MEDet

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

3DonLVIS v1.0
AP novel-LVIS base training· 2022-06-22
22.4
best: 43.4 (LaMI-DETR)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization arXiv:2206.11134
2D ClassificationonLVIS v1.0
AP novel-LVIS base training· 2022-06-22
22.4
best: 43.4 (LaMI-DETR)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization arXiv:2206.11134
2D Object DetectiononLVIS v1.0
AP novel-LVIS base training· 2022-06-22
22.4
best: 43.4 (LaMI-DETR)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization arXiv:2206.11134
16konLVIS v1.0
AP novel-LVIS base training· 2022-06-22
22.4
best: 43.4 (LaMI-DETR)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization arXiv:2206.11134

Computer Vision2 results

Object DetectiononLVIS v1.0
AP novel-LVIS base training· 2022-06-22
22.4
best: 43.4 (LaMI-DETR)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization arXiv:2206.11134
Open Vocabulary Object DetectiononLVIS v1.0
AP novel-LVIS base training· 2022-06-22
22.4
best: 43.4 (LaMI-DETR)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization arXiv:2206.11134