UNO Fini et al. (2021)++

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· 2021-08-19
2.18
best: 19.33 (Cooperative Foundational Models)
SOTA
A Unified Objective for Novel Class Discovery arXiv:2108.08536
2D Object DetectiononLVIS v1.0 val
Known mAP· 2021-08-19
21.09
best: 42.08 (Cooperative Foundational Models)
SOTA
A Unified Objective for Novel Class Discovery arXiv:2108.08536
2D Object DetectiononLVIS v1.0 val
Novel mAP· 2021-08-19
0.61
best: 17.42 (Cooperative Foundational Models)
SOTA
A Unified Objective for Novel Class Discovery arXiv:2108.08536