DetCLIPv2

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

3DonODinW Full-Shot 13 Tasks
AP· 2023-04-10
70.4
best: 73.1 (CP-DETR-L(only optimize prompt))
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment arXiv:2304.04514
2D ClassificationonODinW Full-Shot 13 Tasks
AP· 2023-04-10
70.4
best: 73.1 (CP-DETR-L(only optimize prompt))
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment arXiv:2304.04514
2D Object DetectiononODinW Full-Shot 13 Tasks
AP· 2023-04-10
70.4
best: 73.1 (CP-DETR-L(only optimize prompt))
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment arXiv:2304.04514
16konODinW Full-Shot 13 Tasks
AP· 2023-04-10
70.4
best: 73.1 (CP-DETR-L(only optimize prompt))
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment arXiv:2304.04514

Computer Vision1 result

Object DetectiononODinW Full-Shot 13 Tasks
AP· 2023-04-10
70.4
best: 73.1 (CP-DETR-L(only optimize prompt))
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment arXiv:2304.04514