ViTDet, ViT-H Cascade (multiscale)

Reported on 6 benchmarks across 6 tasks · 1 paper

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

Methodology4 results

3DonCOCO minival
box AP· 2022-03-30
61.3
best: 66 (PE_spatial (DETA))
Exploring Plain Vision Transformer Backbones for Object Detection arXiv:2203.16527
2D ClassificationonCOCO minival
box AP· 2022-03-30
61.3
best: 66 (PE_spatial (DETA))
Exploring Plain Vision Transformer Backbones for Object Detection arXiv:2203.16527
2D Object DetectiononCOCO minival
box AP· 2022-03-30
61.3
best: 66 (PE_spatial (DETA))
Exploring Plain Vision Transformer Backbones for Object Detection arXiv:2203.16527
16konCOCO minival
box AP· 2022-03-30
61.3
best: 66 (PE_spatial (DETA))
Exploring Plain Vision Transformer Backbones for Object Detection arXiv:2203.16527

Computer Vision2 results

Object DetectiononCOCO minival
box AP· 2022-03-30
61.3
best: 66 (PE_spatial (DETA))
Exploring Plain Vision Transformer Backbones for Object Detection arXiv:2203.16527
Instance SegmentationonCOCO minival
mask AP· 2022-03-30
53.1
best: 56.6 (Co-DETR)
Exploring Plain Vision Transformer Backbones for Object Detection arXiv:2203.16527