pith. sign in

preprint arXiv:2012.02166 , year=

Shir Gur, Ameen Ali, Lior Wolf · 2012 · arXiv 2012.02166

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it
read on arXiv browse 2 citing papers

fields

cs.CV 2

years

2023 1 2021 1

verdicts

CONDITIONAL 1 UNVERDICTED 1

representative citing papers

Vision Transformers Need Registers

cs.CV · 2023-09-28 · unverdicted · novelty 6.0

Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Emerging Properties in Self-Supervised Vision Transformers cs.CV · 2021-04-29 · conditional · none · ref 31

    Self-supervised ViTs show emergent semantic segmentation and 78.3% k-NN accuracy on ImageNet; DINO reaches 80.1% linear evaluation with ViT-Base.

  • Vision Transformers Need Registers cs.CV · 2023-09-28 · unverdicted · none · ref 172

    Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.