most citedLearning Correlation Structures for Vision Transformers

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2024★ 2 cited

Learning Correlation Structures for Vision Transformers

Manjin Kim, Paul Hongsuck Seo, Cordelia Schmid +1

We introduce a new attention mechanism, dubbed structural self-attention (StructSA), that leverages rich correlation patterns naturally emerging in key-query interactions of attent…