OV-DINO-T (without COCO data)

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

3DonMSCOCO
AP· uses extra data· 2024-07-10
50.6
best: 58.8 (ScaleDet)
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion arXiv:2407.07844
2D ClassificationonMSCOCO
AP· uses extra data· 2024-07-10
50.6
best: 58.8 (ScaleDet)
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion arXiv:2407.07844
2D Object DetectiononMSCOCO
AP· uses extra data· 2024-07-10
50.6
best: 58.8 (ScaleDet)
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion arXiv:2407.07844
16konMSCOCO
AP· uses extra data· 2024-07-10
50.6
best: 58.8 (ScaleDet)
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion arXiv:2407.07844

Computer Vision1 result

Object DetectiononMSCOCO
AP· uses extra data· 2024-07-10
50.6
best: 58.8 (ScaleDet)
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion arXiv:2407.07844