pith. sign in

*: result is taken from [CXH21]

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2021 1

verdicts

CONDITIONAL 1

representative citing papers

BEiT: BERT Pre-Training of Image Transformers

cs.CV · 2021-06-15 · conditional · novelty 7.0

BEiT pre-trains vision transformers via masked image modeling on visual tokens and reaches 83.2% ImageNet top-1 accuracy for the base model and 86.3% for the large model using only ImageNet-1K data.

citing papers explorer

Showing 1 of 1 citing paper.

  • BEiT: BERT Pre-Training of Image Transformers cs.CV · 2021-06-15 · conditional · none · ref 23

    BEiT pre-trains vision transformers via masked image modeling on visual tokens and reaches 83.2% ImageNet top-1 accuracy for the base model and 86.3% for the large model using only ImageNet-1K data.