List your company

Open-vocabulary Object Detection on ODinW 13 (test)

55.5APGLIPv2
48.11650.03351.9553.867Jun 16, 2023

Evaluation results

MethodLinks
GLIPv2Backbone=Swin-H, Self-training data=CC15M, Self-training vocabulary=tokens, Human box annotations=FiveODs+GoldG, Vocabulary Access Protocol=Open vocabulary2023.0655.5
GLIPv2Backbone=Swin-B, Self-training data=CC15M, Self-training vocabulary=tokens, Human box annotations=FiveODs+GoldG, Vocabulary Access Protocol=Open vocabulary2023.0654.2
OWL-STBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.0653
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 vocabulary2023.0650.1
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 vocabulary2023.0650.1
OWL-STBackbone=SigLIP G/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.0649.9
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 vocabulary2023.0648.9
OWL-STBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.0648.8
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 vocabulary2023.0648.7
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 vocabulary2023.0648.6
GLIPv2Backbone=Swin-T, Self-training data=Cap4M, Self-training vocabulary=tokens, Human box annotations=O365+GoldG, Vocabulary Access Protocol=Open vocabulary2023.0648.5
OWLBackbone=CLIP L/14, Human box annotations=O365+VG, Vocabulary Access Protocol=Open vocabulary2023.0648.4