pith. sign in

17 Published as a conference paper at ICLR 2022 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 Information Loss (%) 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 ImageNet Val Acc@1 R

We hypothesize that the data distribution plays a more crucial rule under evaluation protocols based on frozen features, such that models pre-trained with smaller ImageNet-1K dataset consistently achieve better results · 2022

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

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2021 1

verdicts

UNVERDICTED 1

representative citing papers

iBOT: Image BERT Pre-Training with Online Tokenizer

cs.CV · 2021-11-15 · unverdicted · novelty 7.0

iBOT achieves 82.3% linear probing accuracy and 87.8% fine-tuning accuracy on ImageNet-1K using masked image modeling with a jointly trained online tokenizer.

citing papers explorer

Showing 1 of 1 citing paper.

  • iBOT: Image BERT Pre-Training with Online Tokenizer cs.CV · 2021-11-15 · unverdicted · none · ref 17

    iBOT achieves 82.3% linear probing accuracy and 87.8% fine-tuning accuracy on ImageNet-1K using masked image modeling with a jointly trained online tokenizer.