BEiT-B

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Document Layout AnalysisonPubLayNet val
Figure· 2021-06-15
0.957
best: 0.975 (DETR)
BEiT: BERT Pre-Training of Image Transformers arXiv:2106.08254
Document Layout AnalysisonPubLayNet val
List· 2021-06-15
0.924
best: 0.975 (TRDLU)
BEiT: BERT Pre-Training of Image Transformers arXiv:2106.08254
Document Layout AnalysisonPubLayNet val
Overall· 2021-06-15
0.931
best: 0.962 (VGT)
BEiT: BERT Pre-Training of Image Transformers arXiv:2106.08254
Document Layout AnalysisonPubLayNet val
Table· 2021-06-15
0.973
best: 0.981 (VGT)
BEiT: BERT Pre-Training of Image Transformers arXiv:2106.08254
Document Layout AnalysisonPubLayNet val
Text· 2021-06-15
0.934
best: 0.967 (VSR)
BEiT: BERT Pre-Training of Image Transformers arXiv:2106.08254
Document Layout AnalysisonPubLayNet val
Title· 2021-06-15
0.866
best: 0.939 (VGT)
BEiT: BERT Pre-Training of Image Transformers arXiv:2106.08254