper analyzes attention through the lens of convex duality…

Cited by 38SourcePDFScholar
2018

Neural Proximal Gradient Descent for Compressive Imaging

NeurIPS 2018poster

Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of tr…