BoTNet 50 (72 epochs)

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· 2021-01-27
45.9
best: 66 (PE_spatial (DETA))
Bottleneck Transformers for Visual Recognition arXiv:2101.11605
2D ClassificationonCOCO minival
box AP· 2021-01-27
45.9
best: 66 (PE_spatial (DETA))
Bottleneck Transformers for Visual Recognition arXiv:2101.11605
2D Object DetectiononCOCO minival
box AP· 2021-01-27
45.9
best: 66 (PE_spatial (DETA))
Bottleneck Transformers for Visual Recognition arXiv:2101.11605
16konCOCO minival
box AP· 2021-01-27
45.9
best: 66 (PE_spatial (DETA))
Bottleneck Transformers for Visual Recognition arXiv:2101.11605

Computer Vision2 results

Object DetectiononCOCO minival
box AP· 2021-01-27
45.9
best: 66 (PE_spatial (DETA))
Bottleneck Transformers for Visual Recognition arXiv:2101.11605
Instance SegmentationonCOCO minival
mask AP· 2021-01-27
40.7
best: 56.6 (Co-DETR)
Bottleneck Transformers for Visual Recognition arXiv:2101.11605