Open-Vocabulary Object Detection on LVIS (minival)
55.8APOWL-ST+FT
Evaluation results
| Method | Links | |
|---|---|---|
| OWL-ST+FTBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grm+curated, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Human-curated vocabulary2023.06 | 55.8 | |
| OWL-ST+FTBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Open vocabulary2023.06 | 54.1 | |
| OWL-ST+FTBackbone=SigLIP G/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Open vocabulary2023.06 | 51.3 | |
| OWL-ST+FTBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grm+curated, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Human-curated vocabulary2023.06 | 51.1 | |
| GLIPv2Backbone=Swin-H, Self-training data=CC15M, Self-training vocabulary=tokens, Human box annotations=FiveODs+GoldG, Vocabulary Access Protocol=Open vocabulary2023.06 | 50.1 | |
| GLIPv2Backbone=Swin-B, Self-training data=CC15M, Self-training vocabulary=tokens, Human box annotations=FiveODs+GoldG, Vocabulary Access Protocol=Open vocabulary2023.06 | 48.5 | |
| OWL-ST+FTBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Open vocabulary2023.06 | 47.2 | |
| DetCLIPv2Backbone=Swin-L, Self-training data=CC15M, Self-training vocabulary=Nouns+curated, Human box annotations=O365+GoldG, Vocabulary Access Protocol=Human-curated vocabulary2023.06 | 44.7 | |
| DetCLIPv2Backbone=Swin-T, Self-training data=CC15M, Self-training vocabulary=Nouns+curated, Human box annotations=O365+GoldG, Vocabulary Access Protocol=Human-curated vocabulary2023.06 | 40.4 | |
| OWL-STBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.06 | 38.1 | |
| OWL-STBackbone=SigLIP G/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.06 | 37.8 | |
| OWL-STBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.06 | 31.8 | |
| GLIPv2Backbone=Swin-T, Self-training data=Cap4M, Self-training vocabulary=tokens, Human box annotations=O365+GoldG, Vocabulary Access Protocol=Open vocabulary2023.06 | 29 |