GroundingDINO-L

Reported on 5 benchmarks across 5 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 minival
AP· uses extra data· 2023-03-09
33.9
best: 58.2 (CP-DETR-Pro(without LVIS data))
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection arXiv:2303.05499
2D ClassificationonLVIS v1.0 minival
AP· uses extra data· 2023-03-09
33.9
best: 58.2 (CP-DETR-Pro(without LVIS data))
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection arXiv:2303.05499
2D Object DetectiononLVIS v1.0 minival
AP· uses extra data· 2023-03-09
33.9
best: 58.2 (CP-DETR-Pro(without LVIS data))
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection arXiv:2303.05499
16konLVIS v1.0 minival
AP· uses extra data· 2023-03-09
33.9
best: 58.2 (CP-DETR-Pro(without LVIS data))
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection arXiv:2303.05499

Computer Vision1 result

Object DetectiononLVIS v1.0 minival
AP· uses extra data· 2023-03-09
33.9
best: 58.2 (CP-DETR-Pro(without LVIS data))
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection arXiv:2303.05499