Vision Transformers Need Registers | VitaVision
PaperICLR 2024 · 2023

Vision Transformers Need Registers

Timothée DarcetMaxime OquabJulien MairalPiotr Bojanowski
arXiv 2309.16588
0pages built on it
2more pages cite it
4narratives
0registry papers cite it

In the Atlas

Cited as a reference by 2 pages, grouped by domain

Geometry 1
VGGT (Visual Geometry Grounded Transformer)
Representation learning 1
Attention Mechanism

Appears in 4 narratives

NarrativeFoundation Models for VisionNarrativeDepth Becomes General GeometryNarrativeThe Geometry Pipeline CollapsesNarrativeWhere Did the Inductive Bias Go?

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 0
’20’21’22’23An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2020)DINOv2: Learning Robust Visual Features without Supervision (2023)
Built upon by · 0