ORCA Cao et al. (2022)

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Methodology3 results

2D Object DetectiononLVIS v1.0 val
All mAP· 2021-02-06
2.03
best: 19.33 (Cooperative Foundational Models)
SOTA
Open-World Semi-Supervised Learning arXiv:2102.03526
2D Object DetectiononLVIS v1.0 val
Known mAP· 2021-02-06
20.57
best: 42.08 (Cooperative Foundational Models)
SOTA
Open-World Semi-Supervised Learning arXiv:2102.03526
2D Object DetectiononLVIS v1.0 val
Novel mAP· 2021-02-06
0.49
best: 17.42 (Cooperative Foundational Models)
SOTA
Open-World Semi-Supervised Learning arXiv:2102.03526