Vision Transformers Need Registers (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Vision Transformers Need Registers

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: Do transformers need three projections? Systematic study of QKV variants

Do transformers need three projections? Systematic study of QKV variants (arxiv.org)

202 points by Anon84 4 months ago | 39 comments

Screenshot of arxiv.org: Meissonic, High-Resolution Text-to-Image Synthesis on consumer graphics cards

Meissonic, High-Resolution Text-to-Image Synthesis on consumer graphics cards (arxiv.org)

51 points by jinqueeny 2 years ago | 3 comments

Screenshot of arxiv.org: Transformers as Support Vector Machines

Transformers as Support Vector Machines (arxiv.org)

209 points by fofoz 3 years ago | 129 comments

Screenshot of arxiv.org: Recurrent Vision Transformers for Object Detection with Event Cameras

Recurrent Vision Transformers for Object Detection with Event Cameras (arxiv.org)

17 points by fzliu 3 years ago | 1 comments

Screenshot of arxiv.org: Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows (arxiv.org)

41 points by jonbaer 3 years ago | 12 comments

Screenshot of arxiv.org: Transformers without normalization

Transformers without normalization (arxiv.org)

33 points by kaycebasques 1 year ago | 3 comments